A4 Article in conference proceedings
Emotions and Activity Recognition System Using Wearable Device Sensors (2021)

Rumiantcev, M. (2021). Emotions and Activity Recognition System Using Wearable Device Sensors. In S. Balandin, V. Deart, & T. Tyutina (Eds.), FRUCT '28 : Proceedings of the 28th Conference of Open Innovations Association FRUCT (pp. 381-389). FRUCT Oy. Proceedings of Conference of Open Innovations Association FRUCT. https://doi.org/10.23919/FRUCT50888.2021.9347652

JYU authors or editors

Publication details

All authors or editors: Rumiantcev, Mikhail

Parent publication: FRUCT '28 : Proceedings of the 28th Conference of Open Innovations Association FRUCT

Parent publication editors: Balandin, Sergey; Deart, Vladimir; Tyutina, Tatiana

Place and date of conference: Moscow, Russia, 25.-29.1.2021

eISBN: 978-952-69244-4-1

Journal or series: Proceedings of Conference of Open Innovations Association FRUCT

ISSN: 2305-7254

eISSN: 2343-0737

Publication year: 2021

Pages range: 381-389

Publisher: FRUCT Oy

Publication country: Finland

Publication language: English

DOI: https://doi.org/10.23919/FRUCT50888.2021.9347652

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/74291

Abstract

Nowadays machines have become extremely smart, there are a lot of existing services that seemed to be unexpectable and futuristic decades or even a few years ago. However, artificial intelligence is still far from human intelligence, machines do not have feelings, consciousness, and intuition. How can we help machines to learn about human feelings and understand their needs better? People take their devices wherever they go, what can devices tell us about their owners? Personal preferences and needs are dependent on emotional and situational contexts. Therefore, emotional and activity aware gadgets would be more intuitive and provide more appropriate information to users. Contemporary wearable devices involve wide-ranging sensors. In this paper, I am going to present emotion and activity recognition approaches. The experimental recognition system elaborated during this research, enriched with sensor data collection and machine learning algorithms. It is targeted to guess how users are doing and what they are feeling. Such recognition systems can find applications in different areas such as music recommendations, personal safety or healthcare domains.

Keywords: intelligent systems; smart products; artificial intelligence; machine learning; geographic information; motion detection; facial recognition (computer science); sensors; physical activity; action; mood; emotions

Free keywords: deep learning; image segmentation; zero-shot semantic segmentation

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 1