Rozprawy doktorskie: „AI for health”

1

GLORIOSO, VALERIA PAOLA. "L'universalismo incompiuto.Disuguaglianze socioeconomiche e inquità nell'accesso ai servizi sanitari in Italia". Doctoral thesis, Università degli Studi di Milano-Bicocca, 2013. http://hdl.handle.net/10281/46373.

Pełny tekst źródła

Streszczenie:

Equity has long been considered an important goal in the health sector. Yet, inequalities between different social groups persist. In particular, lower-status socioeconomic groups tend to suffer higher rates of mortality and morbidity than do higher-status socioeconomic groups. Also, disadvantaged groups often use health care services less, despite generally having higher levels of need. Scholars often argue that these inequalities reflect mainly differences in constraints, rather than differences in preferences, so that they should be considered as inequities, i.e., as an instance of social injustice. The purpose of this dissertation is to investigate whether, and to what extent, patterns of access to health care services deviate from the ideal of horizontal equity – i.e., equal access for equal need – in a country with a universal and egalitarian health care system: Italy. The Italian National Health Service (Servizio Sanitario Nazionale – Ssn) was established in 1978 through a major reform largely inspired by the British Nhs, with the declared goal of providing uniform and comprehensive care to all Italian citizens. The reform rested on the egalitarian principle that health care should be financed according to ability to pay – through general taxation – but distributed according to need, thereby setting out equity objectives in terms of both financial contribution and access to care. There is evidence, however, that these goals have not been fully achieved yet. The present work aims at analyzing this issue and bridging some of the method- ological and substantive gaps in existing research. Using large-scale survey data collected in three different years (1994, 2000, and 2005) and multilevel regression modeling, we investigate whether and how the probability of accessing a compre- hensive set of health care services varies among individuals with equal need but different socioeconomic status (Ses). Along with the standard indicators of health care utilization (GP visits, specialist visits, and inpatient hospital care), we consider two other variables generally neglected in previous research: propensity to take basic medical tests and use of diagnostic services. Moreover, in addition to the usual estimation of global horizontal inequity, we carry out a stratified analysis aimed at providing distinct estimates of inequity for each level of need, as proxied by health status. Overall, the results of this study confirm a well-established finding in the inter- national literature on health care: even countries with a universal and egalitarian public health care system, like Italy, exhibit a certain degree of Ses-related hori- zontal inequity in health services utilization. Specifically, we found a significant amount of pro-rich inequity in the utilization of specialist care, diagnostic services, and basic medical tests. Use of primary care was found inequitable, too, but in favor of the less well-off. Finally, we found that hospitalization is essentially equitable. The stratified analysis of inequity by level of health status uncovers a noteworthy pattern of heterogeneity in the phenomenon of interest: the degree of inequity in health services utilization tends to decrease as health status decreases – and, therefore, as the need for health care increases. Although this trend is neither regular nor strictly monotonic, our tests show that it is not a mere artifact of sampling error. Thus, there are good reasons to assume that as the need for health care increases, its utilization approaches equity. Finally, our analyses show no substantial difference in inequity of access to health care across regions and time. The articulation of the Italian Ssn into twenty different – and relatively autonomous – Regional Health Services was expected to generate some regional variation in inequity of health care utilization. Likewise, the reforms the Ssn underwent during the period 1994-2005 were plausible sources of variation over time. However, no systematic evidence of regional or longitudinal heterogeneity was revealed by our analyses, suggesting that socioeconomic inequity of access to health care is a stable, well-structured phenomenon.

Style APA, Harvard, Vancouver, ISO itp.

2

Schiele, Julian [Verfasser], i Jens O. [Akademischer Betreuer] Brunner. "AI-Enabled Decision Support in Health Care / Julian Schiele ; Betreuer: Jens O. Brunner". Augsburg : Universität Augsburg, 2020. http://d-nb.info/1217194029/34.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

3

Gozuyilmaz, Cem. "A System Approach To Occupational Health And Safety Management". Master's thesis, METU, 2003. http://etd.lib.metu.edu.tr/upload/1095231/index.pdf.

Pełny tekst źródła

Streszczenie:

In this thesis, methods used at present in occupational health and safety management are analyzed and a model safety management system is developed. History, development and recent occupational safety regulations in the United States of America and European Union are introduced to give a sight on this subject in developed countries. The suggested model is evaluated with work accident data taken from a company and hazard and risk analysis methods are used to investigate these accidents. Preventive measures to eliminate and reduce the consequences of these accidents are recommended. Finally a model safety management system which can be used in all types of industry is developed.

Style APA, Harvard, Vancouver, ISO itp.

4

Rahaman, Khan Md Atiqur. "Feasibility Analysis of AI based Wearable Data-driven Solution for Safety and Health in Sweden". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-239442.

Pełny tekst źródła

Streszczenie:

This thesis investigates the prospects of AI and IoT based wearable solution in order to enhance the occupational safety and health. Thus this study contributes to find the probable use cases that can be suitable for such a technology. Later also investigation has been done to figure out how appropriate the Swedish market will be to target on. At the beginning of the thesis, it includes an overall scenario about the occupational safety/health globally as well as in Sweden. Later to improve the workplace injuries, how AI based wearable solution can be handy has been visualized. The theoretical framework explains the technical features and working mechanism and how it can implement in a real world. The methods that can be applied for such research has been discussed afterwards. Then investigation has been done to find the probable use cases and Swedish market has been analyzed to verify how fit the solution. The result chapter includes the finding of the analysis thereafter. To conclude, it has been figured out that few of the us cases for Swedish industries can certainly be applicable for such AI based wearable solution to improve the workplace safety scenario.
Denna avhandling undersöker utsikterna för AI och IoT-baserad bärbar lösning för att förbättra arbetssäkerheten och hälsan. Således bidrar denna studie till att hitta de sannolika användningsfall som kan vara lämpliga för en sådan teknik. Senare har också undersökningar gjorts för att ta reda på hur lämpligt den svenska marknaden ska vara inriktad på. I början av avhandlingen ingår det ett övergripande scenario om arbetssäkerhet / hälsa globalt såväl som i Sverige. Senare för att förbättra arbetsplatsskadorna, hur AI-baserad bärbar lösning kan vara användbar har visualiserats. Den teoretiska ramen förklarar de tekniska funktionerna och arbetsmekanismen och hur den kan genomföras i en verklig värld. De metoder som kan tillämpas för sådan forskning har diskuterats efteråt. Sedan har undersökningen gjorts för att hitta de sannolika användningsfallen och den svenska marknaden har analyserats för att verifiera hur lämplig lösningen är. Resultatet kapitlet innehåller analysen av analysen därefter. Avslutningsvis har det visat sig att få av användningsärenden för svenska industrier säkert kan tillämpas för en sådan AI-baserad bärbar lösning för att förbättra arbetssäkerhetsscenariot.

Style APA, Harvard, Vancouver, ISO itp.

5

Dorrikhteh, Masoud. "A Deep-Learning Approach for Marker-less Stride Parameters Analysis with Two Cameras". Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42511.

Pełny tekst źródła

Streszczenie:

Human gait analysis is an essential indicator for physical and neuroglial health of an individual. Recent developments in deep-learning approaches to computer vision make possible new techniques for body segment and joint detection from photos and video frames. In this thesis, we propose a deep learning approach for non-invasive video-based gait analysis using two RGB cameras that would be suitable for routine gait monitoring in senior care and rehabilitation centers. Due to modularity and the low cost of implementation, it is considered an affordable solution for such centers. Furthermore, since the solution does not require any markers or sensors to be worn, it is a pervasive and easy method for daily usage. Our proposed deep-learning approach starts by calibrating both the intrinsic and extrinsic parameters of the cameras. Next, video streams captured from two RGB cameras are used as input, and OpenPose and HyperPose deep-learning frameworks are used to localize the main body key points, including the joints and skeleton based on Body 25 and COCO models, respectively. The 2D parameter outputs from the frameworks are triangulated into 3D vector spaces for further analysis. In order to reduce the noises in our data, we applied median and dual pass butter worth filters to the data. Finally gait parameters has been extracted measured and compared to the manually evaluated ground truth data which has been capture via manual measurement of a domain expert. The approach was evaluated in a laboratory setting similar to an institutional hallway in five types of trials: walking back and forth in a straight line while turning out of frame, walking back and forth in a straight line while turning in frame, circular walking, walking with a cane and a walker. The method brings promising results compared to more expensive and restrictive approaches that use up to 16 cameras and require markers or sensors.

Style APA, Harvard, Vancouver, ISO itp.

6

Bonarrigo, Manuel. "Panoramica dell'approccio architetturale orientato ai microservizi e analisi dell'applicabilità nel contesto TraumaTracker". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16812/.

Pełny tekst źródła

Streszczenie:

Lo scopo di questa tesi consiste in uno studio di fattibilità dell'eventuale migrazione del progetto TraumaTracker, uno strumento informatico realizzato in collaborazione con il TraumaCenter dell'ospedale Maurizio Bufalini di Cesena, verso un approccio architetturale orientato ai microservizi. Le motivazioni che hanno portato alla considerazione di questa recente concretizzazione della service orientation derivano dalla natura di strumento medico-ospedaliero assunta dal TraumaTracker, dal quale ci si aspetta di ottenere gli stessi livelli di resilienza rispetto ai fallimenti di rete, macchine host ed elettricità di cui gode l'infrastruttura ospedaliera; inoltre viene ricercata la possibilità di uno sviluppo agile e dinamico per rispondere alle necessità ed alla sistematica evoluzione del dominio applicativo. Dopo una parte introduttiva delle infrastrutture coinvolte, in cui vengono esplicitate sia l'infrastruttura di massima del TraumaTracker, così come i principi chiave che caratterizzano l'approccio dei microservizi, vengono delineati i cambiamenti necessari affinchè i servizi che compongono il sistema possano essere considerati effettivamente microservizi, concretizzando l'infrastruttura presente grazie al supporto della piattaforma di virtualizzazione Docker.

Style APA, Harvard, Vancouver, ISO itp.

7

Silvaggi, Fabiola. "Il wellness at work come risposta ai cambiamenti della forza lavoro". Doctoral thesis, Università degli studi di Bergamo, 2017. http://hdl.handle.net/10446/77127.

Pełny tekst źródła

Streszczenie:

Il mio progetto di ricerca è stato incentrato su due aspetti del wellness at work: il primo inerente la relazione tra la work ability delle persone con malattie croniche e le variabili socio-economiche ad essa correlate (presentismo, assenteismo, produttività al lavoro, ecc) e il secondo relativo alla relazione tra la prevenzione primaria e le condizioni salutari dei lavoratori, al fine di rilevare quale organizzazione del lavoro delle singole imprese sia più idonea a gestire la presenza o il ritorno in attività di una forza-lavoro con problemi di salute o potenzialmente tale. Ai fini di questo proposito, sono stati studiati i programmi e le iniziative di wellness aziendali mirati alla prevenzione e promozione della salute nella loro validità socio-economica. Inoltre, nella prospettiva di garantire un taglio pratico ed operativo al lavoro, oltre allo studio della dottrina accademica, il presente lavoro ha adottato due diverse metodologie: il primo segue la prospettiva che si basa su analisi di tipo deduttivo attraverso questionari e interviste, mentre il secondo segue la prospettiva dei case studies. L’obiettivo che ci si pone attraverso tale integrazione di metodologie è quello di giungere ad una conoscenza più approfondita del fenomeno in oggetto.

Style APA, Harvard, Vancouver, ISO itp.

8

Franzén, Johnny. "Folkhälsovetenskap i en tid av klimatförändringar, digitalisering och orättvisa : En kartläggande studie om den artificiella intelligensens betydelse i hanteringen av klimatrelaterade folkhälsohot". Thesis, Högskolan i Skövde, Institutionen för hälsovetenskaper, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-19855.

Pełny tekst źródła

Streszczenie:

Introduktion: Varje år dör 300 000 människor i världen på grund av klimatförändringarna och 325 miljoner påverkas allvarligt. De som i huvudsak drabbas är människor som redan är utsatta och de finns både i rika och fattiga länder. Dessa konsekvenser leder till stora sociala orättvisor mellan utvecklade länder och outvecklade men även inom nationer, därför kommer en global hälsa i en vidare mening beträffande naturkapital, humankapital och socialt kapital att krävas. Där bördorna delas och skador undviks genom mitigation, anpassning och hälsoprevention. Den pågående digitaliseringen i samhället genom bland annat AI innebär stora möjligheter ur ett folkhälsoperspektiv att arbeta preventivt. Syfte: Syftet är att generera kunskap om hur artificiell intelligens används i ett hälsopreventivt arbete för att begränsa konsekvenserna av klimatförändringar. Metod: En kvalitativ kartläggande litteraturgranskning med en induktiv innehållsanalys. Resultat: Uteslutande så används maskininlärning som AI i artiklarna för att arbeta preventivt och försöka förutse olika hot mot folkhälsan som ett förändrat klimat bidrar till. Klimatkonsekvenserna som förekommer är vektorburna sjukdomar, zoonoser, värmeböljor och luftföroreningar. Artiklarna sträcker sig från år 2016 till 2020 och genomförs i huvudsak i och av utvecklade länder. Slutsats: AI kan användas i hälsopreventivt arbete för att begränsa konsekvenserna av klimatförändringar baserat på teknikens förmåga att förutse hälsohot. Detta är ett viktigt inslag i hälsopreventivt arbete. Forskningsområdet är i sin linda och behöver ta mer hänsyn till etik, rättvisa och hälsans bestämningsfaktorer.
Introduction: Every year, 300,000 people in the world die due to climate change and 325 million are severely affected. Those who are mainly affected are people who are already vulnerable and they are found in both rich and poor countries. This leads to great social injustices between developed countries and undeveloped but also within nations, therefore global health in a broader sense regarding natural capital, human capital and social capital will be required. Where burdens are shared and injuries are avoided through mitigation, adaptation and health prevention. Gradually, digitalization through, among other things, AI permeates the global society more and more and research believes that for public health work, this means great opportunities to work preventively and that health systems become more efficient, safer and cheaper. Aim: The aim is to generate knowledge about how artificial intelligence is used in health prevention work to limit the consequences of climate change. Method: A qualitative scoping review with an inductive content analysis. Results: Machine learning is used in the articles to work preventively and try to predict various threats to public health that climate change contributes to. The climate consequences that occur are vector-borne diseases, zoonoses, heat waves and air pollution. The articles extend from 2016 to 2020 and are mainly implemented in and by developed countries. Conclusion: AI can be used in health prevention work to limit the consequences of climate change based on the technology's ability to predict health threats. This is an important element in health prevention work. The research area is in its infancy and needs to take more account of ethics, justice and health determinants.

Style APA, Harvard, Vancouver, ISO itp.

9

Karlsson, Jennica, i Ann Charlotte Lindberg. "Hur påverkas folkhälsan av Artificiell Intelligens? : En litteraturstudie av hur hälsans sociala bestämningsfaktorer påverkas av AI inom området avsiktliga skador". Thesis, Högskolan i Skövde, Institutionen för hälsa och lärande, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17128.

Pełny tekst źródła

Streszczenie:

Introduktion: Befolkningens hälsa påverkas i hög grad av hur väl samhället vi lever i fungerar. Samhällen präglade av våld, krig och terror får negativa konsekvenser för människors hälsa. Artificiell Intelligens (AI) är en kraftfull teknik med stora möjligheter att lösa samhällsproblem, men forskare varnar för att AI också kan innebära nya risker. Syfte: Syftet med litteraturstudien är att belysa vilka utmaningar och möjligheter som en ökande utveckling och implementering av AI kan ha på hälsans sociala bestämningsfaktorer inom området avsiktliga skador. Metod: Enligt Denyer och Tranfields (2011) metod genomfördes en systematisk litteraturstudie på 25 tekniska och humanistiska artiklar, som analyserades och syntetiserades med på förhand tydligt uppställda studiefrågor. Resultat: Artiklarna behandlande AI som används inom områden relaterade till avsiktliga skador och kategoriserades som tekniska eller humanistiska. De tekniska artiklarnas syfte var att utveckla AI för problemlösning medan de humanistiska artiklarna analyserade effekterna av implementering av AI. Möjligheterna med AI inkluderade förmågan att göra förutsägelser, fylla kompetensbehov, utnyttja big data och ta fram modeller som kan ge generella lösningar. Utmaningarna bestod av krav på en teoretisk grund, risk för bias, skapa eller välja lämpliga modeller och algoritmer, säkerställa kvalitet på data och databearbetning, validera lösningar, förhindra oavsiktlig användning, tydliggöra ansvar och få acceptans för lösningarna. Utvecklingen och implementeringen av AI påverkar främst tre av hälsans sociala bestämningsfaktorer: stödjande miljöer och friska människor, marknadens ansvar, samt god global styrning. Slutsats: Gemensam global reglering och större samhälleligt engagemang behövs för att säkerställa att konsekvenser för folkhälsan beaktas vid utvecklingen av AI.
Introduction: Public health is affected by the society in which people live. Communities characterized by violence, war and terror have a negative impact on human wellbeing. Artificial Intelligence (AI) is a powerful tool with a capability to solve problems in the society but scientists also warn that AI can induce new types of problems. Aim: The purpose of this literature study is to review which challenges and possibilities an increase in the development and implementation of AI can have on the social determinants of health within the area of deliberate injury. Methods: A systematic literature review was performed according to the method by Denyer and Tranfield (2011) and 25 technical and humanistic articles were analyzed and synthesized according to predefined research questions. Results: The articles about AI in the area of deliberate injuries were categorized as technical or humanistic. The purpose of the technical articles was to develop AI for problem solving while the humanistic articles analyzed the effects of AI implementation. The possibilities with AI included predictions, competence need, big data and models for general purposes. The challenges included theoretical grounds, bias, suitable models and algorithms, data quality and processing, validation, wrongful usage, responsibility and acceptance of the solutions. The development and implementation of AI especially affect three of the social determinants of health: healthy places healthy people, market responsibility and good global governance. Conclusion: A common global control and societal commitment is needed to secure that consequences for the public health is considered while developing AI.

Style APA, Harvard, Vancouver, ISO itp.

10

Johnson, Beverly Elaine. "Attitudes and Perceptions of Mental Health Treatment for Native American Clients". ScholarWorks, 2017. https://scholarworks.waldenu.edu/dissertations/4524.

Pełny tekst źródła

Streszczenie:

The need for mental health service is increasing in American Indian/Alaska Native (AI/AN) communities. While research has examined the availability, access, and effectiveness of provided services to the AI/AN, very little is known about the influence of the attitude and perceptions of both clinicians and clients in their therapeutic relationship in the treatment process. Using the frameworks of liberation, oppression, and trauma theory, this qualitative phenomenological study explored mental health service delivery and utilization issues within an AI/AN community. Data were collected through semistructured interviews with 14 clinician and client participants. The data were sorted into themes and subthemes and analyzed using the NVivo 11 computer software. Intergenerational struggle represented the primary theme and other subthemes such as assimilation, acculturation, and communication were among some of the secondary themes gathered from the data. Analysis of the themes provided greater insights into the dynamics of the participant's lived experience in various organizational structures within the larger community as well as a better understanding of mental health service delivery and utilization in maintaining sobriety in their daily struggles. The results indicated that intergenerational struggle along with other environmental factors were the chief causes of their cyclical journey through the penal and other systems; thus reducing their ability in maintaining longer sobriety and in improving their mental health. The implications for positive social change in this study include the reduction of stigma associated with these health issues through the education of the community and in training clinicians in factor-specific issues impacting life altering critical events in AI/AN struggles.

Style APA, Harvard, Vancouver, ISO itp.

11

Mendes, David, M. J. Lopes, Artur Romão i Irene Pimenta Rodrigues. "Healthcare Computer Reasoning Addressing Chronically Ill Societies Using IoT: Deep Learning AI to the Rescue of Home-Based Healthcare". Bachelor's thesis, IGI Global, 2016. http://hdl.handle.net/10174/19286.

Pełny tekst źródła

Streszczenie:

The authors present a proposal to develop intelligent assisted living environments for home based healthcare. These environments unite the chronical patient clinical history sematic representation with the ability of monitoring the living conditions and events recurring to a fully managed Semantic Web of Things (SWoT). Several levels of acquired knowledge and the case based reasoning that is possible by knowledge representation of the health-disease history and acquisition of the scientific evidence will deliver, through various voice based natural interfaces, the adequate support systems for disease auto management but prominently by activating the less differentiated caregiver for any specific need. With these capabilities at hand, home based healthcare providing becomes a viable possibility reducing the institutionalization needs. The resulting integrated healthcare framework will provide significant savings while improving the generality of health and satisfaction indicators.

Style APA, Harvard, Vancouver, ISO itp.

12

Rönnqvist, Mats, i Magnus Johansson. "Artificiell Intelligens inom medicinsk bilddiagnostik : En allmän litteraturstudie". Thesis, Luleå tekniska universitet, Institutionen för hälsovetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-72969.

Pełny tekst źródła

Streszczenie:

Bakgrund: Artificiell Intelligens (AI) kommer in i vårt samhälle och våra hem i allt större utsträckning. Inom sjukvården och radiologin kan AI utgöra ett hjälpmedel för både radiologer och röntgensjuksköterskor i deras profession. Forskning om AI fortsätter med oförminskad kraft för att finna allt bättre och mer funktionsdugliga algoritmer som kan anta den utmaningen. Syfte: Syftet med denna litteraturstudie är att sammanställa vid vilka modaliteter AI används som stöd. Metod: Studien utfördes som en allmän litteraturstudie vilket genererade femton artiklar som kvalitetsgranskades och kategoriserades efter analys. Resultat: Beroende på tidpunkt när artiklarna var skrivna varierade metoderna hur träning av AI genomfördes. Det varierade även hur bilderna skulle förbearbetats inför träning. Bilderna måste genomgå brusreducering och segmentering för att AI ska kunna klassificera den sjukliga förändringen. Den processen underlättades i senare versioner av AI där alla dessa moment utfördes på en och samma gång. Slutsats: Stora förändringar kommer att ske inom radiologin och förändringarna kommer sannolikt att påverka alla på en röntgenavdelning. Författarna kan se att utvecklingen bara börjat och forskningen måste fortgå många år framöver.
Background: Artificial Intelligence (AI) increasingly comes in to our society and homes. In the field of medical care and radiology, AI will provide an aid for radiologists and radiographers in their professions. Research on AI continues in finding better and more functional algorithms which can achieve that. Purpose: The purpose of this literature study is to compile facts about modalities using artificial intelligence as support. Method: The study was conducted as a general literature study, which generated fifteen articles that were quality-reviewed and categorized after analysis. Result: Depending on the date when the articles were written the methods varied concerning how training of AI was performed. It also varied how the images were pre-processed before training. The images need to be processed by noise reduction and segmentation for AI in order to be able to classify the pathological change. That process was facilitated in later versions of AI where all these steps were performed at the same time. Conclusion: Major changes may occur in radiology and the changes are likely to affect everyone in an X-ray ward. The authors can see that the development has just begun and research has to continue for many years to come.

Style APA, Harvard, Vancouver, ISO itp.

13

DEL, NEGRO Ercole. "Rilascio di applicativi per aumentare il livello tecnologico degli allevamenti e la salute degli animali". Doctoral thesis, Università degli studi di Modena e Reggio Emilia, 2022. https://hdl.handle.net/11380/1291684.

Pełny tekst źródła

Streszczenie:

Farm4trade è una startup italiana che sviluppa sistemi di alta tecnologia per gli allevamenti di animali di produzione e per la salute animale in genere. Tra le applicazioni sviluppate ci sono sistemi di computer vision che sfruttano il machine learning. Tra questi i più importanti sono Photo Animal Identification (PHAID) e Automatic Detection of Abattoir Lesions (ADAL). Nel caso dei questi sistemi di computer vision, la sfida aziendale è quella di rilasciare in produzione per un utilizzo massimo delle applicazioni per ottenere predizioni e in generale risultati in tempo reale. Questi sistemi devono inoltre perfettamente integrarsi con tutte le soluzioni aziendali e fornire informazioni a sistemi terzi. Il lavoro di ricerca ha portato a prendere decisioni importanti rispetto alla tecnica di rilascio dei sistemi che puntassero al massimo verso i bisogni aziendali di efficienza e scalabilità. Per il deployment è stato introdotto un approccio MLOps che prevede l’integrazione dei modelli di Machine Lerning con i sistemi di CI/CD e DevOps aziendali e lo stack tecnologico delle soluzioni web aziendali. Il rilascio dei sistemi di Machine Learning secondo il modello adoperato si è rilevato efficiente e rispondente ai bisogni aziendali. Ci si aspetta di migliorare il modello di MLOps attraverso lo sviluppo di soluzioni web sempre più mirate all’integrazione con il modello di ML che i vari applicativi richiedono. Tutti i modelli effettuano inferenza in realtime e sono capaci di trasmettere attraverso le API le informazioni ai sistemi aziendali e a quelli di terze parti.
Farm4trade is an Italian startup that develops high-tech systems for the breeding of production animals and for animal health in general. Among the applications developed there are computer vision systems that take advantage of machine learning. Among these the most important are Photo Animal Identification (PHAID) and Automatic Detection of Abattoir Lesions (ADAL). In the case of these computer vision systems, the business challenge is to release into production to maximize application use to the company clients and to obtain predictions and overall results in real time. These systems must also seamlessly integrate with all business solutions and deliver information to third-party systems. The research work led to making important decisions with respect to the deploy technique of the systems that aimed to the business needs for efficiency and scalability. For the deployment, an MLOps approach was introduced for the integration of Machine Lerning models with CI / CD and DevOps technologies and the IT stack of corporate web solutions. The release of Machine Learning systems according to the model used was found to be efficient and responsive to business needs. All the models make inference in real time and are capable of transmitting information through the API to corporate systems and those of third parties. We expect to improve the MLOps model through the development of web solutions that are increasingly aimed at integration with the ML model that the various applications require.

Style APA, Harvard, Vancouver, ISO itp.

14

Dang, Mihn Huy. "Is seeing still believing?" Thesis, Umeå universitet, Designhögskolan vid Umeå universitet, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-182464.

Pełny tekst źródła

Streszczenie:

Social media content moderators perform a critical function of modern civic society: they act as first responders on social media platforms, getting confronted with harmful digital content on a daily basis.Without them, the Internet would be at the mercy of the unpredictable, global social climate, likely making the Internet a less safe, less peaceful place to be. Nevertheless, disturbing content screening cannot easily be addressed with the future’s planned full integration of artificial intelligence. Content moderation is not a technical challenge that can be solved by employing artificial intelligence as the solution to the content moderation related issues. Automated tools, for example, which are built to recognise creative permutations of language, fail their job. Cultural nuances and linguistic specificities are challenging to algorithms. For this reason, it is important to keep content moderation as a human process, because algorithms are not infallible in the content screening workflow and despite all the struggles content moderators face with screening content. The design concept explores how the emergence of deep fakes can be tackled by social media content moderators without relying too much on algorithms and computer power, but on human skills.

Style APA, Harvard, Vancouver, ISO itp.

15

Moussallik, Laila. "Towards Condition-Based Maintenance of Catenary wires using computer vision : Deep Learning applications on eMaintenance & Industrial AI for railway industry". Thesis, Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-83123.

Pełny tekst źródła

Streszczenie:

Railways are a main element of a sustainable transport policy in several countries as they are considered a safe, efficient and green mode of transportation. Owing to these advantages, there is a cumulative request for the railway industry to increase the performance, the capacity and the availability in addition to safely transport goods and people at higher speeds. To meet the demand, large adjustment of the infrastructure and improvement of maintenance process are required. Inspection activities are essential in establishing the required maintenance, and it is periodically required to reduce unexpected failures and to prevent dangerous consequences. Maintenance of railway catenary systems is a critical task for warranting the safety of electrical railway operation.Usually, the catenary inspection is performed manually by trained personnel. However, as in all human-based inspections characterized by slowness and lack of objectivity, might have a number of crucial disadvantages and potentially lead to dangerous consequences. With the rapid progress of artificial intelligence, it is appropriate for computer vision detection approaches to replace the traditional manual methods during inspections. In this thesis, a strategy for monitoring the health of catenary wires is developed, which include the various steps needed to detect anomalies in this component. Moreover, a solution for detecting different types of wires in the railway catenary system was implemented, in which a deep learning framework is developed by combining the Convolutional Neural Network (CNN) and the Region Proposal Network (RPN).

Style APA, Harvard, Vancouver, ISO itp.

16

Künkel, Rebecca, i Jens Lomander. "How can digitalization and AI be usedto increase the usage of medicallyprescribed physical activity? : A qualitative and quantitative study on thedigitalization of physical activity on prescription". Thesis, Blekinge Tekniska Högskola, Institutionen för kreativa teknologier, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-17449.

Pełny tekst źródła

Streszczenie:

Medically prescribed physical activity (PaP) is a relatively unknown term, howeverit is nothing new. Being used as an alternative to traditional treatment it aimsto reduce the use of chemical medication where possible. This method has provensuccessful on diseases such as high blood pressure, heart attacks, diabetes, depressionetc. Issues with this treatment stems from the fact that as it is today, it is moreinconvenient and harder to follow up with than the alternatives.In this study we have examined an alternative method to treat people with PaP bydeveloping an AI coach for a PaP-focused smartphone application which’s goal it is tomotivate the patients to fulfill their PaP-schedule. We perform both an experimentwith the usage of the developed AI, as well as a literature study in order to evaluatethe efficiency of an AI coach in comparison with today’s method of real life meetingsand little to no contact between patients and prescribers. With this paper we showthat having an AI-made coaching messages can increase the motivation of the usersof a PaP-focused application.

Style APA, Harvard, Vancouver, ISO itp.

17

Ritari, Annette, i Camilla Franzén. "”Vispelar alltid på varandras bästa fot” : En studieom Appreciative Leadership och de fem kärnstrategiernas praktik". Thesis, Mittuniversitetet, Institutionen för kvalitets- och maskinteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-37401.

Pełny tekst źródła

Streszczenie:

Attutforska och definiera vilka faktorer som bygger upp en långsiktigt hållbarverksamhet med välmående och flexibla medarbetare är viktigt i ett samhälle medkrav på snabba förändringar. Appreciative leadership är en ledarskapsfilosofivars praktik i teorin kommer ur de fem kärnstrategier (5 I) och vars förväntadeeffekter starkt korrelerar med det som i litteraturen be-skrivs somfriskfaktorer i arbetslivet. Syftet med arbetet är att bidra med kunskap kringhur de fem kärnstrategierna kan omsättas i praktik och utforska om utövandetger effekter på den psykosociala arbetsmiljön. I studien användes mixed methodsoch resultatet har sin grund en kvantitativ enkät som följdes upp medkvalitativa djupintervjuer samt fokusgrupp. Till grund för resultatet låg ocksåövergripande observationer samt dokumentanalys. Resultatet visar att samtligafem kärnstrategier i hög grad finns närvarande i verksamheten och att samtligamed-arbetare skattade och beskrev sin psykosociala arbetsmiljö som utmärkt. Detkunde också konstateras att utövande av de fem kärnstrategierna i verksamhetentill stor del sker genom ett antal väl valda arbetssätt och metoder, blandannat en stark hjälpande kultur, inre ledarskap och klar kommunikation. Iresultatet går även att utläsa att det finns utmaningar med arbets-sättet ochatt det finns några grundläggande förutsättningar som beskrivs viktiga för attarbets-sättet som helhet ska fungera, däribland hög grundbemanning och starkgemensam värde-grund. Utifrån att kärnstrategiernas praktiska utövande isamtliga steg i studien beskrivs bidra till arbetslivets friskfaktorer ärslutsatsen att det är högst troligt att ett medvetet och praktiskt utövande av5 I kan bidra till en hälsosam arbetsplats, öka arbetsglädjen och iförlängningen minska risken för arbetsrelaterad ohälsa.
In a society which demands rapid change, exploring and defining which factors build up a long-term sustainable organisation with prosperous and flexible employees is important. Appreciative leadership is a leadership philosophy which can be split into five core strategies. (5 I) These strategies strongly correlate with what is described in the literature as ”health factors” in the work environment. The purpose of this study was to discover how the five core strategies can be put in to practice and to explore what effect this has on the psychosocial work environment. The study used mixed methods and the result is based on a quantitative questionnaire that was followed up by qualitative in-depth interviews and focus group. The basis for the result was also general observation and a brief literature review. The result showed that all five core strategies were present in the organization and that all em-ployees described their psychosocial environment as excellent. It was also noticed that the practice of the five core strategies in the organization takes place through a number of well-chosen methods, including a strong supportive culture, internal leadership and clear communi-cation. The result also revealed that there were challenges with the actual way of working and that there were some basic conditions that were described as important for the method as a whole. These included high staffing and strong common values. The practice of the core stra-tegies were described as contributing to the health factors of working. It was concluded that it is highly likely that a conscious practice of 5 I can contribute to a healthy work place, increase work satisfaction and in the long term decrease the risk for work-related illness.

2019-06-27

Style APA, Harvard, Vancouver, ISO itp.

18

Hantrais, L., P. Allin, M. Kritikos, M. Sogomonjan, Prathivadi B. Anand, S. Livingstone, M. Williams i M. Innes. "Covid-19 and the digital revolution". Taylor and Francis, 2020. http://hdl.handle.net/10454/18161.

Pełny tekst źródła

Streszczenie:

Yes
Since the 1980s, the digital revolution has been both a negative and positive force. Within a few weeks of the Covid-19 outbreak, lockdown accelerated the adoption of digital solutions at an unprecedented pace, creating unforeseen opportunities for scaling up alternative approaches to social and economic life. But it also brought digital risks and threats that placed new demands on policymakers. This article assembles evidence from different areas of social science expertise about the impacts of Covid-19 in digitised societies and policy responses. The authors show how the pandemic supported changes in data collection techniques and dissemination practices for official statistics, and how seemingly insuperable obstacles to the implementation of e-health treatments were largely overcome. They demonstrate how the ethics of artificial intelligence became a primary concern for government legislation at national and international levels, and how the features enabling smart cities to act as drivers of productivity did not necessarily give them an advantage during the pandemic. At the micro-level, families are shown to have become ‘digital by default’, as children were exposed to online risks and opportunities. Globally, the spread of the pandemic provided a fertile ground for cybercrime, while digital disinformation and influencing risked becoming normalised and domesticated.
The full-text of this article will be released for public view at the end of the publisher embargo on 01 May 2022.

Style APA, Harvard, Vancouver, ISO itp.

19

Schultze, Jakob. "Digital transformation: How does physician’s work become affected by the use of digital health technologies?" Thesis, Mittuniversitetet, Institutionen för data- och systemvetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-41260.

Pełny tekst źródła

Streszczenie:

Digital transformation is evolving, and it is driving at the helm of the digital evolution. The amount of information accessible to us has revolutionized the way we gather information. Mobile technology and the immediate and ubiquitous access to information has changed how we engage with services including healthcare. Digital technology and digital transformation have afforded people the ability to self-manage in different ways than face-to-face and paper-based methods through different technologies. This study focuses on exploring the use of the most commonly used digital health technologies in the healthcare sector and how it affects physicians’ daily routine practice. The study presents findings from a qualitative methodology involving semi-structured, personal interviews with physicians from Sweden and a physician from Spain. The interviews capture what physicians feel towards digital transformation, digital health technologies and how it affects their work. In a field where a lack of information regarding how physicians work is affected by digital health technologies, this study reveals a general aspect of how reality looks for physicians. A new way of conducting medicine and the changed role of the physician is presented along with the societal implications for physicians and the healthcare sector. The findings demonstrate that physicians’ role, work and the digital transformation in healthcare on a societal level are important in shaping the future for the healthcare industry and the role of the physician in this future.
Den digitala transformationen växer och den drivs vid rodret för den digitala utvecklingen. Mängden information som är tillgänglig för oss har revolutionerat hur vi samlar in information. Mobila tekniker och den omedelbara och allmänt förekommande tillgången till information har förändrat hur vi tillhandahåller oss tjänster inklusive inom vården. Digital teknik och digital transformation har gett människor möjlighet att kontrollera sig själv och sin egen hälsa på olika sätt än ansikte mot ansikte och pappersbaserade metoder genom olika tekniker. Denna studie fokuserar på att utforska användningen av de vanligaste digitala hälsoteknologierna inom hälso- och sjukvårdssektorn och hur det påverkar läkarnas dagliga rutin. Studien presenterar resultat från en kvalitativ metod som involverar semistrukturerade, personliga intervjuer med läkare från Sverige och en läkare från Spanien. Intervjuerna fångar vad läkare tycker om digital transformation, digital hälsoteknik och hur det påverkar deras arbete. I ett fält där brist på information om hur läkare arbetar påverkas av digital hälsoteknik avslöjar denna studie en allmän aspekt av hur verkligheten ser ut för läkare. Ett nytt sätt att bedriva medicin och läkarens förändrade roll presenteras tillsammans med de samhälleliga konsekvenserna för läkare och vårdsektorn. Resultaten visar att läkarnas roll, arbete och den digitala transformationen inom hälso- och sjukvården på samhällsnivå är viktiga för att utforma framtiden för vårdindustrin och läkarens roll i framtiden.

Style APA, Harvard, Vancouver, ISO itp.

20

Ducore, Susan Elizabeth. "FALL PREVENTION SERVICES FOR OLDER ADULT, AMERICAN INDIANS/ALASKA NATIVES: AN EXAMINATION OF KNOWLEDGE, ATTITUDES, AND PRACTICES OF HEALTH CARE PROVIDERS". Case Western Reserve University Doctor of Nursing Practice / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=casednp152581877516155.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

21

Chahin, Pietro, i Christopher Oskarsson. "Hur kan en digital plattform tillämpas för att effektivisera patienthantering? : En kvalitativ fallstudie om implementering av en digital plattform för digitalisering av patienthantering ur ett leverantörsperspektiv". Thesis, Södertörns högskola, Institutionen för naturvetenskap, miljö och teknik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:sh:diva-45962.

Pełny tekst źródła

Streszczenie:

Digital platforms in healthcare have become an increasingly implemented tool to facilitate and streamline daily care work in hospitals and health centers. In parallel with the new digitized era, this digital transformation has had a major impact on individuals' ways of working in healthcare. It is thus significant that digital competence is prioritized to achieve the intended goals regarding streamlining patient management. The qualitative study sheds light on how digi-physical care affects everyday care work and the patient journey. The study also intends to conclude how digital care platforms affect everyday care work, what advantages and disadvantages can be distinguished. The main purpose of the study is to investigate how digital platforms can be implemented to streamline healthcare and thereby investigate such care platforms from an informatics perspective. The research question refers to, how digital platforms can be applied to streamline patient management, is framed from a supplier perspective of such care platforms. The methodology includes an online survey with 10 questions that 11 respondents answered. The survey is supplemented with three in-depth interviews. These in-depth interviews are conducted via the digital tool Microsoft Teams. These respondents are carefully selected to generate relevant first-hand information about the research topic. Based on the respondents' answers, it can be stated that all respondents considered that there are many positive advantages of using digital platforms in healthcare. These positive effects are achieved by implementing digital platforms in a well-thought-out and structured way. Respondents also then pointed out that care providers must be given the right conditions to adequately use the digital care platforms as part of their works. The extensive criticism that digital care providers have received has been encountered in the study. The main criticism is then that digital care providers more easily prioritize more manageable matters such as easier physical ailments especially for patients with higher socioeconomic status. Based on the survey, the importance of implementing digital care platforms from an equal opportunity perspective is emphasized. In the future, digital platforms need to be implemented and developed with the common goal of increasing accessibility for patients and offering more patient-centered healthcare.
Digitala plattformar inom hälso- och sjukvården implementeras allt mer med syfte att underlätta samt effektivisera det vardagliga vårdarbetet på sjukhus och vårdcentraler. Parallellt med den nya digitaliserade eran har denna digitala transformation haft en stor påverkan på individers arbetssätt inom hälso- och sjukvården. Det är därmed signifikant att den digitala kompetensen prioriteras för att uppnå de avsedda målen gällande effektivisering av patienthantering. Den kvalitativa undersökningen belyser hur den digifysiska vården påverkar det vardagliga vårdarbetet samt patienthantering. Studien ämnar även att dra slutsatser kring hur digitala vårdplattformar påverkar det vardagliga vårdarbetet, vilka för och nackdelar som går att urskilja. Syftet med studien är att undersöka på vilket sätt digitala plattformar kan implementeras för att effektivisera sjukvården och därmed bidra med ett forskningsbidrag till informatikämnet. Forskningsfrågan avser hur digitala plattformar kan tillämpas för att effektivisera patienthantering, ur ett leverantörsperspektiv. Datainsamlingen innefattar en online enkät i form av Google formulär med 10 frågor som 11 respondenter fick besvara. Detta kompletteras med tre intervjuer som utförs via det digitala kommunikationsverktyget Microsoft teams. Dessa respondenter är noggrant utvalda för att generera relevant kunskap kring forskningsämnet. Baserat på respondenternas svar går det att konstatera att samtliga respondenter ansåg att det finns många positiva fördelar med tillämpning av digitala plattformar inom hälso- och sjukvård. Positiva effekter uppnås genom att implementeringen av digitala plattformar sker på ett väl genomtänkt och strukturerat sätt. Merparten av respondenterna poängterade att det är viktigt att vårdgivarna ges rätt förutsättningar för att kunna arbeta utifrån den digitala plattformen. Den omfattande kritiken som digitala vårdgivare har fått påvisas i studien. Den främsta kritiken är att digitala vårdgivare prioriterar mer lätthanterliga ärenden såsom lättare fysiska åkommor för dem som har högre socioekonomisk status. Baserat på undersökningen poängteras vikten av att implementera digitala vårdplattformar ur ett jämställdhetsperspektiv. Framöver behöver digitala plattformar implementeras och utvecklas med den gemensamma målsättningen att öka tillgängligheten för patienter och erbjuda en mer patientcentrerad vård.

Style APA, Harvard, Vancouver, ISO itp.

22

Teren, Andrej, Frank Beutner, Kerstin Wirkner, Markus Löffler i Markus Scholz. "Relationship between determinants of arterial stiffness assessed by diastolic and suprasystolic pulse oscillometry". Universitätsbibliothek Leipzig, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-205538.

Pełny tekst źródła

Streszczenie:

Pulse wave velocity (PWV) and augmentation index (AI) are independent predictors of cardiovascular health. However, the comparability of multiple oscillometric modalities currently available for their assessment was not studied in detail. In the present study, we aimed to evaluate the relationship between indices of arterial stiffness assessed by diastolic and suprasystolic oscillometry. In total, 56 volunteers from the general population (23 males; median age 70 years [interquartile range: 65–72 years]) were recruited into observational feasibility study to evaluate the carotid-femoral/aortic PWV (cf/aoPWV), brachial-ankle PWV (baPWV), and AI assessed by 2 devices: Vicorder (VI) applying diastolic, right-sided oscillometry for the determination of all 3 indices, and Vascular explorer (VE) implementing single-point, suprasystolic brachial oscillometry (SSBO) pulse wave analysis for the assessment of cfPWV and AI. Within- and between-device correlations of measured parameters were analyzed. Furthermore, agreement of repeated measurements, intra- and inter-observer concordances were determined and compared for both devices. In VI, both baPWVand cfPWVinter-correlatedwell and showed good level of agreement with bilateral baPWVmeasured byVE (baPWV[VI]– baPWV[VE]R: overall concordance correlation coefficient [OCCC]¼0.484, mean difference¼1.94 m/s; cfPWV[VI]–baPWV[- VE]R: OCCC¼0.493, mean difference¼1.0m/s). In contrast, SSBO derived aortic PWA (cf/aoPWA[VE]) displayed only weak correlation with cfPWV(VI) (r¼0.196; P¼0.04) and ipsilateral baPWV (cf/ aoPWV[VE]R–baPWV[VE]R: r¼0.166; P¼0.08). cf/aoPWA(VE) correlated strongly with AI(VE) (right-sided: r¼0.725, P<0.001). AI exhibited marginal between-device agreement (right-sided: OCCC¼ 0.298, mean difference: 6.12%). All considered parameters showed good-to-excellent repeatability giving OCCC > 0.9 for 2-point-PWV modes and right-sided AI(VE). Intra- and inter-observer concordances were similarly high except for AI yielding a trend toward better reproducibility in VE (interobserver–OCCC[VI] vs [VE]¼0.774 vs 0.844; intraobserver OCCC[VI] vs [VE]¼0.613 vs 0.769). Both diastolic oscillometry-derived PWV modes, and AI measured either with VI or VE, are comparable and reliable alternatives for the assessment of arterial stiffness. Aortic PWV assessed by SSBO in VE is not related to the corresponding indices determined by traditional diastolic oscillometry.

Style APA, Harvard, Vancouver, ISO itp.

23

Berggren, Andreas, Martin Gunnarsson i Johannes Wallin. "Artificial intelligence as a decision support system in property development and facility management". Thesis, Högskolan i Borås, Akademin för textil, teknik och ekonomi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-25535.

Pełny tekst źródła

Streszczenie:

The construction industry has been hesitant for a long time to apply new technologies. In property development, the industry relies heavily on employees bringing experience from one project to another. These employees learn to manage risks in connection with the acquisition of land, but when these people retire, the knowledge disappears. An AI-based decision-support system that takes the risks and the market into account when acquiring land can learn from each project and bring this knowledge into future projects. In facility management, artificial intelligence could increase the efficiency of the allocation of staff in the ongoing operations. The purpose of the study is to analyse how companies in the real estate industry can improve their decision-making with the help of AI in property development and property management. In this study, two case studies of two different players in the real estate industry have been performed. One player, Bygg-Fast, represents property development and the other player, VGR, represents facility management. The study is based on interviews, discussions, and collected data. By mapping and then quantifying the risks and market indicators that are input data in the process, a basis can be created. The data can be used for a model that lays the foundation for an AI-based decision support system that will help the property developer to make calculated decisions in the land acquisition process. By mapping what a flow through a property looks like, measuring points can be set out to analyse how long the activities take in the specific business. These measured values provide a collection of data that makes it easier to plan the activities conducted in the property. A more efficient flow can be achieved by visualizing the entire process so staff can be allocated to the right part of the flow. By being flexible and being able to re-plan the business quickly if planning is disrupted, a high level of efficiency can be achieved. This could be done by an AI-based decision support system that simulates alternative day plans.
Byggbranschen har länge varit tveksamt till att applicera nya tekniker. Inom fastighetsutveckling bygger branschen mycket på att anställda tar med sig erfarenheter från ett projekt till ett annat. Dessa anställda lär sig hantera risker i samband med förvärv av mark men när dessa personer slutar eller går i pension försvinner kunskapen. Ett AI baserat beslutssystem som tar risk och marknad i beaktning vid förvärv av mark kan lära sig av varje projekt och ta med dessa kunskaper till framtida projekt. Inom fastighetsförvaltning skulle artificiell intelligens kunna effektivisera allokerandet av personal i den pågående verksamheten. Syftet med studien är att analysera hur företag i fastighetsbranschen kan förbättra sitt beslutstagande med hjälp av AI i utveckling av fastigheter samt fastighetsförvaltning. I denna studien har två fallstudier av två olika aktörer i fastighetsbranschen utförts. Ena aktören, Bygg-Fast, representerar fastighetsutveckling och den andra aktören, VGR, representerar fastighetsförvaltning. Studien bygger på intervjuer, diskussioner och insamlade data. Genom att kartlägga och sedan kvantifiera de risker samt marknadsindikatorer som är indata i processen kan ett underlag skapas. Underlaget kan användas för en modell som lägger grunden för ett AI baserat beslutsstödsystem som ska hjälpa fastighetsutvecklaren med att ta kalkylerade beslut i mark förvärvsprocessen. Genom att kartlägga hur ett flöde genom en fastighet ser ut kan mätpunkter sättas ut för att analysera hur lång tid aktiviteterna tar i den specifika verksamheten. Dessa mätvärden ger en samlad data som gör det lättare att planera verksamheten som bedrivs i fastigheten. Ett effektivare flöde kan uppnås genom att visualisera hela processen så personal kan allokeras till rätt del av flödet. Genom att vara flexibel och kunna planera om verksamheten snabbt ifall planering störs kan en hög effektivitet nås. Detta skulle kunna göras av ett AI baserat beslutsstödsystem som simulerar alternativa dagsplaneringar.

Style APA, Harvard, Vancouver, ISO itp.

24

Galozy, Alexander. "Towards Understanding ICU Procedures using Similarities in Patient Trajectories : An exploratory study on the MIMIC-III intensive care database". Thesis, Högskolan i Halmstad, CAISR Centrum för tillämpade intelligenta system (IS-lab), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-37416.

Pełny tekst źródła

Streszczenie:

Recent advancements in Artificial Intelligence has prompted a shearexplosion of new research initiatives and applications, improving notonly existing technologies, but also opening up opportunities for newand exiting applications. This thesis explores the MIMIC-III intensive care unit database and conducts experiment on an interpretable feature space based on sever-ty scores, defining a patient health state, commonly used to predict mortality in an ICU setting. Patient health state trajectories are clustered and correlated with administered medication and performed procedures to get a better understanding of the potential usefulness in evaluating treatments on their effect on said health state, where commonalities and deviations in treatment can be understood. Furthermore, medication and procedure classification is carried out to explore their predictability using the severity subscore feature space.

Style APA, Harvard, Vancouver, ISO itp.

25

Pop, David. "Classification of Heart Views in Ultrasound Images". Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-165276.

Pełny tekst źródła

Streszczenie:

In today’s society, we experience an increasing challenge to provide healthcare to everyone in need due to the increasing number of patients and the shortage of medical staff. Computers have contributed to mitigating this challenge by offloading the medical staff from some of the tasks. With the rise of deep learning, countless new possibilities have opened to help the medical staff even further. One domain where deep learning can be applied is analysis of ultrasound images. In this thesis we investigate the problem of classifying standard views of the heart in ultrasound images with the help of deep learning. We conduct mainly three experiments. First, we use NasNet mobile, InceptionV3, VGG16 and MobileNet, pre-trained on ImageNet, and finetune them to ultrasound heart images. We compare the accuracy of these networks to each other and to the baselinemodel, a CNN that was proposed in [23]. Then we assess a neural network’s capability to generalize to images from ultrasound machines that the network is not trained on. Lastly, we test how the performance of the networks degrades with decreasing amount of training data. Our first experiment shows that all networks considered in this study have very similar performance in terms of accuracy with Inception V3 being slightly better than the rest. The best performance is achieved when the whole network is finetuned to our problem instead of finetuning only apart of it, while gradually unlocking more layers for training. The generalization experiment shows that neural networks have the potential to generalize to images from ultrasound machines that they are not trained on. It also shows that having a mix of multiple ultrasound machines in the training data increases generalization performance. In our last experiment we compare the performance of the CNN proposed in [23] with MobileNet pre-trained on ImageNet and MobileNet randomly initialized. This shows that the performance of the baseline model suffers the least with decreasing amount of training data and that pre-training helps the performance drastically on smaller training datasets.

Style APA, Harvard, Vancouver, ISO itp.

26

Peres, Gustavo. "Avaliação da tixoconformabilidade de ligas AI-Xwt%Si-5wt%Zn". [s.n.], 2012. http://repositorio.unicamp.br/jspui/handle/REPOSIP/264074.

Pełny tekst źródła

Streszczenie:

Orientador: Eugenio José Zoqui
Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica
Made available in DSpace on 2018-08-19T17:22:12Z (GMT). No. of bitstreams: 1 Peres_Gustavo_M.pdf: 111652951 bytes, checksum: c9dbda5e8dc0115d433971c0cb37b4c1 (MD5) Previous issue date: 2012
Resumo: O presente projeto avaliou a tixoconformabilidade de ligas a base de Al-Si-Zn, tendo em vista sua aplicação em escala industrial no que tange a processos de tixoconformação, ou seja, processos que envolvam sua conformação no estado semi-sólido. Para tal objetivo as ligas foram preparas e produzidas em laboratório, fixando-se sua composição química em 5% (em massa) de zinco e variando-se a massa de silício em 3%, 4%, 5% e 6%. Para a produção desse material foi utilizada matriz apresentando agitação eletromagnética em seu interior, visando à agitação da matéria-prima desde seu estado fundido até sua solidificação. Após a produção das matérias primas, estas foram reaquecidas a temperatura semi-sólida utilizando-se como base dois valores, 45% e 60% de fração sólida e estabilizadas a essas temperaturas durante tempos de 0, 30, 90 e 210 segundos. Após o reaquecimento parte da amostras foram resfriadas rapidamente em água para "congelamento" da microestrutura e posterior análise metalográfica, já outra parte das amostras foram submetidas a ensaios de compressão a quente para avaliação de sua viscosidade. Como resultado final observou-se que as ligas apresentaram pouca variação de propriedades, seja tamanho de grão ou viscosidade, para todas as condições estudadas porém, a liga Al-5wt%Si- 5wt%Zn (45% de fração sólida, 30 à 90 segundos de globularização) apresentou uma viscosidade um pouco mais baixa em comparação com as demais condições analisadas, sendo a liga com maior potencial de aplicação em processos de tixoconformação em larga escala. Além disso, a baixa variação de viscosidade observada entre as diversas configurações estudadas é outro ponto de favorecimento a aplicação dessas ligas em reofundição, dada a baixa necessidade de controle preciso de parâmetros como temperatura de fração sólida ou tempo de globularização para conformação, o que é desejável em processos industriais
Abstract: The present project evaluated the thixoformability of Al-Si-Zn alloys, in order to verify their industrial application range in process of thixoforming, it means, processes that use forming at semi-solid state. To achieve this goal the alloys were prepared and produced in laboratory, fixing their chemical composition in 5% (in mass) of zinc and varying the mass of silicon in 3%, 4%, 5% and 6%. To produce the feedstocks was used matrix presenting electromagnetic stirring to provide the best microstructure to the slurries. After having the castings produced, they were re-heated to semi-solid condition, based on two temperatures, 45% and 60% of solid-fraction of the material, then they were stabilized at such temperatures during times of 0, 30, 90 and 210 seconds. After being re-heated, part of the castings were quenched in water for "freezing" of their microstructure and posterior metallographic analysis, moreover the remaining castings were submitted to hot compress tests to evaluate their viscosity as well. As final result could be observed that all alloys presented a low variation of properties (grain size, viscosity etc), for all the conditions analyzed however, the Al-5wt%Si-5wt%Zn alloy (45% of solid-fraction, 30 to 90 seconds of globularization) presented the lowest viscosity in comparison with the other conditions studied, so this alloy is the one that presents the biggest potential to be applied in thixoforming processes in wide scale. Furthermore, the low level of viscosity variation noticed all over the conditions analyzed is another relevant factor that put these alloys in a good level concerning rheocasting, due to the non-necessity of a rigid control of parameters like solidfraction temperature or globularization time, which is desirable at industrial processes
Mestrado
Materiais e Processos de Fabricação
Mestre em Engenharia Mecânica

Style APA, Harvard, Vancouver, ISO itp.

27

Alzwayi, Mabroukah M. A. "An investigation of the effect of short bouts of exercise on adiponectin concentrations in young healthy females". Thesis, University of Glasgow, 2013. http://theses.gla.ac.uk/4552/.

Pełny tekst źródła

Streszczenie:

White adipose tissue is not just a storage organ. It is now recognised as an endocrine organ. It secretes many substances known as adipokines, which are thought to link obesity with type 2 diabetes (T2D). One of the most important adipokines is adiponectin. It is a peptide hormone consisting of 244 amino acids with molecular weight of 30 KD. It circulates in plasma in high concentrations (3-30 4g/ml). Adiponectin polymerises to form many bigger forms. Those are low molecular weight (LMW); middle molecular weight (MMW) and high molecular weight (HMW). The HMW adiponectin is the active form of the hormone. The concentrations of most adipokines are increased in obese people. Adiponectin is unusual in that its concentration is lower in obese people. Consequently its concentration is decreased in some related metabolic disorders. Its concentrations decrease in cardiovascular diseases, diabetes, dyslipidemia and insulin resistances. It is well known that exercise increases insulin sensitivity, also adiponectin was reported to regulate insulin. The effect of exercise on the adiponectin concentrations in plasma is controversial, but the extent to which the exercise regulates the interstitial adiponectin concentrations is not fully examined. The main site of adipokines secretion is adipose tissue. Therefore the study of these substances at the site of their production has a special interest. Recently, microdialysis techniques have been extended to become important in the measurement of substances in the extracellular fluid of many tissues such as subcutaneous adipose tissue. In particular, it has been used for measurement of adipokines. This thesis includes three studies. The first study was aimed at examining the effect of one hour of moderate exercise at 50% of maximum oxygen consumption v on adiponectin concentration in dialysate samples taken from subcutaneous abdominal adipose tissues (SCAAT). 15 healthy young female volunteers, age 22.8 ± 3.0 years (mean ± SD) participated in this experiment divided into two groups depending on their body mass index (BMI), a lean group BMI 22.2 ± 1.6 kg/m2 (mean ± SD) and an overweight group BMI 27.7 ± 1.9 kg/m2 (mean ± SD). The samples were collected using CMA 66 M. Alzwayi iii microdialysis catheters with membrane cut off 100 KD. Fitness assessment was done for all volunteers about one week before the main trials. The main trials were done on two consecutive days, a rest day and an exercise day. Each day lasted for 4 to 6 hours. On the first day the microdialysis catheter were inserted in abdominal subcutaneous tissue 4 cm lateral to the umbilicus on the left side. Dialysate samples were collected every 30 - 45 minutes. On the exercise day volunteers exercised for one hour at 50% 2 . V O max. All samples were analysed for adiponectin concentrations using Mercodia ELISA technique. The principle findings of this study were that CMA 66 microdialysis catheters worked effectively for two consecutive days for fluid recovery. Adiponectin concentrations were very low and varied, in same volunteer from time to time, and between volunteers. However, the statistical analysis showed no significant difference in adiponectin concentrations between lean and overweight groups. Adiponectin concentrations in the first two samples on the first day of the insertion were significantly higher than the first two samples on the second day of the insertion. Finally, adiponectin concentrations in dialysate samples recovered by 100 KD microdialysis catheters were very low. Therefore, the effect of the exercise was not clear. The second study aimed to compare the adiponectin concentrations in plasma and dialysate samples. Six healthy male volunteers age 32.8 ± 13.1 years and BMI 25.9 ± 3.3 kg/m2 (mean ± SD), were recruited for this study. The experiment was run for two consecutive days using the same microdialysis catheters CMA 66. Dialysate samples were collected as before. 2 ml of blood samples were collected using a cannula inserted into the anticubital vein. Samples were taken every hour for a period of five hours each day. The plasma and dialysate samples were analysed for adiponectin using the Mercodia kits. Adiponectin concentrations in plasma samples were 256 and 1791 times higher than the adiponectin concentrations in dialysate samples. The conclusion of the two studies was that the CMA 66 microdialysis catheter with cut off 100 KD membranes only recovers a small part of the total adiponectin present. M. Alzwayi iv Therefore a third study was designed to use plasma samples. The aim of the study was to investigate the effect of acute exercise at 50% 2 . V O max on HMW adiponectin, total adiponectin, interleukin (IL)-6, tumour necrosis factor alpha (TNF-α), insulin and glucose concentrations directly after the exercise, one hour after and 48 hours. 13 young healthy female volunteers age 24.3 ± 2.7 years and BMI 21.9 ± 2.2 kg/m2 (mean ± SD) contributed in this study. The volunteers were invited for five visits. Their fitness was measured on the first visit. Then they came for two main trials rest day and exercise day, which they were randomly assigned. The main trails lasted for two hours. Three blood samples were collected each day using same cannulated system in the second study. The volunteers followed 48 hours after each trial, one blood sample were collected each day. The 8 plasma samples were analysed for: total adiponectin and insulin concentrations via Mercodia ELISA kits, HMW adiponectin, IL-6 and TNF-α concentration via R&D systems and glucose concentration using the glucose oxidase colorimetric method. The results showed no statistical difference in total or HMW adiponectin, TNF-α and glucose concentrations under the effect of moderate exercise at 50% 2 . V O max either directly or 48 (p value > 0.05). IL-6 concentrations increased about two fold one hour after the exercise above the resting level (P value < 0.05). IL-6 concentrations return to the basal level 48 hour latter. Insulin concentrations show a decrease one hour after the exercise finished. The number of volunteers was small and the change was close to significance. A one way ANOVA returned a P value of < 0.05, but a two way ANOVA with repeated measures returned a P value of > 0.05. In conclusion, the acute exercise at 50% 2 . V O max changes IL-6 concentrations but it has no effect on adiponectin concentrations in dialysate or plasma samples. Low adiponectin concentration is related to obesity, insulin resistance and T2D. Therefore, increase in adiponectin concentration probably lies in weight loss and the exercise may play role, even if it has little direct action on adiponectin concentration.

Style APA, Harvard, Vancouver, ISO itp.

28

Ali, Abid. "Analyse vidéo à l'aide de réseaux de neurones profonds : une application pour l'autisme". Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4066.

Pełny tekst źródła

Streszczenie:

La compréhension des actions dans les vidéos est un élément crucial de la vision par ordinateur, avec des implications significatives dans divers domaines. À mesure que notre dépendance aux données visuelles augmente, comprendre et interpréter les actions humaines dans les vidéos devient essentiel pour faire progresser les technologies dans la surveillance, les soins de santé, les systèmes autonomes et l'interaction homme-machine. L'interprétation précise des actions dans les vidéos est fondamentale pour créer des systèmes intelligents capables de naviguer efficacement et de répondre aux complexités du monde réel. Dans ce contexte, les avancées dans la compréhension des actions repoussent les limites de la vision par ordinateur et jouent un rôle crucial dans la transformation des applications de pointe qui impactent notre quotidien. La vision par ordinateur a réalisé des progrès significatifs avec l'essor des méthodes d'apprentissage profond, telles que les réseaux de neurones convolutifs (CNN), repoussant les frontières de la vision par ordinateur et permettant à la communauté de progresser dans de nombreux domaines, notamment la segmentation d'images, la détection d'objets, la compréhension des scènes, et bien plus encore. Cependant, le traitement des vidéos reste limité par rapport aux images statiques. Dans cette thèse, nous nous concentrons sur la compréhension des actions, en la divisant en deux parties principales : la reconnaissance d'actions et la détection d'actions, ainsi que leur application dans le domaine médical pour l'analyse de l'autisme. Dans cette thèse, nous explorons les divers aspects et défis de la compréhension des vidéos, tant d'un point de vue général que spécifique à une application. Nous présentons ensuite nos contributions et solutions pour relever ces défis. De plus, nous introduisons le jeu de données ACTIVIS, conçu pour diagnostiquer l'autisme chez les jeunes enfants. Notre travail est divisé en deux parties principales : la modélisation générique et les modèles appliqués. Dans un premier temps, nous nous concentrons sur l'adaptation des modèles d'images pour les tâches de reconnaissance d'actions en incorporant la modélisation temporelle à l'aide de techniques de fine-tuning efficaces en paramètres (PEFT). Nous abordons également la détection et l'anticipation des actions en temps réel en proposant un nouveau modèle conjoint pour l'anticipation des actions et la détection d'actions en ligne dans des scénarios de la vie réelle. En outre, nous introduisons une nouvelle tâche appelée "interaction lâche" dans des situations dyadiques et ses applications dans l'analyse de l'autisme. Enfin, nous nous concentrons sur l'aspect appliqué de la compréhension des vidéos en proposant un modèle de reconnaissance d'actions pour les comportements répétitifs dans les vidéos d'individus autistes. Nous concluons en proposant une méthode faiblement supervisée pour estimer le score de gravité des enfants autistes dans des vidéos longues
Understanding actions in videos is a crucial element of computer vision with significant implications across various fields. As our dependence on visual data grows, comprehending and interpreting human actions in videos becomes essential for advancing technologies in surveillance, healthcare, autonomous systems, and human-computer interaction. The accurate interpretation of actions in videos is fundamental for creating intelligent systems that can effectively navigate and respond to the complexities of the real world. In this context, advances in action understanding push the boundaries of computer vision and play a crucial role in shaping the landscape of cutting-edge applications that impact our daily lives. Computer vision has made significant progress with the rise of deep learning methods such as convolutional neural networks (CNNs) pushing the boundaries of computer vision and enabling the computer vision community to advance in many domains, including image segmentation, object detection, scene understanding, and more. However, video processing remains limited compared to static images. In this thesis, we focus on action understanding, dividing it into two main parts: action recognition and action detection, and their application in the medical domain for autism analysis.In this thesis, we explore the various aspects and challenges of video understanding from a general and an application-specific perspective. We then present our contributions and solutions to address these challenges. In addition, we introduce the ACTIVIS dataset, designed to diagnose autism in young children. Our work is divided into two main parts: generic modeling and applied models. Initially, we focus on adapting image models for action recognition tasks by incorporating temporal modeling using parameter-efficient fine-tuning (PEFT) techniques. We also address real-time action detection and anticipation by proposing a new joint model for action anticipation and online action detection in real-life scenarios. Furthermore, we introduce a new task called 'loose-interaction' in dyadic situations and its applications in autism analysis. Finally, we concentrate on the applied aspect of video understanding by proposing an action recognition model for repetitive behaviors in videos of autistic individuals. We conclude by proposing a weakly-supervised method to estimate the severity score of autistic children in long videos

Style APA, Harvard, Vancouver, ISO itp.

29

Ricci, Matteo. "La stimolazione del Nervo Vago attraverso la pratica di tecniche respiratorie ai fini della neuroimmunomodulazione del riflesso infiammatorio: a Scoping Review". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/21932/.

Pełny tekst źródła

Streszczenie:

Introduzione: I neuroni colinergici ricoprono un ruolo importante nella regolazione dei processi flogistici, tale scoperta ha portato la ricerca scientifica ad approfondire questo aspetto, provando che la stimolazione del Nervo Vago può essere utilizzata nel trattamento delle patologie infiammatorie. La respirazione potrebbe essere una tecnica volta a stimolare il Nervo Vago, inducendo cosi spostamenti nell’equilibrio simpatico-vagale verso una predominanza parasimpatica, con i conseguenti riflessi anti-infiammatori. Materiali e metodi: È stata effettuata una prima ricerca in letteratura per identificare studi che provassero la funzione immunologica, anti-infiammatoria, bi-direzionale del Nervo Vago. Attraverso la seconda ricerca è stata analizzata la possibile correlazione tra la pratica di pattern respiratori e la stimolazione del Nervo Vago analizzando i marker tonici vagali. Sono stati visionati i database elettronici PUBMED, CINAHL, COCHRANE e PEDRO. La ricerca è stata effettuata nel periodo che va da marzo 2020 ad ottobre 2020. Risultati: Il Nervo Vago è coinvolto nell’omeostasi dei processi infiammatori attraverso un sistema di controllo bi-direzionale neuroimmunologico. È capace di individuare i processi flogistici silenti nella periferia attraverso le vie afferenti, e mediante la via efferente colinergica anti- infiammatoria li disattiva. In base agli studi analizzati, un pattern respiratorio di circa 6 cicli resp/ min con un rapporto basso tra inspirazione ed espirazione evidenzia un aumento significativo nell’analisi dello spettro dell’ Heart Rate Variability, del baroriflesso e dell’aritmia sinusale respiratoria. Conclusioni: In accordo con i risultati biofisici e neurofisiologici e con le attuali pratiche medico ingegneristiche che utilizzano la stimolazione del Nervo Vago, nel trattamento di diverse patologie, si vuole invogliare la ricerca scientifica ad indagare un possibile utilizzo terapeutico della respirazione.

Style APA, Harvard, Vancouver, ISO itp.

30

Wåhlin, Peter. "Enhanching the Human-Team Awareness of a Robot". Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-16371.

Pełny tekst źródła

Streszczenie:

The use of autonomous robots in our society is increasing every day and a robot is no longer seen as a tool but as a team member. The robots are now working side by side with us and provide assistance during dangerous operations where humans otherwise are at risk. This development has in turn increased the need of robots with more human-awareness. Therefore, this master thesis aims at contributing to the enhancement of human-aware robotics. Specifically, we are investigating the possibilities of equipping autonomous robots with the capability of assessing and detecting activities in human teams. This capability could, for instance, be used in the robot's reasoning and planning components to create better plans that ultimately would result in improved human-robot teamwork performance. we propose to improve existing teamwork activity recognizers by adding intangible features, such as stress, motivation and focus, originating from human behavior models. Hidden markov models have earlier been proven very efficient for activity recognition and have therefore been utilized in this work as a method for classification of behaviors. In order for a robot to provide effective assistance to a human team it must not only consider spatio-temporal parameters for team members but also the psychological.To assess psychological parameters this master thesis suggests to use the body signals of team members. Body signals such as heart rate and skin conductance. Combined with the body signals we investigate the possibility of using System Dynamics models to interpret the current psychological states of the human team members, thus enhancing the human-awareness of a robot.
Användningen av autonoma robotar i vårt samhälle ökar varje dag och en robot ses inte längre som ett verktyg utan som en gruppmedlem. Robotarna arbetar nu sida vid sida med oss och ger oss stöd under farliga arbeten där människor annars är utsatta för risker. Denna utveckling har i sin tur ökat behovet av robotar med mer människo-medvetenhet. Därför är målet med detta examensarbete att bidra till en stärkt människo-medvetenhet hos robotar. Specifikt undersöker vi möjligheterna att utrusta autonoma robotar med förmågan att bedöma och upptäcka olika beteenden hos mänskliga lag. Denna förmåga skulle till exempel kunna användas i robotens resonemang och planering för att ta beslut och i sin tur förbättra samarbetet mellan människa och robot. Vi föreslår att förbättra befintliga aktivitetsidentifierare genom att tillföra förmågan att tolka immateriella beteenden hos människan, såsom stress, motivation och fokus. Att kunna urskilja lagaktiviteter inom ett mänskligt lag är grundläggande för en robot som ska vara till stöd för laget. Dolda markovmodeller har tidigare visat sig vara mycket effektiva för just aktivitetsidentifiering och har därför använts i detta arbete. För att en robot ska kunna ha möjlighet att ge ett effektivt stöd till ett mänskligtlag måste den inte bara ta hänsyn till rumsliga parametrar hos lagmedlemmarna utan även de psykologiska. För att tyda psykologiska parametrar hos människor förespråkar denna masteravhandling utnyttjandet av mänskliga kroppssignaler. Signaler så som hjärtfrekvens och hudkonduktans. Kombinerat med kroppenssignalerar påvisar vi möjligheten att använda systemdynamiksmodeller för att tolka immateriella beteenden, vilket i sin tur kan stärka människo-medvetenheten hos en robot.

The thesis work was conducted in Stockholm, Kista at the department of Informatics and Aero System at Swedish Defence Research Agency.

Style APA, Harvard, Vancouver, ISO itp.

31

Elias, Pedro Luis Gomes. "Developing a framework to improve reproducibility in AI models for the health domain". Master's thesis, 2021. https://hdl.handle.net/10216/138045.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

32

Floruss, Julia, i Nico Vahlpahl. "Artificial Intelligence in Healthcare : Acceptance of AI-based Support Systems by Healthcare Professionals". Thesis, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-48572.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

33

MinHu, Jui, i 胡瑞敏. "Value Co-Creation of Long-Term Health Care Institution: The case of Tong Ren Ren-ai Senior Citizens’ Home". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/s5yp68.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

34

Lin, Meng-jie, i 林孟潔. "Effectiveness of Community-based Health Promotion in Change of Knowledge, Attitude and Practice toward Tuberculosis: An Example of Da-Ai Village, Jakarta, Indonesia". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/04413470751829340400.

Pełny tekst źródła

Streszczenie:

碩士
慈濟大學
公共衛生學系碩士班
100
Origin: In the early 2002, Jakarta, Indonesia was flooded by heavy rain. The Tzu-chi foundation in Indonesia brought up a relocation plan. After the relocation, our main goal of the study were health adaptation and quality of the environment for those who lived in Da-Ai villages I and II. Through repeatedly interviews with the residents in Da-Ai villages, we understood that the most concerned disease is Tuberculosis (TB). Objective: To use health promotion to enhance knowledge, attitude and behavior toward tuberculosis of the residents in Da-Ai village I and Tzu-chi school students. Method: This study used quasi-experimental design, based on the limitations of the real situation, to distribute participants into the case group and control group. The case group: Da-Ai village I (N=650) and Tzu-chi school in Da-Ai village I (N=817). The control group: Da-Ai village II (N=541) and three public schools in north Jakarta (N=825). The health promotion applied in Da-Ai village I included TB lectures for parents of students in Tzu-chi schools, education about TB control and prevention in community, chest X-ray screening and propaganda using TB posters and calendars. The health promotion applied in Tzu-chi school included media disseminating, activity disseminating and TB issue education. Pre and post- questionnaires were conducted to get the scores about TB knowledge, attitude and behavior of the case group and control group of community residents and students. Chi-square test, ANOVA, F test and T test were used to compare scores about TB knowledge, attitude and behavior before and after health promotion for community residents and Tzu-chi school students. Result: After health promotion. The scores about TB knowledge of residents in Da-Ai village I was significantly higher than that in Da-Ai village II (p=0.046). Female had better TB knowledge than male (p=0.038). Those who had high level of education had better TB knowledge than those having low level of education (p<0.001). Tzu-chi school students’ TB knowledge and attitude scores were significantly higher than public school students’ scores (p<0.001). Female students had better knowledge scores than male students (p=0.002). Students with high level of education had higher scores of TB knowledge than those with low level of education. Conclusion: The combination of school system and community as a multi-intensive health promotion unit for TB promotion was useful, and schools could be a pipeline to establish contact with community residents. In other dense communities where residents having strong relationship with schools could follow the health promotion model in this study to promote the knowledge of tuberculosis, then to achieve the effect of prevention from tuberculosis.

Style APA, Harvard, Vancouver, ISO itp.

35

(10695907), Wo Jae Lee. "AI-DRIVEN PREDICTIVE WELLNESS OF MECHANICAL SYSTEMS: ASSESSMENT OF TECHNICAL, ENVIRONMENTAL, AND ECONOMIC PERFORMANCE". Thesis, 2021.

Znajdź pełny tekst źródła

Streszczenie:

One way to reduce the lifecycle cost and environmental impact of a product in a circular economy is to extend its lifespan by either creating longer-lasting products or managing the product properly during its use stage. Life extension of a product is envisioned to help better utilize raw materials efficiently and slow the rate of resource depletion. In the case of manufacturing equipment (e.g., an electric motor on a machine tool), securing reliable service life as well as the life extension are important for consistent production and operational excellence in a factory. However, manufacturing equipment is often utilized without a planned maintenance approach. Such a strategy frequently results in unplanned downtime, owing to unexpected failures. Scheduled maintenance replaces components frequently to avoid unexpected equipment stoppages, but increases the time associated with machine non-operation and maintenance cost.

Recently, the emergence of Industry 4.0 and smart systems is leading to increasing attention to predictive maintenance (PdM) strategies that can decrease the cost of downtime and increase the availability (utilization rate) of manufacturing equipment. PdM also has the potential to foster sustainable practices in manufacturing by maximizing the useful lives of components. In addition, advances in sensor technology (e.g., lower fabrication cost) enable greater use of sensors in a factory, which in turn is producing greater and more diverse sets of data. Widespread use of wireless sensor networks (WSNs) and plug-and-play interfaces for the data collection on product/equipment states are allowing predictive maintenance on a much greater scale. Through advances in computing, big data analysis is faster/improved and has allowed maintenance to transition from run-to-failure to statistical inference-based or machine learning prediction methods.

Moreover, maintenance practice in a factory is evolving from equipment “health management” to equipment “wellness” by establishing an integrated and collaborative manufacturing system that responds in real-time to changing conditions in a factory. The equipment wellness is an active process of becoming aware of the health condition and of making choices that achieve the full potential of the equipment. In order to enable this, a large amount of machine condition data obtained from sensors needs to be analyzed to diagnose the current health condition and predict future behavior (e.g., remaining useful life). If a fault is detected during this diagnosis, a root cause of a fault must be identified to extend equipment life and prevent problem reoccurrence.

However, it is challenging to build a model capturing a relationship between multi-sensor signals and mechanical failures, considering the dynamic manufacturing environment and the complex mechanical system in equipment. Another key challenge is to obtain usable machine condition data to validate a method.

A goal of the proposed work is to develop a systematic tool for maintenance in manufacturing plants using emerging technologies (e.g., AI, Smart Sensor, and IoT). The proposed method will facilitate decision-making that supports equipment maintenance by rapidly detecting a worn component and estimating remaining useful life. In order to diagnose and prognose a health condition of equipment, several data-driven models that describe the relationships between proxy measures (i.e., sensor signals) and machine health conditions are developed and validated through the experiment for several different manufacturing-oriented cases (e.g., cutting tool, gear, and bearing). To enhance the robustness and the prediction capability of the data-driven models, signal processing is conducted to preprocess the raw signals using domain knowledge. Through this process, useful features from the large dataset are extracted and selected, thus increasing computational efficiency in model training. To make a decision using the processed signals, a customized deep learning architecture for each case is designed to effectively and efficiently learn the relationship between the processed signals and the model’s outputs (e.g., health indicators). Ultimately, the method developed through this research helps to avoid catastrophic mechanical failures, products with unacceptable quality, defective products in the manufacturing process as well as to extend equipment service life.

To summarize, in this dissertation, the assessment of technical, environmental and economic performance of the AI-driven method for the wellness of mechanical systems is conducted. The proposed methods are applied to (1) quantify the level of tool wear in a machining process, (2) detect different faults from a power transmission mini-motor testbed (CNN), (3) detect a fault in a motor operated under various rotation speeds, and (4) to predict the time to failure of rotating machinery. Also, the effectiveness of maintenance in the use stage is examined from an environmental and economic perspective using a power efficiency loss as a metric for decision making between repair and replacement.

Style APA, Harvard, Vancouver, ISO itp.

36

"Effects of a Novel AI Mobile App on Symptom Severity in Subjects with Irritable Bowel Syndrome: A Randomized Controlled Trial". Master's thesis, 2020. http://hdl.handle.net/2286/R.I.57197.

Pełny tekst źródła

Streszczenie:

abstract: Introduction: A diet high in fermented, oligio-, di-, monosaccharide, and polyols (FODMAP) has been shown to exacerbate symptoms of irritable bowel syndrome (IBS). Previous literature has shown significant improvement in IBS symptoms after adherence to a low FODMAP diet (LFD). However, dietary adherence to the LFD is difficult with patients stating that information provided by healthcare providers (HCPs) is generalized and nonspecific requiring them to search for supplementary information to fit their needs. Notably, studies that have used a combination of online and in-person methods for treatment have shown improved adherence to the LFD. Objective: To determine whether a novel artificial intelligence (AI) dietary mobile application will improve adherence to the LFD compared to a standard online dietary intervention (CON) in populations with IBS or IBS-like symptoms over a 4- week period. Methods: Participants were randomized into two groups: APP or CON. The intervention group was provided access to an AI mobile application, a dietary resource verified by registered dietitians which uses artificial intelligence to individualize dietary guidance in real-time with the ability to scan menus and barcodes and provide individuals with food scores based on their dietary preferences. Primary measures included mobile app engagement, dietary adherence, and manifestation of IBS-like symptoms. Baseline Results: A total of 58 participants were randomized to groups. This is an ongoing study and this thesis details the methodology and baseline characteristics of the participants at baseline and intervention start. Validation of the application could improve the range of offerings for lifestyle diseases treatable through dietary modification.
Dissertation/Thesis
Masters Thesis Nutrition 2020

Style APA, Harvard, Vancouver, ISO itp.

37

Improta, Giovanni. "L'HTA (HEALTH TECHNOLOGY ASSESSMENT) PER IL MANAGEMENT DELLE APPARECCHIATURE BIOMEDICALI DI UN'AZIENDA OSPEDALIERA: RIALLOCAZIONE, DONAZIONE AI PAESI IN VIA DI SVILUPPO, IDEAZIONE E PROGETTAZIONE DI UNA COMUNITÀ VIRTUALE". Tesi di dottorato, 2010. http://www.fedoa.unina.it/8066/1/Improta_Giovanni_23.pdf.

Pełny tekst źródła

Streszczenie:

Al centro dell’analisi c’è lo studio delle possibili procedure di donazione delle apparecchiature biomediche dismesse ma ancora funzionanti via web nell’ambito del Management Sanitario. Nella prima parte dell’elaborato vengono presentati gli strumenti necessari per la classificazione delle apparecchiature biomediche e si sottolinea la necessita della realizzazione e dell’introduzione di uno strumento in grado di valutare le apparecchiature biomedicali, al fine di dichiararne l’eventuale dismissione, al fine di garantire una corretta riorganizzazione del patrimonio tecnologico di qualsivoglia struttura sanitaria. In particolare, coerentemente con una gestione razionalizzata e ottimizzata delle risorse messe a disposizione dal Governo centrale e dalle Regioni, è stato indispensabile ottenere informazioni precise su ogni singolo passo del ciclo di vita di quelle tecnologie ritenute critiche non soltanto per gli effetti che possono avere sullo stato di salute o la qualità della vita di un individuo, ma anche per le modalità con le quali si interfacciano con la struttura nella quale si trovano. Il protocollo realizzato in questo lavoro è stato il presupposto indispensabile per determinare l’eventuale dismissione delle apparecchiature biomedicali poiché, attraverso tale strumento, è stato possibile definire la situazione riguardante la convenienza o la necessità di una dismissione di una o più apparecchiature e/o eventuali nuovi acquisti e, dunque, di conoscere meglio la realtà operativa delle apparecchiature sanitarie appartenenti all’ A.O.R.N. “A. Cardarelli” ed agire di conseguenza, per evitare inutili sprechi sia di risorse che di denaro. Il valore numerico, attraverso il quale l’apparecchiatura viene classificata consente di determinare se l’oggetto in esame risulta pienamente rispondente ai criteri o si trova in Fuori Uso indifferibile o in Fuori Uso programmato: in questo caso, si potrà procedere alla riallocazione o alla donazione, che, prescindendo dall’aspetto legale, rappresentano due valide modalità attraverso le quali continuare ad utilizzare efficacemente le macchine in esame, poiché se in un caso risulta possibile applicare una ridistribuzione del patrimonio tecnologico della struttura sanitaria, nell’altro si realizza una procedura contrattuale attraverso la quale un bene, che altrimenti sarebbe non utilizzato e destinato alla distruzione, viene donato a un’altra struttura donataria. In seguito, alla luce della necessità di migliorare il processo di donazione di apparecchiature biomedicali, per il reciproco vantaggio di donatori e beneficiari, si è proceduto con la creazione di un portale web che consente ai due attori principali di questo sistema di interagire, dotando il portale degli strumenti necessari ad entrambi aumentando cosi l’efficacia delle procedure di donazione. Per sviluppare questa parte si è seguita una linea di tipo economico-gestionale, non prima però di aver fatto luce sulle tecniche di progettazione dei siti web, quali struttura motore di ricerca, interfaccia di navigazione, url e contenuti. Successivamente è stato sviluppato un classico Business Plan nel quale si è ipotizzata la creazione di una società, per la creazione di una comunità virtuale che permettesse la donazione di apparecchiature biomedicali. Il business plan è artcolato in cinque parti: - idea progetto - analisi delle opportunita’ di mercato del progetto comunita’ virtuale - piano organizzativo e produttivo - piano di marketing - piano finanziario Infine, dal punto di vista imprenditoriale, la società ipotizzata dovrebbe portare l’impresa al punto di inversione o pareggio, che nel nostro caso si verificherà durante il II anno, detto anche break even point; a partire da questo punto tutto l’investimento fatto sarà stato recuperato e, quindi, l’impresa inizierà ad avere un profitto; mentre, dal punto di vista tecnico il portale della comunità virtuale permetterà di superare quelli che sono i punti critici della donazione off-linee e di apportare i seguenti vantaggi che sono poi le caratteristiche peculiari del web: - Immediatezza delle azioni degli attori(donatori –beneficiari) - Feedback tra le varie parti del sistema - Capillarità: la capacita di raggiungere i luoghi più disparati grazie ad un semplice doppino telefonico o alla tecnologia gps.

Style APA, Harvard, Vancouver, ISO itp.

38

Huang, Yi–Hsuan, i 黃繹璇. "The Study of the Healthy Modulated Meal‘s Need for the Elder Chronically Ill Outpatients ---A Study of Taiwan Taichung County Dali City’s Jen-Ai Hospital". Thesis, 2005. http://ndltd.ncl.edu.tw/handle/29979507841013982592.

Pełny tekst źródła

Streszczenie:

碩士
東海大學
食品科學系
93
The biotechnology rose and developed in 20th century drive the medicine and hygiene to progress constantly and the medical science and technology to popularize speedy. The increase of age for marriage and average age for giving birth and the decrease of fertility rate year after year make the global tendency of aging population. However, it is easy for aged people to cause chronic disease. Except the medicine control, the treatment and care to chronic disease should be appropriate diet and exercise. Only these three closely cooperated with each other to achieve the therapy. Nearly, more and more people eat outside; however, the diet they eat does not match up the demand of diet control for people with chronic disease certainly, especially for the middle and old aged people. They need to eat differently from others in consideration of their own special state of health. In order to meet the requirement of the big diet market for old aged people, the research is to investigate the market share of health and recuperation diet for middle and old aged people with chronic disease from their physical condition, diet habit and purchase desire, and to offer as the reference resources for policy and medical service systems made by the government or food industries. The objects of this study are outpatients above 55 in Taichung area. The research said, cardiovascular disease and endocrine and metabolic disease are the common diseases for people in middle and old age. Besides, personal diet and living ways should be regulated due to the diseases. Females do well than males. People between 55 and 60 do worse than others. Middle and old aged people eat three meals regularly; they almost eat lunch outside and eat dinner at home. The result also said that people with cardiovascular disease and endocrine and metabolic diseases eat lunch outside is more than common people. 60% of the respondents said that they do not consider to buy health and recuperation diet. The main reason is that “they like to cook for themselves and besides they are not used to eat outside”, the secondary is that “they consider about the efficacy, the hygiene and the safety of the diet. During the respondents who potentially purchase the diet, unmarried males aged between 55 and 60, with or above junior college education or with monthly living expenses more than forty thousand NT dollars, occupied more. People in middle or old age often buy things at “Supermarket,” 24.9％ of respondents said they did not often go shopping at the listed retail routes.

Style APA, Harvard, Vancouver, ISO itp.

39

FORMICONI, Cristina. "LÈD: Il Lavoro È un Diritto. Nuove soluzioni all’auto-orientamento al lavoro e per il recruiting online delle persone con disabilità". Doctoral thesis, 2018. http://hdl.handle.net/11393/251119.

Pełny tekst źródła

Streszczenie:

INTRODUZIONE: Il presente progetto di ricerca nasce all’interno di un Dottorato Eureka, sviluppato grazie al contributo della Regione Marche, dell’Università di Macerata e dell’azienda Jobmetoo by Jobdisabili srl, agenzia per il lavoro esclusivamente focalizzata sui lavoratori con disabilità o appartenenti alle categorie protette. Se trovare lavoro è già difficile per molti, per chi ha una disabilità diventa un percorso pieno di ostacoli. Nonostante, infatti, la legge 68/99 abbia una visione tra le più avanzate in Europa, l’Italia è stata ripresa dalla Corte Europea per non rispettare i propri doveri relativamente al collocamento mirato delle persone con disabilità. Tra chi ha una disabilità, la disoccupazione è fra il 50% e il 70% in Europa, con punte dell’80% in Italia. L’attuale strategia europea sulla disabilità 2010-2020 pone come obiettivi fondamentali la lotta alla discriminazione, le pari opportunità e l’inclusione attiva. Per la realizzazione di tali obiettivi assume un’importanza centrale l’orientamento permanente: esso si esercita in forme e modalità diverse a seconda dei bisogni, dei contesti e delle situazioni. La centralità di tutti gli interventi orientativi è il riconoscimento della capacità di autodeterminazione dell’essere umano, che va supportato nel trovare la massima possibilità di manifestarsi e realizzarsi. Ciò vale ancora di più per le persone con disabilità, in quanto risultano fondamentali tutte quelle azioni che consentono loro di raggiungere una consapevolezza delle proprie capacità/abilità accanto al riconoscimento delle caratteristiche della propria disabilità. L’orientamento assume così un valore permanente nella vita di ogni persona, garantendone lo sviluppo e il sostegno nei processi di scelta e di decisione con l’obiettivo di promuovere l’occupazione attiva, la crescita economica e l’inclusione sociale. Oggi giorno il frame work di riferimento concettuale nel campo della disabilità è l’International Classification of Functioning, Disability and Health (ICF), il quale ha portato a un vero e proprio rovesciamento del termine disabilità dal negativo al positivo: non si parla più di impedimenti, disabilità, handicap, ma di funzioni, strutture e attività. In quest’ottica, la disabilità non appare più come mera conseguenza delle condizioni fisiche dell’individuo, ma scaturisce dalla relazione fra l’individuo e le condizioni del mondo esterno. In termini di progetto di vita la sfida della persona con disabilità è quella di poter essere messa nelle condizioni di sperimentarsi come attore della propria esistenza, con il diritto di poter decidere e, quindi, di agire di conseguenza in funzione del proprio benessere e della qualità della propria vita, un una logica di autodeterminazione. OBIETTIVO: Sulla base del background e delle teorie di riferimento analizzate e delle necessità aziendali è stata elaborata la seguente domanda di ricerca: è possibile aumentare la consapevolezza negli/nelle studenti/esse e laureati/e con disabilità che si approcciano al mondo del lavoro, rispetto alle proprie abilità, competenze, risorse, oltre che alle limitazioni imposte dalla propria disabilità? L’obiettivo è quello di sostenere i processi di auto-riflessione sulla propria identità e di valorizzare il ruolo attivo della persona stessa nella sua autodeterminazione, con la finalità ultima di aumentare e migliorare il match tra le persone con disabilità e le imprese. L’auto-riflessione permetterà di facilitare il successivo contatto dialogico con esperti di orientamento e costituirà una competenza che il soggetto porterà comunque come valore aggiunto nel mondo del lavoro. METODI E ATTIVITÀ: Il paradigma teorico-metodologico adottato è un approccio costruttivista: peculiarità di questo metodo è che ciascuna componente della ricerca può essere riconsiderata o modificata nel corso della sua conduzione o come conseguenza di cambiamenti introdotti in qualche altra componente e pertanto il processo è caratterizzato da circolarità; la metodologia e gli strumenti non sono dunque assoggettati alla ricerca ma sono al servizio degli obiettivi di questa. Il primo passo del progetto di ricerca è stato quello di ricostruzione dello stato dell’arte, raccogliendo dati, attraverso la ricerca bibliografica e sitografica su: l’orientamento, la normativa vigente in tema di disabilità, i dati di occupazione/disoccupazione delle persone con disabilità e gli strumenti di accompagnamento al lavoro. A fronte di dati mancanti sul territorio italiano relativi alla carriera e ai fabbisogni lavorativi degli/delle studenti/esse e laureati/e con disabilità, nella prima fase del progetto di ricerca è stata avviata una raccolta dati su scala nazionale, relativa al monitoraggio di carriera degli studenti/laureati con disabilità e all’individuazione dei bisogni connessi al mondo del lavoro. Per la raccolta dati è stato sviluppato un questionario ed è stata richiesta la collaborazione a tutte le Università italiane. Sulla base dei dati ricavati dal questionario, della letteratura e delle indagini esistenti sulle professioni, nella fase successiva della ricerca si è proceduto alla strutturazione di un percorso di auto-orientamento, volto ad aumentare la consapevolezza nelle persone con disabilità delle proprie abilità e risorse, accanto a quella dei propri limiti. In particolare, il punto di partenza per la costruzione del percorso è stata l’Indagine Istat- Isfol sulle professioni (2012) e la teoria delle Intelligenze Multiple di H. Gardner (1983). Si è arrivati così alla strutturazione del percorso di auto-orientamento, composto da una serie di questionari attraverso i quali il candidato è chiamato ad auto-valutare le proprie conoscenze, le competenze, le condizioni di lavoro che gli richiedono più o meno sforzo e le intelligenze che lo caratterizzano, aggiungendo a questi anche una parte più narrativa dove il soggetto è invitato a raccontare i propri punti di forza, debolezza e le proprie aspirazioni in ambito professionale. Per sperimentare il percorso di auto-orientamento creato, nell’ultima fase della ricerca è stato predisposto uno studio pilota per la raccolta di alcuni primi dati qualitativi con target differenti, studenti/esse universitari/e e insegnanti di scuola superiore impegnati nel tema del sostegno e dell’orientamento, e utilizzando diversi strumenti (autopresentazioni, test multidimensionale autostima, focus group). CONCLUSIONI: I dati ottenuti dallo studio pilota, seppur non generalizzabili, in quanto provenienti da un campione esiguo, hanno evidenziato come il percorso di auto-orientamento attivi una riflessione sulla visione di sé nei diversi contesti e un cambiamento, in positivo o in negativo, nell’autostima e nella valutazione di sé in diverse aree, ad esempio nell’area delle relazioni interpersonali, del vissuto corporeo, dell’emotività ecc. Tali dati ci hanno permesso soprattutto di evidenziare punti di forza e debolezza del percorso creato e di apportare modifiche per una maggiore comprensione e adattabilità del prodotto stesso. Il valore del percorso orientativo è connesso al ruolo attivo di auto-valutatore giocato dal candidato con disabilità, affiancando a questa prima fase di autovalutazione un successivo confronto dialogico con un esperto, tale da permettere un ancoraggio alla realtà esterna, al contesto in cui il soggetto si trova a vivere. In questo senso, l’orientamento assume il valore di un processo continuo e articolato, che ha come scopo principale quello di sostenere la consapevolezza di sé e delle proprie potenzialità, agendo all’interno dell’area dello sviluppo prossimale della persona verso la realizzazione della propria identità personale, sociale e professionale.

Style APA, Harvard, Vancouver, ISO itp.

Rozprawy doktorskie na temat „AI for health”

Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych