Logo des Repositoriums

Auflistung nach Autor:in "Gebhard, Patrick"

1 - 2 von 2
  • Workshopbeitrag
    An analysis of the effects of swarm cycling on cyclists’ stress levels
    (Mensch und Computer 2023 - Workshopband, 2023) Schaffer, Stefan; Meng, Linglong; Hemdane, Alaaeddine; Wolf, Katrin; Tsovaltzi, Dimitra; Chehayeb, Lara; Gebhard, Patrick
    Swarm cycling has been proposed in previous researches as a novel concept for urban mobility, by adopting the "safety in number" approach, to enhance the visibility of cyclists in urban traffic and to increase the safety of cyclists. To investigate the effects of swarm cycling on the stress level of bicyclists, we conducted an experiment in an enclosed traffic training field with stressors, such as construction sites, etc. to simulate the stress situations in real traffic. A stress detection system utilizing the Galvanic Skin Response (GSR) sensor and an Android application was developed to monitor participants’ stress responses during cycling. In this research, 21 participants engaged in various cycling scenarios, including cycling alone, cycling within a swarm, and cycling in different positions within the swarm. GSR signal data were collected to quantify the number of stress peaks experienced by each participant during the rides. The data were subjected to statistical analysis to compare stress levels among the different cycling scenarios. The results of the statistical analysis indicate that swarm cycling has a positive impact on individual cyclist stress levels compared to cycling alone. However, there was no statistically significant difference in stress levels observed among different cycling positions within the swarm. This research provides insights into the potential benefits of swarm cycling as an urban mobility solution, emphasizing its positive influence on cyclist stress levels, thus encouraging the adoption of this novel concept to enhance safety and comfort for urban cyclists.
  • Zeitschriftenartikel
    Designing Emotions
    (KI - Künstliche Intelligenz: Vol. 25, No. 3, 2011) Kipp, Michael; Dackweiler, Thomas; Gebhard, Patrick
    While current virtual characters may look photorealistic they often lack behavioral complexity. Emotion may be the key ingredient to create behavioral variety, social adaptivity and thus believability. While various models of emotion have been suggested, the concrete parametrization must often be designed by the implementer. We propose to enhance an implemented affect simulator called ALMA (A Layered Model of Affect) by learning the parametrization of the underlying OCC model through user studies. Users are asked to rate emotional intensity in a variety of described situations. We then use regression analysis to recreate these reactions in the OCC model. We present a tool called EMIMOTO (EMotion Intensity MOdeling TOol) in conjunction with the ALMA simulation tool. Our approach is a first step toward empirically parametrized emotion models that try to reflect user expectations.