Logo des Repositoriums

Auflistung nach Autor:in "Schmitz, Martin"

1 - 10 von 90
  • Konferenzbeitrag
    A Digital Application for Digital Natives to Improve Orientation Competence and Career Choice Decisions
    (Mensch und Computer 2022 - Tagungsband, 2022) Brandenburger, Jessica; Mergan, Hamid; Schametat, Jan; Vergin, Annika; Engel, Alexandra; Janneck, Monique
    Many young people find it difficult to choose a career. The range of options is diverse and often opaque. A digital application is being developed as part of the JOLanDA project - Improving the orientation skills of young people in rural regions in biographical decision-making processes - funded by the Federal Ministry of Education and Research. The aim is to improve the orientation of young people and to promote career choice decisions. Especially young people from rural regions are often under a double burden: they have to make a career choice decision and at the same time consider whether this profession can be practiced in their region. This is often associated with a migration decision for them (leave or stay?). By using various methods, such as gamification, digital natives who have grown up with technologies of the digital age [18] are to be prepared for the career orientation phase in a playful way. On the platform, young people go on a journey of discovery, they can start different expeditions and walk along discovery paths where they can find out what might suit them professionally and what makes them happy. The application aims to raise awareness of the dynamics of biographical decisions.
  • Konferenzbeitrag
    A Speech-Based AI for Political Participation
    (Mensch und Computer 2022 - Tagungsband, 2022) Bräuer, Paula; Mazarakis, Athanasios
    This study presents a first experimental approach for the use of intelligent virtual assistants (IVA) to support political participation. In order to involve as many citizens as possible in participatory political processes, such as the search for a repository site for high-level radioactive waste, IVAs could offer a possibility to convey information in an interactive way and to arouse interest in such complex topics. However, the question arises whether an IVA can adequately convey such a topic and ensure appropriate usability despite many complex dialogues with the user. The explorative study presents the results with a prototypically implemented Amazon Alexa Skill. Compared to a website that addresses the same questions as the Skill, a slightly poorer usability was found. Based on this first study, various questions arose that need to be investigated in future studies. These include questions related to the trustworthiness of such applications and challenges related to the auditive representations of different political opinions.
  • Konferenzbeitrag
    Accessible Mobile Map Application and Interaction for People with Visual or Mobility Impairments
    (Mensch und Computer 2022 - Tagungsband, 2022) Rottmann, Sebastian; Loitsch, Claudia; Weber, Gerhard
    Modern map applications provide their users with a multitude of functions that can be used through different forms of interactions. However, many map providers do not adequately meet the needs of users with blindness, low vision or mobility impairments. Therefore, we investigated interaction concepts for an accessible mobile map application. Theses concepts not only focus on the user interface, but also on the map content, which should be accessible to the target groups as well. We conducted a pilot study in which nine participants tested the usability and accessibility of the developed application. Our results show that we created a viable alternative for making map content accessible to people with different needs by providing an additional list view. Feedback from subjects indicated that in future, the listed items need to be meaningfully classified and ordered such that users with visual impairments or blindness can use them to form a mental picture of their surroundings.
  • Konferenzbeitrag
    Activity Recognition over Temporal Distance using Supervised Learning in the Context of Dementia Diagnostics
    (Mensch und Computer 2022 - Tagungsband, 2022) Staab, Sergio; Bröning, Lukas; Luderschmidt, Johannes; Martin, Ludger
    In the case of neurological diseases, the progression of the disease can be detected by monitoring movements and activities. Documenting such monitoring requires time-consuming work, which can hardly be covered in the context of a constantly decreasing availability of nursing staff. In cooperation with two dementia residential communities, we incrementally develop a process that supports the nursing staff by providing an approach for a semiautomated documentation. This paper presents an approach to aggregate individual activities over a care period using smartwatches in combination with supervised learning algorithms. A smartwatch offers the opportunity to integrate sensor technology into a patient’s daily routine without disturbing them, as many patients already wear watches. We are investigating promising combinations of sensor technologies and supervised learning algorithms, collecting data from the accelerometer, heart rate sensor, gyroscope, gravity and position sensor at 20 Hz and sending it to a web server. The activities are then classified multiple times using Fast Forest, Logistic Regression and Support Vector Machines over a maintenance layer. We present an activity classification prototype over time distance for automated activity recognition, which, after a number of classifications and the likelihood of these, suggests to the nurse a statement of activities over the respective time period of a nursing shift, in the form of a completed documentation. In addition, the work provides an interpretation of how the knowledge gained can be used to recognise motor skills in the course of caring for patients with neurological diseases.
  • Konferenzbeitrag
    Adopting Just Another Digital Assistant or Establishing Social Interactions with a New Friend?
    (Mensch und Computer 2022 - Tagungsband, 2022) Carolus, Astrid; Wienrich, Carolin
    Social interactions have been exclusive to human-human interactions, until recently. However, modern technologies with adaptive and intelligent features such as smart speakers imitate human social characteristics and appear to be allegedly social interaction partners. Research going beyond the analysis of mere usage and conceptualizing devices as interaction partners is rare, also because studying the establishment of social interactions would require analyses over time. The present paper addresses this research desideratum and introduces a concept of a longitudinal study which involves the collection of different data types from different sources (online questionnaire, providers’ log files, interview) and interdisciplinary data analytical methods (social science, data science). Its cross-sectional and longitudinal research questions ask for the adoption and the usage of the usage of smart speakers, for the establishment of social interactions with the device. In sum, this study contributes to the research area by presenting a conceptual research model, which provides a framework for the systematic long-term analysis of both the adoption of technology over time as well as the establishment of potential social interactions.
  • Konferenzbeitrag
    AID-Watch - Smartwatch for People with Cognitive Impairments
    (Mensch und Computer 2022 - Tagungsband, 2022) Schneider, Rahel; Wendt, Hauke; Kuon, Alexander
    In many cases, individuals with cognitive impairments are unable to use basic daily living aids such as a watch and are therefore not able to plan or even go through their daily lives without additional help. For this reason, we developed iteratively and in collaboration with a potential user the product concept AID-Watch. The basic idea of AID-Watch is to replace the traditional wrist-watch with an individual and interactive daily schedule displayed on a Smartwatch. In general, a schedule consists of customizable symbols associated with the user's daily events. This way, users can follow the watch hand wandering past events, rather than common digits of a clock. Furthermore, AID-Watch is complemented by vibrotactile and auditory notification features of ordinary Smart-watches. AID-Watch has been validated in user tests, where we identified improvements in the ability to keep appointments independently, as well as a more extensive understanding of the daily structure. This technological aid could therefore not only relieve family members or caregivers, but also give people with cognitive impairments more independence and autonomy through better time perception.
  • Konferenzbeitrag
    Alexa, It’s Me! An Online Survey on the User Experience of Smart Speaker Authentication
    (Mensch und Computer 2022 - Tagungsband, 2022) Renz, Andreas; Baldauf, Matthias; Maier, Edith; Alt, Florian
    Verifying the identify of the speaker is a crucial requirement for security-critical voice-based services on smart speakers, such as transferring money or making online purchases. Whilst various studies have explored novel authentication mechanisms for voice based services, there is little research on the user experience of respective authentication methods. To address this gap, we conducted a comprehensive online survey (n=696). We compared five authentication methods (spoken PIN, biometrics, app with button/voice confirmation, card reader) regarding their perceived efficiency, security, ease of use, and error susceptibility. Additionally, we investigated users’ willingness to use security-critical services in banking and government. We found an overall preference to confirm actions triggered by voice by pressing a button on a mobile authentication app followed by PIN-based authentication. In contrast, biometric authentication by voice is considered unreliable, while applying a card reader is regarded secure, yet less convenient.
  • Konferenzbeitrag
    Analyzing Eye Tracking Data in Mirror Exposure
    (Mensch und Computer 2022 - Tagungsband, 2022) Döllinger, Nina; Göttfert, Christopher; Wolf, Erik; Mal, David; Latoschik, Marc Erich; Wienrich, Carolin
    Mirror exposure is an important method in the treatment of body image disturbances. Eye tracking can support the unaffected assessment of attention biases during mirror exposure. However, the analysis of eye tracking data in mirror exposure comes with various difficulties and is associated with a high manual workload during data processing. We present an automated data processing framework that enables us to determine any body part as an area of interest without placing markers on the bodies of participants. A short, formative user study proved the quality compared to the gold standard. The automatic processing and openness for different systems allow a broad range of applications.
  • Konferenzbeitrag
    An AR User Interface for the Evaluation of Visuospatial Abilities
    (Mensch und Computer 2022 - Tagungsband, 2022) Imenkamp, Charlotte; Hanert, Annika; Schönfeld, Robby; Bartsch, Thorsten; Woelk, Felix
    Early pathogen processes of Alzheimers dementia (AD) develop years before the time of diagnosis. The process starts in hippocampal regions, which play an important role in spatial cognitive abilities including spatial memory. The decrease of these abilities leads to deficits in orientation and navigation and has a high impact on everyday live. A simple, fast and exact evaluation of the spatial memory impairment could help to detect the disease at an early stage (e.g. during a regular screening) and could thus enable stopping or slowing down the process. This work aims at the development of such a screening tool by combining a version of the established Smith-Milner paradigm (SMP) [26, 27] for analysis of spatial-cognitive deficits with the technical possibilities of the augmented-reality (AR) technology. A new AR-application was developed and the user acceptance was evaluated with a first group of healthy subjects (N = 40). The user interface of the AR application was specifically tailored for easy use by older participants and non-technical physicians.
  • Konferenzbeitrag
    Auto-Generating Multimedia Language Learning Material for Children with Off-the-Shelf AI
    (Mensch und Computer 2022 - Tagungsband, 2022) Draxler, Fiona; Haller, Laura; Schmidt, Albrecht; Chuang, Lewis L.
    The unique affordances of mobile devices enable the design of novel language learning experiences with auto-generated learning materials. Thus, they can support independent learning without increasing the burden on teachers. In this paper, we investigate the potential and the design requirements of such learning experiences for children. We implement a novel mobile app that auto-generates context-based multimedia material for learning English. It automatically labels photos children take with the app and uses them as a trigger for generating content using machine translation, image retrieval, and text-to-speech. An exploratory study with 25 children showed that children were ready to engage to an equal extent with this app and a non-personal version using random instead of personal photos. Overall, the children appreciated the independence gained compared to learning at school but missed the teachers’ support. From a technological perspective, we found that auto-generation works in many cases. However, handling erroneous input, such as blurry images and spelling mistakes, is crucial for children as a target group. We conclude with design recommendations for future projects, including scaffolds for the photo-taking process and information redundancy for identifying inaccurate auto-generation results.