Akio Sashima
ABSTRACT
Smartwatches are widely used as sensing devices for health management, but their use as multi-sensor wearable service platforms has not been fully explored. Recently, research in artificial intelligence, especially on large language model (LLM), has made remarkable progress, involving both academia and industry. By combining LLM technology with the sensing function of smartwatches, it may be possible to realize a new service platform to develop various pervasive intelligent support for people's daily lives. In this demonstration, we will show a prototype of a mobile sensing platform, CANSASI, which integrates the sensing of the smartwatch and the text generation of the LLM. It uses the smartwatch to sense the user's environment and noise level, and sends the data and a natural language prompt to the LLM. The LLM then analyzes the data with the prompt and responds with some comments and advice about the data. We will demonstrate the features of CANSASI and discuss the issues raised by the integration of these technologies.
- Apple Developer. 2024. Sound Analysis: Classify various sounds by analyzing audio files or streams. Retrieved Jan. 15, 2024 from https://developer.apple.com/documentation/soundanalysisGoogle Scholar
- OpenAI developer platform. 2024. Text generation modelsI. Retrieved Jan. 15, 2024 from https://platform.openai.com/docs/guides/text-generationGoogle Scholar
Index Terms
- Demo: CANSASI: Mobile Sensing Platform powered by Large Language Models
Recommendations
Ubiquitous Mobile Sensing: Behaviour, Mood, and Environment
UbiComp '18: Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable ComputersOur world is increasingly interconnected via a wide variety of computers, IoT, wearable and mobile devices. The information provided collectively through these devices offers insightful information on our everyday lives, daily patterns, mood, behaviour, ...
Wearable ESM: differences in the experience sampling method across wearable devices
MobileHCI '16: Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and ServicesThe Experience Sampling Method is widely used for collecting self-report responses from people in natural settings. While most traditional approaches rely on using a phone to trigger prompts and record information, wearable devices now offer new ...
Mobile Phone Sensing as a Service: Business Model and Use Cases
NGMAST '13: Proceedings of the 2013 Seventh International Conference on Next Generation Mobile Apps, Services and TechnologiesWith the ubiquity and ever-increasing capabilities of mobile devices and the integration of more and more sensors in them, such devices now have the potential to act not only as personal communication and computing platforms but also as sensing ...
Comments