.png){kind=icon}
.png){kind=icon}
Return
Toward Personalized Activity Recognition Systems With a Semipopulation Approach
.png){kind=icon}
PRE
AI
DOI：10.1109/THMS.2015.2489688.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Activity recognition is a key component of context-aware computing to support people's physical activity, but conventional approaches often lack in their generalizability and scalability due to problems of diversity in how individuals perform activities, overfitting when building activity models, and collection of a large amount of labeled data from end users. To address these limitations, we propose a semipopulation-based approach that exploits activity models trained from other users; therefore, a new user does not need to provide a large volume of labeled activity data. Instead of relying on any additional information from users like their weight or height, our approach directly measures the fitness of others' models on a small amount of labeled data collected from the new user. With these shared activity models among users, we compose a hybrid model of Bayesian networks and support vector machines to accurately recognize the activity of the new user. On activity data collected from 28 people with a diversity in gender, age, weight, and height, our approach produced an average accuracy of 83.4% (kappa: 0.852), compared with individual and (standard) population models that had accuracies of 77.3% (kappa: 0.79) and 77.7% (kappa: 0.743), respectively. Through an analysis on the performance of our approach and users' demographic information, our approach outperforms others that rely on users' demographic information for recognizing their activities, which may contradict the commonly held belief that physically similar people would have similar activity patterns.
Keywords:
Pattern recognition
sensor systems and applications
ubiquitous computing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.4
Papers:
1.1K
Citations:
3.5K