期刊论文详细信息
Proceedings | |
Human Activity Recognition through Weighted Finite Automata | |
Salomón, Sergio1  TîrnÄucÄ, Cristina2  | |
[1] Axpe Consulting Cantabria S.L., 39600 Camargo, Cantabria, Spain;Departamento de Matemáticas, EstadÃstica y Computación, Universidad de Cantabria, 39005 Santander, Cantabria, Spain | |
关键词: human activity recognition; weighted finite automaton; regular expression; pattern mining; | |
DOI : 10.3390/proceedings2191263 | |
学科分类:社会科学、人文和艺术(综合) | |
来源: mdpi | |
【 摘 要 】
This work addresses the problem of human activity identification in an ubiquitous environment, where data is collected from a wide variety of sources. In our approach, after filtering noisy sensor entries, we learn userâs behavioral patterns and activitiesâ sensor patterns through the construction of weighted finite automata and regular expressions respectively, and infer the inhabitantâs position for each activity through frequency distribution of floor sensor data. Finally, we analyze the prediction results of this strategy, which obtains 90.65% accuracy for the test data.
【 授权许可】
CC BY
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201910254027249ZK.pdf | 346KB | download |