Techn. Hochsch., Diss.--Zürich, 2005.

Italian Polka is an experiment that builds a bridge between Music and the field of Costume Design. It explores the new relationship of integration and artistic possibility between Music, Costume Design, Dance, and Digital Art. This is also an attempt to participate in a new form of performing art: a combination of a live concert and a costume show. / text

Indiana University-Purdue University Indianapolis (IUPUI) / Biomechanical Big Data is of great significance to precision health applications, among which we take special interest in Physical Activity Detection (PAD). In this study, we have performed extensive research on deep learning-based PAD from biomechanical big data, focusing on the challenges raised by the need for real-time edge inference. First, considering there are many places we can place the motion sensors, we have thoroughly compared and analyzed the location difference in terms of deep learning-based PAD performance. We have further compared the difference among six sensor channels (3-axis accelerometer and 3-axis gyroscope). Second, we have selected the optimal sensor and the optimal sensor channel, which can not only provide sensor usage suggestions but also enable ultra-lowpower application on the edge. Third, we have investigated innovative methods to minimize the training effort of the deep learning model, leveraging the transfer learning strategy. More specifically, we propose to pre-train a transferable deep learning model using the data from other subjects and then fine-tune the model using limited data from the target-user. In such a way, we have found that, for single-channel case, the transfer learning can effectively increase the deep model performance even when the fine-tuning effort is very small. This research, demonstrated by comprehensive experimental evaluation, has shown the potential of ultra-low-power PAD with minimized sensor stream, and minimized training effort. / 2023-06-01

The World Health Organization (WHO) estimates 488 million people worldwide suffer from a visual impairment and of these about 327 million have severe visual impairments. Some individuals with severe visual impairments can navigate and orient independently in well-known surroundings, but even for these people independent navigation and orientation are likely to be a challenge in unfamiliar places. To overcome these challenges, assistive technologies have been developed to support independent wayfinding tasks; however, those with severe visual impairments often experience frustration when they try to use assistive technologies since these technologies lack address the environmental factors that influence their independent wayfinding. This research developed and evaluated the efficacy of a framework called an environmental user interface (EUI). In particular, this research explored whether or not the proposed EUI framework was effective when used with user-centered design (UCD) to design a wayfinding system to capture environmental requirements, thus aiding those with severe visual impairments. Two studies, the first of which consisted of a requirements elicitation and the second usability testing, were conducted. The studies revealed that the EUI framework was indeed more effective than the conventional UCD design method alone in identifying environmental factors, and participants with severe visual impairments preferred to use the prototype designed using UCD and the EUI framework. The proposed EUI framework was found to be an effective way to enhance the design process as it played an important role in eliciting a greater number of environmental factors, and hence produced a device that was preferred by the users with visual impairments. Both prototypes influenced how well the wayfinding tasks were performed by the five participants with severe visual impairments, but the prototype implemented based on the requirements elicited by UCD and the EUI framework was much preferred by the participants. / Ph. D.

International Telemetering Conference Proceedings / October 22-25, 2001 / Riviera Hotel and Convention Center, Las Vegas, Nevada / A systems engineering development for acquisition, transmission, processing, dissemination and display of information vital to combat casualty care and related first responder activities is presented. It utilizes a synergistic combination of two existing state-of-the-art Defense Advanced Research Projects Agency/Space and Naval Warfare Systems Center San Diego (DARPA/SSCSD) technologies (Sensate-Liner and ENCOMPASS) coupled via the Enhanced Position Location Reporting System (EPLRS), an existing wireless military tactical communication data system. Transmission Security and Communication Security (TRANSEC/COMMSEC) of environmental and biomedical data is thus accomplished from the battlefield via selected data links and Ethernet. System functionality and appropriate candidate interfacing technologies will be discussed.

The presence of a device meant to enhance the medical encounter may alter the nature of the doctor-patient interaction in a way that affects patient satisfaction. The focus of this study was to examine the social impact of introducing advanced exam-room technologies to the doctor-patient interaction. By comparing cohorts (young: 18-39 and older: 62-89) we examined a possible age-related interaction. Participants viewed one of several video conditions portraying a physician conducting a medical interview in which he uses one of various documenting technologies (Nothing, Pen and Paper, PDA, Desktop Computer, Wearable Computer). After viewing the interaction, participants completed a series of questionnaires evaluating their general satisfaction with the quality of care (QoC) given during the medical interview. Patient satisfaction levels did significantly vary depending on the technology condition, participant cohort, and participant gender. Overall, young adults and females rated the doctor more favorably. The favorability of ratings for each technology condition depended on the aspect of QoC examined.

Biomechanical Big Data is of great significance to precision health applications, among which we take special interest in Physical Activity Detection (PAD). In this study, we have performed extensive research on deep learning-based PAD from biomechanical big data, focusing on the challenges raised by the need of real-time edge inference. First, considering there are many places we can place the motion sensors, we have thoroughly compared and analyzed the location difference in terms of deep learning-based PAD performance. We have further compared the difference among six sensor channels (3-axis accelerometer and 3-axis gyroscope). Second, we have selected the optimal sensor and the optimal sensor channel, which can not only provide sensor usage suggestions but also enable ultra-low-power application on the edge. Third, we have investigated innovative methods to minimize the training effort of the deep learning model, leveraging the transfer learning strategy. More specifically, we propose to pre-train a transferable deep learning model using the data from other subjects and then fine-tune the model using limited data from the target-user. In such a way, we have found that, for single-channel case, the transfer learning can effectively increase the deep model performance even when the fine-tuning effort is very small. This research, demonstrated by comprehensive experimental evaluation, have shown the potential of ultra-low-power PAD with minimized sensor stream and minimized training effort.

This thesis is an investigation of the complex processes and relationships between the physical human performer and the technologically manufactured cyber-human counterpart. I acted as both researcher and the physical human performer, deeply engaged in the moment-to-moment creation of events unfolding within a shared virtual reality environment. As the primary instigator and activator of the cyber-human partner, I maintained a balance between the live and technological performance elements, prioritizing the production of content and meaning. By way of using practice as research, this thesis argues that in considering interactions between cyber-human and human performers, it is crucial to move beyond discussions of technology when considering interactions between cyber-humans and human performers to an analysis of emotional content, the powers of poetic imagery, the trust that is developed through sensory perception and the evocation of complex relationships. A theoretical model is constructed to describe the relationship between a cyber-human and a human performer in the five works created specifically for this thesis, which is not substantially different from that between human performers. Technological exploration allows for the observation and analysis of various relationships, furthering an expanded understanding of ‘movement as content’ beyond the electronic connection. Each of the works created for this research used new and innovative technologies, including virtual reality, multiple interactive systems, six generations of wearable computers, motion capture technology, high-end digital lighting projectors, various projection screens, smart electronically charged fabrics, multiple sensory sensitive devices and intelligent sensory charged alternative performance spaces. They were most often collaboratively created in order to augment all aspects of the performance and create the sense of community found in digital live dance performances/events. These works are identified as one continuous line of energy and discovery, each representing a slight variation on the premise that a working, caring, visceral and poetic content occurs beyond the technological tools. Consequently, a shift in the physical human’s psyche overwhelms the act of performance. Scholarship and reflection on the works have been integral to my creative process throughout. The goals of this thesis, the works created and the resulting methodologies are to investigate performance to heighten the multiple ways we experience and interact with the world. This maximizes connection and results in a highly interactive, improvisational, dynamic, non-linear, immediate, accessible, agential, reciprocal, emotional, visceral and transformative experience without boundaries between the virtual and physical for physical humans, cyborgs and cyber-humans alike.