1752 research outputs found
Sort by
Conception and realization of an EMA-assisted mHealth application for daily measurements of stress
No full textNowadays, many people have to cope with a high stress level. Current trends on the market for mobile applications show significant increases in amount of mHealth apps targeting many different groups and issues. The development of smart devices in the last years holds potential benefits for end users as well as companies and research institutes. Ulm University therefore develops different platforms for specific chronic disorders or specific life situations, one of them aiming at stress measurements - TrackYourStress. The goal of this thesis was to increase the reach of the TrackYourStress platform. Besides the existing website [1], a mobile application that is intuitive and user-friendly has been developed now as well. This paper presents the architecture and design decisions that have been made throughout the development process
Statistical Analysis and Clustering of Tinnitus related Data with respect to the perceived Symptoms
No full textA lot of people suffer from chronic diseases. Sometimes, cause or treatment methods are not well-known or well-researched. In order to gain a better understanding, personal data is collected. Afterwards, the collected data can be analyzed using a huge set of different techniques. One of these techniques is cluster analysis. Cluster analysis is mostly used to group a data set into multiple smaller sets. The new identified sets contain only data points which are similar to each other. In this thesis, we are evaluating popular clustering algorithms and test them on our tinnitus related data set. Data points were collected beforehand from applications like TrackYourTinnitus and TrackYourHearing. Both applications provided questions with predefined answers. The purpose of these applications will be addressed in this work. Also, all relevant algorithms are explained in detail. Furthermore, advantages and disadvantages of each approach are discussed. One approach that is considered in this work is Latent Class Analysis. It is a special case of Structural Equation Modeling which in general is a statistical modeling technique primarily used in behavioral science. We also make use of two well-known machine learning clustering algorithms. The two other approaches are K-Means/K-Modes clustering and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). K-Means/K-Modes clustering and DBSCAN are both unsupervised machine learning algorithm whose goal it is to
find appropriate clusters. In the end of this work, the results are evaluated. The mayor goal of this work is to gain a better understanding of tinnitus perception for individuals and their
clusters
Differential Analysis of Acoustical Smartphone Recording Capabilities - a Contribution towards Smartphone-modulated Perception of Tinnitus
Get PDFLoud noise is a common risk factor for physical and mental health in our industrialized world, which can trigger different sorts of health issues like permanent hearing loss and tinnitus. To mitigate noise-induced problems in daily life, smartphones can be used as an easy way to observe noise levels. As recording quality differs depending on smartphone models and calibration techniques, standardized methods are needed to acquire comparable results. To examine such possibilities in more detail, several acoustical experiments were performed regarding the recording capabilities of in-build smartphone microphones compared to an external microphone to figure out optimal smartphone recording conditions as this further increases measurement accuracy. Additionally, various different calibration approaches differing in effort and accuracy are evaluated. Results show that smartphones are capable of measuring sound pressure levels accurately with only small deviations of about +-3 dB(A). Moreover, smartphone microphones are heavily frequency dependent, which is why an approach was presented to normalize for these variations. Gathered calibration data was further brought in conjunction with sound perception data of tinnitus probands, to show an application in health issues. The presented methods provide a straightforward approach to measure sound levels with a smartphone and compare them to other device conditions, opening the use of smartphones in the modulation of sound perception in tinnitus and other conditions
Driver Assistance for Safe and Comfortable On-Ramp Merging Using Environment Models Extended through V2X Communication and Role-Based Behavior Predictions
No full textStay Present with Your Phone: A Systematic Review and Standardized Rating of Mindfulness Apps in European App Stores
No full textMindfulness-based interventions show positive effects on physical and mental health. For a better integration of mindfulness techniques in daily life, the use of apps may be promising. However, only a few studies have examined the quality of mindfulness apps using a validated standardized instrument. This review aims to evaluate the content, quality, and privacy features of mindfulness-focused apps from European commercial app stores
How to Deal with Inaccurate Sensor Data?
No full textA lot of domains and applications rely on high quality sensor data. In chemical processes, the stability of the process is critical, while in mobile health apps the well-being of the patient is being involved. Contrary to chemical processes, mobile health apps feature a lot of sensors as it is very easy to collect huge amounts of sensor data using techniques like mobile crowdsensing. For example, the Apple Heart Study has collected the data of over 400,000 users. In mobile health apps, sensor faults are more likely due to the larger number of sensors and they are harder to predict because each user has their own device with a potentially different kind of sensor like it is the case with TYT. In this work, we are going to primarily focus on the domain of mobile health apps that are powered by mobile crowdsensing like the Apple Heart Study or TYT. Studies and research on the sensed data allow the processing of large amounts of data that would otherwise be very difficult with a conventional study. However, this flexibility also comes with a cost. While in a conventional study, every participant can use the same measurement device, a study based on mobile crowdsensing involves a huge number of different device types. As previously told, these different device types reduce the predictability of sensor faults. That’s why our goal should be to develop an algorithm, which can detect and identify sensor faults in mobile health data sets. Devices, where the faults are too severe, should be excluded from the data set. In addition to the sensed data, the algorithm should also use additional information that is gathered along with the sensor data. For example, this extra information are the answers to the questions that rate the tinnitus severity in the case of TYT
Design and Implementation of a Generic Framework for Rule-based Automated User Role Management
Get PDFMany systems that host groups of users, like social media platforms, provide solutions or tools for users and groups of users. Within these groups, there can exist roles, which again might be connected to permissions. The role model itself can vary from system to system. Some are hierarchical, some have flat hierarchies, some are related to the permissions, others with notifications. Decoupling the role model implementation from the rest of the system has multiple advantages, such as achieving automatic role assignment more easily and being able to change a role model on the fly. Within this master thesis, challenges of automated role assignment are examined and necessary elements for how a development tool can help are distilled. The main contribution is the tool karmantra, which allows to integrate arbitrary role models in software projects and lets developers extend or alter them. The tool is kept in a very generic way to be expandable easily. With this tool, a step is taken towards decoupled and transparent role systems, that can not only serve the needs of common commercial platform needs
Learning to Read by Learning to Write: Evaluation of a Serious Game to Foster Business Process Model Comprehension
Get PDFBackground: The management and comprehension of business process models are of utmost importance for almost any enterprise. To foster the comprehension of such models, this paper has incorporated the idea of a serious game called Tales of Knightly Process.
Objective: This study aimed to investigate whether the serious game has a positive, immediate, and follow-up impact on process model comprehension.
Methods: A total of two studies with 81 and 64 participants each were conducted. Within the two studies, participants were assigned to a game group and a control group (ie, study 1), and a follow-up game group and a follow-up control group (ie, study 2). A total of four weeks separated study 1 and study 2. In both studies, participants had to answer ten comprehension questions on five different process models. Note that, in study 1, participants in the game group played the serious game before they answered the comprehension questions to evaluate the impact of the game on process model comprehension.
Results: In study 1, inferential statistics (analysis of variance) revealed that participants in the game group showed a better immediate performance compared to control group participants (P<.001). A Hedges g of 0.77 also indicated a medium to large effect size. In study 2, follow-up game group participants showed a better performance compared to participants from the follow-up control group (P=.01); here, a Hedges g of 0.82 implied a large effect size. Finally, in both studies, analyses indicated that complex process models are more difficult to comprehend (study 1: P<.001; study 2: P<.001).
Conclusions: Participants who played the serious game showed better performance in the comprehension of process models when comparing both studies
Shades Of Noise: Konzeption und Realisierung einer mobilen Interventionsapp zur Unterstützung von Tinnituspatienten mithilfe gezielter auditorischer Stimulation
Get PDF10-15% der Menschheit leiden häufig oder konstant unter Tinnitusbeschwerden. Etwa 1-2% haben starke Beschwerden, sodass sie in ihrer Lebensqualität eingeschränkt sind. Durch die demographisch alternde Gesellschaft steigert sich dieser Anteil weiter. Bis heute gibt es keine generell anwendbare Heilung für die durch Tinnitus hervorgerufene Geräuschwahrnehmung. Im Zuge dieser Arbeit wird eine mobile iOS-Anwendung zur Durchführung von Studien und der Erfassung von Datensätzen bezüglich der auditorischen Stimulation als Behandlungsmaßnahme für Tinnituserkrankte entwickelt. Mit dem in dieser Arbeit entwicklten Prototypen soll gezielt der Tinnitus der Studienteilnehmer per auditorischer Stimulation gemildert werden. Die zugehörigen Datensätze sollen für Studien auswertbar erfasst werden. Diese Arbeit führt zunächst eine Anforderungsanalyse durch und stellt daraus abgeleitet ein Architekturkonzept zur Verfügung. In dem realisierten Prototypen stehen den Benutzern eine Vielzahl an Geräuschen zur Verfügung. Diese sind teilweise natürliche Geräusche und teilweise generierte Geräusche. Nach der auditorischen Stimulation wird der Benutzer aufgefordert, die Verbesserung bezüglich seiner Beschwerden zu bewerten. Diese Daten werden zusammen mit der Dauer der Stimulation und dem angehörten Geräusch gespeichert
Entwicklung einer Web Scraping Plattform für mobile Anwendungen
Get PDFSmartphones sind für viele Menschen zu alltäglichen Begleitern geworden. Damit einher geht auch eine breite Auswahl an Apps für diese. Für Forschungszwecke, Erstellung von Statistiken, Archivierung oder ähnliche Szenarien ist es nützlich, eine einfache Möglichkeit zu haben, um möglichst systematisch und automatisiert Metadaten über solche Apps zu erhalten. Da es für die großen App Stores keine oder nur unzulängliche öffentliche API's oder anderweitige Schnittstellen zur Datenabfrage gibt, ist es notwendig, auf Web Scraping zurückzugreifen.
In dieser Arbeit wird ein solcher Web Scraper für den Google Play Store und den Apple App Store entwickelt, welcher basierend auf den Webseiten der Stores die relevanten Daten extrahiert. Dabei wird zunächst darauf eingegangen, wie die Daten übertragen und repräsentiert werden und anschließend eine Implementierung entwickelt, die es möglichst einfach machen soll, neue Stores zu ergänzen und Änderungen seitens der Stores umzusetzen. Zuletzt wird die Funktionalität dieser Scrapers in Form einer REST-API zur Verfügung gestellt, um einen Ressourcen-zentrierten Zugriff zu erlauben und Programmiersprachen-Unabhängigkeit zu erlangen