Logo des Repositoriums

Auflistung nach Schlagwort "multimodal"

1 - 5 von 5
  • Konferenzbeitrag
    Google Glass++: Evaluating Multimodal Alarms on Google Glass
    (Mensch und Computer 2019 - Tagungsband, 2019) Cobus, Vanessa; Busse, Steffen; Heuten, Wilko
    Around 350 alarms per patient a day make intensive care units a loud, stressful, and highly cognitive demanding working environment for nurses. Each alarm needs to be identified and evaluated regarding its urgency which requires to interrupt nursing tasks. Alarm fatigue is a prominent result of alarm exposure and a well-known problem for caregivers, causing a desensitization and delayed response time for alarms. To counteract this issue, we suggest to forward patient alarms and alarm relevant information just to the responsible nurse, using head-mounted displays. In a first user study, we evaluated the suitability of patient relevant information displayed via Google Glass EE in combination with peripherally visual and audible alarms during nursing specific loads. Therefore, we enhanced Glass with a peripheral light display. For both conditions (light/sound), the readability of the display, and the alarms' identifiability and distraction, were rated as good. Finally, our prototype was rated as comfortable.
  • Workshopbeitrag
    Interacting with Wheelchair Mounted Navigator Robot
    (Mensch und Computer 2019 - Workshopband, 2019) Yamazaki, Akiko; Yamazaki, Keiichi; Arano, Yusuke; Saito, Yosuke; Iiyama, Emi; Fukuda, Hisato; Kobayashi, Yoshinori; Kuno, Yoshinori
    Currently, robotic researchers focus on developing robot systems that are explicitly designed to operate cooperatively with people in public, and provide the resources for projections for humans in public places.Our socio-technological project, engineers developed a robotic wheelchair with attaching a robot in order to provide embodied projective signals to human and designed two settings for the robot’s behavior. One is the robot turns its face towards the human (Face-to-Face model), the other is robot turns its face and they turn around its body in order to index where to go (Body Torque model). The reasons of attaching a robot to a robotic wheelchair and designed two settings are, by analysis of sociologiosts, we reveal how embodied actions of the robot as a resource for projection and considered what kind of projection are possible and how such projections provide the coordination of co-operative actions between multiple people in the public places.
  • Konferenzbeitrag
    MobiBits: Multimodal Mobile Biometric Database
    (BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Bartuzi, Ewelina; Roszczewska, Katarzyna; Trokielewicz, Mateusz; Białobrzeski, Radosław
    This paper presents a novel database comprising representations of five different biometric characteristics, collected in a mobile, unconstrained or semi-constrained setting with three different mobile devices, including characteristics previously unavailable in existing datasets, namely hand images, thermal hand images, and thermal face images, all acquired with a mobile, off-the-shelf device. In addition to this collection of data we perform an extensive set of experiments providing insight on benchmark recognition performance that can be achieved with these data, carried out with existing commercial and academic biometric solutions. This is the first known to us mobile biometric database introducing samples of biometric traits such as thermal hand images and thermal face images. We hope that this contribution will make a valuable addition to the already existing databases and enable new experiments and studies in the field of mobile authentication. The MobiBits database is made publicly available to the research community at no cost for non-commercial purposes.
  • Textdokument
    Pool Adjacent Violators Based Biometric Rank Level Fusion
    (BIOSIG 2017, 2017) Susyanto,Nanang
    We propose a new method in rank level fusion for biometric identification. Our method is based on the pool adjacent violators (PAV) algorithm after the ranks have been transformed to the approximated scores.We then show that our method outperforms various approaches that commonly used in biometric rank level fusion on NIST BSSR1 multimodal database.
  • Konferenzbeitrag
    PROTECT Multimodal DB: fusion evaluation on a novel multimodal biometrics dataset envisaging Border Control
    (BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Sequeira, Ana F.; Chen, Lulu; Ferryma, James; Galdi, Chiara; Chiesa, Valeria; Dugelay, Jean-Luc; Maik, Patryk; Gmitrowicz, Piotr; Szklarski, Lukasz; Prommegger, Bernhard; Kauba, Christof; Kirchgasser, Simon; Uhl, Andreas; Grudzien, Artur; Kowalski, Marcin
    This work presents a novel multimodal database comprising 3D face, 2D face, thermal face, visible iris, finger and hand veins, voice and anthropometrics. This dataset will constitute a valuable resource to the field with its number and variety of biometric traits. Acquired in the context of the EU PROTECT project, the dataset allows several combinations of biometric traits and envisages applications such as border control. Based upon the results of the unimodal data, a fusion scheme was applied to ascertain the recognition potential of combining these biometric traits in a multimodal approach. Due to the variability on the discriminative power of the traits, a leave the n-best out fusion technique was applied to obtain different recognition results.