Дисертації з теми "Artificial Intelligence of Thing"

The Internet of Things (IoT) has deeply changed how we interact with our world. Today, smart homes, self-driving cars, connected industries, and wearables are just a few mainstream applications where IoT plays the role of enabling technology. When IoT became popular, Cloud Computing was already a mature technology able to deliver the computing resources necessary to execute heavy tasks (e.g., data analytic, storage, AI tasks, etc.) on data coming from IoT devices, thus practitioners started to design and implement their applications exploiting this approach. However, after a hype that lasted for a few years, cloud-centric approaches have started showing some of their main limitations when dealing with the connectivity of many devices with remote endpoints, like high latency, bandwidth usage, big data volumes, reliability, privacy, and so on. At the same time, a few new distributed computing paradigms emerged and gained attention. Among all, Edge Computing allows to shift the execution of applications at the edge of the network (a partition of the network physically close to data-sources) and provides improvement over the Cloud Computing paradigm. Its success has been fostered by new powerful embedded computing devices able to satisfy the everyday-increasing computing requirements of many IoT applications. Given this context, how can next-generation IoT applications take advantage of the opportunity offered by Edge Computing to shift the processing from the cloud toward the data sources and exploit everyday-more-powerful devices? This thesis provides the ingredients and the guidelines for practitioners to foster the migration from cloud-centric to novel distributed design approaches for IoT applications at the edge of the network, addressing the issues of the original approach. This requires the design of the processing pipeline of applications by considering the system requirements and constraints imposed by embedded devices. To make this process smoother, the transition is split into different steps starting with the off-loading of the processing (including the Artificial Intelligence algorithms) at the edge of the network, then the distribution of computation across multiple edge devices and even closer to data-sources based on system constraints, and, finally, the optimization of the processing pipeline and AI models to efficiently run on target IoT edge devices. Each step has been validated by delivering a real-world IoT application that fully exploits the novel approach. This paradigm shift leads the way toward the design of Edge Intelligence IoT applications that efficiently and reliably execute Artificial Intelligence models at the edge of the network.

The Internet of Things (IoT) has deeply changed how we interact with our world. Today, smart homes, self-driving cars, connected industries, and wearables are just a few mainstream applications where IoT plays the role of enabling technology. When IoT became popular, Cloud Computing was already a mature technology able to deliver the computing resources necessary to execute heavy tasks (e.g., data analytic, storage, AI tasks, etc.) on data coming from IoT devices, thus practitioners started to design and implement their applications exploiting this approach. However, after a hype that lasted for a few years, cloud-centric approaches have started showing some of their main limitations when dealing with the connectivity of many devices with remote endpoints, like high latency, bandwidth usage, big data volumes, reliability, privacy, and so on. At the same time, a few new distributed computing paradigms emerged and gained attention. Among all, Edge Computing allows to shift the execution of applications at the edge of the network (a partition of the network physically close to data-sources) and provides improvement over the Cloud Computing paradigm. Its success has been fostered by new powerful embedded computing devices able to satisfy the everyday-increasing computing requirements of many IoT applications. Given this context, how can next-generation IoT applications take advantage of the opportunity offered by Edge Computing to shift the processing from the cloud toward the data sources and exploit everyday-more-powerful devices? This thesis provides the ingredients and the guidelines for practitioners to foster the migration from cloud-centric to novel distributed design approaches for IoT applications at the edge of the network, addressing the issues of the original approach. This requires the design of the processing pipeline of applications by considering the system requirements and constraints imposed by embedded devices. To make this process smoother, the transition is split into different steps starting with the off-loading of the processing (including the Artificial Intelligence algorithms) at the edge of the network, then the distribution of computation across multiple edge devices and even closer to data-sources based on system constraints, and, finally, the optimization of the processing pipeline and AI models to efficiently run on target IoT edge devices. Each step has been validated by delivering a real-world IoT application that fully exploits the novel approach. This paradigm shift leads the way toward the design of Edge Intelligence IoT applications that efficiently and reliably execute Artificial Intelligence models at the edge of the network.

The purpose of this thesis is to explore the drivers and barriers of adoption of technology such as AI and how it could facilitate an internationalization. The thesis also hopes to explore how Born Global e-commerce companies are working towards an adoption of AI into the companies CRM-system. The model of multiple case study was chosen together with a qualitative method and an abductive approach. This was done by collecting primary data from three different Born Global firms within the e-commerce sector, as well as one CRM expert company, all located in Sweden and active on the international market. Furthermore, the theoretical framework presented Born Global, Technology Adoption, Customer Relationship Management and Artificial Intelligence. With the theoretical framework in mind, the conceptual framework was developed to show how the theories are connected to each other. Thereafter, the empirical findings were first presented and analysed together with theory and the voice of the authors of the thesis. The analysis visualize both similarities and dissimilarities between the empirical findings and the theory presented in the thesis. The final chapter concludes the barriers and drivers that Born Global e-commerce companies faces when adopting AI into their CRM-system. It also explains how AI within CRM could be beneficial as a tool on the Global market, rather than in the actual process of internationalization. To conclude the authors present the fact that companies are not working towards an adoption of AI into their CRM-systems. However, further development within the field is presented as well as theoretical and practical implications.

This thesis presents optical characterization of the static and dynamic magnetic interactions in ferromagnetic and multiferroic heterostructures with time-resolved and interface-specific optical techniques. The focus of the thesis is on elucidating the underlying physics of key physical parameters and novel approaches, crucial to the performance of magnetic recording and spintronic devices.;First, time-resolved magneto-optical Kerr effect (TRMOKE) is applied to investigate the spin dynamics in L10 ordered FePt thin films, where perpendicular magnetic anisotropy Ku and intrinsic Gilbert damping alpha0 are determined. Furthermore, the quadratic dependence of Ku and alpha0 on spin-orbit coupling strength xi is demonstrated, where xi is continuously controlled through chemical substitution of Pt with Pd element. In addition, a linear correlation between alpha0 and electron scattering rate 1/T e is experimentally observed through modulating the anti-site disorder c in the L10 ordered structure. The results elucidate the basic physics of magnetic anisotropy and Gilbert damping, and facilitate the design and fabrication of new magnetic alloys with large perpendicular magnetic anisotropy and tailored damping properties.;Second, ultrafast excitation of coherent spin precession is demonstrated in Fe/CoO heterostructures and La0.67Ca0.33MnO 3 thin films using TRMOKE technique. In the Fe/CoO thin films, Instant non-thermal ferromagnet (FM) -- antiferromagnet (AFM) exchange torque on Fe magnetization through ultrafast photo-excited charge transfer possesses in the CoO layer is experimentally demonstrated at room temperature. The efficiency of spin precession excitation is significantly higher and the recovery is notably faster than the demagnetization procedure. In the La0.67Ca 0.33MnO3 thin films, pronounced spin precessions are observed in a geometry with negligible canting of the magnetization, indicating that the transient exchange field is generated by the emergent AFM interactions due to charge transfer and modification of the kinetic energy of eg electrons under optical excitation. The results will help promoting the development of novel device concepts for ultrafast spin manipulation.;Last, the interfacial spin state of the multiferroic heterostructure PbZr0.52Ti0.4803/La0.67Sr0.33MnO 3 and its dependence on ferroelectric polarization is investigated with interface specific magnetization induced second harmonic generation (MSHG). The spin alignment of Mn ions in the first unit cell layer at the heterointerface can be tuned from FM to AFM exchange coupled, while the bulk magnetization remains unchanged as probed with MOKE. The discovery provides new insights into the basic physics of interfacial magneto-electric (ME) coupling.

La consommation, en général, représente le processus d’utilisation d’un type de ressource où des économies doivent être réalisées. La consommation d’énergie est devenue l’un des principaux problèmes d’urbanisation et de crise énergétique, car l’épuisement des combustibles fossiles et le réchauffement climatique mettent en péril l’utilisation de l’énergie des plantes. Cette thèse présent une méthode d’économie d’énergie a été adoptée pour la réduction de consommation d’énergie prévu le secteur résidentiel et les maisons passives. Un modèle mathématique basé sur des mesures expérimentales a été développé pour simuler le comportement d’un laboratoire d’essai de l’UPB. Le protocole expérimental a été réalisé à la suite d’actions telles que : la construction de bases de données sur les paramètres, la collecte de données météorologiques, l’apport de flux auxiliaires tout en considérant le comportement humain. L’algorithme de contrôle-commande du système est capable de maintenir une température constante à l’intérieur du bâtiment avec une consommation minimale d’énergie. Les mesures et l’acquisition de données ont été configurées à deux niveaux différents: les données météorologiques et les données sur les bâtiments. La collection de données est faite sur un serveur qui a été mis en œuvre dans l’installation de test en cours d’exécution d’un algorithme complexe qui peut fournir le contrôle de consommation d’énergie. La thèse rapporte plusieurs méthodes numériques pour envisage la consommation d’énergie, utilisée avec l’algorithme de contrôle. Un cas expérimental basé sur des méthodes de calcul dynamiques pour les évaluations de performance énergétique de construction a été faite à Grenade, en Espagne, l’information qui a été plus tard utilisée dans cette thèse. L’estimation des paramètres R-C avec la prévision du flux de chaleur a été faite en utilisant la méthode nodal, basée sur des éléments physiques, des données d’entrée et des informations météorologiques. La prévision d’énergie de consommation présent des résultats améliorés tandis que la collecte de données IoT a été téléchargée sur une carte à base de système de tarte aux framboises. Tous ces résultats ont été stables montrant des progrès impressionnants dans la prévision de la consommation d’énergie et leur application en énergie
Consumption, in general, represents the process of using a type of resource where savings needs to be done. Energy consumption has become one the main issue of urbanization and energy crisis as the fossil depletion and global warming put under threat the planet energy utilization. In this thesis, an automatic control of energy was developed to reduce energy consumption in residential area and passive house buildings. A mathematical model founded on empirical measurements was developed to emphasize the behavior of a testing laboratory from Universitatea Politehnica din București - Université Politechnica de Bucarest - Roumanie. The experimental protocol was carried out following actions such as: building parameters database, collecting weather data, intake of auxiliary flows while considering the controlling factors. The control algorithm is controlling the system which can maintain a comfortable temperature within the building with minimum energy consumption. Measurements and data acquisition have been setup on two different levels: weather and buildings data. The data collection is gathered on a server which was implemented into the testing facility running a complex algorithm which can control energy consumption. The thesis reports several numerical methods for estimating the energy consumption that is further used with the control algorithm. An experimental showcase based on dynamic calculation methods for building energy performance assessments was made in Granada, Spain, information which was later used in this thesis. Estimation of model parameters (resistances and capacities) with prediction of heat flow was made using nodal method, based on physical elements, input data and weather information. Prediction of energy consumption using state-space modeling show improved results while IoT data collection was uploaded on a Raspberry Pi system. All these results were stable showing impressive progress in the prediction of energy consumption and their application in energy field

It is estimated that by 2020, more than 50 billion devices will be interconnected, to form what is called the Internet of Things. Those devices range from consumer electronics to utility meters, including vehicles. Provided with sensory capabilities, those objects will be able to transmit valuable information about their environment, not only to humans, but even more importantly to other machines, which should ultimately be able to interpret and take decisions based on the information received. This “smartness” implies gifting those devices with a certain degree of automation. This Master’s Thesis investigates how recent advances in artificial intelligence planning can be helpful in building such systems. In particular, an artificial intelligence planner able to generate workflows for most of IoT-related use cases has been connected to an IoT platform. A performance study of a state-of-the planner, Fast Downward, on one of the most challenging IoT application, Smart Garbage Collection (which is similar to the Traveling Salesman Problem) has also been carried out. Eventually, different pre-processing and clustering techniques are suggested to tackle the latest AI planners’ inefficiency on quickly finding plans for the most difficult tasks.

Countries around the world are facing urban planning challenges in fast-growing areas. As a developed country, Australia has a sound social system, with laws, rules and regulations. Rapid growth has brought new development opportunities, but also accompanied by serious social planning and decision-making issues. In some fast-growing areas, investments for infrastructure cannot keep up with the rapid population growth due to inaccurate data and other factors. As a result, sometimes it’s becoming very hard and challenging for the government to make the best decision for investments in order to achieve the maximum potential. Embracing emerging technologies, to build smart cities in Australia, to improve governance and decision making has become critical. This thesis explores challenges we are facing in fast-growing areas in Australia and how emerging technology-aided strategy making, community consultation and smart governance can help building a smart city. We demonstrate in-depth in how emerging technologies like Internet of Things and Big Data can improve a city’s operation efficiency and assisting decision-makers to solve challenging leadership, planning and decision-making issues. This thesis demonstrates by using these technologies how a planning decision or a community consultation which currently take months to process could be reduced to days, or how an operational decision which currently takes a week could be reduced to a day.

Il contesto sociale di oggi è modellato da due tendenze coesistenti: spinta tecnologica e richiesta di applicazioni. Con il primo termine si intende l'emergere, la rapida evoluzione e l'applicazione di tecnologie innovative, del regno dell'ICT (come IoT) e dell'analisi dei dati (come Intelligenza Artificiale, Machine e Deep Learning). La seconda tendenza è invece una peculiarità del mercato odierno, costruito su requisiti come il basso costo, l’alto tasso tecnologico, la personalizzazione e la facile accessibilità tra gli altri. Grazie a queste due tendenze coesistenti e sinergiche, l'intera società sta rapidamente passando al livello successivo (da cui i paradigmi Industria 4.0 e Società 5.0). Il ragionamento che ha permesso questa rapida evoluzione, è stato la comprensione del fatto che prendere decisioni basate su informazioni reali estratte dalla complessa realtà in cui viviamo, consente miglioramenti in termini di costi, tempi e qualità. In quasi tutti i contesti, disporre di buoni sistemi che consentano il passaggio da dati grezzi effettivamente raccolti sul campo, a conoscenze significative, è la chiave del successo. Da un punto di vista architetturale, ci sono tre livelli principali che consentono la creazione di conoscenza e saggezza partendo dalla realtà: acquisizione, comunicazione ed analitica. L'innovazione a uno o più livelli è essenziale per lo sviluppo della comunità mondiale. Questa tesi presenta numerosi contributi innovativi ed esplorazioni tecnologiche, appartenenti a uno o più livelli dell’architettura semplificata a tre livelli, per lo più focalizzati nell'ambito delle pratiche dell'Industria 4.0, come la manutenzione basata sulle condizioni e i sistemi di visione artificiale, e nelle pratiche della società 5.0, come i dispositivi indomabili per la sanità intelligente e i Sistemi Visual-IoT per la gestione delle inondazioni nelle smart cities del futuro. I paradigmi tecnologici IoT e IA sono stati profondamente analizzati sia da un punto di vista teorico che pratico. Attraverso la loro applicazione in diverse attività di ricerca, ciascuna focalizzata su aspetti specifici, è stato raggiunto l'obiettivo finale di sviluppare una comprensione ampia e completa. L'IoT è un paradigma rivoluzionario, che abbraccia i tre livelli tra i dati grezzi e la conoscenza significativa, essendo quindi un argomento complesso da affrontare in modo completo. L'IA è un fattore essenziale per rendere tangibile l'impatto dell'IoT ed al contempo le metodologie e le tecniche dell'IA sono diversificate e complesse. Per questo motivo è stato adottato un approccio dal basso verso l’alto, partendo da una varietà di casi d’uso reali focalizzati su un livello specifico, ognuno dei quali affrontato applicando rigorosamente il metodo scientifico di ricerca, sono state estratte conoscenze globali e adattabili sull’IoT e sull’IA. Le fonti di casi d'uso sono state aziende private, progetti di ricerca nazionali ed internazionali, focalizzati sui paradigmi Industria 4.0 e Società 5.0, come verrà presentato più in dettaglio. Nello specifico verranno presentate le seguenti attività di ricerca: un sistema di e-Health basato su sensori indossabili, un sistema IoT per il monitoraggio in tempo reale degli edifici, un proxy cross-protocollo per reti di sensori IoT, un algoritmo di Machine Vision per il conteggio dei pezzi assemblati manualmente, un Modello basato su ML per valutare lo stato di salute della cinghia di trasmissione di un robot cartesiano, un modello basato su ML in grado di valutare lo stato di salute di una macchina per lo stampaggio ad iniezione sulla base dei parametri di processo raccolti da sensori diffusi, un sistema basato su OCR in grado di suggerire interventi di manutenzione per le targhe utilizzate nella gestione degli ordini di un sistema di robot per la verniciatura, una soluzione di visione artificiale per il monitoraggio del livello dell'acqua dei fiumi attraverso una telecamera che inquadra l’asta idrometrica ed infine un modello dinamico di razionamento del consumo di energia per gli impianti di raffinazione del petrolio. Affrontando casi reali più o meno specifici incentrati su IoT e AI, è stato possibile comprendere le possibilità e le peculiarità architetturali e software dei due paradigmi. Questa ampia varietà di possibilità dovrebbe essere ottimizzata per soddisfare il più possibile il contesto e i requisiti specifici del compito. In conclusione, IoT ed IA possono avvantaggiarsi a vicenda grazie alla stretta interconnessione nel paradigma edge-AI, che insieme all'in-network e al cloud computing, sono stati ritenuti essenziali per il futuro successo di una società più intelligente.
The societal context of today is shaped by two coexisting tendencies: technology-push and application-pull. The former is the emergence and rapid evolution and application of innovative technologies, in the realm of ICT (like IoT) and Data Analysis (like Artificial Intelligence, Machine and Deep Learning). The latter tendency is the trend of the market of today, built on requirements like low-cost, high-tech, customized, easily accessible, and so on so forth. Thanks to these coexisting and synergistic tendencies, the entire society is rapidly passing to the next level (hence Industry 4.0 and Society 5.0 paradigms). The reasoning that allowed this rapid evolution, has been the comprehension of the fact that making decisions based on real information extracted from the complex reality we live in, allows improvements in terms of costs, time, and quality. In almost every context, having good systems that allow the passage from raw actual data collected to meaningful knowledge is the key for success. From an architectural point of view, there are three main levels that allow the creation of knowledge and wisdom from the reality: acquisition, communication, and analytic. Innovation in either one or multiple levels is essential for the development of the worldwide community. This thesis presents several innovative contributions and technological explorations, belonging to either one or multiple levels, mostly focused in the realm of Industry 4.0 practices, like Condition-Based Maintenance, and Machine Vision Systems, and Society 5.0 practices, like e-Health devices and Visual-IoT systems for flood management in smart cities. IoT and AI technological paradigms have been deeply analysed from both a theoretical and practical point of view. Through their application in several research activities, each focused on specific aspects, the final aim of developing a broad and comprehensive understanding has been achieved. IoT is a revolutionary paradigm, which spans the three levels between raw data and meaningful knowledge, thus being a complex topic to deal with comprehensively. AI is an essential enabler for making IoT's impact tangible, and AI methodologies and techniques are diversified and complex too. For this reason, a bottom-up approach has been adopted, starting from a variety of real cases focused on a specific level, and each addressed rigorously applying the scientific method of research, global and adaptable knowledge about IoT and AI has been extracted. The sources of use cases have been private companies, National and International research projects, committed to Industry 4.0 and Society 5.0 paradigms, as will be presented. Specifically, the following research activities will be presented: an e-Health system based on wearable sensors, an IoT system for real-time building monitoring, a cross-protocol proxy for sensors networks, a Machine Vision algorithm for counting manually assembled pieces, a ML-based model for assessing the health status of a cartesian robot's drive belt, a ML-based model able to assess the health of an injection moulding machine based on process parameters collected by widespread sensors, an OCR-based system able to suggest maintenance intervention for painting robot's number plates, a Computer Vision solution for monitoring the water level of rivers through a camera framing the gauge, and a dynamic energy consumption rationing model for oil refining plants. By addressing more or less specific real cases centered on IoT and AI, it has been possible to understand architectural and software possibilities and peculiarities of the two paradigms. These wide variety of possibilities should be tuned in order to satisfy as better as possible context and task-specific requisites. Concluding, IoT and AI can benefit each other by the strict interconnection into the edge-AI paradigm, which together with in-network and cloud computing, have been found essential for the future successful achievement of smarter society.

The present study is aiming to evaluate the Intelligent Personal Assistants usage motivations, addressing at the same time various privacy issues and concerns related to this emergent technology. To fulfil the purpose of the study I have applied two different research methods. Initially, a web survey conducted gathered 18 respondents answering 24 questions related to the presented topic. Subsequently, was organised a focus group by gathering seven respondents who shared their opinions on the subject of research. Two research questions were developed based on two hypotheses. First research question: “To what extent IPA users agree to personal data collection in order to gratify their sought needs?”; exploring the participants’ opinions when it comes to the degree of acceptance of personal information disclosure to gratify their needs. Moreover, second research question: “What are the motivating criteria that determine the usage of IPA?”. This question develops opinions and experiences on the usage of Intelligent Personal Assistants, as well as the way people perceive this new technology. The finding of this studies reveals that users of new media are concerned and aware of their personal data collection. However, as a result, they feel trapped in the network society by the peer pressure towards the usage of favourite mediums. Therefore, the denial of technology would bring unfavourable consequences from a social perspective. Further researches can be conducted on this topic, addressing in depth the Artificial Intelligence and its societal implications, possible utilities of the Intelligent Personal Assistants as a companion for children, elders and people with disabilities, Artificial Intelligence used in public administration. Consequently, many different aspects can be explored having the topic of this thesis as a starting point.

Aquesta tesi explora les percepcions de la IA per part de la indústria de la publicitat i el màrqueting i les contrasta amb l’estat actual de desenvolupament de la IA. La indústria de la publicitat és un punt focal interessant per discussions amb relació a la IA, ja que és una indústria emblemàtica i creativa, sovint vista com una àrea en què les màquines únicament poden copiar o donar suport però no pas idear i crear. La intel·ligència artificial (IA) és una intel·ligència exposada per màquines. En la ciència de la computació, una màquina “intel·ligent” ideal és un agent flexible i racional que percep el seu entorn i pren accions per minimitzar les seves possibilitats de succés envers un objectiu arbitrari (Russell i Norvig, 2013). Els desenvolupaments de la IA estan canviant la societat. Algunes millores són petites, com per exemple la IA de Google amb relació a les millores del Gmail per contestar els correus de manera més fàcil i ràpida. Altres canvis estan en procés. Aquest és el cas de la versió d’iteració de Tesla en el cas dels programes de vehicles autònoms. També estan havent-hi altres canvis com succeeix amb Echo, l’assistent personal d’Amazon per la teva llau que s’activa amb la veu. Tots aquests exemples i molts més estan fent possible que la IA formi part del nostre dia a dia. En el camp dels mitjans, Mark Zuckerberg, el fundador i CEO de Facebook, ofereix chat-bots en la seva plataforma de missatges instantanis per empreses que vulguin comunicar-se amb els seus consumidors. En el món de la publicitat i el màrqueting, la IA està començant a ser més que un tema de ciència-ficció o una estratègia a imitar per inèrcia. Creatius, executius en els mitjans de comunicació i emprenedors AdTech estan activament explorant la IA. En el 2016, l’empresa de publicitat McCann va anunciar que la seva divisió japonesa dirigida al públic jove, anomenada McCann Millennials, havia construït i estava utilitzant un director creatiu d’IA (Doland, 2016). En contrast amb el moviment cap a la IA, diversos creadors d’anuncis mítics es mantenen fermament compromesos amb la idea que la creativitat humana individual es mantingui en el centre del procés creatiu dels mitjans de comunicació i del màrqueting. En els últims anys, el llegendari executiu publicitari John Hegarty va defensar el paper crític que els humans juguen per raonar i curar i, finalment, crear bon màrqueting (Arthur, 2016). La recerca principal de la tesi es basa en una enquesta a grups d’interès clau de la publicitat i el món del màrqueting sobre el tema de la IA. Després d’emplenar el qüestionari, un grup més reduït d’enquestats va participar en entrevistes de seguiment per ampliar les seves opinions sobre diverses àrees de l’enquesta. Aquesta tesi explora el tema de la IA en el màrqueting i la percepció de la IA per part dels venedors. Els resultats mostren una indústria interessada amb prudència en la IA i el seu potencial, però desconeguda i poc preparada per aquells reptes que aquest salt tecnològic presenta. La majoria dels participants en l’estudi van destacar la seva comprensió limitada de la IA. Dels 440 enquestats, la gran majoria de les dades van caure en el quartil més baix, situant-se en el rang 3 / 3.5 sobre 10. Quan se'ls va preguntar sobre la capacitat creativa de la IA, els participants van respondre de forma negativa, amb una mitjana de 3,0 en una escala de l’1 al 10. Quan se’ls va preguntar quines feines podrien ser substituïdes per la IA, l’opció favorita va ser “no pot ser substituïda per la IA” quan les feines estaven relacionades amb la creativitat, l’estratègia i el lideratge. Un 82% dels enquestats va dir que les seves empreses no oferien formació en IA.
Esta tesi explora las percepciones de la IA por parte de la industria de la publicidad y el marketing y las contrasta con el estado actual de desarrollo de la IA. La indústria de la publicidad es un punto focal interesante para discusiones relacionadas con la IA, ya que es una industria emblemática y creativa, a menudo vista como una área en que las máquinas únicamente puede copiar o dar soporte y no idear y crear. La IA es una inteligencia expuesta para máquinas. En la ciencia de la computación, una máquina “inteligente” ideal es un agente flexible y racional que percibe su entorno y toma acciones para minimizar sus posibilidades de éxito hacia un objetivo arbitrario (Russell y Norvig, 2013). Los desarrollos de la IA están cambiando la sociedad. Algunas mejoras son pequeñas, como por ejemplo la IA de Google en relación a las mejoras del Gmail para contestar los correos de modo más fácil y rápido. Otros cambios están en proceso. Este es el caso de las versiones de Tesla al software de vehículos autónomos. También están habiendo otros cambios como sucede con Echo, el asistente personal de Amazon para tu casa que se activa con la voz. Todos estos ejemplos y muchos más están haciendo posible que la IA forme parte de nuestro día a día. En el campo de los medios, Mark Zuckerberg, el fundador y CEO de Facebook, ofrece chat-bots en su plataforma de mensajería instantánea para empresas que quieran comunicarse con sus consumidores. En el mundo de la publicidad y el marketing, la IA está empezando a ser más que un tema de ciencia ficción o una estrategia a imitar por inercia. Creativos, ejecutivos en los medios de comunicación y emprendedores AdTech están activamente explorando la IA. En el 2016, la empresa de publicidad McCann anunció que su división joven japonesa para jóvenes llamada McCann Millennial había construido y estaba utilizando un director creativo basado en IA (Doland, 2016). En contraste con el movimiento hacia la IA, distintos creadores de anuncios míticos se mantienen firmemente comprometidos con la idea que la creatividad humana individual se mantenga en el centro del proceso creativo de los medios de comunicación y del marketing. En los últimos años, el legendario ejecutivo publicitario John Hegarty defendió el papel crítico que los humanos juegan para razonar y curar y, finalmente, crear un buen marketing (Arthur, 2016). Los resultados de la tesis se basan en una encuesta a grupos de interés clave de la publicidad y el mundo del marketing sobre el tema de la IA. Después de rellenar el cuestionario, un grupo más reducido de encuestados participó en entrevistas de seguimiento para ampliar sus opiniones sobre diversas áreas de la encuesta. Esta tesi explora el tema de la IA en el marketing y la percepción de la IA por parte de sus vendedores. Los resultados muestran una industria interesada con prudencia en la IA y en su potencial, pero que es todavía desconocida, y poco preparada para aquellos retos que este salto tecnológico presenta. La mayoría de los participantes en el estudio destacaron su comprensión limitada de la IA. De los 440 encuestados, la gran mayoría de los datos cayeron en el cuartil más bajo, situándose en el rango 3/3.5 sobre 10. Cuando se les preguntó cómo de creativa puede ser la IA, los participantes respondieron de forma negativa, con una media de 3.0 en una escala de 1 al 10. Cuando se les preguntó qué trabajos podrían ser sustituidos por la IA, la opción más popular cuando se referían a labores relacionadas con la creatividad, la estrategia y el liderazgo fue “no puede ser substituida por la IA”. Un 82% de los encuestados dijeron que sus empresas no ofrecían formación en IA.
This thesis explores perceptions of artificial intelligence (AI) by the advertising industry and contrasts those perceptions with the state of AI marketing development today. The advertising industry is an interesting focal point for a discussion regarding AI because it is one of the emblematic creatively focused industries, and creative is often viewed as an area where machines can only copy or support and not ideate. Artificial intelligence (AI) is the intelligence exhibited by machines. In computer science, an ideal "intelligent" machine is a flexible rational agent that perceives its environment and takes actions that maximize its chance of success at an arbitrary goal (Russell and Norvig, 2003). AI technology developments are changing society. Some are small improvements like Google's AI enhancements in its’ Gmail product that makes it easier and faster to respond to messages. Others are on-going shifts like Tesla's version iterations to autonomous vehicle software. And even others such as Echo, Amazon's voice-activated personal assistant for your home, begin to make AI-enabled machines part of daily life. In the media space, Facebook's Founder and CEO Mark Zuckerberg offers chat-bots in their instant messaging platform that speak to consumers for brands. In the advertising and marketing world, artificial intelligence is starting to be more than a science fiction topic or a nifty copy strategy. Creatives, media executives, and AdTech entrepreneurs are actively exploring AI. In 2016, the advertising firm McCann announced that their Japanese youth division titled McCann Millennials had built and was using an AI creative director (Doland, 2016). In contrast to the movement towards AI, several legendary ad creators remain firmly committed to the idea of the individual creative human being staying solely at the center of the media and marketing creative process. In recent years, legendary ad executive Sir John Hegarty, defended the critical role humans play to reason and curate and ultimately create great marketing (Arthur, 2016). The primary research for the thesis is a survey of key stakeholders in the advertising and marketing world on the topic of artificial intelligence. After fielding the questionnaire, a smaller set of respondents participated in follow-up interviews to expand their opinions on various areas of the survey. This thesis explores the topic of artificial intelligence in marketing and the perception of AI by marketers. The results show an industry cautiously interested in AI and its potential, but woefully unaware and unprepared for the challenges this technological leap-forward presents. The majority of participants in the study highlighted their limited understanding of AI. Out of the 440 respondents, the vast majority of the data fell in the lowest quartile, being in the 3/3.5 range out of 10. When asked how creative AI can be, participants consistently responded negatively, with an average of 3.0 on a scale of 1 to 10 in terms of how creative AI can become. When asked what jobs AI can replace, roles that received the highest number of mentions for "cannot be replaced by AI" were mostly creative, strategic or leadership. An astounding 82% of respondents said their companies did not offer training in AI. This thesis wrestles with the luddite and progressive perspectives of AI in marketing and the machine-learning breakthroughs that challenge the role of the marketing department and advertising industry.

In the late 1990's, when sophisticated personal computers and electronic devices with miniaturized sensors were being mass produced, the concept of ambient intelligence (AmI) emerged. An environment that has AmI is a space containing objects which includes technologies that are not visible to users, and which generates intelligent responses when appropriate. When people interact with an AmI environment, they intuitively use technologies according to their own needs and gain more awareness of their actions, thereby improving their quality of life, comfort, and empowerment. Currently, healthcare professionals work inside a complex adaptive system in which the clinical environment and the health status of patients vary dynamically, and resources are limited. This can generate an increasing number of adverse events as well as medical errors and consequently patients are more exposed to potential harm during a hospital stay. Many researchers are creating new AmI tools to overcome these challenges. This is especially important in intensive care units (ICUs), where there are seriously ill patients who need advanced infrastructure and equipment to receive continuous clinical monitoring and treatment in as safe a way as possible. Three out of every ten patients in an ICU suffer some type of clinical safety issue, which puts their lives at risk. In this context, the main aim of the work I present in this thesis is to develop an AmI environment for improving the efficiency of processes related to patient safety in ICUs. I have written this thesis with the collaboration of the clinical and engineering team of the Smart ICU at the Hospital Cl(n ic in Barcelona (HCB). That AmI environment is equipped mainly with technologies related to the Internet of Things (IoT) that provide an adaptive and dynamic distribution of clinical information based on the role and location of each professional as well as the clinical health status of patients. I divided the development of this thesis into three phases. Firstly, I designed, built, and tested a prototype to simulate the AmI environment in a laboratory setting, considering the main patient safety issues which arise in ICUs. I considered 5 patient safety issues: a code blue, a code red, a code pink, control of nosocomial infections and drug-related errors. Secondly, that prototype was adapted and implemented in a Smart ICU at HCB. Thirdly, I collected and analysed data generated by the AmI. It is important to highlight that part of the data collection and analysis related to the AmI environment took place during the SARS-CoV-2 epidemic (Covid- 19). To summarize, my thesis evaluates the efficiency of the use of new technologies to improve patient safety processes in critical care. It improves clinical and educational standards in terms of patient safety processes at the unit concerned. Moreover, it enables quantification of events related to patient safety as well as heightening awareness of them.
A finales de la década de 1990, cuando las computadoras personales y los dispositivos electrónicos se producían en masa, el concepto de inteligencia en el entorno (AmI – Ambient Intelligence en inglés) surgió. Un entorno que contiene AmI es un espacio con objetos que incluyen tecnologías, invisibles para los usuarios, y que les generan respuestas inteligentes cuando sea necesario. Actualmente, los profesionales sanitarios están trabajando dentro de un sistema complejo adaptativo en el que el entorno clínico y el estado de salud del paciente varían dinámicamente. Esto es especialmente importante en las Unidades de Cuidados Intensivos (UCIs), donde hay pacientes gravemente enfermos que necesitan infraestructuras y equipos avanzados para recibir monitorización de la forma más segura posible. En este contexto, el objetivo principal del trabajo que presento en esta tesis es desarrollar un entorno AmI para mejorar la eficiencia en los procesos relacionados con la seguridad del paciente en las UCIs. He elaborado esta tesis con la colaboración del equipo de la UCI inteligente del Hospital Clínic de Barcelona (HCB). El desarrollo de esta tesis se ha dividido en tres fases. En primer lugar, he diseñado, construido y probado un prototipo para simular el entorno AmI en un escenario de laboratorio considerando los principales problemas de seguridad clínica que ocurren en las UCIs. En segundo lugar, este prototipo ha sido adaptado e implementado en una UCI inteligente del HCB. En tercer lugar, he recogido y analizado los datos generados por el entorno inteligente. En conclusión, mi tesis evalúa la eficiencia del uso de nuevas tecnologías para mejorar los procesos de seguridad clínica en cuidados críticos, mejora los estándares clínicos y educativos sobre los procesos de seguridad del paciente en esta unidad y, finalmente, permite cuantificar los eventos relacionados con la seguridad clínica, así como ganar más conciencia sobre ellos.

The increase in popularity for wearable technologies (see: Apple Watch and Microsoft Band) has opened the door for an Internet of Things solution to healthcare. One of the most prevalent healthcare problems today is the poor survival rate of out-of hospital sudden cardiac arrests (9.5% on 360,000 cases in the USA in 2013). It has been proven that heart rate derived features can give an early indicator of sudden cardiac arrest, and that providing an early warning has the potential to save many lives. Many of these new wearable devices are capable of providing this warning through their heart rate sensors. This thesis paper introduces a prospective dataset of physical activity heart rates collected via Microsoft Band. This dataset is indicative of the heart rates that would be observed in the proposed Internet of Things solution. This dataset is combined with public heart rate datasets to provide a dataset larger than many of the ones used in related works and more indicative of out-of-hospital heart rates. This paper introduces the use of LogitBoost as a classifier for sudden cardiac arrest prediction. Using this technique, a five minute warning of sudden cardiac arrest is provided with 96.36% accuracy and F-score of 0.9375. These results are better than existing solutions that only include in-hospital data.

Internet of things (IoT) generates massive amount of heterogeneous data, which should be efficiently utilized to support services in different domains. Specifically, data need to be supplied to services by understanding the needs of services and by understanding the environment changes, so that necessary data can be provided efficiently but without overfeeding. However, it is still very difficult for IoT to fulfill such data supply with only the existing supports of communication, network, and infrastructure; while the most essential issues are still unaddressed, namely the heterogeneity issue, the recourse coordination issue, and the environments’ dynamicity issue. Thus, this necessitates to specifically study on those issues and to propose a method to utilize the massive amount of heterogeneous data to support services in different domains. This dissertation presents a novel method, called the data-centric network of things (DNT), which handles heterogeneity, coordinates resources, and understands the changing IoT entity relations in dynamic environments to supply data in support of services. As results, various services based on IoT (e.g., smart cities, smart transport, smart healthcare, smart homes, etc.) are supported by receiving enough necessary data without overfeeding. The contributions of the DNT to IoT and big data research are: firstly the DNT enables IoT to perceive data, resources, and the relations among IoT entities in dynamic environments. This perceptibility enhances IoT to handle the heterogeneity in different levels. Secondly, the DNT coordinates IoT edge resources to process and disseminate data based on the perceived results. This releases the big data pressure caused by centralized analytics to certain degrees. Thirdly, the DNT manages entity relations for data supply by handling the environment dynamicity. Finally, the DNT supply necessary data to satisfy different service needs, by avoiding either data-hungry or data-overfed status.

Logic Programming as a Service (LPaaS) è un paradigma per supportare intelligenza situata e distribuita nei sistemi dell’Internet of Things. Il modello di riferimento mira ad abilitare comportamenti intelligenti nei sistemi distribuiti tenendo in particolare considerazione la definizione spazio-temporale dell’ambiente in cui gli oggetti sono immersi. Dal punto di vista architetturale e tecnologico LPaaS è progettato come servizio, coerentemente alle Service-Oriented-Architecture (SOA) che rappresentano oggi giorno uno standard nei sistemi distribuiti. In quest’ottica, LPaaS fornisce una vista astratta di un motore inferenziale situato, rappresentato come servizio. E' così possibile eseguire ragionamenti correlati al contesto ed all'ambiente in cui gli oggetti si trovano immersi, abilitando la coordinazione e la cooperazione tra le diverse entità del sistema. Partendo dallo studio e dall’analisi di questo paradigma, la tesi si pone come obiettivo di fornire una prima realizzazione (seppur prototipale) del servizio, sfruttando a livello tecnologico un motore Prolog e i Web Services. A tal fine il motore Prolog viene incapsulato all’interno di un Web Service e reso fruibile nel sistema pervasivo. Il prototipo viene infine messo alla prova in uno scenario applicativo, realizzando uno Smart Bathroom in grado di monitorare le funzioni fisiologiche degli utenti, con l'obiettivo di avvertirli proattivamente su eventuali patologie riscontrate.

The heavy duty vehicle industry has today no requirement to providea tire pressure monitoring system by law. This has created issues sur-rounding unknown tire pressure and thread depth during active service.There is also no standardization for these kind of systems which meansthat different manufacturers and third party solutions work after theirown principles and it can be hard to know what works for a given vehicletype. National Highway Traffic Safety Administration (NHTSA) put out a new study that determined that underinflated tires of 25% or less are 3 times more likely to be involved in a crash related to tire issues versus vehicles with properly inflated tires. The objective for this thesis is to create an indirect tire monitoring system that can generalize a method that detect both incorrect tire pressure and thread depth for different type of vehicles within a fleet without the need for additional physical sensors or vehicle specific parameters. Drivec Bridge hardware interprets existing sensors from the vehicle. By using supervised machine learning a classifier was created for each axle where the main focus was the front axle which had the most issues.The classifier will classify the vehicles tires condition. The classifier will be implemented in Drivecs cloud service and use data to classify  the tires condition. The resulting classifier of the project is a random forest implemented in Python. The result from the front axle with a dataset consisting of 9767 samples of buses with correct tire condition and 1909 samples of buses with incorrect tire condition it has an accuracy of90.54% (±0.96%). The data sets are created from 34 unique measurements from buses between January and May 2017. The developed solution is called Indirect Tire Monitoring System (ITMS) and is seen as a process. The project group has verified with high accuracy that a vehicle has been classified as bad and then been reclassified as good over a time span of 16 days. At the first day offboard measurements were performed and it showed that the tires of the front axle were underinflated. The classifier indicated that the vehicle had bad classifications until day 14. At this day an offboard measurement was performed and it was concluded that they were no longer underinflated and the classifier indicated this as well. To verify the result the workshop was contacted and verified that the vehicle had changed tires of the front axle at day 14. This has verified that the classifier is able to detect change and stay consistent in the results over a longer time period.

I dagens samhälle går den tekniska utvecklingen fort framåt. Artificiell intelligens och Internet of Things är två tekniker inom utvecklingen vars popularitet har ökat på senare tid. Dessa tekniker i integration har visat sig kunna bidra med stora verksamhetsnyttor, bland annat i form av ökad precishet vad gäller analyser, bättre kundvärde och effektivisering av ”downtime”. Med ny teknik kommer även utmaningar. I takt med att teknologierna ständigt växer uppstår frågor kring säkerhet och etik och hur detta ska hanteras. Målet med denna studien var att ta reda på hur experter värderar etiska frågor när artificiell intelligens används i kombination med Internet of Things-enheter. Vi fokuserade på följande forskningsfråga för att nå vårt mål: Hur värderas frågor om etik när artificiell intelligens används i kombination med Internet of Things? Resultatet vi kom fram till visar att både forskare och näringslivet värderar de etiska aspekterna högt. Studien visar även att de ansåg att teknikerna kan vara lösningen till många samhällsproblem men att etiken bör vara ett ämne som löpande bör diskuteras.
In today's society, technological developments are moving fast. Artificial intelligence and the Internet of Things are two technologies within the development whose popularity has increased in recent years. These technologies in integration have proven to be able to contribute with major business benefits, including in the form of increased precision with regard to analyzes, better customer value and efficiency of downtime. New technology also presents challenges. As the technologies are constantly growing, issues arise regarding safety and ethics and how this should be managed. The aim of this study is to find out how experts value ethical issues when using artificial intelligence in combination with the Internet of Things devices. We focused on the following research question to reach our goal: How are ethical issues evaluated when using artificial intelligence in combination with the Internet of Things? The result we found shows that both researchers and the business world value the ethical aspects highly. The study also shows that they considered the techniques to be the solution to many societal problems, but that ethics should be a topic that should be discussed on an ongoing basis.

Internet of Things (IoT) is a promising technology with great potential for individuals, society, governments, and the economy. IoT is expected to become ubiquitous and influence every aspect of everyday experience. Thus, IoT represents an important phenomena for both organizational and behavioral information system (IS) researchers. This dissertation seeks to contribute to IS research by studying the aspects that influence IoT adoption and use at both consumer and organizational levels. This dissertation achieves this purpose in a series of three essays. The first essay focuses on IoT acceptance in the context of smart home. The second essay focuses on examining the effect of artificial intelligence (AI) capabilities on consumers' IoT perceptions and intentions. Finally, the third essay focuses on the organizational investment and adoption of IoT technologies.

Cette thèse s’inscrit dans le domaine des maisons intelligentes, plus précisément dans l’optimisation énergétique et l’utilisation d’un système de récupération et stockage de l’énergie ambiante. L’objectif est de proposer, après collecte d’un ensemble d’informations pertinentes (courant, puissance active et réactive, température, etc.), des services liés à la gestion de la consommation électrique domestique et favorisant l’autoconsommation. Dans cette thèse, la collecte des données a tout d’abord été basée sur une approche intrusive. A défaut de pouvoir construire notre propre base de données, nous avons utilisé une base de données disponible en ligne. Différents algorithmes d’apprentissage supervisés ont été évalués à partir de ces données afin de reconnaître un appareil électrique. Nos résultats ont montré que les puissances active et réactive seules suffisent à identifier de manière précise un appareil électrique. Afin d’améliorer l’identification des différents appareils, une technique basée sur une moyenne glissante a été utilisée pour le pré-traitement des données. Dans cette thèse, une approche non-intrusive consistant à mesurer la consommation électrique d’une habitation de manière globale, a finalement été privilégiée. A partir de cette mesure globale, des prédictions de l’énergie globale consommée à partir d’algorithmes d’apprentissage automatique (LSTM) a été proposée. L’algorithme LSTM (Long Short-Term Memory) a également été utilisé afin de prédire la puissance récupérée par des cellules photovoltaïques, ceci pour différents profils d’ensoleillement. Ces prédictions de l’énergie consommée et récupérée sont finalement exploitées par un algorithme de gestion de l’énergie favorisant l’autoconsommation
This PhD thesis is in the field of smart homes, and more specifically in the energy consumption optimization process for a home having an ambient energy source harvesting and storage system. The objective is to propose services to handle the household energy consumption and to promote self-consumption. To do so, relevant data must be first collected (current, active and reactive power consumption, temperature and so on). In this PhD, data have been first sensed using an intrusive load approach. Despite our efforts to build our own data base, we decided to use an online available dataset for the rest of this study. Different supervised machine learning algorithms have been evaluated from this dataset to identify home appliances with accuracy. Obtained results showed that only active and reactive power can be used for that purpose. To further optimize the accuracy, we proposed to use a moving average function for reducing the random variations in the observations. A non-intrusive load approach has been finally adopted to rather determine the global household active energy consumption. Using an online existing dataset, a machine learning algorithm based on Long Short-Term Memory (LSTM) has then been proposed to predict, over different time scale, the global household consumed energy. Long Short-Term Memory was also used to predict, for different weather profiles, the power that can be harvested from solar cells. Those predictions of consumed and harvested energy have been finally exploited by a Home Energy Management policy optimizing self-consumption. Simulation results show that the size of the solar cells as well as the battery impacts the self-consumption rate and must be therefore meticulously chosen

I en värld driven av kontinuerliga framsteg inom teknologisektorn, i samband med ökad konkurrens, har detaljhandelslandskapet genomgått en förändring där kundernas förväntningar har förändrats drastiskt. Introduktionen av internet, ”smartphones” och sociala plattformar har resulterat till oöverträffade nivåer av tillgång till enkel kommunikation mellan individer, samt till geografiskt avlägsna klädbutiker som inte tidigare var möjliga att shoppa ifrån. Den här utvecklingen har lett till att kunderna förväntar sig mer från företag och nöjer sig därför inte längre med ”one-size-fits-all” upplevelse, utan förväntar sig istället en upplevelse som är präglad av individuell anpassning. Då kunder idag har tillgång till många olika alternativ att köpa kläder ifrån så behöver dagens klädbutiker förändra sitt värdeerbjudande. Teknik och personifiering av shoppingupplevelsen är därför två viktiga komponenter som klädbutiker behöver investera i för att kunna leva upp till de krav som framtidens kund kommer att ställa. Med detta i åtanke har följande syfte formulerats: "Syftet med uppsatsen är att undersöka vilka nya tekniker som kan implementeras i framtida klädbutiker för att förbättra kundupplevelsen och därmed möta de framtida kundernas behov." Baserat på de resultat och analyser som genomfördes under studiens gång, så bör dagens klädbutiker fokusera på följande tekniker för att kunna tillgodose de krav som framtidens kund kommer att ställa: RFID-taggar, digitala speglar, online avatarer, artificiell intelligens, biometritekniker, förstärkt verklighet och maskininlärning.
In a volatile business world, continuous advancements within the technology sector along with increased competition has led the retailing landscape to go through a transformation of late and have subsequently led customers to view retail stores in a different light. The rise of internet, smartphones, and social networking platforms has led to unprecedented levels of customer connection and empowerment. This development has led the customers to expect more from companies and no longer settle for a “one-size-fits-all” service experience, but instead expects individualized customization. As customers are undoubtedly in power and desires a personalized experience, technology and personalization are therefore two key components that retailers need to invest in to solidify a competitive edge in the imminent future.  “The purpose of the thesis is to investigate what emerging technologies could be implemented in future apparel retail stores to enhance the customer experience and address the needs of the future customer.” Based on the results and analysis derived from the study, findings suggest that companies should focus on the following technologies to have the means to meet the needs of the future customer, with the intention to enhance the overall customer experience: RFID tags, digital mirrors, online avatars, artificial intelligence, biometrics, augmented reality, and machine learning.

Cette thèse traite du sujet de l’intelligence ambiante, fusion entre l’intelligence artificielle et l’internet des objets. L’objectif de ce travail est d’extraire des règles de prédiction à partir des données fournies par les objets connectés dans un environnement, afin de proposer aux utilisateurs des automatisations. Notre principale motivation repose sur la confidentialité, les interactions entre utilisateurs et l’explicabilité du fonctionnement du système. Dans ce contexte, plusieurs contributions ont été apportées. La première est une architecture d’intelligence ambiante qui fonctionne localement et traite les données provenant d’un seul environnement connecté. La seconde est un processus de discrétisation sans a priori sur les données d’entrée, permettant de prendre en compte les différentes données provenant de divers objets. La troisième est un nouvel algorithme de recherche de règles sur une série temporelle, qui évite les limitations des algorithmes de l’état de l’art. L’approche a été validée par des tests sur deux bases de données réelles. Enfin, les perspectives de développement du système sont présentées
This thesis deals with the subject of Ambient Intelligence, the fusion between Artificial Intelligence and the Internet of Things. The goal of this work is to extract prediction rules from the data provided by connected objects in an environment, in order to propose automation to users. Our main concern relies on privacy, user interactions, and the explainability of the system’s operation. In this context, several contributions were made. The first is an ambient intelligence architecture that operates locally, and processes data from a single connected environment. The second is a discretization process without a priori on the input data, allowing to take into account different kinds of data from various objects. The third is a new algorithm for searching rules over a time series, which avoids the limitations of stateoftheart algorithms. The approach was validated by tests on two real databases. Finally, prospects for future developments in the system are presented

Technology of artificial intelligence will soon be able to help ensure the safety of your family, protecting it from the threat of international and domestic burglaries. In the USA the Department of Security also implements special software in its monitoring system, which scans phone calls and other messages. These programs can rapidly process large volumes of data and are even able to distinguish between a normal conversation from a potential threat. The old security system simply relied on sensors that reacted to a movement. Modern systems are directly related to artificial intelligence, which helps detect the presence of a stranger in the house. When you are citing the document, use the following link http://essuir.sumdu.edu.ua/handle/123456789/33830

This project is born merging my personal interest in IoT and AI fields and the collaboration with WiLab, Bi-rex and EBWorld. By joining different skills, the final result is the realization of an end-to-end Industrial IoT application. This IIoT use-case focuses on monitoring accelerations that characterize a turntable, on which mechanical parts are processed. The purpose of the monitoring is to implement predictive maintenance to report potential malfunctions. The turntable in question belongs to DMG Mori, a five-axis turning and milling machine for subtractive manufacturing, machine located at Bi-Rex. Bi-rex is a national competence center introduced by the Ministry of the Economic Development, focused on Big Data and Industry 4.0. It is a public-private consortium aimed to deal with digital transformation and technological innovation, based in Bologna. The technology applied for monitoring is LoRa at 2.4 GHz and the network implemented is a tree topology system of WiLab property, called IMMUNeT (Industrial Machine Monitoring Unplugged Network). Beginning from the adaptation of the accelerometer firmware, moving to the dispatching of extracted data to the server, developing machine learning techniques aimed at predictive maintenance, I lastly exhibit the operating state through the Node-RED dashboard. The resulting data describes if it is required to take actions on the machine or to stop it, in order to avoid a dangerous situation or crack the machinery. This critical information is shown graphically on a 3D interactive map to ensure a more user-friendly interface.

Den här uppsatsen har som syfte att undersöka huruvida det är möjligt att ta fram riktlinjer för vad privata verksamheter behöver ta i beaktande inför en planerad implementering av artificiell intelligens. Studien kommer belysa faktorer som hjälper företag att förstå vad som krävs inför en sådan omställning, men även de hinder som måste övervinnas för att lyckas. Studiens datainsamling har genomförts med två metoder, först en litteraturstudie sedan kvalitativa, semistrukturerade forskningsintervjuer. Dessa har sedan analyserats med vars en analysmetod som kompletterar varandra och därefter tolkats för att se mönster som kan besvara studiens frågeställning: Vad måste svenska organisationer inom den privata sektorn beakta för att lyckas implementera Artificiell intelligens i sin verksamhet? Resultatet har tagits fram genom att jämföra vetenskapliga texter och intervjuer, för att undersöka om den akademiska och praktiska synen skiljer sig åt. Studien resulterade i åtta faktorer som företag borde ta i beaktning inför en implementering av artificiell intelligens. Författarna hoppas att med den här studien kunna främja svensk utveckling inom artificiell intelligens och på så vis generera ett större nationellt mervärde och en starkare konkurrenskraft internationell.
The purpose of this paper is to investigate the possibilities to develop guidelines for businesses to take into account before an implementation of artificial intelligence. The study will highlight different factors that will help companies to understand what is required to make this kind of digital transition, it will also highlight the obstacles companies have to overcome in order to succeed. The data collection was conducted in two parts, first a literature study and then qualitative, semi-structured interviews. These were analyzed with their own analysis which supplement each other, and interpreted to identify patterns that could answer the study's main question: What must Swedish organizations in the private sector consider in order to successfully implement Artificial Intelligence in their operations?The result of the study has been produced by comparing scientific texts and interviews, to investigate whether the academic and practical views differ. The study resulted in eight factors that companies should consider before implementing artificial intelligence. The authors hope that the study will promote Swedish development in artificial intelligence and thus generate a greater national value and international competitiveness.

En gymnasielärare i teknik i den svenska skolan påverkar och påverkas av samhället utanför skolans väggar. Samhällets digitalisering kan påverka tekniklärarens relativt stora möjligheter att välja det tekniska innehållet i kurserna, i olika grad. För att vara konkurrenskraftig i samhället behöver framtida tekniker ha goda kunskaper om de just för stunden aktuella teknikområdena och tidigare studier har visat att skolans resultat i hög grad beror av vilka kunskaper läraren har. I den här studien undersöktes tre tekniklärare på olika gymnasieskolor i Sverige, med avseende på synen på deras kunskaper i att undervisa om artificiell intelligens (AI), sakernas internet (Internet of Things - IoT) och robotteknik. Vidare studerades vilka undervisningsmetoder de avsåg att använda, samt vilka begränsande ramar de kunde se i detta uppdrag. Via enkät och intervjuer samlades data om frågeställningarna in. Rådata transkriberades och analyserades med utgångspunkt i Shulmans teori om Pedagogical Content Knowledge (PCK – ibland kallat ämnesdidaktisk kunskap på svenska) och även med stöd av ramfaktorteori och läroplansteori. Resultatet visar att de deltagande lärarna har behov av kompetenshöjning inom dessa tre teknikområden, samt att valet av undervisningsmetoder är beroende av de ramar som bland annat i form av tid och ekonomi påverkar undervisningen. Resultatet skiljer sig inte från liknande tidigare studier genomförda på lärare i grundskolan.
A technology teacher in the Swedish upper secondary school acts and is influenced by society outside the school walls. The digitalisation of society more or less influences how the technology teacher will choose the ways of implementing the curriculum, with respect to the technicalcontent of the courses. To be competitive in society, future technicians must have goodknowledge of the current technical areas, and previous studies have shown that the school's results largely depend on what knowledge the teacher has. In this study, three technology teachers at various upper secondary schools in Sweden were examined, regarding their view of their knowledge in teaching about artificial intelligence (AI), the Internet of Things (IoT) and robotics. The study also investigated their intended teaching methods and the framing factors they perceived when trying to perform this task. Through a survey and interviews, data on the issues were collected. Raw data were transcribed and analysed based on the theory of Pedagogical Content Knowledge (PCK), by Shulman and with the support of frame factor theory and curriculum theory. The results show that the participating teachers need more competence in these three technology areas, and that the choice of teaching methods depends on the resources provided, for instance in the form of time and finances. The results do not differ from similar previous studies conducted on primary school teachers.

Forskning visar att det är vanligt med hjärtstopp utanför sjukhusen och att de oftast har en dödlig utgång om de inte får vård snarast. Många hjärtstopp sker i privata miljöer där det inte finns någon hjärtstartare, en familjemedlem eller utomstående som kan hjälpa till. Syftet med denna studie är att ta reda på hur ett distansövervakningssystem med ett användargränssnitt via en app kan utformas för att realtidsdiagnostisera hjärt-och kärlsjuka patienter utanför sjukhuset och påskynda utryckning vid hjärtstillestånd. Studien har utgått ifrån konceptdriven designforskning med en kvalitativ ansats och intervjuer med både öppna och stängda frågor. Individerna som har intervjuats är kardiologer som jobbar på den kardiologiska avdelningen på Länssjukhuset Ryhov i Jönköping. Den valda metoden har kombinerats med en litteratursökning inom sjukvårdsteknik och UX/UI-design. Studien resulterar i ett förslag på ett användargränssnitt, via en app, som erbjuder hälsoöversikt och realtidsdiagnostisering. Med hjälp av denna statistik kan algoritmer meddela användaren i appen om deras värden är normala eller onormala. Algoritmerna kan också varna användaren via notiser vid allvarliga hälsoförändringar när användaren behöver akut vård. Appen erbjuder också platslokalisering och att SOS-alarm kan direktlarmas vid de allvarliga hälsoförändringarna. Utryckning kan då påskyndas genom att SOS-alarm skickar en ambulans till platsen som patienten befinner sig på omgående.
Research shows that cardiac arrest is common outside hospitals and that they usually have a fatal outcome if they do not receive care as soon as possible. Many cardiac arrests occur in private settings where there is no pacemaker, family member or outsider who can help. The purpose of this study is to find out how a remote monitoring system with a user interface through an app can be designed to real-time diagnose patients with cardiovascular disease outside the hospital and accelerate emergency response. The study has been based on concept-driven design research with a qualitative approach and interviews with both open and closed questions. The individuals who have been interviewed are cardiologists who work in the cardiology department at Ryhov County Hospital in Jönköping. The chosen method has been combined with a literature search in healthcare technology and UX / UI design. The study results in a proposal for a user interface, through an app, which offers health overview and real-time diagnosis. Using these statistics, algorithms can notify the user in the app if their values are normal or abnormal. The algorithms can also warn the user through notifications in the event of serious health changes when the user needs urgent care. The app also offers site location and that SOS-alarm can be alerted directly in the event of serious health changes. Emergency response can then be accelerated by SOS-alarm sending an ambulance to the place where the patient is located immediately.

This MPhil thesis provides a macroscopic overview of existing smart home research to generate an understanding of its evolution, existing practices, emerging trends, and adoption matters in the context of 'shifting to smart living'. It may assist practitioners, researchers, policymakers and planners to recognise the potential of smart homes in shaping future living, cities, and societies, and help to address the potential influences and challenges that may be posed by this innovation.

This paper addresses the question of whether Artificial Intelligence can have intentionality. This question is part of a larger discussion of whether or not Artificial Intelligence can ever be 'conscious'. Ultimately, I come to the conclusion that while we can see how intentionality can be transferred, it has yet to be shown that intentionality can be created within Artificial Intelligence. To begin, I define intentionality. I then discuss the Turing Test (Alan Turing, "Computing Machinery and Intelligence" and the Chinese Room (John R. Searle, "Minds, Brains, and Programs"). I conclude by expressing my own opinions and where I believe Artificial Intelligence will be in the near future.

The work deals with artificial intelligence as one of the most exciting field in robotics. AI has penetrated almost every industry, from construction, transport and manufacturing to business intelligence, education and healthcare.
Робота стосується штучного інтелекту як однієї з найбільш захоплюючих галузей робототехніки. Штучний інтелект проник майже в усі галузі, від будівництва, транспорту та виробництва до бізнес-розвідки, освіти та охорони здоров'я.
Работа посвящена искусственному интеллекту как одной из самых захватывающих областей робототехники. Искусственный интеллект проник почти во все отрасли, от строительства, транспорта и производства до бизнес-аналитики, образования и здравоохранения.

Healthcare systems play a critical role in ensuring people's health. Establishing accurate diagnoses is a vital element of this process. As sources highlight misdiagnoses and missed diagnoses as a common issue, a solution must be sought. Diagnostic errors are common in the emergency departments, which has been recognized as a stressful work environment. Today's industries are forced to deal with rapidly changing technological advances that result in reshaped systems, products, and services. Artificial Intelligence (AI) is one of such technologies that can work as a solution to diagnosis issues but comes with technical, ethical and legal challenges. Hence, the thesis intends to investigate how AI can affect the accuracy of diagnosis as well as how its integration in healthcare relates to the technical, ethical and legal aspects. The thesis begins with a literature review, which serves as a theoretical foundation and allows for a conceptual framework to be formed. The conceptual framework is used to select interviewees, which results in 12 interviews with professors, researchers, doctors and politicians. In addition, a survey is conducted to obtain the general public’s opinion on the matter. The findings present that AI is already mature enough to make more accurate diagnoses than doctors as well as release burden from medical practitioners in the form of administrative tasks. One obstacle is the incomplete data available since laws hinder sharing of patient data. Furthermore, the AI algorithms must be fit for all social minorities and not demonstrate racial discrimination. The European AI Alliance was established in 2018 with the aim to keep the technology in check. Similar initiatives can be created on a national- and regional level to maintain some form of control over its proper use.
Sjukvårdssystem utgör en avgörande roll för att säkerställa människors välmående och hälsa. Att fastställa korrekta diagnoser är en viktig del av denna process. Enligt källor är feldiagnoser och uteblivna diagnoser ett vanligt problem och bör därför lösas. Diagnostiska fel är vanligt förekommande på akutmottagningar, vilka karaktäriseras som en stressig arbetsmiljö. Dagens industrier tvingas hantera snabbt föränderliga tekniska framsteg som resulterar i omformade system, produkter och tjänster. Artificiell Intelligens (AI) är en av sådana tekniker som kan fungera som en lösning på diagnosfrågor. Dock kommer den med tekniska, etiska och legala utmaningar. Examensarbetet avser därför att undersöka hur AI kan påverka diagnosens precision samt hur integrationen i vården relaterar till de tekniska, etiska och legala aspekterna. Rapporten inleds med en litteraturstudie, vilket fungerar som en teoretisk grund och bidrar till att skapa ett konceptuellt ramverk. Det konceptuella ramverket används för att välja intervjupersoner, vilket resulterar i 12 intervjuer med professorer, forskare, läkare och politiker. Dessutom genomförs en enkätundersökning för att få allmänhetens åsikt i frågan. Rapportens resultat visar att AI redan är tillräckligt utvecklad för att göra en mer precisionssäker diagnos än en läkare samt kan avlasta läkare i form av administrativa uppgifter. Ett hinder är att den data som finns tillgänglig är ofullständig på grund av lagar som hindrar delning av patientdata. AI-algoritmerna måste dessutom vara lämpliga för alla sociala minoriteter och inte leda till rasdiskriminering. European AI Alliance grundades 2018 med målet att hålla tekniken i schack i förhållande till de etiska och legala aspekterna. Liknande initiativ kan skapas på nationell och regional nivå för att bibehålla någon form av kontroll över dess korrekta användning.

In this thesis we proposed new neural architectures and information theory approaches. By means of wavelet analysis, neural networks, and the results of our own creations, namely the wavelet recurrent neural networks and the radial basis probabilistic neural networks,we tried to better understand, model and cope with the human behavior itself. The first idea was to model the workers of a crowdsourcing project as nodes on a cloud-computing system, we also hope to have exceeded the limits of such a definition. We hope to have opened a door on new possibilities to model the behavior of socially interconnected groups of people cooperating for the execution of a common task. We showed how it is possible to use the Wavelet Recurrent Neural Networks to model a quite complex thing such as the availability of resources on an online service or a computational cloud, then we showed that, similarly, the availability of crowd workers can be modeled, as well as the execution time of tasks performed by crowd workers. Doing that we created a tool to tamper with the timeline, hence allowing us to obtain predictions regarding the status of the crowd in terms of available workers and executed workflows. Moreover, with our inanimate reasoner based on the developed Radial Basis Probabilistic Neural Networks, firstly applied to social networks, then applied to living companies, we also understood how to model and manage cooperative networks in terms of workgroups creation and optimization. We have done that by automatically interpreting worker profiles, then automatically extrapolating and interpreting the relevant information among hundreds of features for each worker in order to create workgroups based on their skills, professional attitudes, experience, etc. Finally, also thanks to the suggestions of prof. Michael Bernstein of the Stanford University, we simply proposed to connect the developed automata. We made use of artificial intelligence to model the availability of human resources, but then we had to use a second level of artificial intelligence in order to model human workgroups and skills, finally we used a third level of artificial intelligence to model workflows executed by the said human resources once organized in groups and levels according to their experiences. In our best intentions, such a three level artificial intelligence could address the limits that, until now, have refrained the crowds from growing up as companies, with a well recognizable pyramidal structure, in order to reward experience, skill and professionalism of their workers. We cannot frankly say whether our work will really contribute or not to the so called "crowdsourcing revolution", but we hope at least to have shedded some light on the agreeable possibilities that are yet to come.

The world is changing rapidly. Developments in information technology are affecting every aspect of people’s lives, but also economies or politics all over the world. The fourth industrial revolution started at the beginning of the twenty-first century, it is manifested by emerging technology breakthroughs in many fields, which include artificial intelligence (AI), biotechnology, 3D printing, the Internet of Things, and blockchain. In the last decade, the technology sector has driven the worldwide economy, and big tech companies such as Amazon, Apple, Microsoft, Tencent, Baidu, and Alibaba are dominating the market. Many other companies are riding the wave, while others are staying behind. AI is impacting many industries, from transportation to agriculture, passing through healthcare, communication, media, retail, entertainment, and others. But one of the major sector involved is finance. This qualitative research focuses on applications of AI, especially in the financial field. The theoretical part aims to introduce the concept of AI, the different types of AI, examples of AI technologies, and countries and companies that are leading the AI race. The second part of the research focuses on AI applications in different sectors, examining the influence, benefits, and challenges of this breakthrough innovation.

In this thesis we proposed new neural architectures and information theory approaches. By means of wavelet analysis, neural networks, and the results of our own creations, namely the wavelet recurrent neural networks and the radial basis probabilistic neural networks,we tried to better understand, model and cope with the human behavior itself. The first idea was to model the workers of a crowdsourcing project as nodes on a cloud-computing system, we also hope to have exceeded the limits of such a definition. We hope to have opened a door on new possibilities to model the behavior of socially interconnected groups of people cooperating for the execution of a common task. We showed how it is possible to use the Wavelet Recurrent Neural Networks to model a quite complex thing such as the availability of resources on an online service or a computational cloud, then we showed that, similarly, the availability of crowd workers can be modeled, as well as the execution time of tasks performed by crowd workers. Doing that we created a tool to tamper with the timeline, hence allowing us to obtain predictions regarding the status of the crowd in terms of available workers and executed workflows. Moreover, with our inanimate reasoner based on the developed Radial Basis Probabilistic Neural Networks, firstly applied to social networks, then applied to living companies, we also understood how to model and manage cooperative networks in terms of workgroups creation and optimization. We have done that by automatically interpreting worker profiles, then automatically extrapolating and interpreting the relevant information among hundreds of features for each worker in order to create workgroups based on their skills, professional attitudes, experience, etc. Finally, also thanks to the suggestions of prof. Michael Bernstein of the Stanford University, we simply proposed to connect the developed automata. We made use of artificial intelligence to model the availability of human resources, but then we had to use a second level of artificial intelligence in order to model human workgroups and skills, finally we used a third level of artificial intelligence to model workflows executed by the said human resources once organized in groups and levels according to their experiences. In our best intentions, such a three level artificial intelligence could address the limits that, until now, have refrained the crowds from growing up as companies, with a well recognizable pyramidal structure, in order to reward experience, skill and professionalism of their workers. We cannot frankly say whether our work will really contribute or not to the so called "crowdsourcing revolution", but we hope at least to have shedded some light on the agreeable possibilities that are yet to come.

Actuellement, dans les domaines du Big Data et de l’IoT, les recherches menées sont restées longtemps concentrées sur des problématiques en amont liées aux protocoles de communication pour la collecte des données, ou en aval pour l’exploitation des données collectés. Peu d’attention a été tourné vers des problématiques pourtant importantes qui se situent justement entre celles en amont et celles en aval telles que le déploiement, la mise en œuvre d’architectures logicielles modulables (au niveau Edge, Fog ou Cloud Computing), le contrôle fin du comportement des IoTs pour une meilleure utilisation du réseau et de l’énergie limitée des dispositifs. Dans le cadre de ce travail, la démarche prend en compte deux problématiques auxquelles nous devons faire face lors de l’implémentation d’une technologie Big Data / IoT. Premièrement, quelle architecture générique pourrions-nous adopter pour mettre en œuvre une plateforme reconfigurable selon les futures fonctionnalités visées pour un client donné ? En d’autres termes, comment mettre en œuvre une plateforme multi micro-services que l’on peut déverrouiller ou créer à la demande pour personnaliser une offre ? Deuxièmement, vers quelles méthodes de modélisation formelles s’orienter pour lever les obstacles rencontrés lors du déploiement de projets opérationnels liés aux IoTs et pour optimiser les performances, notamment énergétiques, étant donné que l’on peut les considérer comme des systèmes dynamiques à événements discrets ? Pour répondre à la première problématique, une plateforme logicielle modulable et configurable d’analyse de données Big Data a été développée constituée de fonctions nécessaires : (a) à l’acquisition des données IoT mais également d’informations provenant d’autres sources et protocoles, (b) au contrôle et traitement nécessaire à leur exploitation, et (c) au stockage des données massives. Un service Data Science, intégrant une approche IA, attaché à la plateforme nécessaire, (d) à l’extraction de connaissance et (e) à la prévision pour le diagnostic et l’aide à la décision a été développée. De plus, la plateforme se doit être modulable (i.e., possibilité d’ajouter ou de retirer des micro-services à la demande) et configurable (i.e., possibilité de personnaliser le paramétrage de la plateforme selon les besoins et les règles métier de chaque client). Pour répondre à la deuxième problématique, nous avons développé des approches algébriques basées sur l’algèbre Max Plus, pour répondre à des problèmes réels rencontrés dans des projets opérationnels liés aux objets connectés. Ceci a permis la mise en œuvre de solutions permettant en particulier de rendre plus efficients le déploiement et la gestion de l’énergie des IoTs. Ce travail a été effectué en s’appuyant sur une approche de modélisation analytique, pour l’établissement de critères de contrôle et d’évaluation des performances des solutions
Currently, in the fields of Big Data and IoT, the research carried out has for a long time remained focused on upstream issues related to communication protocols for data collection, or downstream issues related to the exploitation of collected data. Few attention has been paid to important issues that lie precisely between those upstream and those downstream problems, such as deployment, modular software architectures implementation (at Edge, Fog or Cloud Computing level), fine control of IoTs behaviors for a better use of the network bandwidth and the limited energy of devices. In the context of this work, the following questions that one has to deal with to implement Big Data / IoT technology solutions are considered. Firstly, what generic architecture could we adopt to implement a reconfigurable platform according to expected functionalities for a client? In other words, how can we implement a multi-micro-services platform that could be unlocked or created on demand to customize an offer? Secondly, which formal modelling method should be used to overcome encountered obstacles when deploying IoT operational projects to optimize performance, considering that an IoT based systems can be viewed as discrete-event dynamic systems? To address the first issue, a modular and configurable Big Data analysis platform has been developed with essential functions: (a) data acquisition from IoT devices but also information gathered from other sources and protocols, (b) control and processing components for their exploitation, and (c) massive data storage. A Data Science service has been developed, integrating AI approaches, (d) for knowledge discovery and (e) forecasting for diagnosis and decision support. In addition, the platform must be modular (i.e. the possibility of adding or removing micro-services on demand) and configurable (i.e. the possibility to customize the platform's parameters according to the needs and business rules of each user). To address the second issue, an approach based on Max Plus algebra is developed, to tackle real problems encountered in IoT operational projects. This has enabled the implementation of solutions that make the deployment and energy management of IoTs more efficient. This work has been carried out using an analytical modelling approach to establish criteria for monitoring and assessing the performance of the solutions

Acquiring new knowledge often requires an agent or a system to explore, search and discover. Yet us humans build upon the knowledge of our forefathers, as did they, using previous knowledge; there does exist a mechanism which allows transference of knowledge without searching, exploration or discovery. That mechanism is known as imitation and it exists everywhere in nature; in animals, insects, primates, and humans. Enabling artificial, cognitive and software agents to learn by imitation could potentially be crucial to the emergence of the field of autonomous systems, robotics, cyber-physical and software agents. Imitation in AI implies that agents can learn from their human users, other AI agents, through observation or using physical interaction in robotics, and therefore learn a lot faster and easier. Describing an imitation learning framework in AI which uses the Internet as the source of knowledge requires a rather unconventional approach: the procedure is a temporal-sequential process which uses reinforcement based on behaviouristic Psychology, deep learning and a plethora of other Algorithms. Ergo an agent using a hybrid simulating-emulating strategy is formulated, implemented and experimented with. That agent learns from RSS feeds using examples provided by the user; it adheres to previous research work and theoretical foundations and demonstrates that not only is imitation learning in AI possible, but it compares and in some cases outperforms traditional approaches.

There are any number of vaguely plausible reasons why Friendly AI might be humanly impossible, and it is still more likely that the problem is. But one should not so quickly write of the challenge, especially considering the stakes. When you are citing the document, use the following link http://essuir.sumdu.edu.ua/handle/123456789/16063

Astronomy is the ultimate observational science. Objects outside our solar system are beyond our reach, so we are limited to acquiring knowledge at a distance. This motivates the need to advance astrophysical imaging technologies, particularly for the field of high contrast imaging, where some of the most highly prized science goals require high fidelity imagery of exoplanets and of the circumstellar structures associated with stellar and planetary birth. Such technical capabilities address questions of both the birth and death of stars which in turn informs the grand recycling of matter in the chemical evolution of the galaxy and universe itself. Ground-based astronomical observation primarily relies on extreme adaptive optics systems in order to extract signals arising from faint structures within the immediate vicinity of luminous host stars. These systems are distinguished from standard adaptive optics systems in performing faster and more precise wavefront correction which leads to better imaging performance. The overall theme of this thesis therefore ties together advanced topics in artificial intelligence with techniques and technologies required for the field of high contrast imaging. This is accomplished with demonstrations of deep learning methods used to improve the performance of extreme adaptive optics systems and is deployed and benchmarked with data obtained at the Subaru Coronagraphic Extreme Adaptive Optics (SCExAO) system operating at the observatory on the summit of Mauna Kea in Hawaii. Solutions encompass both hardware and software, with optimal recovery of scientific outcomes delivered by model fitting of high contrast imaging data with modern machine learning techniques. This broad-ranging study subjecting acquisition, analysis and modelling of data hopes to yield more accurate and higher fidelity observables which in turn delivers improved interpretation and scientific delivery.