Дисертації з теми "Artificial section"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Artificial section".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Sanchez, Maguiña Mildred Madeleine, and Feliz Pool Rusbel Vidal. "Optimización de las dimensiones de placas mediante el uso de IA para reducir los costos en edificios de 6 pisos en el distrito de Miraflores." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2020. http://hdl.handle.net/10757/652826.
Повний текст джерелаThis article investigates the use of Artificial Neural Networks as a type of Artificial Intelligence in order to reduce the costs of reinforced concrete. For this reason, the use of this type of algorithm was proposed with the objective of optimizing the sections of the shear walls in 6-story buildings without irregularities. Ten different neural networks were configured in order to choose the one that best suits the data used for training. In each algorithm, the width and length of the building; and the distance between maximum span of the X and Y axis were established as input variables. However, the number of hidden layers and the number of neurons in each of them was different. In the training stage, 30 cases with optimized dimensions were used, with this it was obtained that the neuronal network predicts the total length of the shear wall and its thickness with an error of 10%.
Trabajo de investigación
Szames, Esteban Alejandro. "Few group cross section modeling by machine learning for nuclear reactor." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASS134.
Повний текст джерелаModern nuclear reactors utilize core calculations that implement a thermo-hydraulic feedback requiring accurate homogenized few-group cross sections.They describe the interactions of neutrons with matter, and are endowed with the properties of smoothness and regularity, steaming from their underling physical phenomena. This thesis is devoted to the modeling of these functions by industry state-of-theart and innovative machine learning techniques. Mathematically, the subject can be defined as the analysis of convenient mapping techniques from one multi-dimensional space to another, conceptualize as the aggregated sum of these functions, whose quantity and domain depends on the simulations objectives. Convenient is intended in terms of computational performance, such as the model’s size, evaluation speed, accuracy, robustness to numerical noise, complexity,etc; always with respect to the engineering modeling objectives that specify the multidimensional spaces of interest. In this thesis, a standard UO₂ PWR fuel assembly is analyzed for three state-variables, burnup,fuel temperature, and boron concentration.Library storage requirements are optimized meeting the evaluation speed and accuracy targets in view of microscopic, macroscopic cross sections and the infinite multiplication factor. Three approximation techniques are studied: The state-of-the-art spline interpolation using computationally convenient B-spline basis, that generate high order local approximations. A full grid is used as usually donein the industry. Kernel methods, that are a very general machine learning framework able to pose in a normed vector space, a large variety of regression or classification problems. Kernel functions can reproduce different function spaces using an unstructured support,which is optimized with pool active learning techniques. The approximations are found through a convex optimization process simplified by the kernel trick. The intrinsic modular character of the method facilitates segregating the modeling phases: function space selection, application of numerical routines and support optimization through active learning. Artificial neural networks which are“model free” universal approximators able Artificial neural networks which are“model free” universal approximators able to approach continuous functions to an arbitrary degree without formulating explicit relations among the variables. With adequate training settings, intrinsically parallelizable multi-output networks minimize storage requirements offering the highest evaluation speed. These strategies are compared to each other and to multi-linear interpolation in a Cartesian grid, the industry standard in core calculations. The data set, the developed tools, and scripts are freely available under aMIT license
Hou, Chuanchuan. "Vibration-based damage identification with enhanced frequency dataset and a cracked beam element model." Thesis, University of Edinburgh, 2016. http://hdl.handle.net/1842/20434.
Повний текст джерелаFatima, Samar. "Mapping artificial intelligence affordances for the public sector." Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/235926/1/Samar%2BFatime%2BThesis.pdf.
Повний текст джерелаGomes, Cristina Maria da Silva Ganchinho. "Desafios da adoção de inteligência artificial no sector público." Master's thesis, Instituto Superior de Economia e Gestão, 2020. http://hdl.handle.net/10400.5/21099.
Повний текст джерелаA transformação digital provocada pela introdução da Inteligência Artificial nos negócios, trouxe muitas vantagens competitivas às organizações, através da otimização de processos de trabalho, possibilidade de investimentos em novas áreas de Mercado, entre outros. A evolução tecnológica evidencia cada vez mais o papel da IA nesta crescente transformação digital sendo por isso importante compreender o seu efeito nas organizações e nas pessoas. Este estudo pretende identificar quais são os potenciais desafios que o Setor Publico enfrenta na adoção de tecnologias suportadas em IA. Para tal foi realizada uma investigação, de caracter exploratório, com recurso a entrevistas a gestores da área tecnológica de várias organizações do Sector Público. Foram realizadas cinco entrevistas com questões abertas onde se pretendeu responder a questões relacionadas com a decisão de adoção de IA. Os resultados do estudo demonstram que existe motivação para a adoção destas tecnologias, no entanto existem alguns constrangimentos que influenciam a adoção destas tecnologias, destacamos a falta de recursos humanos e a capacitação dos mesmos como sendo um dos maiores dos desafios.
The digital transformation brought by the introduction of Artificial Intelligence in business provided many competitive advantages to organizations, through the optimization of work processes, the possibility of investments in new business areas among others. Technological evolution increasingly highlights the role of AI in this growing digital transformation and therefore it is important to understand its effect on organizations and in people. This study aims to identify which are the potential challenges that the Public Sector faces in the adoption of technologies supported by AI. To achieve this goal, an exploratory investigation was carried out using interviews with managers in the IT area of distinct business areas of the Public Sector. Five interviews were conducted with open questions about the decision to adopt AI in organizations of the Public Sector. The results show that despite the motivation for the adoption of these technologies, there are some important constraints affecting this adoption, namely the lack of human resources and their training as one of the greatest challenges.
info:eu-repo/semantics/publishedVersion
Gustafsson, Victor. "Artificial intelligence effect on jobs in the financial sector." Thesis, Mittuniversitetet, Avdelningen för ekonomivetenskap och juridik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-34247.
Повний текст джерелаCarbajal, Valverde Giuliana Mayte, and Correa Gianella Alejandra Segura. "Consecuencias positivas y negativas de la inteligencia artificial en el sector hotelero." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2021. http://hdl.handle.net/10757/656854.
Повний текст джерелаTechnology is an essential factor because it transforms, influences, and provides great benefits to humanity; inside it, artificial intelligence stands out, which has been of great help to different areas in recent years. One of them is the hotel sector, which has been implementing artificial intelligence in its services according to market demands. This research work is focused on determining the consequences of artificial intelligence in the hotel sector. It will analyze this technology’s positive and negative aspects and how it is currently being implemented in the hotel industry. This study is based on the literature review of scientific journals and theses. Furthermore, this research uses the integrative methodological approach, which synthesizes and examines the literature to find new definitions and perspectives. In conclusion, the use of artificial intelligence benefits the hotel sector in different ways, for example, automating services, reducing time and costs, among others. In conclusion, artificial intelligence is beneficial for the hotel sector, since it reduces time, reduces costs, and helps to obtain valuable information for decision-making.
Trabajo de investigación
Amaro, Jorge Filipe Montez Vaz Monteiro. "Modelos de avaliação em massa : redes neuronais artificiais aplicadas ao sector imobiliário residencial em Portugal? : estudo de caso na cidade de Lisboa." Master's thesis, Instituto Superior de Economia e Gestão, 2012. http://hdl.handle.net/10400.5/10737.
Повний текст джерелаAs redes neuronais artificiais são uma metodologia alternativa aos modelos tradicionais de previsão. A sua utilização tem-se vindo a massificar, sobretudo nas áreas da medicina, finanças, indústria automóvel e, mais recentemente em modelos de avaliação em massa aplicados ao mercado imobiliário. Este trabalho teve como objectivo fundamental a realização de experiências que utilizassem esta metodologia de previsão não paramétrica (não linear). No estudo de caso apresentado, foram analisadas 2.013 transacções, que ocorreram entre 2007 e 2012, mediadas pela rede de franchisados RE/MAX, relativas ao segmento residencial na cidade de Lisboa. Com esta base de dados, e depois de encontrada a melhor rede neuronal, foi possível obter um erro médio percentual absoluto (MAPE) na ordem dos 19%, em que para cerca de 67% da amostra foi alcançado um erro de estimação abaixo dos 20%. Utilizando esta metodologia, também foi observado que a rede neuronal funciona melhor se eliminados os outliers da amostra, aumentando a sua precisão. Foi ainda experimentada a introdução de variáveis temporais e de localização, tais como o ano de transacção de um determinado imóvel e a sua idade, ou ainda a freguesia onde está inserido, tendo sido obtidos comportamentos positivos no desempenho das redes. Para além da originalidade do tema, é de destacar que foram utilizados para este trabalho, valores reais de transacção relativos ao sector residencial em Portugal, tendo sido verificada uma aproximação do comportamento e da tendência do valor de transacção estimado pela rede, aos verificados pelo mercado.
The artificial neural networks are an alternative approach to traditional forecasting. Its use has been largely used, particularly in the areas of medicine, finance, automotive, and more recently in mass valuation models applied to the real estate market. This work had as main objective conducting experiments that used this methodology to forecast nonparametric (nonlinear). In the case study were analyzed 2013 transactions that occurred between 2007 and 2012, mediated by the network of franchisees RE / MAX, for the residential segment in Lisbon. With this database, and after found the best neural network, it was possible to obtain an mean absolute percent error (MAPE) of around 19%, in which to approximately 67% of the sample was reached estimation error below 20 %. Using this methodology, it was also observed that the neural network works better if the outliers are removed from the sample, increasing its accuracy. It also experienced the introduction of temporal variables and location, such as the year of a particular property transaction and its age, or the parish where it is located, having obtained positive behaviors in network performance. Beyond the originality of the subject, it is worth noting that was used for this work, actual transaction values for the residential sector in Portugal, having been verified an approximation of the behavior and trend of the transaction value estimated by the network, verified by the market.
Mendieta, Retuerto Carlos Andres. "El uso del Chatbot con respecto a la satisfacción del cliente en empresas del sector financiero en Lima Metropolitana." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2020. http://hdl.handle.net/10757/651915.
Повний текст джерелаTechnology has been evolving in recent years. Artificial intelligence has managed to enter markets around the world as a new technology and a new way of seeing the world. That is why, in this study, the dimensions of the chatbot are explored, which are three: Information quality, system quality and service quality in relation to customer satisfaction in the financial system in Metropolitan Lima. This study is divided into two parts: a qualitative and a quantitative study. In the qualitative part, where the opinion of three experts of the subject was sought and, likewise, three focus groups were carried out. With respect to the quantitative study, a sample of 250 people was used. The data analyzed suggest that there is a relationship between the dimensions of the chatbot and customer satisfaction, but this relationship is very low negative.
Trabajo de investigación
Kloub, Maha, and Annika Gerigoorian. "A Cross-Sectional Technology Acceptance Study of an AI CAD System in a Breast Screening Unit." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299859.
Повний текст джерелаI januari 2021, implementerades ett artificiellt intelligent datorstött detektionssystem som ska upptäcka bröstcancer på Capio S:t Görans sjukhus i Stockholm. Användning av AI CAD för att upptäcka bröstcancer är lovande, men det kan endast bli en framgångsrik implementering om det accepteras av de som använder systemet. Denna studie undersöker och utvärderar de initiala faktorer som är avgörande för användaracceptansen av AI CAD hos radiologipersonal genom att utgå från den senaste versionen av teknologiacceptansmodellen – Technology Acceptance Model 3 (TAM3). Ett frågeformulär utformades i enlighet med modellen och distribuerades till 28 yrkesverksamma på S:t Görans mammografiavdelning. Den kvantitativa data som samlades in från enkäten analyserades med hjälp av det statistiska verktyget SPSS. De empiriska resultaten visade att radiologipersonalens avsikt att använda AI CAD påverkades direkt av den upplevda användbarheten av systemet och indirekt av personalens upplevda syn på hur enkelt systemet är att använda, att systemet är relevant för personalens jobb samt att systemet kan höja personalens image. Dessutom bekräftade studien att den subjektiva normen påverkar systemets image. Slutligen upptäcktes två nya associationer, i vilken TAM3 inte antar. Dessa påträffades mellan image och den beteendemässiga intentionen till att använda systemet samt mellan jobbrelevansen och den beteendemässiga intentionen till att använda systemet. Organisationsstöd, systemrelaterade aktiviteter samt information och kommunikation med personal är interventioner som föreslås baserat på resultaten i denna studie som mammografiavdelningen på S:t Görans sjukhus bör utnyttja för att öka acceptansen av AI CAD systemet.
Drobotowicz, Karolina. "Guidelines for Designing Trustworthy AI Services in the Public Sector." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-291108.
Повний текст джерелаArtificiell intelligens (AI) är ett populärt ämne inom olika områden i världen. Således är det naturligt att dess användning beaktas i den offentliga sektorn. AI ger många möjligheter för offentliga institutioner och medborgare, som till exempel, mer attraktiva, tillgängliga och flexibla tjänster. Men befintliga berättelser från användare visar också att oetisk eller ogenomskinlig användning av AI kan avsevärt minska medborgarnas förtroende för ansvariga offentliga institutioner. Eftersom det är viktigt att upprätthålla ett sådant förtroende, får pålitliga AI-tjänster mer och mer intresse. Detta arbete syftar till att svara på frågan om vad som måste beaktas vid utformningen pålitliga AI-tjänster inom offentlig sektor. Studien gjordes i Finland. Forskningsmetoden som användes var en designprocess och den bestod av kvalitativa intervjuer, en design workshop samt validering med användartestning. Sammanlagt deltog mer än 30 finländska invånare i studien. För närvarande finns det mer positiva än negativa röster om användningen av AI i den offentliga sektorn, dock är antalet i den senare kategorin betydande. De mest negativa rösterna kommer från äldre personer med låg utbildning och från yngre AI-specialister. Dessutom finns starkt förtroende för den offentliga sektorn. Ändå uttryckte medborgarna flera problem, såsom säkerhet eller integritet. Det är viktigt att offentliga tjänster är transparenta för att behålla förtroendet för den offentliga sektorn och bygga förtroende för AI. Medborgarna behöver veta när AI används, hur och i vilket syfte samt vilka uppgifter som används och varför de får specifika resultat. Medborgarnas behov och bekymmer, såväl som etiska krav, borde tas upp i utformningen och utvecklingen av en pålitlig AI-tjänster i offentlig sektor. Exempelvis genom att mildra diskrimineringsrisker, ge medborgare kontroll över sina uppgifter och att ha en person involverad i AI processer. Utformare och utvecklare av pålitliga AI-tjänster inom offentlig sektor bör syfta till att förstå medborgarna och säkerställa dem om deras behov och bekymmer genom den transparenta tjänsten och den positiva upplevelsen att använda tjänsten.
Calligola, Francesca. "Systemic models for supporting flood warning procedures in river sections with no rating curves: application to a set of Emilia-Romagna watersheds." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/14293/.
Повний текст джерелаVillón, Cabrera Nicole. "Inteligencia Artificial aplicada al marketing: Impacto del uso de Chatbots Cognitivos en la satisfacción del cliente del sector bancario." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2020. http://hdl.handle.net/10757/652700.
Повний текст джерелаNowadays, we live in a digitized world, where more and more companies try to provide better services to differentiate between them. In this way, chatbots allow to answer customer queries and provide a different service. In this research, I analyze the use of chatbots in the Peruvian banking sector and how it impacts customer satisfaction. In addition, the effect of quality of service, quality of information and ease of use is observed. Data was collected from 250 respondents. The results allowed a vision for the banks to be able to strengthen the satisfaction of their clients through chatbots.
Trabajo de investigación
Zanetti, Fernando Luiz [UNESP]. "A condição da artee os novos paraísos artificiais." Universidade Estadual Paulista (UNESP), 2007. http://hdl.handle.net/11449/97630.
Повний текст джерелаCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Esta pesquisa parte da problemática relacionada às condições de formação estética do homem contemporâneo e aos lugares da arte em nossa atualidade. Pudemos constatar que há uma grande quantidade de instituições públicas e privadas – ONGs (Organizações Não- Governamentais), escolas, hospitais, centros de recuperação de viciados em drogas – que praticam atividades artísticas com objetivos específicos da sua área de atuação, ora com fins terapêuticos, ora com fins pedagógicos e psicológicos, ora com fins políticos de promoção da cidadania. Essas atividades são intituladas pelas diversas práticas sociais como oficinas artísticas ou culturais. Nesse sentido, nosso trabalho delimita as oficinas como um dispositivo no qual a arte se torna uma das estratégias do capital para controle da população. No interior desse dispositivo são propostas finalidades para o homem, para o mundo e para a arte. No que concerne à arte, essas finalidades são criadas na mediação que as diversas instituições realizam entre o público e as obras. Essa mediação faz da arte um instrumento de interpretação que lhe retira sua potência de criar condições de diferenciação para o mundo e para a vida humana. Nesse lugar, a arte perde sua condição de nos fazer acreditar na potência ilimitada de inventar mundos e outras realidades sensíveis. Palavras-Chave: Arte; Oficinas; Terceiro Setor; Organizações Não-Governamentais; Controle Social.
This research is based on the issues related to the conditions of aesthetic formation of the contemporary man and the role of art in our days. We could observe that a large number of public and private institutions – Non-Governmental Organizations (NGO’s), schools, hospitals and recovering centers for drug addicts – offer some art activities aiming at specific goals in their field of work , contemplating therapeutic, educational or psychological purposes or even political purposes for citizenship promotion. These activities are considered and called artistic or cultural workshops. In this sense, our work restricts these workshops to a device where art becomes a strategy used by the capitalist system with the aim of controlling the population. Through this device proposals are made having in mind men, the world and art. Concerning art, these proposals can be observed in the mediation several institutions perform between the public and the works of art. Such mediation transforms art into an interpretative tool thus destroying its creative power of differentiation to the world and to human life. Therefore, art loses its ultimate objective, that is, the ability to make us believe in the unlimited power of inventing new worlds and other sensitive realities.
Jensen, Linn. "Artificial intelligence in the public sector : A study of the perceptions of AI in a municipal department and their effects." Thesis, Umeå universitet, Institutionen för informatik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-172923.
Повний текст джерелаBenguira, Audrey Shoshana. "International cooperation in the private satellite communications sector : enhancing commercial exploitation of outer space." Thesis, McGill University, 2002. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=78202.
Повний текст джерелаHowever, the new millennium has brought its share of intellectual renewal and in the field of space law it has been translated in the acknowledgement that the private sector would have an important role to play, on the international scene, for the improvement of space law. It is this new legal thinking that has been characterized as "international cooperation" as applied to the private sector, that is the subject of this study. Hence, what is looked at is the position of the satellite communications sector on the international scene and what expertise it has to share with public fora for the overall improvement of space law and space activities.
Zanetti, Fernando Luiz. "A condição da artee os novos paraísos artificiais." Assis : [s.n.], 2007. http://hdl.handle.net/11449/97630.
Повний текст джерелаBanca: Carlos Eduardo Jordão Machado
Banca: Julio Roberto Groppa Aquino
Resumo: Esta pesquisa parte da problemática relacionada às condições de formação estética do homem contemporâneo e aos lugares da arte em nossa atualidade. Pudemos constatar que há uma grande quantidade de instituições públicas e privadas - ONGs (Organizações Não- Governamentais), escolas, hospitais, centros de recuperação de viciados em drogas - que praticam atividades artísticas com objetivos específicos da sua área de atuação, ora com fins terapêuticos, ora com fins pedagógicos e psicológicos, ora com fins políticos de promoção da cidadania. Essas atividades são intituladas pelas diversas práticas sociais como oficinas artísticas ou culturais. Nesse sentido, nosso trabalho delimita as oficinas como um dispositivo no qual a arte se torna uma das estratégias do capital para controle da população. No interior desse dispositivo são propostas finalidades para o homem, para o mundo e para a arte. No que concerne à arte, essas finalidades são criadas na mediação que as diversas instituições realizam entre o público e as obras. Essa mediação faz da arte um instrumento de interpretação que lhe retira sua potência de criar condições de diferenciação para o mundo e para a vida humana. Nesse lugar, a arte perde sua condição de nos fazer acreditar na potência ilimitada de inventar mundos e outras realidades sensíveis. Palavras-Chave: Arte; Oficinas; Terceiro Setor; Organizações Não-Governamentais; Controle Social.
Abstract: This research is based on the issues related to the conditions of aesthetic formation of the contemporary man and the role of art in our days. We could observe that a large number of public and private institutions - Non-Governmental Organizations (NGO's), schools, hospitals and recovering centers for drug addicts - offer some art activities aiming at specific goals in their field of work , contemplating therapeutic, educational or psychological purposes or even political purposes for citizenship promotion. These activities are considered and called artistic or cultural workshops. In this sense, our work restricts these workshops to a device where art becomes a strategy used by the capitalist system with the aim of controlling the population. Through this device proposals are made having in mind men, the world and art. Concerning art, these proposals can be observed in the mediation several institutions perform between the public and the works of art. Such mediation transforms art into an interpretative tool thus destroying its creative power of differentiation to the world and to human life. Therefore, art loses its ultimate objective, that is, the ability to make us believe in the unlimited power of inventing new worlds and other sensitive realities.
Mestre
Ivorra, Martínez Eugenio. "Desarrollo de técnicas de visión hiperespectral y tridimensional para el sector agroalimentario." Doctoral thesis, Universitat Politècnica de València, 2015. http://hdl.handle.net/10251/48541.
Повний текст джерелаIvorra Martínez, E. (2015). Desarrollo de técnicas de visión hiperespectral y tridimensional para el sector agroalimentario [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/48541
TESIS
Samuelsson, Karin, and Ellen Hultberg. "Kommunal redovisning : förekomsten av artificiell resultatstyrning i kommuner." Thesis, Högskolan i Borås, Akademin för textil, teknik och ekonomi, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-12610.
Повний текст джерелаThis thesis is an analysis of the occurrence of earnings management in Swedish municipalities. Previous theory claims that the change from cash accounting to accrual accounting has made it easier to involve in earnings management actions and that these actions are broadly used in both municipalities and corporate companies. Similar studies proves economy, politics and civil servants to be explanatory for why earnings management takes place in municipalities.We seek to explain this occurrence by using the accounting record contribution to national infrastructure. The aim is to answer what the main incentives are for manipulating the results in municipalities and how these incentives affect the decision making progress.This is mainly a documentary study that focuses on the public financial reports of municipalities. A statistical analysis is performed and conclusions are drawn. We find evidence that earnings management exist in municipalities and that the biggest explaining factor of how the contribution is accounted for depend on the size of the contribution to infrastructure and if the municipality has received any big amounts from the government in form of AFA-insurances, AFA-premier or cyclical support that year or not. This indicates a short-term thinking with high focus on net income. This study is hereafter written in Swedish.
Galarreta, Velarde Anibal Antonio, and Aylas Edgard Martin Marquez. "Sistema de gestión de inventarios en la producción de autotransformadores eléctricos para electrodomésticos en PYMES del sector manufactura usando machine learning." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2021. http://hdl.handle.net/10757/656319.
Повний текст джерелаThe use of machine learning as a scientific discipline in the field of artificial intelligence applied to the field of manufacturing industry has advantages such as obtaining predictions and estimates based on the electronic collection of information and the experience acquired during industrial processes. In this sense, the present work aims to provide an architecture and design proposal for an information system for inventory management with the use of machine learning as a solution to optimize the duration of the manufacturing process of electrical autotransformers for household appliances in SMES. Among the problems of the manufacturing process are the stock absence of necessary supplies for the manufacture of products, delays in obtaining them and the absence of timely information that allows forecasting both the necessary amount of supplies for a production process and the estimation of demand for orders for production batches. The work carried out includes the study of the business, analysis and modeling of the manufacturing process to identify the problem, analysis of the requirements, modeling of the optimized process, design of the software architecture for the proposed IT solution, as well as project management. As a result, it is possible to apply machine learning in inventory management for the manufacturing process that allows predicting requirements for the purchase of production supplies, alerting the best time to order from suppliers, estimating product demand, estimating production, as well as generate reports on the management of supplies and the production process.
Tesis
Corrêa, Fernanda. "Aplicação de redes neurais artificiais no setor de transportes no Brasil." Universidade Federal de São Carlos, 2008. https://repositorio.ufscar.br/handle/ufscar/4257.
Повний текст джерелаUniversidade Federal de Sao Carlos
The development of Artificial Neural Networks in the Brazilian´s Sector of Transports comes carrying through great done in what it refers to the promotion of the use of the technique in the solution of problems found in this area. Artificial Neural Networks are computational techniques with capacity to simulate the cerebral activity human being, making future forecasts from the analysis of data. This technique, throughout the years comes greatly stimulating the research in planning of transports in such a way in the exterior how much in Brazil. As objective, this work brings an exploratory research, trying to lift the state of the art of the use and application of the technique Artificial Neural Networks in the Section of Transports in Brazil, drawing a comparison of what has been accomplished at the developed countries and in Brazil. In Brazil, the ANNs had started to be developed in the Sector of Transports for return of the years of 1990, today, the research in this area is generating important works very for the planning of transports, however, the technique of Artificial Neural Networks still has much to be improved better to be used as administrative tools in the country.
O desenvolvimento das Redes Neurais Artificiais no Setor de Transportes no Brasil vem realizando grandes feitos no que tange o fomento da utilização da técnica na solução de problemas encontrados nesta área. As Redes Neurais Artificiais são técnicas computacionais com capacidade de simular a atividade cerebral humana, fazendo previsões futuras a partir da análise de dados. Essa técnica, ao longo dos anos vem estimulando grandemente as pesquisas em planejamento de transportes tanto no exterior quanto no Brasil. Como objetivo, este trabalho traz uma pesquisa exploratória, procurando-se levantar o estado da arte do uso e aplicação da técnica Redes Neurais Artificiais no Setor de Transportes no Brasil, traçando uma comparação do que vem sendo realizado nos países desenvolvidos e no Brasil. No Brasil, as RNAs começaram a ser desenvolvidas no Setor de Transportes por volta dos anos de 1990, hoje, as pesquisas nesta área estão gerando trabalhos muito importantes para o planejamento de transportes, no entanto, a técnica de Redes Neurais Artificiais ainda tem muito a ser aprimorada para melhor ser utilizados como ferramentas administrativas no país.
López, Malca Jiam Carlos. "Comparación de modelos de aprendizaje de máquina en la predicción del incumplimiento de pago en el sector de las microfinanzas." Master's thesis, Pontificia Universidad Católica del Perú, 2019. http://hdl.handle.net/20.500.12404/19546.
Повний текст джерелаThe financial institutions dedicated to Microfinance offer their services to a target audience that, for the most part, has low economic resources and/or whose access to traditional banking systems is limited, these institutions to develop in an unfavorable context the risks of non-compliance in the payments are greater compared to traditional banking, therefore it is required to make a financial economic evaluation with a greater degree of detail, requiring for this purpose the participation of a business expert that based on information obtained and own expertise determine if the potential client will be a good payer, this way of evaluating a customer has evolved in the financial sector in recent years, this largely due to the application of technologies such as artificial intelligence and machine learning, offering a uniqueness that is the ability to learn from the data, demanding less effort and human participation mana, and yielding higher levels of accuracy. This article presents the results of the experimentation carried out with the following machine learning models: Logistic Regression, XGBoost, Random Forest, Gradient Boosting, Multilayer Perceptron (MLP) and deep learning algorithms for the prediction of non-payment, applying subsampling and oversampling balancing techniques, including the SMOTE technique, and the One Hot Encoding technique was applied for the treatment of categorical variables. The different models of machine learning were applied to a data set provided by a leading Peruvian institution in the microfinance sector, with the XGBoost model reporting the best results, with an accuracy of 97.53% and an F1-Score of 0.1278.
Srour, Zainab. "Modeling and Analyzing Systemic Risk in European Banking Sector." Thesis, Rennes 1, 2019. http://www.theses.fr/2019REN1G007.
Повний текст джерелаThis dissertation investigates the systemic risk subject in three different empirical frameworks. Besides listing the existing works related to the systemic risk in the first chapter, we examine the impact of two risk-taking factors in affecting the systemic risk level of European banks. The second chapter investigates the impact of the ownership structure on systemic risk contribution of 79 banks in 16 western European countries during the 2004-2016 period. The results show that higher ownership concentration is associated with greater banks’ systemic risk contribution. Moreover, we found that banks’ systemic risk contribution is even stronger for banks where institutional investors and States are the largest controlling owners. We go deeper and investigate the effect of regulatory variables on the relationship between systemic risk and ownership structure. We find that higher ownership concentration increased banks’ systemic risk contribution in countries with high deposit insurance, lower capital stringency and higher asset diversification. The third chapter explores the effect of another risk-taking incentive, the liquidity creation, on banks systemic risk contribution end exposure. We use the same sample consisting of 79 European banks during the 2004-2016 period. The findings emphasize that during normal time, systemic risk exposure of banks are exacerbated by high liquidity creation. Moreover we show that, during distress times, high liquidity creation affects negatively not only banks exposure to systemic risk but also their contribution. Chapter four investigates a different facet of the systemic risk. Using a sample of 134 banks in 16 European countries ranging from 2002 to 2016, we construct three forecasting methods to predict systemic risk contribution and exposure values. We use artificial neural network, support vector machine and generalised autoregressive conditional heteroskedasticity specification. Our results show that two hidden layers artificial neural networks outperform other models in effectively predicting systemic risk
Abdel, Ahad George, and Abo Jack Dilli. "Digitalisering utifrån ekonomers perspektiv : En fallstudie vid två offentliga organisationer." Thesis, Högskolan Väst, Avd för företagsekonomi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:hv:diva-16627.
Повний текст джерелаDigitalization is a current topic at present and technology has grown and affected society. It has affected economists and their way of working. There are several studies regarding how digitalization affects the role of economists in the private sector, research on economists' own experiences and in the public sector is, however, few. The public sector has been criticized as technological development does not progress at the pace of the rest of society. This is because they have structures that make it difficult to introduce modernization work. The purpose of the study is to map and analyze experiences with digitization as well as opportunities and challenges around it from the perspective of economists. The study was conducted through a qualitative method where data collection was done on two public organizations through six semi-structured interviews. Digitization results in analog information shifting to being digitized. It improves internal efficiency by streamlining work processes by eliminating manual handling and reducing human error. Management control systems are about influencing the behavior of employees, but also managers' behavior in the organization. The empirical results of the study show that digitization has contributed to a transition from the analog to the digital. It also shows that digitalization has streamlined work processes within organizations. With regard to management control in the organizations, the study has identified that there is both results control and action control in the organizations. The conclusions that the study presents are that the advantages of digitization are that it has led to more efficient workflow processes and freed up time for more qualified tasks. The possibilities are that the streamlining leads to more focus being placed on dealing with qualified tasks that require the human eye and reduce human errors. A disadvantage is that economists do not possess IT skills, and need the help of the IT department, which is a challenge as challenges arise regarding communication. Due to this, economists experience that the systems are not always optimal to handle based on their tasks. Another disadvantage of digitalization is that it negatively affects social contact and creative ability as a result of more digital encounters instead of meeting physically.
Bladh, Oskar, Hedvig Henrekson, and Ida Modée. "The Impact of Virtual Agents on Customer Loyalty in Major Swedish Banks." Thesis, Internationella Handelshögskolan, Högskolan i Jönköping, IHH, Företagsekonomi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-39856.
Повний текст джерелаValentin, Luangraj Sontsada. "Vers une approche non-linéaire de la commande d'attitude de satellites par jets de gaz." Toulouse, ENSAE, 2004. http://www.theses.fr/2004ESAE0019.
Повний текст джерелаHultman, Anna, and Mikaela Zarki. "Do you mind talking to a chatbot? : A quantitative study about how chatbots affect the digital customer experience within Swedish banks." Thesis, Linnéuniversitetet, Institutionen för marknadsföring (MF), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-104863.
Повний текст джерелаMena, O'Meara Nicolay Antonio. "PLANIFICACIÓN MAESTRA DE OPERACIONES EN LA GESTIÓN DE LA CADENA DE SUMINISTRO EN CONTEXTO DE INCERTIDUMBRE EN EL SECTOR CERÁMICO. PROPUESTA DE MODELADO Y RESOLUCIÓN BASADA EN REDES NEURONALES ARTIFICIALES (ANN)." Doctoral thesis, Universitat Politècnica de València, 2010. http://hdl.handle.net/10251/9088.
Повний текст джерелаMena O'meara, NA. (2010). PLANIFICACIÓN MAESTRA DE OPERACIONES EN LA GESTIÓN DE LA CADENA DE SUMINISTRO EN CONTEXTO DE INCERTIDUMBRE EN EL SECTOR CERÁMICO. PROPUESTA DE MODELADO Y RESOLUCIÓN BASADA EN REDES NEURONALES ARTIFICIALES (ANN) [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/9088
Palancia
Makasi, Tendai. "Cognitive computing systems and public value: The case of chatbots and public service delivery." Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/230002/1/Tendai_Makasi_Thesis.pdf.
Повний текст джерелаSrinivasan, Sujatha. "Low-dimensional modeling and analysis of human gait with application to the gait of transtibial prosthesis users." Columbus, Ohio : Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1179865923.
Повний текст джерелаAnantharajah, Anusanth. "Spectroscopie infrarouge lointain et moyen à haute résolution par transformée de Fourier de molécules complexes d’intérêt atmosphérique : ClNO₂, Cl₂CO et ClONO₂." Electronic Thesis or Diss., Université Paris Cité, 2020. https://theses.md.univ-paris-diderot.fr/ANANTHARAJAH_Anusanth_va2.pdf.
Повний текст джерелаMeasuring concentrations of trace species that may have a significant impact on health, climate or the stability of the ozone layer, is a serious challenge. Future space missions, planned at high sensitivity, will bring progress if and only if the necessary spectral parameters are available. For some species of atmospheric interest such as nitryl chloride (ClNO₂), phosgene (Cl₂CO) and chlorine nitrate (ClONO₂), spectroscopic data are incomplete or almost non-existent. The challenge in this thesis is to get spectroscopic parameters (line positions and intensities or absorption cross sections) for these species in support of atmospheric applications. However, apart from Cl₂CO, spectroscopy of ClNO₂ and ClONO₂ is made difficult by their very complicated chemical synthesis, their reactivity with metals and organic materials, and their instability in the presence of light and heat. Moreover, these molecules are quite heavy (presence of chlorine with its two isotopomers) and exhibit dense spectra that are quite complicated by numerous perturbations affecting vibration-rotation levels.In the case of ClNO₂, spectra were recorded in the range 300 – 900 cm-1 with much improved experimental conditions (high resolution, low temperature, long path, low pressure) using the synchrotron radiation of the AILES beamline at SOLEIL. Precise modelling of the 370 and 790 cm-1 regions has been performed. These regions could be used for a future atmospheric remote sensing by FTIR spectroscopy respectively by FORUM and IASI-NG instruments. The low energy vibrations of ClONO₂ that have been never observed at high resolution before this work were also measured. A first modelling of the torsional region around 120 cm-1 is presented in this thesis. The analysis of these vibrations will be useful for the modelling of hot bands in the atmospheric windows where ClONO₂ is currently detected, and in fine will lead to a much more precise retrieval of the ClONO₂ concentration profile. Regarding Cl₂CO, cross sections have been measured at LISA, on one hand, at room temperature to compare data with previous works and, on the other, in stratospheric conditions to support satellite remote sensing applications
Júnior, Roberto Marcio de Oliveira. "Avaliação da estimulação ventricular direita crônica em crianças e adultos jovens com bloqueio atrioventricular congênito isolado." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/5/5156/tde-14082014-114613/.
Повний текст джерелаIntroduction: Isolated congenital atrioventricular block (iCAVB) is a rare condition with multiple clinical presentations. Permanent cardiac pacing is the most effective therapy for this population resulting in satisfactory long-term outcomes. However, approximately 10% of patients may have ventricular remodeling and severe heart failure. Objectives: To study the long-term effects of chronic right ventricular (RV) pacing in children and young adults with iCAVB in order to determine: prevalence of clinical and laboratory signs of heart failure and ventricular remodeling, functional capacity, quality of life and predictors of clinical, functional or echocardiographic abnormalities. Methods: Cross-sectional study of a cohort of iCAVB patients with <= 21 years old at initial pacemaker (PM) implantation and single or dual-chamber pacing in a unique RV site for a minimum of one year. All subjects underwent clinical and laboratory assessment, functional capacity, quality of life and echocardiogram. Mothers and research subjects were investigated for rheumatic diseases. Data were stored in REDCap (Research Electronic Data Capture) system and analyzed by SAS (Statistical Analysis System), SPSS (Statistical Package for the Social Sciences) and R Studio programs. Data analysis included: univariate analysis for associations between predictor variables and outcomes, Pearson correlation coefficient and linear regression multivariate model. Results: Between March/2010 and December/2013, we evaluated 63 subjects aged 1-40 years old, 68% female, under PM for 13.4 ± 6.5 years and under RV pacing for 10.0 ± 5.4 years. Pacing mode was atrioventricular in 55.6%, percentage of RV pacing was 97.9 ± 4.2% and paced QRS duration was 152.4 ± 20.1 ms. Overall, the majority (88.9%) were asymptomatic and did not use cardiovascular drugs. Longer time under PM (P= 0.013), or even under RV pacing (P= 0.005), higher age at study inclusion (P= 0.032) and lower left ventricular ejection fraction (LVEF) (P= 0.013) were associated with functional class II (NYHA) and / or drug use. B-natriuretic peptide values were normal in all tests. C reactive protein ultrasensitive, tumor necrosis factor alfa and interleukin-6 were increased in 66%, 34% and 13% tests, respectively. The mean walked distance in the sex minute walk test was 546.9 ± 76.2 meters (91.0 ± 12.5% of the predicted value). Mean scores of quality of life were 78.1 ± 17.7 for \"Physical Summary\" and 76.6 ± 17.1 for \"Mental Summary\" in the Short Form 36 (SF-36) and 77.4 ± 18.5 for \"Physical Summary\" and 77.7 ± 21.6 for \"Psychosocial Summary\", of Child Health Questionnaire - Parent Form 50 (CHQ-PF50). Decreased LVEF was detected in 39.7% and increased left ventricular end-diastolic diameter (LVDD) in 22.2% of subjects. Higher age at the first PM implant was negatively correlated with lower LVEF (r= -0.302; P= 0.016); paced QRS duration (r= 0.447; P= 0.002) and time under RV pacing (r= 0.416; P= 0.007) were positively correlated with LVDD. Ventricular dyssynchrony was detected in 60.3 % of individuals. Intra-left ventricular electromechanical delay was 86.5 ± 56.9 ms and interventricular was 141.9 ± 88 ms. However, ventricular dyssynchrony was not correlated with the studied variables. Autoantibodies anti-SSA/Ro were detected in 18 (32.1%) mothers. There was association between age at PM implant (P= 0.032) and use of ventricular PM at the time of the study (P= 0.022) and presence of anti-SSA/Ro. Multivariate linear regression showed significant correlation between age at PM implant with LVEF (P= 0.016); and paced QRS duration (P= 0.005) and time under RV pacing (P= 0.014) with LVDD. Conclusions: Clinical and laboratorial manifestations of heart failure presented low prevalence in this population. On the other hand, the prevalence of left ventricular remodeling was high. Functional capacity was adequate, as well as quality of life, in both physical and emotional aspects. Higher age at first PM implant, longer time under pacing and wider paced QRS duration were independent factors of ventricular remodeling and/or manifestation of heart failure
Scarfe, Bradley Edward. "Oceanographic Considerations for the Management and Protection of Surfing Breaks." The University of Waikato, 2008. http://hdl.handle.net/10289/2668.
Повний текст джерелаLin, Chun-Wei, and 林軍威. "Prediction of Wind Spectrum using Artificial Neural Networks for Rectangular Cross-section High-rise Buildings." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/78226913136300796977.
Повний текст джерела淡江大學
土木工程學系碩士班
97
With the progress of science and technology, people can use computers to deal with and solve a lot of engineering problems for the purposes of raising efficiency, lowering costs, etc. Still there are a lot of problems in many fields that require to carry out experiments and to use approximate solutions. Wind engineering belongs to the latter. Wind tunnel tests usually provide the most reliable design wind loads in current wind engineering practice. Nevertheless, wind tunnel tests are expensive and time consuming. It is very desirable to save resources and to obtain relatively accurate design wind loads at preliminary design stage. It can save a lot of time for engineers. The reported research employed artificial neural networks to predict wind spectra and calculate wind loadings for rectangular cross-section buildings. Similar buildings can be used to anticipate the relevant information of the target building, and proceed to complete the preliminary design. In this thesis, MATLAB was used to implement the Radial Basis Function Neural Networks (RBFNN) constructed. The training and validation of the RBFNN cover alongwind, acrosswind and torsional wind force spectra in all three exposure conditions. For all three kinds of exposures, the spectrum errors under the most frequently used frequencies (0.15 ~ 0.4) are less than 3.96% for the training set and less than 4.07% for the validation set. As for the dynamic responses, the errors are less than 11.62% for the training set and less than 13.60% for the validation set. These results show that using aerodynamic database constructed from wind-tunnel test data to train RBFNN is a prospective approach to predict wind spectra.
"Metasurface-Based Techniques for Broadband Radar Cross-Section Reduction of Complex Structures." Doctoral diss., 2020. http://hdl.handle.net/2286/R.I.62941.
Повний текст джерелаDissertation/Thesis
Doctoral Dissertation Electrical Engineering 2020
Liao, Hsiang-Yu, and 廖祥宇. "A study of Artificial Neural Network to forecast the Productivity of Shield-Tunneling Method-A Case Study on Kaohsiung Mass Rapid Transport section CO4." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/62254613232253881185.
Повний текст джерела國立高雄第一科技大學
營建工程所
97
The most construction of KMRT have been achieved and operated fully in September, 2008. It’s the beginning of the construction by learning and self-criticism, but the whole construction of the momentous traffic construction was influenced by STM. the cost of the tunnel account for the total cost of the construction is the very large of the ratio. How to promote the rate of excavation to expedite the impetus of the public construction has become the important study in the project. STM was introduced into Taiwan in 1976. In the future, there are more about the construction of the SMT will be develop in Taiwan. This study that Productivity of STM was collected 788 data, making the data of excavation, Carry Principal Component Analysis and Artificial Neural Network out. Construction productivity of STM is affected by several factors. According to the literature that few studies were explored the productivity data of STM. due to The STM plays an important role in the KMRT, in this paper establish a great deal of database and strengthen the method of analysis in order to find out and discuss what different they are. Finally, this paper studied that predict the modeling productivity of the STM effective. On the normal excavation stage, it can manage STM by predicting the productivity of the excavation correctly and have the important factors in hand.
Chen, Chi-Wei, and 陳啟偉. "Applying Artificial Neural Networks to the Characteristics of Slope Failures along the Road—A Case Study on Hualian Section of the 11th Provincial Highway." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/45357236071001507771.
Повний текст джерела國立東華大學
自然資源管理研究所
94
The topic of this study is to discuss the factors of slope failures along Hualian section of 11th provincial highway. Firstly, this study is to compare the difference of slope failures between single factor and inter-relative of other factors. Secondly, the relative importance of these factors are analyzed and stressed. Finally, this article points out the possibility and potential analysis ability of applying Artificial Neural Networks (ANN). Principally, this article describes the analysis methods used in factors of data and historical records of land units, and applying ANN. Some factors should be considered, such as stratum (7 items), slop (3 items), engineering types of the slope (12 items), height of slope toe cutting (1 item), distance between geologic structure and land units (7 items) and aspect (1 item), total 6 types, 31 factors and analyzed 573 cases (have 218 landslide and 355 stable cases). Moreover, three sections, namely training data (60 % of all), validation data (20 % of all), and testing data (20 % of all) are developed via employing normalize and randomize of those data. In order to meet the aim of this study, therefore, three distributions should be compared such as the minimum error number of validation data (named MV), the error number of testing data correspond to MV (named TMV) and the minimum error number of testing data (named MT). To conclude it, according to research result, the use of ANN (error percentage is 1.22 %) is more applicable than use of discriminate analysis (error percentage is 18 %). As refer to the result of these data, it is not recommend considering the only answer as the final result. Meanwhile, for the result of extent of relationship of every functions and slope failures, the sequence is slope (1.390), stratum (0.608), engineering types of the slope (0.591) and distance between ecologic structure and land units (0.562), height of slope toe cutting (0.550)and aspect (0.546); only the first two factors and sequence is same as the results of Chung-Hua Chen’s (2004). Considering the ability of ANN, the range of MV is less than TMV, and the range of TMV is more than MT; which means the result of this simulation is fluctuant. Otherwise, the average of error percentage of MT is less than TMV; which means ANN has potential simulant ability, but it is difficult to display on the data.
Simão, Carolina Gonçalves Silva. "Artificial intelligence for fraud detection in motor insurance sector." Master's thesis, 2022. http://hdl.handle.net/10362/133845.
Повний текст джерелаOne of the major problems in the insurance sector is related to fraud, aside from tax fraud, insurance fraud is the most practiced fraud in the world since insurance, by its nature is very susceptible to it. Fraud could be minimized by investigating each claim that occurs but that also means an increase of the costs for the insurance companies. The fraudulent clients or agents that will be caught with the investigation and the amount of money spent by looking into every new claim is not worth it. Insurance fraud is usually caught only when the fraudsters get greedy and it becomes obvious that they are involved in a scheme. To minimize the investigation costs by only looking at suspicious claims, this project tries to identify the ones that are worth to scrutinize, through machine learning techniques. Five different predictive models will be used: Logistic Regression, Decision Tree, Random Forest, Neural Network and Gradient Boosting. The goal is to build an optimal model that will determine which automobile claims have higher probability of being fraudulent. An efficient fraud management can reduce costs, minimize claims and increase profits. This goal was accomplished with a Gradient Boosting classifier with 400 estimators, that is able to predict correctly 49% of the fraudulent claims, with 75% less investigated claims. There is still room for improvement by introducing the expected claim and investigation costs in the model. Since only the ones with significant costs would be worth to open an investigation, an even greater decrease in the number of investigated claims would be possible and, consequently, a decrease in the company’s costs with claims. Also, it would be expected that the claims with higher costs are more likely fraudulent than the ones with small indemnities; hence, this variable could lead to a higher precision of the model. These two features will be available in the future.
Oliveira, Joana Teixeira De. "State-of-art of artificial intelligence in the portuguese food retail sector." Master's thesis, 2020. http://hdl.handle.net/10362/104026.
Повний текст джерелаVan, Wyk Carel Johannes. "Assessment of synchronization in the SDH satellite sector." Thesis, 2012. http://hdl.handle.net/10210/6053.
Повний текст джерелаThe increase of multimedia and broadband communications in recent years has brought about the creation and implementation of synchronousdigital hierarchy (SDH) in the terrestrial network. The implementation of SDH in the satellite sector is a natural extension to improve the current available networks. It will drastically increase the flexibility and usability of the current under-utilized satellite sector. Unfortunately, SDH has still not been implemented in the satellite sector due to certain inherent synchronization problems of SDH and satellites. This thesis investigates some of these synchronization problems. A simulation tool was created that makes an accurate assessment of SDH synchronization in the satellite sector. The tool was used to study SDH links over goestationary (GEO), medium earth orbiting (MEO) and low earth orbiting (LEO) satellites. Various changeable SDH parameters were investigated to determine their influences. Parameters like the bit rate and elastic store length or hysteresis lengths were considered.
Rodrigues, Ana Rita Dias. "Inteligência artificial, transformação digital e cibersegurança no sector bancário: uma estrutura multi-stakeholder." Master's thesis, 2021. http://hdl.handle.net/10071/22884.
Повний текст джерелаhe world is in constant evolution, with new discoveries emerging every day. The human being is the motto for this evolution, and new technologies are a great ally in this quest for new conquests. The banking sector, namely traditional banking institutions, are currently under great pressure from their stakeholders to adapt to new technologies. However, considering the nature of this sector, the security of its users’ data cannot be put into question. The high level of trust that users place in their bank branches greatly characterizes the type of relationship kept between banking institutions and their clients. In addition, banks’ reputation directly affects their success, their capacity to attract new customers, as well as to retain existing ones. All these issues make decision making within the problematics of incorporating artificial intelligence (AI), digital transformation, and cybersecurity into the banking sector a complex decision problem. This study sought to develop a realistic model based on the combination of cognitive mapping and the "DEcision MAking Trial and Evaluation Laboratory" (DEMATEL) method to address this topic. Group sessions with an expert panel were carried out for application of the methodological procedures, allowing realism to be incorporated into the final results. Advantages and limitations of our framework are also discussed.
SUN, HSIN-YI, and 孫欣怡. "Applications of Artificial Intelligence in Financial Service Sector and Its Challenges to Legal System." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/f8q3jv.
Повний текст джерела東吳大學
法律學系
107
Development and promotion of Information and Communication Technology (ICT) has promoted the usage of Artificial Intelligence (AI) in various industries around the world. Even if the introduction of new technology can improve industrial transformation and create new added value; however if its industrial development is related to human life and property, such as the usage of artificial intelligence in the development of financial service, then special attention to related issues in development is needed, such as ethics, ideology, social perception, interactive behavior and bias, economic benefit, legal rights and obligations, etc. This thesis will investigate the challenges faced by our financial legal system when it comes to our financial services using the artificial intelligence and is going to explain the significance of artificial intelligence, and the current situation of the world's financial services with its related issues and controversies. In today's business model of artificial intelligence used in the financial services, common financial services are customer service, investment consulting, investment product analysis and recommendation, claims process guidance, smart contract drafting, investment product design, and marketing advertising. Since the financial services use artificial intelligence technology, it also has a relative impact and effect; hence, the WEF propose the impact and effect at nine major aspects, such as customer loyalty, self-motivated financial behavior, integrated solutions for shared issues, and differences in market structure, new ethical dilemmas, and more. Therefore, this thesis is going to give ‘Ethical Issues’, ‘Privacy Issues’, ‘Related Legal Rights and Obligations’, (, which are based on the above-mentioned nine major aspects), in-depth discussion, including the transparency, Open Banking, PSD2, de-identification, liability for damages, etc. Secondly, this thesis introduces the relevant financial legal system measures through the usage of artificial intelligence in the financial service in countries such as the United States, the European Union, and the United Kingdom. In the United States, the US government released the ‘Accelerating America’s Leadership in Artificial Intelligence’ executive order in 2019, also, IEEE announced the ‘The IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems’ in the academia. Furthermore IBM and Microsoft has also promoted the artificial intelligence being implemented in the design and development of algorithms in the industry. On the other side, in the European Union, European Parliament has signed the ‘Artificial Intelligence Cooperation Declaration’, and released the ‘com/2018/237 final’ in 2018, combining with the General Data Protection Regulation (GDPR) to accelerate the promotion of artificial intelligence technology to the financial services in the EU. In addition, in the United Kingdom, the government released the ‘AI in the UK: ready, willing and able?’, which includes the discussion of the artificial intelligence from different aspects, such as concept, participation, design, research and development, use, life, health care, risk reduction, and shaping the future of artificial intelligence, etc. In order to promote the development of artificial intelligence technology in the various industries of the UK. Finally, this thesis refers the way financial services operate Artificail Intelligence in the United States, the European Union, and the United Kingdom, to list the main laws, policies and plans for the development of artificial intelligence in our country. At the same time, according to the application of robot investment consultants in our country, enumerate the current laws and regulations. And then investigate the possible impacts and effects in our financial legal system at three aspects, ‘Ethical Issues’, ‘Privacy Issues’, and ‘Related Legal Rights and Obligations’. Then, we summarize the conclusions and recommendations at the end of this thesis.
Pires, Sofia Filipa Gonçalves. "O impacto da inteligência artificial no setor bancário." Master's thesis, 2020. http://hdl.handle.net/10071/21722.
Повний текст джерелаThe international financial markets, where banks assume a central role, face a growing organizational change in their activity, due to the strong impact of technology, the so-called Digital Transformation, and it is precisely this change that we intend to analyze in this dissertation. The purpose of this dissertation is, therefore, to analyze and study the impact of Artificial Intelligence on the Banking Sector, with special focus on Banco Best and the Acatis Artificial Intelligence Global Equities Fund. In order to do that, the methodology employed was based on a mixed method, which encompasses a quantitative methodology, through the analysis of reports from Banco Best and the comparison of profitability, and a qualitative methodology through an the realization of an interview with the Investment Director at Banco Best, Dr. Carlos Almeida, with the aim of making it possible to access the complexity and other perspectives of the topic that was intended to be studied. Empirical results of the present dissertation allowed to conclude that the investment of Artificial Intelligence in the Banking Sector presents positive impacts, although at the present time Artificial Intelligence has not yet managed to surpass Man in terms of profitability. However, the results obtained, despite being positive, show that banks should unite to use this technology as a tool to obtain competitive capacity and, in turn, stimulate growth.
Garcia, Miguel Alexandre da Cruz. "Impacto da inteligência artificial no setor financeiro." Master's thesis, 2021. http://hdl.handle.net/10071/23975.
Повний текст джерелаConsidering the current business landscape, one of the main issues corresponds to society's transition to the information age. It is increasingly important to adapt business models and adopt systems capable of interpreting large amounts of data, using Artificial Intelligence (AI). The financial industry is one of the sectors of the economy that will, sooner or later, face the challenges of this transition. The objective of this study is to understand what the most determinant factors in the decision to adopt AI are in the financial sector and what implications this transition has for the structure of the industry, taking into account the main challenges associated not only with the intelligent systems, but also with the existing barriers in this sector. After conducting this research, it was possible to conclude that although the benefits associated with AI and intelligent systems are clear, there is still some inertia regarding their adoption, associated not only with the risks associated with AI, such as transparency issues, but also issues associated with corporate culture. It was also possible to conclude that perceptions regarding the impact that AI may have on this industry are different when observed from an operational perspective, among the individuals who will effectively deal with these technologies, than from a strategic perspective. Additionally, the adoption of AI brings benefits not only related to the potential of the systems themselves, but also advantages related to the entry in this industry of companies that have innovative technologies.
Spanaki, K., E. Karafili, Uthayasankar Sivarajah, S. Despoudi, and Zahir Irani. "Artificial Intelligence and Food Security: Swarm Intelligence of AgriTech Drones for Smart AgriFood Operations." 2020. http://hdl.handle.net/10454/17961.
Повний текст джерелаThe Sustainable Development Goals (SDGs) present the emerging need to explore new ways of AgriFood production and food security as ultimate targets for feeding future generations. The study adopts a Design Science methodology and proposes Artificial Intelligence (AI) techniques as a solution to food security problems. Specifically, the proposed artefact presents the collective use of Agricultural Technology (AgriTech) drones inspired by the biomimetic ways of bird swarms. The design (artefact) appears here as a solution for supporting farming operations in inaccessible land, so as unmanned aerial devices contribute and improve the productivity of farming areas with limited capacity. The proposed design is developed through a scenario of drone swarms applying AI techniques to address food security issues. The study concludes by presenting a research agenda and the sectoral challenges triggered by the applications of AI in Agriculture.
European Union's H2020 research and innovation programme under the Marie Skłodowska-Curie grant (agreement No. 746667)
The full-text of this article will be released for public view at the end of the publisher embargo on 25 Feb 2022.
Cordeiro, Pedro Filipe da Silva. "Implementação de equipamentos auxiliares do processo de injeção de peças para o sector automóvel." Master's thesis, 2017. http://hdl.handle.net/10400.26/25377.
Повний текст джерелаCarmona, Pedro Bernardo Resina Baptista Barreiros. "Automated Machine Learning implementation framework in the banking sector." Master's thesis, 2022. http://hdl.handle.net/10362/134199.
Повний текст джерелаAutomated Machine Learning is a subject in the Machine Learning field, designed to give the possibility of Machine Learning use to non-expert users, it aroused from the lack of subject matter experts, trying to remove humans from these topic implementations. The advantages behind automated machine learning are leaning towards the removal of human implementation, fastening the machine learning deployment speed. The organizations will benefit from effective solutions benchmarking and validations. The use of an automated machine learning implementation framework can deeply transform an organization adding value to the business by freeing the subject matter experts of the low-level machine learning projects, letting them focus on high level projects. This will also help the organization reach new competence, customization, and decision-making levels in a higher analytical maturity level. This work pretends, firstly to investigate the impact and benefits automated machine learning implementation in the banking sector, and afterwards develop an implementation framework that could be used by banking institutions as a guideline for the automated machine learning implementation through their departments. The autoML advantages and benefits are evaluated regarding business value and competitive advantage and it is presented the implementation in a fictitious institution, considering all the need steps and the possible setbacks that could arise. Banking institutions, in their business have different business processes, and since most of them are old institutions, the main concerns are related with the automating their business process, improving their analytical maturity and sensibilizing their workforce to the benefits of the implementation of new forms of work. To proceed to a successful implementation plan should be known the institution particularities, adapt to them and ensured the sensibilization of the workforce and management to the investments that need to be made and the changes in all levels of their organizational work that will come from that, that will lead to a lot of facilities in everyone’s daily work.
Hoppe, Niklas. "Disruptive innovation in the healthcare sector : the advent of AI chatbots." Master's thesis, 2020. http://hdl.handle.net/10400.14/31219.
Повний текст джерелаNas últimas décadas, o setor da saúde enfrentou muitos desafios. Nestes podem destacar-se a escassez de médicos, especialmente nas zonas rurais, custos de tratamento elevados e um número crescente de doenças a precisarem de ser tratadas. Esta tese foca-se no potencial e nas limitações de uma forma revolucionária de resolver problemas na área da saúde – o uso de chatbots de IA. Destacamos a perspetiva do utilizador em relação à assistência médica através da tecnologia de chatbot de IA. Com base em pesquisas qualitativas e quantitativas, concluímos que esta tecnologia inovadora oferece novas oportunidades para diagnósticos, permite que o trabalho seja realizado com mais eficiência e oferece ao paciente a capacidade de se autodiagnosticar. Os chatbots de IA ainda não atingiram todo o seu potencial devido a restrições legais, dados insuficientes e à falta de capacidade de integrá-los em diferentes sistemas. Ainda que o número de utilizadores de chatbot de IA esteja a aumentar, as pessoas confiam menos nos chatbots do que nos médicos. Para encorajar um maior envolvimento do utilizador e criar um nível mais alto de confiança, entidades credíveis como médicos e o governo podem recomendar o uso de chatbots de IA. A aceitação generalizada dos chatbots deve ser analisada por país, uma vez que é explicada por fatores socioeconómicos (educação, idade, rendimento), fatores relacionados com a personalidade (atitude perante coisas novas, curiosidade) e fatores de comportamento na comunicação.
Nilsson, Adam, and Abbas Hathalia. "Drömmen om Artificiell Intelligens (AI) : En studie angående utmaningar med att implementera Artificiell Intelligens inom myndigheter." Thesis, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-25471.
Повний текст джерелаSchneider, Leandro Rodrigo. "Oportunidades e desafios da inteligência artificial no setor público: o caso do tribunal de contas de Portugal." Master's thesis, 2021. http://hdl.handle.net/10071/24312.
Повний текст джерелаArtificial Intelligence has stood out among digital technologies in the administrative modernization of the public sector due to the great potential of applications and solutions that can be explored in the most diverse levels of activity in the State. The inspection of the use of public financial resources is a growing concern due to their scarcity, and the verification of their proper application becomes a great challenge in today's world. The Court of Auditors has been using technologies that encompass the concept of Artificial Intelligence and this work seeks to explore and understand, through a case study, how these technologies are being used to control and supervise the use of public financial resources in Portugal. At an early stage of development, the use of technologies aims to subsidize and support the actions of auditors, in the rendering of accounts and contracts of entities under the jurisdiction of the court, in order to analyze data and information and find network models that make it possible to perceive influential groups and finding patterns that underlie the triggering of new assessment actions. The results obtained reinforce the efficiency and effectiveness of Artificial Intelligence technologies in their applications, however, they only serve as indicatives, as they do not yet encompass all entities and do not have sufficient history to generate forecasts.