Human Activity Recognition through Weighted Finite Automata

Proceedings

Sergio Salomón¹  Cristina Tîrnăucă² 

[1] Axpe Consulting Cantabria S.L., 39600 Camargo, Cantabria, Spain;Departamento de Matemáticas, Estadística 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

来源: DOAJ

【 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 user’s behavioral patterns and activities’ sensor patterns through the construction of weighted finite automata and regular expressions respectively, and infer the inhabitant’s 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】

Unknown