1752 research outputs found
Sort by
Predicting Ecological Momentary Assessments in an App for Tinnitus by Learning From Each User's Stream With a Contextual Multi-Armed Bandit
Full text linkEcological Momentary Assessments (EMA) deliver insights on how patients perceive tinnitus at different times and how they are affected by it. Moving to the next level, an mHealth app can support users more directly by predicting a user's next EMA and recommending personalized services based on these predictions. In this study, we analyzed the data of 21 users who were exposed to an mHealth app with non-personalized recommendations, and we investigate ways of predicting the next vector of EMA answers. We studied the potential of entity-centric predictors that learn for each user separately and neighborhood-based predictors that learn for each user separately but take also similar users into account, and we compared them to a predictor that learns from all past EMA indiscriminately, without considering which user delivered which data, i.e., to a “global model.” Since users were exposed to two versions of the non-personalized recommendations app, we employed a Contextual Multi-Armed Bandit (CMAB), which chooses the best predictor for each user at each time point, taking each user's group into account. Our analysis showed that the combination of predictors into a CMAB achieves good performance throughout, since the global model was chosen at early time points and for users with few data, while the entity-centric, i.e., user-specific, predictors were used whenever the user had delivered enough data—the CMAB chose itself when the data were “enough.” This flexible setting delivered insights on how user behavior can be predicted for personalization, as well as insights on the specific mHealth data. Our main findings are that for EMA prediction the entity-centric predictors should be preferred over a user-insensitive global model and that the choice of EMA items should be further investigated because some items are answered more rarely than others. Albeit our CMAB-based prediction workflow is robust to differences in exposition and interaction intensity, experimentators that design studies with mHealth apps should be prepared to quantify and closely monitor differences in the intensity of user-app interaction, since users with many interactions may have a disproportionate influence on global models
Design and Implementation of a UI & UX Concept for an Android Monitoring App
No full textThe content and target of this Thesis, was the design and implementation of a new user interface (UI) and user experience (UX) concept for the Android app of the large-scale application monitoring platform (LAMP) framework. LAMP uses the phone's sensors and notifications to gather user data. An app prototype was already created in a previous work, to proof, that the concept is working, but the app was only equipped with the bare functionality, ignoring many of the user's needs, UX design principles, design conventions and aesthetics. This made the data collection non-transparent and the app unpleasant to use. To convince the users in large-scale studies to share their data, it is necessary that they trust the app and the related framework. A new UI and UX concept was needed, to assure this, therefore a new Android app was designed and implemented. Various methods from UX design, design thinking and agile software development were used to craft the requirements and to design and implement the app, making sure, that the final product fulfilled the users needs. In this Thesis, an introduction is given, to present the motivation, the objective, and the contents. Then the fundamental concepts like LAMP, UI and UX are presented, to create a basis for the conceptualization of the new app. To assure, that the app meets the users expectations, the requirements were engineered, the process and its' results are presented. The design process and the implementation are documented and presented, showcasing the creative and technical aspects of the new app concept. The resulting new app implementation is then compared to the previous implementation, concerning UI, UX and technical aspects. Finally the Thesis is concluded with a summary and an outlook into the future
Design and Implementation of a Framework for the Creation of BPMN 2.0 Process Models based on Textual Descriptions
Full text linkDevelopment of a Rule-based Smart Notification Service
No full textWith more and more parts of our live getting digitized, the number of notifications rises, that arrive at an inopportune moment interrupting the work of the user. This thesis investigates a possibility to handle notifications in a multi device environment. We implemented a prototype of a multi device smart notification system. The system uses rules to allow, block, or postpone notifications to an opportune moment for the user. As part of the system, we developed an Android application as a client. Android is currently the only operating system that allows to capture and delete notifications from the notification drawer. It suggests the rules based on the past behaviour of the user, making the system adaptable to changes. Furthermore, the user can create their own rules too. The system also synchronizes all notifications across all logged in devices of the user. With the developed system, the user can read their notifications on the device of their choosing, block annoying notifications, or postpone notifications to an opportune moment
Impact of the GDPR on the Development of eHealth Software
Full text linkThe new EU General Data Protection Regulation (GDPR) became effective on May 25, 2018 and regulates how personal data may be processed by companies, government agencies and other organizations in the European Union (EU). Since prior research focused mostly on the GDPR in general, its implications and impact on the development of health software are not as intuitive as one may think. Even though our main goal was to analyze the impact of the GDPR on health software, we have simultaneously covered several other important aspects of complying with the GDPR by researching relevant literature. We have outlined the history and content of the GDPR as well as other regulations like the Federal Data Protection Act (FDPA) and put them into the context of health. As a result, we were able to identify best practices for health-app providers and possibilities on how to comply with specific key aspects of the GDPR. Several other regulations and norms have been considered and illustrated concisely in this thesis. We have subsequently applied or analysis on eSano, the health platform of the University of Ulm. Our results show that eSano is GDPR-compliant with minor room for improvement
Object detection in picking: Handling variety of a warehouse’s articles
Full text linkPurpose: The automation of picking is still a challenge as a high amount of flexibility is needed to handle different articles according to their requirements. Enabling robot picking in a dynamic warehouse environment consequently requires a sophisticated object detection system capable of handling a multitude of different articles.
Methodology: Testing the applicability of object detection approaches for logistics research started with few objects producing promising results. In the context of warehouse environments, the applicability of such approaches to thousands of different articles is still doubted. Using different approaches in parallel may enable handling a plethora of different articles as well as the maintenance of object detection approach in case of changes to articles or assortments occur.
Findings: Existing object detection algorithms are reliable if configured correctly. However, research in this field mostly focuses on a limited set of objects that need to be distinguished showing the functionality of the algorithm. Applying such algorithms in the context of logistics offers great potential, but also poses additional challenges. A huge variety of articles must be distinguished during picking, increasing complexity of the system with each article. A combination of different Convolutional Neural Networks may solve the problem.
Originality: The suitability of existing object detection algorithms originates from research on automation of established processes in existing warehouses. A process model was already introduced enabling the transformation of laboratory trained CNNs to industrial warehouses. Experiments with CNNs according to this approach are published now
Data-Driven Evolution of Activity Forms in Object- and Process-Aware Information Systems
Full text linkAbstract. Object-aware processes enable the data-driven generation of forms based on the object behavior, which is pre-specified by the respective object lifecycle process. Each state of a lifecycle process comprises a number of object attributes that need to be set (e.g., via forms) before transitioning to the next state. When initially modeling a lifecycle process, the optimal ordering of the form fields is often unknown and only a guess of the lifecycle process modeler. As a consequence, certain form fields might be obsolete, missing, or ordered in a non-intuitive manner. Though this does not affect process executability, it decreases the usability of the automatically generated forms. Discovering respective problems, therefore, provides valuable insights into how object- and process-aware information systems can be evolved to improve their usability. This paper presents an approach for deriving improvements of object lifecycle processes by comparing the respective positions of the fields of the generated forms with the ones according to which the fields were actually filled by users during runtime. Our approach enables us to discover missing or obsolete form fields, and additionally considers the order of the fields within the generated forms. Finally, we can derive the modeling operations required to automatically restructure the internal logic of the lifecycle process states and, thus, to automatically evolve lifecycle processes and corresponding forms
A systematic quality rating of available mobile health apps for borderline personality disorder
Full text linkBackground Mobile health apps (MHAs) may offer a mean to overcome treatment barriers in Borderline Personality Disorder (BPD) mental health care. However, MHAs for BPD on the market lack transparency and quality assessment.
Methods European app stores were systematically searched, and two independent trained reviewers extracted relevant MHAs. Employed methods and privacy and security details documentation of included MHAs were extracted. MHAs were then assessed and rated using the German version of the standardized Mobile Application Rating Scale (MARS-G). Mean values and standard deviations of all subscales (engagement, functionality, aesthetics, information, and therapeutic gain) and correlations with user ratings were calculated.
Results Of 2,977 identified MHAs, 16 were included, showing average quality across the four main subscales (M=3.25, SD=0.68). Shortcomings were observed with regard to engagement (M=2.87, SD = 0.99), potential therapeutic gain (M=2.67, SD=0.83), existing evidence base (25.0% of included MHAs were tested empirically), and documented privacy and security details. No significant correlations were found between user ratings and the overall total score of the MARS-G or MARS-G main subscales.
Conclusions Available MHAs for BPD vary in quality and evidence on their efficacy, effectiveness, and possible adverse events is scarce. More substantial efforts to ensure the quality of MHAs available for patients and a focus on transparency, particularly regarding privacy and security documentation, are necessary
Evaluating Sensor Data in the Context of Mobile Crowdsensing
Full text linkWith the recent rise of the Internet of Things the prevalence of mobile sensors in our daily life experienced a huge surge. Mobile crowdsensing (MCS) is a new emerging paradigm that realizes the utility and ubiquity of smartphones and more precisely their incorporated smart sensors. By using the mobile phones and data of ordinary citizens, many problems have to be solved when designing an MCS-application. What data is needed in order to obtain the wanted results? Should the calculations be executed locally or on a server? How can the quality of data be improved? How can the data best be evaluated? These problems are addressed by the design of a streamlined approach of how to create an MCS-application while having all these problems in mind. In order to design this approach, an exhaustive literature research on existing MCS-applications was done and to validate this approach a new application was designed with its help. The procedure of designing and implementing this application went smoothly and thus shows the applicability of the approach
Konzeption und Realisierung einer Backend-Anwendung als Basis eines Content Management Systems für mobile Anwendungen
No full textDie Evolution des Internets von statischen Dokumenten zu häufig aktualisierten Webseiten mit digitalen Inhalten unterschiedlicher Art hat zur Etablierung von Content Management Systemen beigetragen. Diese vereinfachen die Entwicklung erheblich, indem sie dem Entwickler viele Entwicklungsschritte abnehmen. Weitverbreitete CMS wie WordPress ermöglichen es Nutzern, dynamische Webseiten zu erstellen und bieten dafür einen Baukasten zum Generieren der Benutzeroberfläche. Durch die Etablierung der Smartphones ist es allerdings nötig geworden, Inhalte sowohl auf Webseiten als auch auf mobilen Applikationen darzustellen. Traditionelle CMS kommen hier an ihre Grenzen und moderne Systeme bieten häufig nur die Möglichkeit, eine Schnittstelle zu definieren, aber keine Oberflächen.
Das Ziel dieser Masterarbeit ist die Entwicklung einer Backendanwendung für ein CMS, welches für mobile Applikationen optimiert ist und mittels einer Webanwendung bedient werden kann. Hierfür wird ein detailliertes Konzept vorgestellt, das in Teilen implementiert und validiert wurde. Mit dem vorgestellten CMS können strukturierte, wiederverwendbare Inhalte und deren Benutzeroberflächen definiert werden. Anhand dieser wird eine Schnittstelle erstellt, die von einer mobilen Anwendung angesprochen werden kann. Außerdem werden typische Anforderungen wie Projekt- und Versionsverwaltung unterstützt. Soll eine Schnittstelle veröffentlicht werden, wird anhand der in dieser Arbeit implementierten Backendanwendung ein Build-Prozess angestoßen. In diesem wird eine weitere Backendanwendung generiert, die die im Vorhinein definierte Schnittstelle bereitstellt, so dass eine mobile Client-Anwendung diese ansprechen kann. Das Ergebnis dieser Arbeit ist eine Backendanwendung, die die Basis des Gesamtsystems bildet