Towards Robust Activity Recognition for Everyday Life: Methods and Evaluation
| Autor: | Gustaf Hendeby, Didier Stricker, Attila Reiss |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Engineering
Unknown activity Remote patient monitoring business.industry Signalbehandling Machine learning computer.software_genre Activity recognition Robustness (computer science) Regular daily routine Signal Processing Recognition system Information system Artificial intelligence Everyday life business Systemvetenskap informationssystem och informatik computer Information Systems |
| Zdroj: | PervasiveHealth |
| DOI: | 10.4108/icst.pervasivehealth.2013.251928 |
| Popis: | The monitoring of physical activities under realistic, everyday life conditions --- thus while an individual follows his regular daily routine --- is usually neglected or even completely ignored. Therefore, this paper investigates the development and evaluation of robust methods for everyday life scenarios, with focus on the task of aerobic activity recognition. Two important aspects of robustness are investigated: dealing with various (unknown) other activities and subject independency. Methods to handle these issues are proposed and compared, a thorough evaluation simulates usual everyday scenarios of the usage of activity recognition applications. Moreover, a new evaluation technique is introduced (leave-one-other-activity-out) to simulate when an activity recognition system is used while performing a previously unknown activity. Through applying the proposed methods it is possible to design a robust physical activity recognition system with the desired generalization characteristic. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|