Literatura científica selecionada sobre o tema "User­Driven Classification"

An fuzzy classification rules extraction model for online analytical mining (OLAM) was explained in this article. The efficient integration of the concept of data warehousing, online analytical processing (OLAP) and data mining systems converges to OLAM results in an efficient decision support system. Even after associative classification proved as most efficient classification technique there is a lack of associative classification proposals in field of OLAM. While most of existing data cube models claims their superiority over other the fuzzy multidimensional data cubes proved to be more intuitive in user perspective and effectively manage data imprecision. Considering these factors, in this paper we propose an associative classification model which can perform classification over fuzzy data cubes. Our method aimed to improve accuracy and intuitive ness of classification model using fuzzy concepts and hierarchical relations. We also proposed a generalization-based criterion for ranking associative classification rules to improve classifier accuracy. The model accuracy tested on UCI standard database.

Depression is a severe dispute in wide-ranging personal health for all. Every year millions of populace endures depression and some few of them receive adequate treatment. Through their Face-book postings and statuses, whatsapp statuses and shares of post, expressive words handling during they speak or post, emotional icons or pictures they post or from their browse histories, expressing user interests, feelings and daily routines can be measured. Many researchers proved that usage of User Generated Content in a proper mode helps to decide one’s depression level. Analyzing the Generated user related contents helps in prediction of depression (Marcus, M., et al., 2012. Depression: A Global Public Health Concern. WHO Dataset, pp.6–8). Leveraging Social media like Facebook, Twitter and Instagram has valuable sign for designating depression in persons. In the proposed work, potential use of Facebook to sense and identify main depressive chaos in individual is explored. Sharing or posting of images or text by an individual plays a vital role in identifying the victim with depression. Text based analysis done on posted or shared textual content, whereas Chromatic analysis done on the images along with text based analysis for the images with textual contents. Emotion features and color features of these two analyses are used to identify the depression level of the individual by psychological classification using Support Vector Machine (SVM). The performance of the SVM is compared with Naïve Bayes Classifier. The Findings and methods of the proposed work, presents a road map in developing new methodologies in identifying the major depression levels of those who suffer and to guide healthcare agencies.

Medical health systems have been concentrating on artificial intelligence techniques for speedy diagnosis. However, the recording of health data in a standard form still requires attention so that machine learning can be more accurate and reliable by considering multiple features. The aim of this study is to develop a general framework for recording diagnostic data in an international standard format to facilitate prediction of disease diagnosis based on symptoms using machine learning algorithms. Efforts were made to ensure error-free data entry by developing a user-friendly interface. Furthermore, multiple machine learning algorithms including Decision Tree, Random Forest, Naive Bayes and Neural Network algorithms were used to analyze patient data based on multiple features, including age, illness history and clinical observations. This data was formatted according to structured hierarchies designed by medical experts, whereas diagnosis was made as per the ICD-10 coding developed by the American Academy of Ophthalmology. Furthermore, the system is designed to evolve through self-learning by adding new classifications for both diagnosis and symptoms. The classification results from tree-based methods demonstrated that the proposed framework performs satisfactorily, given a sufficient amount of data. Owing to a structured data arrangement, the random forest and decision tree algorithms’ prediction rate is more than 90% as compared to more complex methods such as neural networks and the naïve Bayes algorithm.

Embedding household appliances with smart capabilities is becoming common practice among major fabric-care producers that seek competitiveness on the market by providing more efficient and easy-to-use products. In Vertical Axis Washing Machines (VA-WM), knowing the laundry composition is fundamental to setting the washing cycle properly with positive impact both on energy/water consumption and on washing performance. An indication of the load typology composition (cotton, silk, etc.) is typically provided by the user through a physical selector that, unfortunately, is often placed by the user on the most general setting due to the discomfort of manually changing configurations. An automated mechanism to determine such key information would thus provide increased user experience, better washing performance, and reduced consumption; for this reason, we present here a data-driven soft sensor that exploits physical measurements already available on board a commercial VA-WM to provide an estimate of the load typology through a machine-learning-based statistical model of the process. The proposed method is able to work in a resource-constrained environment such as the firmware of a VA-WM.

This work explores the characteristics of the usage behaviour of station-based car-sharing users based on the actual operation data from a car-sharing company in Gansu, China. We analyse the characteristics of the users’ demands, such as usage frequency and order quantity, for a day with 24 1 h time intervals. Results show that most car-sharing users are young and middle-aged men with a low reuse rate. The distribution of users’ usage during weekdays shows noticeable morning and evening peaks. We define two attributes, namely, the latent ratio and persistence ratio, as classification indicators to understand the user diversity and heterogeneity thoroughly. We apply the k-means clustering algorithm to group the users into four categories, namely, lost, early loyal, late loyal, and motivated users. The usage characteristics of lost users, including maximum rental time and travel distance, minimum percentage of same pickup and return station, and low percentage of locals, have noticeable differences from those of the other users. Late loyal users have lower rental time and travel distance than those of the other users. This manifestation is in line with the short-term lease of shared cars to complete short- and medium-distance travel design concepts. We also propose a model that predicts the driver cluster based on the decision tree. Numerical tests indicate that the accuracy is 91.61% when the user category is predicted four months in advance using the observation-to-judgment period ratio of 3 : 1. The results in this study can support enterprises in user management.

The energy use behavior analysis method can dig out the user’s energy use behavior rules from the energy use big data, thereby improving the quality of the grid-side management service in the integrated energy system. Firstly, it summarizes the characteristics of the integrated energy system and constructs the integrated energy system service system; secondly, it summarizes the data-driven electricity consumption behavior analysis research model. Then, it elaborates on the collection and aggregation of electricity consumption information, and refined user classification. Next, the comprehensive application of energy consumption behavior analysis in load forecasting, demand response modeling and other typical scenarios is deeply analyzed. Finally, the challenges that may be encountered in further research are clarified and the follow-up work is prospected.

Abstract Sanitation policy and development has undergone a paradigm shift away from supply-driven toward behavioral-based demand-driven approaches. This shift to increase sanitation demand requires multiple stakeholders with varying degrees of interest, knowledge, and capacity. Currently, the design of appropriate sanitation technology disconnects user preference integration from sanitation technology design, resulting in fewer sanitation technologies being adopted and used. This research examines how preferences for specific attributes of appropriate sanitation technologies and implementation arrangements influence their adoption and usage. Data collected included interviews of 1,002 sanitation users living in a peri-urban area of South Africa; the surveyed respondents were asked about their existing sanitation technology, their preferences for various sanitation technology design attributes, as well as their perspectives on current and preferred sanitation implementation arrangements. The data revealed that user acceptability of appropriate sanitation technology is influenced by the adoption classification of the users. Statistically significant motives and barriers to sanitation usage showed a differentiation between users who share private sanitation from those who use communal sanitation facilities. The user acceptability of appropriate sanitation systems is dependent on the technical design attributes of sanitation. The development of utility functions detailed the significance of seven technical design attributes and determined their respective priorities.

Digital documentation of cultural heritage structures is increasingly more common through the application of different imaging techniques. Many works have focused on the application of laser scanning and photogrammetry techniques for the acquisition of threedimensional (3D) geometry detailing cultural heritage sites and structures. With an abundance of these 3D data assets, there must be a digital environment where these data can be visualized and analyzed. Presented here is a feedback driven visualization framework that seamlessly enables interactive exploration and manipulation of massive point cloud data. The focus of this work is on the classification of different building materials with the goal of building more accurate as-built information models of historical structures. User defined functions have been tested within the interactive point cloud visualization framework to evaluate automated and semi-automated classification of 3D point data. These functions include decisions based on observed color, laser intensity, normal vector or local surface geometry. Multiple case studies are presented here to demonstrate the flexibility and utility of the presented point cloud visualization framework to achieve classification objectives.

Diese Diplomarbeit behandelt das Themengebiet der automatischen Erzeugung von grafischen Benutzeroberflächen (GUIs) im Kontext von Webservices. Es geht dabei konkret um einen Editor, mit dem Hinweise zur Generierung von Dialogen erstellt werden können. Diese Hinweise sollen dann von den dialogerzeugenden Anwendungen einbezogen werden, um eine dynamische Interaktion mit Webservices durch beliebige Nutzer ohne dienstspezifische Software zu ermöglichen. Die Arbeit führt in die aktuellen Techniken zur GUI-Generierung ein und stellt Transformationsprinzipien vor, die eine Generierung ausgehend von einem formalen Datenmodell ermöglichen. Dabei müssen mangelnde Modellparameter in Beschreibungen von Webservices manuell ausgeglichen werden (WSGUI-Konzepte). Diese Zielstellung führt zum Entwurf des WSGUI-Editors. Die anschließende Implementierung berücksichtigt darüber hinaus Integrationsaspekte wie die Publizierung von WSGUI-Hinweisen, Einbindung von GUI-Übersetzungen und eine Vorschau auf die zu generierenden Dialoge. Abgeschlossen wird die Arbeit mit einer Bewertung des Editors, aber auch einer Reihe von Vorschlägen zur Vereinfachung ähnlich gelagerter zukünftiger Projekte im Umfeld von Webservices.

This paper aims to show that controlled hydraulic drives, when properly considered and approached, are a technology that allows for a systematic and safe system design with regard to performance and energy efficiency. Controlled hydraulic drives are predestinated to be an indispensable alternative to electromechanical drives for many fields of application, especially against the background of Industry 4.0. But hydraulic drives will only be able to play this role if they see themselves as a part of mechatronics, speak the language of mechatronics and recognize the increasing importance of electric drives as part of the hydraulic toolbox as a chance.

This work provides an in-depth-view of driver motivational aspects when driver assistance Systems (DAS) are considered. Thereby, the role of driver actual experience with DAS use was also identified and highlighted. A central outcome of this thesis is the STADIUM model describing the interplay of motivational factors that determine the engagement in secondary activities while taking actual DAS use experience into account. The role of motives in showing attentive behaviour depending on DAS (the navigation system) could also be underlined. The relevance, enrichment and need of combining qualitative and quantitative approaches when the effects of safety countermeasures on driver behaviour are investigated could also be shown. The results are discussed in terms of hierarchical driver behaviour models, the theory of planned behaviour and its extended versions and the strengths of the introduced studies and limitations. Implications for traffic safety are provided and future research issues are recommended
Diese Arbeit liefert einen gründlichen Einblick, welche Rolle motivationale Aspekte spielen, wenn Fahrerassistenzsysteme (FAS) genutzt werden. Dabei wurde auch die Funktion der tatsächlichen Erfahrung mit FAS identifiziert und hervorgehoben. Ein zentrales Ergebnis dieser Arbeit ist das STADIUM Modell, welches das Zusammenspiel motivationaler Faktoren in Abhängigkeit von der tatsächlichen Erfahrung mit FAS erklärt, die wiederum bestimmen, inwieweit und ob andere Aktivitäten während des Fahrens ausgeführt werden. Außerdem konnte unterstrichen werden, welche Rolle Motive spielen, aufmerksames Verhalten in Abhängigkeit von der Nutzung von FAS (dem Navigationssystem) zu zeigen. Zusätzlich konnte dargestellt werden, wie relevant, bereichernd und nützlich es ist, qualitative und quantitative Methoden zu kombinieren, wenn die Effekte von FAS auf das FahrerInnenverhalten untersucht werden. Die Ergebnisse werden diskutiert indem auf hierarchische Fahrerverhaltensmodelle, auf die Theorie des geplanten Verhaltens und ihre erweiterten Versionen und auf die Stärken und Schwächen der Studien Bezug genommen wird. Es werden Implikationen dargestellt und zukünftige Forschungsfragen und Problemstellungen empfohlen

To achieve the widespread diffusion of autonomous electric buses (AEBs) and thus harness their environmental potential, a broad acceptance of new technology-based mobility concepts must be fostered. Still, there remains little known about the factors determining their acceptance, especially in the combination of vehicles with alternative fuels and autonomous driving modes, as is the case with AEBs. In this study, we first conducted qualitative research to identify relevant factors influencing individual acceptance of autonomously driven electric buses. We then developed a comprehensive research model that was validated through a survey of 268 passengers of an AEB, operated in regular road traffic in Germany. The results indicate that a mix of individual factors, social impacts, and system characteristics determine an individual’s acceptance of AEBs. Notably, it is important that users perceive AEBs, not only as advantageous, but also trustworthy, enjoyable, and in a positive social light. Our research supplements the existing corpora by demonstrating the importance of individual acceptance and incorporating it to derive policy implications.

In the course of the current demographic change, the proportion of the population aged 65 and older is projected to steadily increase in many countries of the world (UN DESA Population Division, 2015). The ageing society is reflected in an increasing number of older road users (Koppel & Berecki-Gisolf, 2015), especially considering the growing need for older adults to maintain individual mobility (Eby & Molnar, 2012). This development raises new issues of transportation research, since age-related changes in mobility patterns as well as sensory, cognitive, and motor functions reduce older adults’ traffic safety (Polders, Vlahogianni, Leopold, & Durso, 2015). Accordingly, new strategies to aid older drivers and their mobility needs are required, which could potentially be provided by emerging in-vehicle technologies (Karthaus & Falkenstein, 2016). The overall aim of present dissertation project was to evaluate whether in-vehicle technologies that appear promising to support older drivers can actually contribute to their individual mobility, which requires an improvement in aspects related to driving performance as well as the acceptance of such systems in this age group. Therefore, contact-analogue head-up displays (also labelled as Augmented Reality Displays, ARDs) and highly automated driving were selected as two exemplary technologies, representing completely different levels of driving automation and accordingly different approaches to support drivers. The ARD-technology represents a technical implementation approach for IVIS and therefore an example for Automation Level 0 (no automation; SAE International, 2014) by helping the driver to execute the driving task manually through useful information. In contrast, the HAD-technology aims at supporting the driver by taking over the driving task, which corresponds to Automation Level 4 (high automation; SAE International, 2014). Despite these different approaches, both technologies were previously assumed to have a strong potential to support especially older drivers (Meyer & Deix, 2014; Polders et al., 2015; Rusch et al., 2013; Schall et al., 2013). Three empirical studies were conducted to examine performance- and acceptance-related aspects of both technologies. All studies were carried out with a group of older drivers (maximum age range: 65 85 years) and a younger comparison group (maximum age range: 25-45 years) representing the ‘average’ (i.e. young, but experienced) driver in order to identify age-specific results. Focusing on performance-related aspects of the ARD-technology, Study I represents a reaction time experiment conducted in a driving simulator. One age-specific beneficial function of such an ARD is to provide prior information about approaching complex traffic situations, which addresses older drivers’ tendency to process multiple information successively (serially) rather than simultaneously (parallel) (Davidse, Hagenzieker, van Wolffelaar, & Brouwer, 2009; Küting & Krüger, 2002). Therefore, the aim of this study was to examine the effects of an ARD providing prior information about approaching intersections on drivers’ speed and accuracy of perceiving these intersections, which is considered a necessary precondition for a safe driving performance (Crundall & Underwood, 2011). Based on concerns about the counterproductive effects of presenting information via an ARD, especially in cases of inaccurate information, system failures were included in this examination. The ARD-information aided drivers from both age groups in identifying more relevant aspects of the intersections without increasing response time, indicating the potential of the system to support both older and younger drivers in complex traffic situations. Experiencing system failures (i.e. inaccurate information) did offset this positive effect for the study’s duration, particularly for older drivers. This might be because it was difficult to ignore inaccurate prior information due to their presentation via an ARD. Study II represents a driving simulator study on acceptance-related aspects of an ARD providing prior information about approaching intersections. This study focused on the effects of system experience on drivers’ acceptance as well as on the identification of age-specific acceptance barriers that could prevent older drivers from using the technology. In summary, older and younger drivers’ evaluation of the ARD was positive, with a tendency to more positive evaluations with than without system experience in the driving simulator. Compared to the younger group, older drivers reported a more positive attitude towards using the ARD, even though they evaluated their self-efficacy in handling the system and environmental conditions facilitating its usage as less strong. Both performance- and acceptance-related aspects of HAD were addressed in Study III, a two-stage driving simulator study. The focus of the performance perspective shifted in parallel with the shift of the human role from driver to passenger due to the increasing driving automation. Accordingly, the examination of HAD was focused on the human evaluation of the automated system’s driving performance. In this context, affective components of human-automation interaction, such as comfort and enjoyment, are considered important for the acceptance and thus usage of automated vehicles (Tischler & Renner, 2007). It is assumed that the implemented driving style has an impact on such affective components in the context of HAD (Bellem, Schönenberg, Krems, & Schrauf, 2016). One theoretical approach to increase the comfort of HAD recommends the implementation of familiar, natural driving styles to mimic human control (Elbanhawi, Simic, & Jazar, 2015). Therefore, the effects of driving automation and the familiarity of the HAD-style on driving comfort and enjoyment were examined. Automation increased both age groups’ comfort, but decreased younger drivers’ enjoyment. For all dependent variables, driving style familiarity significantly interacted with drivers’ age the same way: while younger drivers preferred a familiar HAD-style, older drivers preferred an unfamiliar driving style in a highly automated context. Accordingly, the familiarity approach can be supported at least for younger drivers, but not for older drivers, whose manual driving styles are characterised by strategies to compensate for age-related impairments of sensory, cognitive, or motor functions. HAD-style preferences of this age group seem to be more influenced by the desire to regain a driving style free from these compensation strategies than by a need for familiar driving manoeuvres. In parallel with the evaluation of the ARD, acceptance-related issues in the context of HAD included the effects of system experience on drivers’ acceptance and potential age-specific acceptance barriers. Considering a system-specific design issue, it was additionally examined whether drivers’ acceptance of HAD is modifiable by the familiarity of the implemented driving style. In this driving simulator study, members of both age groups showed slightly positive a priori acceptance ratings, which significantly increased after the initial experience and remained stable afterwards. Similar to drivers’ acceptance of the ARD, older drivers reported a more positive attitude towards using HAD despite their lower self-assessed self-efficacy and environmental conditions facilitating HAD-usage compared to younger drivers. Regarding HAD-style, acceptance was subject to the same interaction between drivers’ age and driving style familiarity as driving comfort and enjoyment. These findings demonstrate that effective approaches to support the independent mobility of older adults are provided by emerging in-vehicle technologies on different levels of driving automation. The majority of the performance-related improvements did apply to both older and younger drivers, confirming that automotive technologies suggested for older drivers have the potential to support drivers of other age groups as well. Regarding drivers’ acceptance, findings suggest that both systems would be accepted by different age groups, which correspondents to the results from the performance perspective. The comparable acceptance patterns identified for two systems at different stages of driving automation, such as ARDs and HAD, indicate underlying general aspects of older adults’ acceptance of in-vehicle technologies. This includes their strong need to preserve their individual mobility as well as their lower self-efficacy in handling relevant technologies and insufficient access to a support infrastructure. These insights can enrich both theories of older drivers’ acceptance of in-vehicle technologies and measures to ensure the successful development and introduction of systems aiding them in maintaining a safe individual mobility. Considering the importance of driving for older adults’ physiological and psychological well-being (e.g. Adler & Rottunda, 2006; Lutin, Kornhauser, & Lerner-Lam, 2013), these results emphasise the potential of emerging in-vehicle technologies to improve both older drivers’ traffic safety and quality of life
Im Zuge des aktuellen demografischen Wandels wird für zahlreiche Länder der Welt eine stetige Zunahme des Bevölkerungsanteils von Personen im Alter von 65 Jahren und älter prognostiziert (UN DESA Population Division, 2015). Die daraus resultierende alternde Gesellschaft spiegelt sich auch in der steigenden Anzahl älterer Verkehrsteilnehmer wieder (Koppel & Berecki-Gisolf, 2015). Dieser Effekt wird durch das ebenfalls ansteigende Bedürfnis älterer Personen, ihre Individualmobilität auch bis ins hohe Alter hinein aufrecht zu erhalten, noch verstärkt (Eby & Molnar, 2012). Berücksichtigt man die Auswirkungen altersbedingter Veränderungen von Mobilitätsmustern und fahrrelevanten Fähigkeiten auf die Sicherheit älterer Verkehrsteilnehmer (Polders et al., 2015), stellt diese demographische Entwicklung neue Herausforderungen an die Verkehrsforschung. So bedarf es neuartiger Strategien zur Unterstützung älterer Fahrzeugführer und ihrer Mobilitätsbedürfnisse. Aufgrund aktueller technologischer Entwicklungen eröffnen vor allem durch neuartige Fahrzeugtechnologien zur Fahrerunterstützung innovative Möglichkeiten, diesem Bedarf gerecht zu werden (Karthaus & Falkenstein, 2016). An diesem Punkt setzt die vorliegende Dissertation an. Ziel des Dissertationsprojektes war es zu evaluieren, inwieweit aktuell in Entwicklung befindliche Fahrzeugtechnologien, die aus theoretischer Sicht als geeignete Mittel zur Unterstützung älterer Fahrer erscheinen, tatsächlich zu deren Individualmobilität beitragen können. Um das Potential derartiger Technologien abzuschätzen, wurde einerseits untersucht, inwieweit sie zur Verbesserung von Variablen, die in Beziehung zur Fahrleistung stehen, beitragen können. Anderseits wurde ihre Akzeptanz bei potentiellen zukünftigen Nutzern evaluiert. Für diese Untersuchungen wurden zwei exemplarische Technologien als Repräsentanten grundlegend unterschiedlicher Stufen der Fahrzeugautomatisierung ausgewählt: ein kontaktanaloge Head-up Display (auch Augmented Reality Display, ARD) und hochautomatisiertes Fahren. ARDs stellen einen technologischen Ansatz zur Implementierung von Fahrerinformationssystemen und dementsprechend ein Beispiel für Automatisierungsstufe 0 (no automation; SAE International, 2014) dar, indem sie den Fahrer durch die Bereitstellung verkehrsrelevanter Informationen bei der manuellen Ausführung der Fahraufgabe unterstützen. Im Gegensatz dazu zielt die Technologie des hochautomatisierten Fahrens auf eine Unterstützung des Fahrers durch die vollständige Übernahme der Fahraufgabe ab, was Automatisierungsstufe 4 (high automation; SAE International, 2014) entspricht. Trotz dieser grundlegend unterschiedlichen Ansätze wird beiden Technologien ein hohes Potential zur Unterstützung insbesondere älterer Fahrer zugesprochen (Meyer & Deix, 2014; Polders et al., 2015; Rusch et al., 2013; Schall et al., 2013). Die Untersuchung Performanz- und Akzeptanz-bezogener Aspekte beider Technologien erfolgte im Rahmen von drei empirische Studien. Um altersspezifische Befunde identifizieren zu können, wurden allen Studien mit Vertretern der Zielgruppe von älteren Fahrern (65-85 Jahre alt) sowie einer jüngeren Vergleichsgruppe ‚durchschnittlicher‘ (d.h. junger, erfahrener) Fahrer (25-45 Jahre alt) durchgeführt. Bei Studie I handelte es sich um eine im Fahrsimulator durchgeführte Reaktionszeitstudie, in deren Rahmen Leistungs-bezogene Aspekte von ARDs untersucht wurden. Unter den vielfältigen Möglichkeiten zur Anwendung dieser Technologie wird vor allem die Präsentation von Vorinformationen über bevorstehende komplexe Fahrsituationen während der Fahrt als gewinnbringend für ältere Fahrer eingestuft. Diese Strategie adressiert die Tendenz älterer Fahrer zu einer eher seriellen als parallelen Verarbeitung gleichzeitig verfügbarer Informationen während der Fahrt (Davidse et al., 2009; Küting & Krüger, 2002). Vor diesem Hintergrund lag der Fokus von Studie I auf den Effekten einer kontaktanalogen Präsentation von Vorinformationen über bevorstehende Kreuzungen auf die Geschwindigkeit und Genauigkeit der Wahrnehmung dieser Kreuzungen durch den Fahrer, was eine Grundvoraussetzung für eine sichere Fahrleistung darstellt (Crundall & Underwood, 2011). Basierend auf bestehenden Befürchtungen über kontraproduktive Effekte einer kontaktanalogen Informationsdarstellung während der Fahrt, insbesondere im Falle inkorrekter Informationen, wurden zudem die Auswirkungen von Systemfehlern untersucht. Mit Hilfe der kontaktanalogen Vorinformationen gelang es sowohl älteren als auch jüngeren Fahrern, ohne erhöhten Zeitbedarf einen höheren Anteil relevanter Aspekte in Kreuzungssituationen wahrzunehmen. Allerdings wurde die positive Systemwirkung durch das Erleben von Systemfehlern (in diesem Fall inkorrekten Vorinformationen) zumindest für die Dauer der Untersuchung aufgehoben. Dieser Effekt war besonders ausgeprägt für ältere Fahrer und könnte auf die Schwierigkeit, inkorrekte Informationen auf Grund ihrer Darstellung im ARD zu ignorieren, zurückzuführen sein. Studie II stellte eine Fahrsimulatorstudie zu Akzeptanz-bezogenen Aspekten eines ARDs, welches dem Fahrer Vorinformationen über bevorstehende Kreuzungen zur Verfügung stellt, dar. Inhalt dieser Studie waren zum einen die Effekte von Systemerfahrung auf die Nutzerakzeptanz des Systems, zum anderen altersspezifische Akzeptanzbarrieren, welche ältere Fahrer potentiell von der Nutzung der Technologie abhalten könnten. Insgesamt bewerteten sowohl ältere als auch jüngere Fahrer das ARD positiv. Dabei fielen Bewertungen auf Basis von Systemerfahrung im Fahrsimulator tendenziell besser aus als Bewertungen ohne vorherige Systemerfahrung. Obwohl ältere Fahrer im Vergleich zu jüngeren Fahrern ihre Selbstwirksamkeit im Umgang mit dem ARD sowie Umgebungsfaktoren, welche dessen Nutzung unterstützen könnten, als geringer ausgeprägt wahrnahmen, war die positive Einstellung gegenüber der Nutzung des Systems bei ihnen im Durchschnitt stärker ausgeprägt. Leistungs- und Akzeptanz-bezogene Aspekte des hochautomatisierten Fahrens wurden in Studie III, einer zweistufigen Fahrsimulatorstudie, untersucht. Parallel zur Veränderung der Rolle des Menschen vom Fahrzeugführer zum Passagier im Zuge der zunehmenden Fahrzeugautomatisierung veränderte sich dabei auch der Fokus der Leistungsperspektive. Dem entsprechend stand die Bewertung der Fahrleistung des automatisierten Systems durch den mitfahrenden Menschen im Mittelpunkt dieser Untersuchung. Affektive Komponenten der Mensch-Automatisierungs-Interaktion wie Fahrkomfort und Fahrspaß werden in diesem Kontext als bedeutsam zur Gewährleistung der Nutzerakzeptanz und damit auch Nutzung automatisierter Fahrzeuge betrachtet (Tischler & Renner, 2007). Es wird angenommen, dass derartige affektive Komponenten im Kontext des hochautomatisierten Fahrens vor allem vom implementierten Fahrstil abhängen (Bellem et al., 2016). In einem theoretischen Ansatz zur Verbesserung des Fahrkomforts wird die Implementierung vertrauter (d.h. dem eigenen manuellen Fahrstil ähnlicher) Fahrstile empfohlen, um einen menschlichen Fahrzeugführer nachzuahmen und so Bedenken gegenüber einer automatisierten Fahrzeugführung abzubauen (Elbanhawi et al., 2015). Diesem Ansatz folgend wurden in Studie III die Effekte der Fahrzeugautomatisierung sowie der Ähnlichkeit des implementierten Fahrstils zum individuellen manuellen Fahrstil des jeweiligen Fahrers auf Fahrkomfort und Fahrspaß untersucht. Es konnte gezeigt werden, dass mit höherer Automatisierung der Fahrkomfort älterer und jüngerer Fahrer anstieg, der Fahrspaß jüngerer Fahrer sich jedoch verringerte. Alle abhängigen Variablen wurden von einer vergleichbaren Interaktion zwischen Fahreralter und Fahrstilähnlichkeit beeinflusst: Während jüngere Fahrer hochautomatisierte Fahrstile bevorzugten, die ihren jeweiligen manuellen Fahrstilen ähnelten, präferierten ältere Fahrer im hochautomatisierten Kontext eher unähnliche Fahrstile. Dem entsprechend kann der Vertrautheitsansatz basierend auf den Ergebnissen von Studie III zumindest für jüngere Fahrer unterstützt werden, nicht aber für die Zielgruppe älterer Fahrer, deren manuelle Fahrstile durch Kompensationsstrategien zum Ausgleich altersbedingter Einschränkungen ihrer sensorischen, kognitiven und motorischen Fähigkeiten geprägt sind. Fahrstilpräferenzen im hochautomatisierten Kontext scheinen in dieser Altersgruppe mehr von dem Wunsch, einen von diesen Kompensationsstrategien unbeeinträchtigten Fahrstil wiederzuerlangen, geprägt zu sein als von dem Bedürfnis nach vertraut gestalteten Fahrmanövern. Analog zur Evaluation des ARDs beinhaltete die Untersuchung Akzeptanz-bezogener Aspekte des hochautomatisierten Fahrens die Effekte von Systemerfahrung auf die Nutzerakzeptanz sowie potentielle altersspezifische Akzeptanzbarrieren. Einen systemspezifischen Designaspekt aufgreifend wurde zudem untersucht, ob die Nutzerakzeptanz des hochautomatisierten Fahrens ebenfalls durch den implementierten Fahrstil modifizierbar ist. Fahrer beider Altersgruppen berichteten tendenziell positive a priori Akzeptanzwerte, welche sich nach der Ersterfahrung mit dem System signifikant erhöhten und sich anschließend stabilisierten. Vergleichbar mit den Ergebnissen zum ARD war die positive Einstellung gegenüber der Nutzung eines hochautomatisierten Fahrzeuges bei älteren Fahrern im Durchschnitt stärker ausgeprägt als bei jüngeren, obwohl sie ihre Selbstwirksamkeit im Umgang mit dem System sowie unterstützende Umgebungsfaktoren als geringer ausgeprägt bewerteten. Bezüglich des hochautomatisierten Fahrstils unterlag die Systemakzeptanz derselben Interaktion zwischen Fahreralter und Fahrstilähnlichkeit wie Fahrkomfort und Fahrspaß. Diese Ergebnisse demonstrieren, dass Fahrzeugtechnologien auf verschiedenen Automatisierungsstufen effektive Ansätze zur Unterstützung der Individualmobilität älterer Personen liefern können. Die Mehrzahl der identifizierten Leistungs-bezogenen Verbesserungen zeigte sich sowohl für ältere als auch jüngere Fahrer. Diese Befunde weißen auf das Potential von Systemen, welche den Bedürfnissen älterer Fahrer entsprechen, zur Unterstützung verschiedener Altersgruppen hin. Die Ergebnisse der Akzeptanzperspektive deuten an, dass die evaluierten Systeme von Fahrern verschiedener Altersgruppen akzeptiert werden würden, was die Ergebnisse der Leistungsebene widerspiegelt. Die Vergleichbarkeit der Muster verschiedener Akzeptanzprädiktoren, welche für zwei Systeme auf grundlegend unterschiedlichen Automatisierungsstufen identifiziert werden konnten, legt die Existenz zugrundeliegender genereller Aspekte der Fahrzeugtechnologie-Akzeptanz älterer Fahrer nahe. Diese beinhalten deren stark ausgeprägtes Bedürfnis zur Erhaltung ihrer Individualmobilität sowie deren geringere Selbstwirksamkeit im Umgang mit relevanten Technologien und den unzureichenden Zugang zu unterstützenden Infrastrukturen. Diese Erkenntnisse liefern Implikationen für theoretische Modelle der Akzeptanz von Fahrzeugtechnologien durch ältere Fahrer sowie für Maßnahmen zur Absicherung einer erfolgreichen Entwicklung und Markteinführung von Systemen, die darauf abzielen, ältere Menschen beim Erhalt ihrer Individualmobilität zu unterstützen. Berücksichtigt man die Bedeutsamkeit des Fahrens eines eigenen Automobils für das physiologische und psychologische Wohlbefinden im Alter (Adler & Rottunda, 2006; Lutin et al., 2013; Whelan, Langford, Oxley, Koppel, & Charlton, 2006), unterstreichen diese Ergebnisse das Potential neu entstehender Fahrerunterstützungstechnologien für die Verbesserung der Verkehrssicherheit, aber auch Lebensqualität älterer Menschen

This study investigates the impact of peripheral visual information in alleviating motion sickness when engaging in non-driving tasks in fully automated driving. A peripheral visual feedforward system (PVFS) was designed providing information about the upcoming actions of the automated car in the periphery of the occupant’s attention. It was hypothesized that after getting the information from the PVFS, the users’ situation awareness is improved while motion sickness is prevented from developing. The PVFS was also assumed not to increase mental workload nor interrupt the performance of the non-driving tasks. The study was accomplished on an actual road using a Wizard of Oz technique deploying an instrumented car that behaved like a real fully automated car. The test rides using the current setup and methodology indicated high consistency in simulating the automated driving. Results showed that with PVFS, situation awareness was enhanced and motion sickness was lessened while mental workload was unchanged. Participants also indicated high hedonistic user experience with the PVFS. While providing peripheral information showed positive results, further study such as delivering richer information and active head movement are possibly needed.

Virtualization of products means the representation of some of their properties by models. In a stronger digitalized world, these models will gain a much broader use than models had in engineering so far. Even for one modelling aspect different models of the same product will be used, depending on the specific need of the model user. That need may change in the course of product life, between first product concepts till over the different phases of development, to product use, maintenance, or even recycling. Since a digitalized world use of these diverse models will not be limited to experts model consistency will play a much stronger role. Model hierarchies will play a stronger role and can serve also as means for teaching product users a deeper understanding of product properties. A consistent model hierarchy leading from a simple to a more advanced property representation can support this learning process. In this paper perturbation methods are analyzed as a means for setting up model hierarchies in a consistent manner. This is studied by models for the behavior of a electrohydraulic drive, which consists of a variable speed motor, a pump, a double stroke cylinder and a counterbalance valve. Model hierarchy is achieved by model reduction in the sense of perturbation theory. The use of these different models for different questions in a system design context and their interrelations are exemplified.

Data masses on the World Wide Web can hardly be managed by humans or machines. One option is the formal description and linking of data sources using Semantic Web and Linked Data technologies. Ontologies written in standardised languages foster the sharing and linking of data as they provide a means to formally define concepts and relations between these concepts. A second option is visualisation. The visual representation allows humans to perceive information more directly, using the highly developed visual sense. Relatively few efforts have been made on combining both options, although the formality and rich semantics of ontological data make it an ideal candidate for visualisation. Advanced visualisation design systems support the visualisation of tabular, typically statistical data. However, visualisations of ontological data still have to be created manually, since automated solutions are often limited to generic lists or node-link diagrams. Also, the semantics of ontological data are not exploited for guiding users through visualisation tasks. Finally, once a good visualisation setting has been created, it cannot easily be reused and shared. Trying to tackle these problems, we had to answer how to define composable and shareable mappings from ontological data to visual means and how to guide the visual mapping of ontological data. We present an approach that allows for the guided visualisation of ontological data, the creation of effective graphics and the reuse of visualisation settings. Instead of generic graphics, we aim at tailor-made graphics, produced using the whole palette of visual means in a flexible, bottom-up approach. It not only allows for visualising ontologies, but uses ontologies to guide users when visualising data and to drive the visualisation process at various places: First, as a rich source of information on data characteristics, second, as a means to formally describe the vocabulary for building abstract graphics, and third, as a knowledge base of facts on visualisation. This is why we call our approach ontology-driven. We suggest generating an Abstract Visual Model (AVM) to represent and »synthesise« a graphic following a role-based approach, inspired by the one used by J. v. Engelhardt for the analysis of graphics. It consists of graphic objects and relations formalised in the Visualisation Ontology (VISO). A mappings model, based on the declarative RDFS/OWL Visualisation Language (RVL), determines a set of transformations from the domain data to the AVM. RVL allows for composable visual mappings that can be shared and reused across platforms. To guide the user, for example, we discourage the construction of mappings that are suboptimal according to an effectiveness ranking formalised in the fact base and suggest more effective mappings instead. The guidance process is flexible, since it is based on exchangeable rules. VISO, RVL and the AVM are additional contributions of this thesis. Further, we initially analysed the state of the art in visualisation and RDF-presentation comparing 10 approaches by 29 criteria. Our approach is unique because it combines ontology-driven guidance with composable visual mappings. Finally, we compare three prototypes covering the essential parts of our approach to show its feasibility. We show how the mapping process can be supported by tools displaying warning messages for non-optimal visual mappings, e.g., by considering relation characteristics such as »symmetry«. In a constructive evaluation, we challenge both the RVL language and the latest prototype trying to regenerate sketches of graphics we created manually during analysis. We demonstrate how graphics can be varied and complex mappings can be composed from simple ones. Two thirds of the sketches can be almost or completely specified and half of them can be almost or completely implemented.:Legend and Overview of Prefixes xiii 1 Introduction 1 2 Background 11 2.1 Visualisation 11 2.1.1 What is Visualisation? 11 2.1.2 What are the Benefits of Visualisation? 12 2.1.3 Visualisation Related Terms Used in this Thesis 12 2.1.4 Visualisation Models and Architectural Patterns 12 2.1.5 Visualisation Design Systems 14 2.1.6 What is the Difference between Visual Mapping and Styling? 14 2.1.7 Lessons Learned from Style Sheet Languages 15 2.2 Data 16 2.2.1 Data – Information – Knowledge 17 2.2.2 Structured Data 17 2.2.3 Ontologies in Computer Science 19 2.2.4 The Semantic Web and its Languages 19 2.2.5 Linked Data and Open Data 20 2.2.6 The Metamodelling Technological Space 21 2.2.7 SPIN 21 2.3 Guidance 22 2.3.1 Guidance in Visualisation 22 3 Problem Analysis 23 3.1 Problems of Ontology Visualisation Approaches 24 3.2 Research Questions 25 3.3 Set up of the Case Studies 25 3.3.1 Case Studies in the Life Sciences Domain 26 3.3.2 Case Studies in the Publishing Domain 26 3.3.3 Case Studies in the Software Technology Domain 27 3.4 Analysis of the Case Studies’ Ontologies 27 3.5 Manual Sketching of Graphics 29 3.6 Analysis of the Graphics for Typical Visualisation Cases 29 3.7 Requirements 33 3.7.1 Requirements for Visualisation and Interaction 34 3.7.2 Requirements for Data Awareness 34 3.7.3 Requirements for Reuse and Composition 34 3.7.4 Requirements for Variability 35 3.7.5 Requirements for Tooling Support and Guidance 35 3.7.6 Optional Features and Limitations 36 4 Analysis of the State of the Art 37 4.1 Related Visualisation Approaches 38 4.1.1 Short Overview of the Approaches 38 4.1.2 Detailed Comparison by Criteria 46 4.1.3 Conclusion – What Is Still Missing? 60 4.2 Visualisation Languages 62 4.2.1 Short Overview of the Compared Languages 62 4.2.2 Detailed Comparison by Language Criteria 66 4.2.3 Conclusion – What Is Still Missing? 71 4.3 RDF Presentation Languages 72 4.3.1 Short Overview of the Compared Languages 72 4.3.2 Detailed Comparison by Language Criteria 76 4.3.3 Additional Criteria for RDF Display Languages 87 4.3.4 Conclusion – What Is Still Missing? 89 4.4 Model-Driven Interfaces 90 4.4.1 Metamodel-Driven Interfaces 90 4.4.2 Ontology-Driven Interfaces 92 4.4.3 Combined Usage of the Metamodelling and Ontology Technological Space 94 5 A Visualisation Ontology – VISO 97 5.1 Methodology Used for Ontology Creation 100 5.2 Requirements for a Visualisation Ontology 100 5.3 Existing Approaches to Modelling in the Field of Visualisation 101 5.3.1 Terminologies and Taxonomies 101 5.3.2 Existing Visualisation Ontologies 102 5.3.3 Other Visualisation Models and Approaches to Formalisation 103 5.3.4 Summary 103 5.4 Technical Aspects of VISO 103 5.5 VISO/graphic Module – Graphic Vocabulary 104 5.5.1 Graphic Representations and Graphic Objects 105 5.5.2 Graphic Relations and Syntactic Structures 107 5.6 VISO/data Module – Characterising Data 110 5.6.1 Data Structure and Characteristics of Relations 110 5.6.2 The Scale of Measurement and Units 112 5.6.3 Properties for Characterising Data Variables in Statistical Data 113 5.7 VISO/facts Module – Facts for Vis. Constraints and Rules 115 5.7.1 Expressiveness of Graphic Relations 116 5.7.2 Effectiveness Ranking of Graphic Relations 118 5.7.3 Rules for Composing Graphics 119 5.7.4 Other Rules to Consider for Visual Mapping 124 5.7.5 Providing Named Value Collections 124 5.7.6 Existing Approaches to the Formalisation of Visualisation Knowledge . . 126 5.7.7 The VISO/facts/empiric Example Knowledge Base 126 5.8 Other VISO Modules 126 5.9 Conclusions and Future Work 127 5.10 Further Use Cases for VISO 127 5.11 VISO on the Web – Sharing the Vocabulary to Build a Community 128 6 A VISO-Based Abstract Visual Model – AVM 129 6.1 Graphical Notation Used in this Chapter 129 6.2 Elementary Graphic Objects and Graphic Attributes 131 6.3 N-Ary Relations 131 6.4 Binary Relations 131 6.5 Composition of Graphic Objects Using Roles 132 6.6 Composition of Graphic Relations Using Roles 132 6.7 Composition of Visual Mappings Using the AVM 135 6.8 Tracing 135 6.9 Is it Worth Having an Abstract Visual Model? 135 6.10 Discussion of Fresnel as a Related Language 137 6.11 Related Work 139 6.12 Limitations 139 6.13 Conclusions 140 7 A Language for RDFS/OWL Visualisation – RVL 141 7.1 Language Requirements 142 7.2 Main RVL Constructs 145 7.2.1 Mapping 145 7.2.2 Property Mapping 146 7.2.3 Identity Mapping 146 7.2.4 Value Mapping 147 7.2.5 Inheriting RVL Settings 147 7.2.6 Resource Mapping 148 7.2.7 Simplifications 149 7.3 Calculating Value Mappings 150 7.4 Defining Scale of Measurement 153 7.4.1 Determining the Scale of Measurement 154 7.5 Addressing Values in Value Mappings 156 7.5.1 Determining the Set of Addressed Source Values 156 7.5.2 Determining the Set of Addressed Target Values 157 7.6 Overlapping Value Mappings 158 7.7 Default Value Mapping 158 7.8 Default Labelling 159 7.9 Defining Interaction 159 7.10 Mapping Composition and Submappings 160 7.11 A Schema Language for RVL 160 7.11.1 Concrete Examples of the RVL Schema 163 7.12 Conclusions and Future Work 166 8 The OGVIC Approach 169 8.1 Ontology-Driven, Guided Editing of Visual Mappings 172 8.1.1 Classification of Constraints 172 8.1.2 Levels of Guidance 173 8.1.3 Implementing Constraint-Based Guidance 173 8.2 Support of Explicit and Composable Visual Mappings 177 8.2.1 Mapping Composition Cases 178 8.2.2 Selecting a Context 180 8.2.3 Using the Same Graphic Relation Multiple Times 181 8.3 Prototype P1 (TopBraid-Composer-based) 182 8.4 Prototype P2 (OntoWiki-based) 184 8.5 Prototype P3 (Java Implementation of RVL) 187 8.6 Lessons Learned from Prototypes & Future Work 190 8.6.1 Checking RVL Constraints and Visualisation Rules 190 8.6.2 A User Interface for Editing RVL Mappings 190 8.6.3 Graph Transformations with SPIN and SPARQL 1.1 Update 192 8.6.4 Selection and Filtering of Data 193 8.6.5 Interactivity and Incremental Processing 193 8.6.6 Rendering the Final Platform-Specific Code 196 9 Application 197 9.1 Coverage of Case Study Sketches and Necessary Features 198 9.2 Coverage of Visualisation Cases 201 9.3 Coverage of Requirements 205 9.4 Full Example 206 10 Conclusions 211 10.1 Contributions 211 10.2 Constructive Evaluation 212 10.3 Research Questions 213 10.4 Transfer to Other Models and Constraint Languages 213 10.5 Limitations 214 10.6 Future Work 214 Appendices 217 A Case Study Sketches 219 B VISO – Comparison of Visualisation Literature 229 C RVL 231 D RVL Example Mappings and Application 233 D.1 Listings of RVL Example Mappings as Required by Prototype P3 233 D.2 Features Required for Implementing all Sketches 235 D.3 JSON Format for Processing the AVM with D3 – Hierarchical Variant 238 Bibliography 238 List of Figures 251 List of Tables 254 List of Listings 257
Datenmassen im World Wide Web können kaum von Menschen oder Maschinen erfasst werden. Eine Option ist die formale Beschreibung und Verknüpfung von Datenquellen mit Semantic-Web- und Linked-Data-Technologien. Ontologien, in standardisierten Sprachen geschrieben, befördern das Teilen und Verknüpfen von Daten, da sie ein Mittel zur formalen Definition von Konzepten und Beziehungen zwischen diesen Konzepten darstellen. Eine zweite Option ist die Visualisierung. Die visuelle Repräsentation ermöglicht es dem Menschen, Informationen direkter wahrzunehmen, indem er seinen hochentwickelten Sehsinn verwendet. Relativ wenige Anstrengungen wurden unternommen, um beide Optionen zu kombinieren, obwohl die Formalität und die reichhaltige Semantik ontologische Daten zu einem idealen Kandidaten für die Visualisierung machen. Visualisierungsdesignsysteme unterstützen Nutzer bei der Visualisierung von tabellarischen, typischerweise statistischen Daten. Visualisierungen ontologischer Daten jedoch müssen noch manuell erstellt werden, da automatisierte Lösungen häufig auf generische Listendarstellungen oder Knoten-Kanten-Diagramme beschränkt sind. Auch die Semantik der ontologischen Daten wird nicht ausgenutzt, um Benutzer durch Visualisierungsaufgaben zu führen. Einmal erstellte Visualisierungseinstellungen können nicht einfach wiederverwendet und geteilt werden. Um diese Probleme zu lösen, mussten wir eine Antwort darauf finden, wie die Definition komponierbarer und wiederverwendbarer Abbildungen von ontologischen Daten auf visuelle Mittel geschehen könnte und wie Nutzer bei dieser Abbildung geführt werden könnten. Wir stellen einen Ansatz vor, der die geführte Visualisierung von ontologischen Daten, die Erstellung effektiver Grafiken und die Wiederverwendung von Visualisierungseinstellungen ermöglicht. Statt auf generische Grafiken zielt der Ansatz auf maßgeschneiderte Grafiken ab, die mit der gesamten Palette visueller Mittel in einem flexiblen Bottom-Up-Ansatz erstellt werden. Er erlaubt nicht nur die Visualisierung von Ontologien, sondern verwendet auch Ontologien, um Benutzer bei der Visualisierung von Daten zu führen und den Visualisierungsprozess an verschiedenen Stellen zu steuern: Erstens als eine reichhaltige Informationsquelle zu Datencharakteristiken, zweitens als Mittel zur formalen Beschreibung des Vokabulars für den Aufbau von abstrakten Grafiken und drittens als Wissensbasis von Visualisierungsfakten. Deshalb nennen wir unseren Ansatz ontologie-getrieben. Wir schlagen vor, ein Abstract Visual Model (AVM) zu generieren, um eine Grafik rollenbasiert zu synthetisieren, angelehnt an einen Ansatz der von J. v. Engelhardt verwendet wird, um Grafiken zu analysieren. Das AVM besteht aus grafischen Objekten und Relationen, die in der Visualisation Ontology (VISO) formalisiert sind. Ein Mapping-Modell, das auf der deklarativen RDFS/OWL Visualisation Language (RVL) basiert, bestimmt eine Menge von Transformationen von den Quelldaten zum AVM. RVL ermöglicht zusammensetzbare »Mappings«, visuelle Abbildungen, die über Plattformen hinweg geteilt und wiederverwendet werden können. Um den Benutzer zu führen, bewerten wir Mappings anhand eines in der Faktenbasis formalisierten Effektivitätsrankings und schlagen ggf. effektivere Mappings vor. Der Beratungsprozess ist flexibel, da er auf austauschbaren Regeln basiert. VISO, RVL und das AVM sind weitere Beiträge dieser Arbeit. Darüber hinaus analysieren wir zunächst den Stand der Technik in der Visualisierung und RDF-Präsentation, indem wir 10 Ansätze nach 29 Kriterien vergleichen. Unser Ansatz ist einzigartig, da er eine ontologie-getriebene Nutzerführung mit komponierbaren visuellen Mappings vereint. Schließlich vergleichen wir drei Prototypen, welche die wesentlichen Teile unseres Ansatzes umsetzen, um seine Machbarkeit zu zeigen. Wir zeigen, wie der Mapping-Prozess durch Tools unterstützt werden kann, die Warnmeldungen für nicht optimale visuelle Abbildungen anzeigen, z. B. durch Berücksichtigung von Charakteristiken der Relationen wie »Symmetrie«. In einer konstruktiven Evaluation fordern wir sowohl die RVL-Sprache als auch den neuesten Prototyp heraus, indem wir versuchen Skizzen von Grafiken umzusetzen, die wir während der Analyse manuell erstellt haben. Wir zeigen, wie Grafiken variiert werden können und komplexe Mappings aus einfachen zusammengesetzt werden können. Zwei Drittel der Skizzen können fast vollständig oder vollständig spezifiziert werden und die Hälfte kann fast vollständig oder vollständig umgesetzt werden.:Legend and Overview of Prefixes xiii 1 Introduction 1 2 Background 11 2.1 Visualisation 11 2.1.1 What is Visualisation? 11 2.1.2 What are the Benefits of Visualisation? 12 2.1.3 Visualisation Related Terms Used in this Thesis 12 2.1.4 Visualisation Models and Architectural Patterns 12 2.1.5 Visualisation Design Systems 14 2.1.6 What is the Difference between Visual Mapping and Styling? 14 2.1.7 Lessons Learned from Style Sheet Languages 15 2.2 Data 16 2.2.1 Data – Information – Knowledge 17 2.2.2 Structured Data 17 2.2.3 Ontologies in Computer Science 19 2.2.4 The Semantic Web and its Languages 19 2.2.5 Linked Data and Open Data 20 2.2.6 The Metamodelling Technological Space 21 2.2.7 SPIN 21 2.3 Guidance 22 2.3.1 Guidance in Visualisation 22 3 Problem Analysis 23 3.1 Problems of Ontology Visualisation Approaches 24 3.2 Research Questions 25 3.3 Set up of the Case Studies 25 3.3.1 Case Studies in the Life Sciences Domain 26 3.3.2 Case Studies in the Publishing Domain 26 3.3.3 Case Studies in the Software Technology Domain 27 3.4 Analysis of the Case Studies’ Ontologies 27 3.5 Manual Sketching of Graphics 29 3.6 Analysis of the Graphics for Typical Visualisation Cases 29 3.7 Requirements 33 3.7.1 Requirements for Visualisation and Interaction 34 3.7.2 Requirements for Data Awareness 34 3.7.3 Requirements for Reuse and Composition 34 3.7.4 Requirements for Variability 35 3.7.5 Requirements for Tooling Support and Guidance 35 3.7.6 Optional Features and Limitations 36 4 Analysis of the State of the Art 37 4.1 Related Visualisation Approaches 38 4.1.1 Short Overview of the Approaches 38 4.1.2 Detailed Comparison by Criteria 46 4.1.3 Conclusion – What Is Still Missing? 60 4.2 Visualisation Languages 62 4.2.1 Short Overview of the Compared Languages 62 4.2.2 Detailed Comparison by Language Criteria 66 4.2.3 Conclusion – What Is Still Missing? 71 4.3 RDF Presentation Languages 72 4.3.1 Short Overview of the Compared Languages 72 4.3.2 Detailed Comparison by Language Criteria 76 4.3.3 Additional Criteria for RDF Display Languages 87 4.3.4 Conclusion – What Is Still Missing? 89 4.4 Model-Driven Interfaces 90 4.4.1 Metamodel-Driven Interfaces 90 4.4.2 Ontology-Driven Interfaces 92 4.4.3 Combined Usage of the Metamodelling and Ontology Technological Space 94 5 A Visualisation Ontology – VISO 97 5.1 Methodology Used for Ontology Creation 100 5.2 Requirements for a Visualisation Ontology 100 5.3 Existing Approaches to Modelling in the Field of Visualisation 101 5.3.1 Terminologies and Taxonomies 101 5.3.2 Existing Visualisation Ontologies 102 5.3.3 Other Visualisation Models and Approaches to Formalisation 103 5.3.4 Summary 103 5.4 Technical Aspects of VISO 103 5.5 VISO/graphic Module – Graphic Vocabulary 104 5.5.1 Graphic Representations and Graphic Objects 105 5.5.2 Graphic Relations and Syntactic Structures 107 5.6 VISO/data Module – Characterising Data 110 5.6.1 Data Structure and Characteristics of Relations 110 5.6.2 The Scale of Measurement and Units 112 5.6.3 Properties for Characterising Data Variables in Statistical Data 113 5.7 VISO/facts Module – Facts for Vis. Constraints and Rules 115 5.7.1 Expressiveness of Graphic Relations 116 5.7.2 Effectiveness Ranking of Graphic Relations 118 5.7.3 Rules for Composing Graphics 119 5.7.4 Other Rules to Consider for Visual Mapping 124 5.7.5 Providing Named Value Collections 124 5.7.6 Existing Approaches to the Formalisation of Visualisation Knowledge . . 126 5.7.7 The VISO/facts/empiric Example Knowledge Base 126 5.8 Other VISO Modules 126 5.9 Conclusions and Future Work 127 5.10 Further Use Cases for VISO 127 5.11 VISO on the Web – Sharing the Vocabulary to Build a Community 128 6 A VISO-Based Abstract Visual Model – AVM 129 6.1 Graphical Notation Used in this Chapter 129 6.2 Elementary Graphic Objects and Graphic Attributes 131 6.3 N-Ary Relations 131 6.4 Binary Relations 131 6.5 Composition of Graphic Objects Using Roles 132 6.6 Composition of Graphic Relations Using Roles 132 6.7 Composition of Visual Mappings Using the AVM 135 6.8 Tracing 135 6.9 Is it Worth Having an Abstract Visual Model? 135 6.10 Discussion of Fresnel as a Related Language 137 6.11 Related Work 139 6.12 Limitations 139 6.13 Conclusions 140 7 A Language for RDFS/OWL Visualisation – RVL 141 7.1 Language Requirements 142 7.2 Main RVL Constructs 145 7.2.1 Mapping 145 7.2.2 Property Mapping 146 7.2.3 Identity Mapping 146 7.2.4 Value Mapping 147 7.2.5 Inheriting RVL Settings 147 7.2.6 Resource Mapping 148 7.2.7 Simplifications 149 7.3 Calculating Value Mappings 150 7.4 Defining Scale of Measurement 153 7.4.1 Determining the Scale of Measurement 154 7.5 Addressing Values in Value Mappings 156 7.5.1 Determining the Set of Addressed Source Values 156 7.5.2 Determining the Set of Addressed Target Values 157 7.6 Overlapping Value Mappings 158 7.7 Default Value Mapping 158 7.8 Default Labelling 159 7.9 Defining Interaction 159 7.10 Mapping Composition and Submappings 160 7.11 A Schema Language for RVL 160 7.11.1 Concrete Examples of the RVL Schema 163 7.12 Conclusions and Future Work 166 8 The OGVIC Approach 169 8.1 Ontology-Driven, Guided Editing of Visual Mappings 172 8.1.1 Classification of Constraints 172 8.1.2 Levels of Guidance 173 8.1.3 Implementing Constraint-Based Guidance 173 8.2 Support of Explicit and Composable Visual Mappings 177 8.2.1 Mapping Composition Cases 178 8.2.2 Selecting a Context 180 8.2.3 Using the Same Graphic Relation Multiple Times 181 8.3 Prototype P1 (TopBraid-Composer-based) 182 8.4 Prototype P2 (OntoWiki-based) 184 8.5 Prototype P3 (Java Implementation of RVL) 187 8.6 Lessons Learned from Prototypes & Future Work 190 8.6.1 Checking RVL Constraints and Visualisation Rules 190 8.6.2 A User Interface for Editing RVL Mappings 190 8.6.3 Graph Transformations with SPIN and SPARQL 1.1 Update 192 8.6.4 Selection and Filtering of Data 193 8.6.5 Interactivity and Incremental Processing 193 8.6.6 Rendering the Final Platform-Specific Code 196 9 Application 197 9.1 Coverage of Case Study Sketches and Necessary Features 198 9.2 Coverage of Visualisation Cases 201 9.3 Coverage of Requirements 205 9.4 Full Example 206 10 Conclusions 211 10.1 Contributions 211 10.2 Constructive Evaluation 212 10.3 Research Questions 213 10.4 Transfer to Other Models and Constraint Languages 213 10.5 Limitations 214 10.6 Future Work 214 Appendices 217 A Case Study Sketches 219 B VISO – Comparison of Visualisation Literature 229 C RVL 231 D RVL Example Mappings and Application 233 D.1 Listings of RVL Example Mappings as Required by Prototype P3 233 D.2 Features Required for Implementing all Sketches 235 D.3 JSON Format for Processing the AVM with D3 – Hierarchical Variant 238 Bibliography 238 List of Figures 251 List of Tables 254 List of Listings 257

Das Ziel der Dissertation war, zu untersuchen, welche Aspekte bei Design und Implementierung von Gestensteuerung im Bereich Mensch-Maschine Interaktion wichtig sind. Der Schwerpunkt des ersten Teiles richtet sich auf Aspekte eines Gestenvokabulars und die Frage eines zusätzlichen Feedbacks unter Bezugnahme auf Usability, mentale Belastung und Nutzerzufriedenheit. Der Schwerpunkt des zweiten Teils liegt auf den Auswirkungen von Gestensteuerung auf das Fahrverhalten. In der vorliegenden Dissertation wurden drei relevante Aspekte von Gestensteuerung herausgestellt. Experiment 1 und 2 der Vorstudie untersuchten, wie ein Gestenvokabular aussehen sollte im Hinblick auf die Form der Gesten und die Anzahl verschiedener Gesten, die in einem System implementiert werden. Als Ergebnis schnitt die höchste Anzahl an Gesten (6) in Bezug auf User Experience und Akzeptanz am besten ab. Ebenso das Gestenset, das an die menschliche Kommunikation angelehnt war. Im Unterschied zur Bedienung eines Touchscreens gibt es bei Gestensteuerung kein direktes haptisches Feedback. Aus diesem Grund wurde in Experiment 3 der Vorstudie untersucht, ob es einen Ersatz für das fehlende direkte Feedback geben sollte. Als Ergebnis kann festgehalten werden, dass alle genutzten Feedback-Varianten nicht signifikant besser abschnitten als die Variante mit keinem zusätzlichen Feedback. Die Simulator- und die VIL-Studie untersuchten den Einfluss von Gestensteuerung auf das Blickverhalten und die Reaktion auf kritische Ereignisse im Straßenverkehr. Für diesen Zweck wurde das Gestensteuerungs-Setup in einen Simulator beziehungsweise das Vehicle in the Loop (VIL) übertragen. Die Simulator-Studie konnte zeigen, dass die Fahrer weniger häufig auf das Display im Fahrzeuginneren schauten wenn sie Gestensteuerung benutzten im Vergleich zu Touchsteuerung. Außerdem fühlten sie sich sicherer und die Gebrauchstauglichkeit wurde als gut beschrieben. Die VIL-Studie konnte einen positiven Einfluss auf Reaktionszeiten auf kritische Ereignisse zeigen. Insgesamt kann damit Gestensteuerung als sichere Alternative für Interaktion im Fahrzeug bezeichnet werden, die darüber hinaus auch beliebt bei den Fahrern zu sein scheint.
This thesis investigates aspects of designing and implementing gestures in human-machine interaction (HMI). The first part focuses on aspects of a gesture set and additional feedback with regard to usability, workload, and user satisfaction. The second part focuses on the impact of gesture-based interaction (GBI) on driving behavior. More specifically, this thesis identifies three elementary aspects of designing a GBI. Pre-study experiments 1 and 2 examine how a gesture set should appear in terms of the shape and number of gestures used. The results indicate that the highest number of gestures, six, performs best in terms of user experience and acceptance. However, a gesture set borrowed from human communication performs equally well. In contrast to touch-based interaction (TBI), direct haptic feedback for mid-air gestures is not present. Therefore, pre-study experiment 3 is conducted in order to determine whether a surrogate is necessary. The results of this experiment suggest that implemented forms of feedback are not rated significantly higher than special feedback. The simulator-study and VIL-study investigate the real-world impact of GBI on driver behavior in terms of gaze behavior and reaction to critical events. For this purpose, the GBI setup is transferred into a simulator environment with a Vehicle in the Loop (VIL) to evaluate GBI for IVIS use. The simulator-study demonstrates that drivers look less to the display when using GBI compared to TBI. Moreover, they feel safer, and the user experience is better rated. Therefore, GBI has a positive impact on driver distraction. The VIL-study reveals a positive impact on reaction times to critical events. In conclusion, gestures can be a safe alternative for in-car interaction, an alternative which is popular among drivers.

Health informatics is concerned with the structure, acquisition, and use of health information. Its origins can be traced back to the publication of Bills of Mortality by the parishes of London in the sixteenth century. Interest in health information accelerated during the late nineteenth century with the development of an internationally recognized classification of the causes of death. Further work on the classification of diseases and causes of death has resulted in the ICD-10, while SNOMED CT provides an international thesaurus of medical terms suitable for use in computerized medical record systems. In 1932, Tovell and Dunn described the systematic collection of data about anaesthetics with the aim of identifying areas for improvement. The improvement of healthcare is the main driver for the implementation of electronic patient record systems in hospitals. A natural corollary is the implementation of computerized anaesthetic information management systems. Computerized record systems can automatically store the output of physiological monitors and reduce errors with active and passive decision support. Although the recording and processing of health information in the twenty-first century almost always involves the use of computers, this can give rise to problems with security and inter-operability. Computer technology also has other uses in modern anaesthetic practice. The modelling of physiological processes and the use of simulators in the training of anaesthetists are good examples.

Idiopathic inflammatory myopathies (IIM) of childhood are rare serious disorders, of which the most common is juvenile dermatomyositis (JDM). It is recognized increasingly that, even within JDM, there is significant heterogeneity. Recently defined biomarkers, such as the myositis-specific autoantibodies (MSA) have been valuable to define juvenile IIM subgroups and may provide novel methods of classification. Although randomized controlled trials in JDM are challenging, an increasing consensus-based body of evidence is being used to drive standardization of treatment and care, with new drugs for severe cases being increasingly tested. Significant differences between adults and children with dermatomyositis (DM) exist, and are reviewed in this chapter. These differences emphasize the importance of specialists in the area of transition of young people who have had JDM to receive their care from a team of health professionals with comprehensive knowledge of JDM, as well as transitional care issues.

This book addresses different linguistic and philosophical aspects of referring to the self in a wide range of languages from different language families, including Amharic, English, French, Japanese, Korean, Mandarin, Newari (Sino-Tibetan), Polish, Tariana (Arawak), and Thai. In the domain of speaking about oneself, languages use a myriad of expressions that cut across grammatical and semantic categories, as well as a wide variety of constructions. Languages of Southeast and East Asia famously employ a great number of terms for first-person reference to signal honorification. The number and mixed properties of these terms make them debatable candidates for pronounhood, with many grammar-driven classifications opting to classify them with nouns. Some languages make use of egophors or logophors, and many exhibit an interaction between expressing the self and expressing evidentiality qua the epistemic status of information held from the ego perspective. The volume’s focus on expressing the self, however, is not directly motivated by an interest in the grammar or lexicon, but instead stems from philosophical discussions of the special status of thoughts about oneself, known as de se thoughts. It is this interdisciplinary understanding of expressing the self that underlies this volume, comprising philosophy of mind at one end of the spectrum and cross-cultural pragmatics of self-expression at the other. This unprecedented juxtaposition results in a novel method of approaching de se and de se expressions, in which research methods from linguistics and philosophy inform each other. The importance of this interdisciplinary perspective on expressing the self cannot be overemphasized. Crucially, the volume also demonstrates that linguistic research on first-person reference makes a valuable contribution to research on the self tout court, by exploring the ways in which the self is expressed, and thereby adding to the insights gained through philosophy, psychology, and cognitive science.

AbstractThis chapter addresses privacy challenges that stem particularly from working with big data. Several classification schemes of such challenges are discussed. The chapter continues by classifying the technological solutions as proposed by current state-of-the-art research projects. Three trends are distinguished: (1) putting the end user of data services back as the central focal point of Privacy-Preserving Technologies, (2) the digitisation and automation of privacy policies in and for big data services and (3) developing secure methods of multi-party computation and analytics, allowing both trusted and non-trusted partners to work together with big data while simultaneously preserving privacy. The chapter ends with three main recommendations: (1) the development of regulatory sandboxes; (2) continued support for research, innovation and deployment of Privacy-Preserving Technologies; and (3) support and contribution to the formation of technical standards for preserving privacy. The findings and recommendations of this chapter in particular demonstrate the role of Privacy-Preserving Technologies as an especially important case of data technologies towards data-driven AI. Privacy-Preserving Technologies constitute an essential element of the AI Innovation Ecosystem Enablers (Data for AI).

AbstractDeep Neural Networks (DNNs) are being deployed in a wide range of settings today, from safety-critical applications like autonomous driving to commercial applications involving image classifications. However, recent research has shown that DNNs can be brittle to even slight variations of the input data. Therefore, rigorous testing of DNNs has gained widespread attention.While DNN robustness under norm-bound perturbation got significant attention over the past few years, our knowledge is still limited when natural variants of the input images come. These natural variants, e.g., a rotated or a rainy version of the original input, are especially concerning as they can occur naturally in the field without any active adversary and may lead to undesirable consequences. Thus, it is important to identify the inputs whose small variations may lead to erroneous DNN behaviors. The very few studies that looked at DNN’s robustness under natural variants, however, focus on estimating the overall robustness of DNNs across all the test data rather than localizing such error-producing points. This work aims to bridge this gap.To this end, we study the local per-input robustness properties of the DNNs and leverage those properties to build a white-box (DeepRobust-W) and a black-box (DeepRobust-B) tool to automatically identify the non-robust points. Our evaluation of these methods on three DNN models spanning three widely used image classification datasets shows that they are effective in flagging points of poor robustness. In particular, DeepRobust-W and DeepRobust-B are able to achieve an F1 score of up to 91.4% and 99.1%, respectively. We further show that DeepRobust-W can be applied to a regression problem in a domain beyond image classification. Our evaluation on three self-driving car models demonstrates that DeepRobust-W is effective in identifying points of poor robustness with F1 score up to 78.9%.

Abstract We present xspells, a model-agnostic local approach for explaining the decisions of a black box model for sentiment classification of short texts. The explanations provided consist of a set of exemplar sentences and a set of counter-exemplar sentences. The former are examples classified by the black box with the same label as the text to explain. The latter are examples classified with a different label (a form of counter-factuals). Both are close in meaning to the text to explain, and both are meaningful sentences – albeit they are synthetically generated. xspells generates neighbors of the text to explain in a latent space using Variational Autoencoders for encoding text and decoding latent instances. A decision tree is learned from randomly generated neighbors, and used to drive the selection of the exemplars and counter-exemplars. We report experiments on two datasets showing that xspells outperforms the well-known lime method in terms of quality of explanations, fidelity, and usefulness, and that is comparable to it in terms of stability.

AbstractThis chapter aimed to present different data driven Vibration-Based Methods (VBMs) for Structural Health Monitoring (SHM). This family of methods, widely used for engineering applications, present several advantages for damage identification applications. First, VBMs provide continuous information on the health state of the structure at a global level without the need to access the damaged elements and to know their location. Furthermore, damage can be identified using the dynamic response of the structure measured by sensors non-necessarily located in the proximity of damage and without any prior knowledge about the damage location. By principle, VBMs can identify damage related to changes in the dynamic properties of structures, such as stiffness variations due to modifications in the connections between structural elements, or changes in geometric and material properties. A classification of different VBMs was presented in this chapter. Furthermore, several case studies were presented to demonstrate the potential of these methods.

AbstractCamera traps are used worldwide to monitor wildlife. Despite the increasing availability of Deep Learning (DL) models, the effective usage of this technology to support wildlife monitoring is limited. This is mainly due to the complexity of DL technology and high computing requirements. This paper presents the implementation of the light-weight and state-of-the-art YOLOv5 architecture for automated labeling of camera trap images of mammals in the Białowieża Forest (BF), Poland. The camera trapping data were organized and harmonized using TRAPPER software, an open-source application for managing large-scale wildlife monitoring projects. The proposed image recognition pipeline achieved an average accuracy of 85% F1-score in the identification of the 12 most commonly occurring medium-size and large mammal species in BF, using a limited set of training and testing data (a total of 2659 images with animals).Based on the preliminary results, we have concluded that the YOLOv5 object detection and classification model is a fine and promising DL solution after the adoption of the transfer learning technique. It can be efficiently plugged in via an API into existing web-based camera trapping data processing platforms such as e.g. TRAPPER system. Since TRAPPER is already used to manage and classify (manually) camera trapping datasets by many research groups in Europe, the implementation of AI-based automated species classification will significantly speed up the data processing workflow and thus better support data-driven wildlife monitoring and conservation. Moreover, YOLOv5 has been proven to perform well on edge devices, which may open a new chapter in animal population monitoring in real-time directly from camera trap devices.

Real time data acquisition and evaluation are required to save lives. Such data with utilization and application of the latest technologies in hospitals around the world can improve patient treatments and well beings. The delivery of patient's medical data needs to be secure. Secure and accurate real time data acquisition and analysis of patient data and the ability to update such data will assist in reducing cost while improving patient's care. A wireless framework based on radio frequency identification (RFID) can integrate wireless networks for fast data acquisition and transmission, while maintaining the privacy issue. This chapter discusses the development of a framework that can be considered for secure patient data collection and communications in a hospital environment. A new method for data classification and access authorization has also been developed, which will assist in preserving privacy and security of data. Several Case studies are offered to show the effectiveness of this framework.

Electromyographic (EMG) processing is an important research area with direct applications to prosthetics, exoskeletons and human-machine interaction. Current state of the art decoding methods require intensive training on a single user before it can be utilized, and have been unable to achieve both user-independence and real-time performance. This paper presents a real-time EMG classification method which generalizes across users without requiring an additional training phase. An EMG-embedded sleeve quickly positions and records from EMG surface electrodes on six forearm muscles. An optimized decision tree classifies signals from these sensors into five distinct movements for any given user using EMG energy synergies between muscles. This method was tested on 10 healthy subjects using leave-one-out validation, resulting in an overall accuracy of 79±6.6%, with sensitivity and specificity averaging 66% and 97.6%, respectively, over all classified motions. The high specificity values demonstrate the ability to generalize across users, presenting opportunities for large-scale studies and broader accessibility to EMG-driven applications.

This article presents a systematic procedure and Artificial Neural Networks (ANN) based tool for comfort objectification and customer classification, to support drive train developer during the product development process. In this case, the term “comfort objectification” can be clarified as reproduction of subjectively sensed convenience of a passenger through objectively measurable values. Many factors, such as noise, vibration, physical or psychological condition of a passenger generally influence the ride comfort. The main purpose of this project is to develop the drive train and his assemblies which can sustain customers’ demand of vibration comfort. The presented methods enable the identification and the evaluation of vehicle dynamic properties from the passengers’ point of view during start-up, shifting, steering as well as other procedures in the early stage of the product development process. For instance, this tool is developed for the evaluation of ride comfort during a start-up of a front-drive, intermediate-class car. To estimate the subjective sensation, the new driver modeling tool based on ANN is developed from the way individual drivers make their assessment. This paper presents a user-friendly interface which allows both experts and users who are still short of experience in the ANN field, to create different network structures depending on the task. By means of this tool, the modeling process can be effectively simplified and shortened. As a result, the objective values captured during each drive test are efficiently correlated with the subjective sensation. Consequently, the high performance of comfort prediction can be achieved. By using self organizing map as a tool for driver classification, the different types of drivers can be considered due to their comfort expectation and style of driving. The comfort prediction concerning each driver group can then be carried out. According to the approach of virtual drive train development, in this study, the elaborated multi-body simulation models are primarily used to generate several virtual start-up processes. This enables the determination of NVH properties of the future product and allows the developer to investigate the effect of vibration like judder and jerking on the degree of ride comfort. By applying objective data from the simulation, the comfort assessment using the presented tools can be executed. In the long run, costly drive tests and cost-intensive prototypes can be partially replaced.

This study deals with behavior identification of Electric-Powered Wheelchair (EPW) drivers. User’s actions on the joystick determine this behavior. We assume that a driver evaluation can be performed using reference behaviors which are determined a priori. This study was carried out with two valid populations. The first one includes eight experimented subjects. The second includes six novice subjects. We propose to implement the Fuzzy C-Means (FCM) classification to separate different behaviors. The FCM was applied on the experimented population in order to determine reference’s behaviors. This shows that there were basically two different behaviors. An evaluation is performed on novice users by comparing their behaviors with respect to the reference ones. The results show that this population has an erratic behavior during the learning phase. Subsequently, users converge to one of the identified reference behaviors. We also evaluated a subject who suffers from muscular dystrophy and uses an EPW in everyday life. The results show a steady driving behavior.

Ball-driven mobility platforms have shown that spherical wheels can enable substantial freedom of mobility for ground vehicles. Accurate and robust actuation of spherical wheels for high acceleration maneuvers and graded terrains can, however, be challenging. In this paper, a novel design for a magnetically coupled ball drive is presented. The proposed design utilizes an internal support structure and magnetic coupling to eliminate the need for an external claw-like support structure. A model of the proposed design is developed and used to evaluate the slip/no-slip operational window. Due to the high-dimensional nature of the model, the design space is sampled using randomly generated design instances and the data is used to train a support vector classification machine. Principal component analysis and feature importance detection are used to identify critical parameters that control the slip behavior and the feasible (no-slip) design space. The classification shows an increase in the feasible design space with the addition of, and increase in, the magnetic coupling force. Based on the results of the machine learning algorithm, FEA design tools and experimental testing are used to design a spherical magnetic coupler array configuration that can realize the desired magnetic coupling force for the ball drive.