Auflistung nach Autor:in "Abdelrahman, Yomna"
1 - 2 von 2
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragEnthusiasts, Pragmatists, and Skeptics: Investigating Users’ Attitudes Towards Emotion- and Personality-Aware Voice Assistants across Cultures(Mensch und Computer 2022 - Tagungsband, 2022) Ma, Yong; Abdelrahman, Yomna; Drewes, Heiko; Petz, Barbarella; Alt, Florian; Hussmann, Heinrich; Butz, AndreasVoice Assistants (VAs) are becoming a regular part of our daily life. They are embedded in our smartphones or smart home devices. Just as natural language processing has improved the conversation with VAs, ongoing work in speech emotion recognition also suggests that VAs will soon become emotion- and personality-aware. However, the social implications, ethical borders and the users’ general attitude towards such VAs remain underexplored. In this paper, we investigate users’ attitudes towards and preferences for emotionally aware VAs in three different cultures. We conducted an online questionnaire with N = 364 participants in Germany, China, and Egypt to identify differences and similarities in attitudes. Using a cluster analysis, we identified three different basic user types (Enthusiasts, Pragmatists, and Skeptics), which exist in all cultures. We contribute characteristic properties of these user types and highlight how future VAs should support customizable interactions to enhance user experience across cultures.
- ZeitschriftenartikelVPID: Towards Vein Pattern Identification Using Thermal Imaging(i-com: Vol. 18, No. 3, 2019) Faltaous, Sarah; Liebers, Jonathan; Abdelrahman, Yomna; Alt, Florian; Schneegass, StefanBiometric authentication received considerable attention lately. The vein pattern on the back of the hand is a unique biometric that can be measured through thermal imaging. Detecting this pattern provides an implicit approach that can authenticate users while interacting. In this paper, we present the Vein-Identification system, called VPID. It consists of a vein pattern recognition pipeline and an authentication part. We implemented six different vein-based authentication approaches by combining thermal imaging and computer vision algorithms. Through a study, we show that the approaches achieve a low false-acceptance rate (“FAR”) and a low false-rejection rate (“FRR”). Our findings show that the best approach is the Hausdorff distance-difference applied in combination with a Convolutional Neural Networks (CNN) classification of stacked images.