1752 research outputs found
Sort by
Evaluation moderner Browserschnittstellen zur Entwicklung mobiler Anwendungen (PWA)
No full textDas Setzen auf plattformübergreifende Lösungen, bei der Entwicklung von Softwareprodukten, hat diverse Vorteile. Zum einen werden Arbeitskräfte und Infrastruktur gespart, wodurch die Kosten gesenkt werden. Zum anderen wird der potentielle Nutzerkreis vergrößert. Da auf den meisten Endgeräten ein moderner Browser zur Verfügung steht, stellt das Web eine mögliche Lösung dar. Mehrere Organisationen und Arbeitsgruppen spezifizieren regelmäßig neue Webschnittstellen und sorgen für deren Standardisierung. Das Konzept der Progressive Web Apps nutzt diese Schnittstellen, um dem Nutzer Funktionen zur Verfügung zu stellen, welche nativen Anwendungen vorbehalten waren. Herausforderung hierbei ist die Tatsache, dass Browserhersteller nicht zur Implementierung dieser Schnittstellen verpflichtet sind. Mit dem Ziel, den Entwicklungsstand diverser Schnittstellen zu untersuchen, werden in der vorliegenden Arbeit mehrere Prototypen erstellt. Mit Hilfe dieser Prototypen kann getestet werden, welche Funktionen der jeweils ausführende Browser unterstützt. Auf Grundlage der daraus gewonnenen Erkenntnisse wird deutlich, dass die Nutzung einiger Schnittstellen gewissen Einschränkungen unterliegt. Progressive Web Apps stellen somit noch keinen vollwertigen Ersatz für native Applikationen dar
Towards Incorporating Contextual Knowledge into the Prediction of Driving Behavior
Full text linkPredicting the behavior of surrounding traffic
participants is crucial for advanced driver assistance systems and autonomous driving. Most researchers however do not consider contextual knowledge when predicting vehicle motion. Extending former studies, we investigate how predictions are affected by external conditions. To do so, we categorize different kinds of contextual information and provide a carefully chosen definition as well as examples for external conditions. More precisely, we investigate how a state-of-the-art approach for lateral motion prediction is influenced by one selected external condition, namely the traffic density. Our investigations demonstrate that this kind of information is highly relevant in order to
improve the performance of prediction algorithms. Therefore,
this study constitutes the first step towards the integration of such information into automated vehicles. Moreover, our motion prediction approach is evaluated based on the public highD data set showing a maneuver prediction performance with areas under the ROC curve above 97 % and a median lateral prediction error of only 0.18 m on a prediction horizon of 5 s
Measuring Mental Effort for Creating Mobile Data Collection Applications
Full text linkTo deal with drawbacks of paper-based data collection procedures, the QuestionSys approach empowers researchers with none or little programming knowledge to flexibly configure mobile data collection applications on demand. The mobile application approach of QuestionSys mainly pursues the goal to mitigate existing drawbacks of paper-based collection procedures in mHealth scenarios. Importantly, researchers shall be enabled to gather data in an efficient way. To evaluate the applicability of QuestionSys, several studies have been carried out to measure the efforts when using the framework in practice. In this work, the results of a study that investigated psychological insights on the required mental effort to configure the mobile applications are presented. Specifically, the mental effort for creating data collection instruments is validated in a study with N=80 participants across two sessions. Thereby, participants were categorized into novices and experts based on prior knowledge on process modeling, which is a fundamental pillar of the developed approach. Each participant modeled 10 instruments during the course of the study, while concurrently several performance measures are assessed (e.g., time needed or errors). The results of these measures are then compared to the self-reported mental effort with respect to the tasks that had to be modeled. On one hand, the obtained results reveal a strong correlation between mental effort and performance measures. On the other, the self-reported mental effort decreased significantly over the course of the study, and therefore had a positive impact on measured performance metrics. Altogether, this study indicates that novices with no prior knowledge gain enough experience over the short amount of time to successfully model data collection instruments on their own. Therefore, QuestionSys is a helpful instrument to properly deal with large-scale data collection scenarios like clinical trials
mHealth Crowdsensing Cloud-Lösung - mHealth Crowdsensing Cloud-Lösungs-Konzept für TrackYourTinnitus
No full textTrack-your-Tinnitus (TyT) ist eine mHealth Crowdsensing Applikation. Nutzer können sich eine App auf ihr Smartphone laden, diese fordert die Nutzer dann mehrmals am Tag auf Fragebögen über den aktuellen Zustand ihres Tinnitus zu beantworten. Diese Art der Befragung wird Ecological Momentary Assesment genannt und verspricht bessere Genauigkeit im Vergleich zu klassischen Befragungen. TyT hat seinen Server in lokalen Rechenzentren an der Universität Ulm. Da die Vorteile der Cloud vielversprechend sind und TyT eine hohe Nutzeranzahl hat, ist eine Übersetzung von TyT in die Cloud sinnvoll. Da von TyT aber medizinische persönliche Daten verarbeitet werden, stellt sich hierbei der Datenschutz als Hindernis heraus. Diese Arbeit gibt zuerst einen Überblick über geltenden Datenschutz und entwickelt daraufhin ein Konzept für TyT. Die Ergebnisse zum Datenschutz in der Cloud ergeben, dass entweder eine Trusted Cloud verwendet werden muss oder die verarbeitenden Daten anonymisiert werden müssen. Das schlussendliche Konzept enthält einen zentralen Server der sich in einer Trusted Cloud befindet und ein global einsetzbaren Server, der für die Datensammlung zuständig ist und nur anonymisierte Daten sammelt. Das Fazit ist, dass das entwickelte Konzepte nicht den kompletten Service von TyT in der Cloud darstellen sollte, da es keine Möglichkeit für personalisiertes Feedback liefert, sondern es kann einen zusätzlichen Service darstellen, welcher globale Datensammlung erleichtert. Das Konzept liefert auch Anstöße in andere zu erforschende Richtungen, so ermöglicht das Konzept z. B. Edge Computing
Konzeption und Realisierung eines Patienten-Edukationsmoduls für eine multizentrische und multinationale mHealth-App für eine paneuropäische Tinnitus-Studie
Full text linkDiese Arbeit soll zeigen, wie ein Edukationsmodul einer multizentrischen und multinationalen mHealth-App entwickelt werden kann, um Tinnitus-Patienten zu unterstützen. Mithilfe diesem und weiteren Modulen sollen im Rahmen des europäischen UNITI-Projektes Studien durchgeführt werden, um mögliche weitere Behandlungsmethoden zu identifizieren
Developing an approach to automate the building and deployment of configurable Progressive Web Applications
Full text linkThe omnipresence of smartphones enables new methods of collecting data for research purposes on a certain research group. One possibility is the use of Ecological Momentary Assessments where a person completes assessments in his natural environment and chronologically close to the event he has to assess. This reduces the distortion of the research data compared to a retrospective assessment. Combined with Mobile Crowdsensing, where the sensors of the smartphone are used to collect additional context data, new insights on topics like chronic diseases can be gained.
However, there is no generic software solution to build and run EMA applications in combination with Mobile Crowdsensing to collect research data. In this thesis, a framework to automate the building and deployment process of configurable Progressive Web Applications (PWAs) is implemented. The thesis examines related projects to define the functional and non-functional requirements for the implementation. In the next step, a concept with technological and architectural aspects and an interface design for the web application are developed. The resulting implementation of the framework covers the processes of configuring, building and running the PWA, as well as the functionality of the PWA with notification scheduling, sensor usage and offline access. A comparison between the requirements and the actual implementation shows that the framework achieved the goal to develop an approach for building and deploying configurable PWAs
Entwurf and Implementierung eines Frameworks für Mobile Context-Awareness im Bereich eHealth
Full text linkDas Ziel der vorliegenden Bachelorarbeit war es, eine Middleware zu entwickeln, welche die Sensoren von Android- und iOS-Geräten nutzt, um Informationen über die Situation, in welcher sich das Gerät und sein Nutzer befinden, zu erlangen. Bei diesen Informationen handelt es sich im speziellen um den Ort, an welchem sich das Smartphone befindet, seine Position relativ zum Nutzer und die gegenwärtige Fortbewegungsart des Nutzers. Von den verfügbaren Sensoren wurden das GPS, Gyroskop, Accelerometer und Magnetometer verwendet. Es wurden sowohl frühere Projekte ähnlicher Art betrachtet als auch eigene Messungen in praxisnahen Situationen durchgeführt. Die Umsetzung fand mithilfe von Ionic statt. Die Bachelorarbeit ist interessant für Personen, welche selbst eine derartige Middleware entwickeln oder eine bereits bestehende Middleware für kontextsensitive Anwendungen in ein anderes Projekt integrieren wollen
A Fleet Learning Architecture for Enhanced Behavior Predictions during Challenging External Conditions
Full text linkAlready today, driver assistance systems help to make daily traffic more comfortable and safer. However, there are still situations that are quite rare but are hard to handle at the same time. In order to cope with these situations and to
bridge the gap towards fully automated driving, it becomes necessary to not only collect enormous amounts of data but rather the right ones. This data can be used to develop and validate the systems through machine learning and simulation
pipelines. Along this line this paper presents a fleet learning-based architecture that enables continuous improvements of systems predicting the movement of
surrounding traffic participants. Moreover, the presented architecture is applied to a testing vehicle in order to prove the general feasibility of the system. Finally, it is shown that the system collects meaningful data which are helpful to improve the underlying prediction systems
Deep Learning in the Context of Inventory Valuation in the Pharmaceutical Industry
No full textArtificial intelligence is currently one of the hot topics in business in general and thus also in the pharmaceutical industry. Due to the increasing digitalization of processes, the amount of data is growing daily. Data always also means a kind of "knowledge" that can be subsequently used by applying the right methods. With over 23,000 different stock positions, Teva ratiopharm offers a wide range of local inventory at the site in Ulm, Germany. Recurrently, from an accounting perspective, this inventory must be calculated to its value for the item on the balance sheet. With the amount of inventory, it is currently not possible for humans to value each item individually – there is a general average evaluation. Due to the mass of data, complex patterns and dependencies can be hidden in data that humans are not able to recognize with the eye. Consequently, the more abstract granularity of the valuation does not allow any conclusions to be drawn about inventory optimization. In this master thesis, we present the development and implementation of a prediction model, which is based on historical destruction data and is supposed to predict future destruction of every single stock position. By predicting the destruction of a stock item, its residual value can be easily derived. We only focus on the area of deep learning in order to be able to go into more detail about the methodologies and functionalities in this area. By using neural feedforward networks, the process of inventory valuation within Teva ratiopharm will be optimized and automated. In addition to the application of neural networks, rule-based manual process steps are automated using the robotic process automation approach. This work describes one of the first Teva ratiopharm internal projects towards artificial intelligence. The project should also include the development of knowledge and experience in this field and the networking of structures and people within the company for future digitalization projects. Furthermore, the topic artificial intelligence is still quite new at Teva ratiopharm and digital transformation has just started.
Therefore, a kind of trust in artificial intelligence and other approaches in this direction must first be established within the organization and among employees. An important component of trust describes the explainability of such models. We will take a closer look at three different
approaches in the area of explainable artificial intelligence and discuss the topic in the context
of the inventory valuation process
Conceptualization and Realization of a Database Migration Path for an International and mHealth Tinnitus Database
Full text linkThe mobile crowdsensing platform TrackYourTinnitus (TYT) was created to monitor and visualize fluctuations of tinnitus perception by affected individuals using smart devices. The platform aims to gather data of tinnitus patients for research purposes and to help those affected to better understand the fluctuations of tinnitus perception. Users have to answer specific questionnaires to assess tinnitus perception and tinnitus-related parameters during their daily routine. The gathered data from the questionnaires are stored in the MariaDB database running on the back-end of the application. In the future, the data of TrackYourTinnitus will be merged with clinical databases to broaden the researches related to the tinnitus symptom. Consequently, the amount of data stored in the relational database will notably increase. Additionally, MRI scans will be joined to patients? data to allow a better overview of the tinnitus development for individuals. For this purpose, it is considered to look for an alternative system for hosting the TYT database, since the current database running on MariaDB does not deliver the performance required. This work attempts to transfer the TrackYourTinnitus database from MariaDB to SQL Server. The system migration aims to ensure smooth database operations when dealing with data on a large scale as well as to benefit from the advanced features of T-SQL, the query language used by SQL Server