Abstract | ||
---|---|---|
Motivated by the reports about assaults on women, especially college girls, in China, we take the first step to explore possibility of using off-the-shelf smartphone for physical assault detection. The most difficult one among challenges in our design is the extraordinary complexity and diversity of various assault instances, which lead to an extremely hard, if not impossible, to perform fine-grained recognition. To this end, we decide to focus on the characteristics of intensity and irregularity, based on which several features are extracted. Moreover, we proposed a combinatorial classification scheme considering individuality of user's ADLs(Activities of Daily Living) and universality of differences between ADLs and assaults to most people. The data we used for evaluation are collected from simulated assaults which are performed by our volunteers in controlled settings. Our experiment results showed that physical assaults could be distinguished with the majority of ADLs in our proposed feature space, and our proposed system could correctly detect most instances of aggravated assault with low false alarm rate and short delay. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-21837-3_47 | WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS |
Keywords | Field | DocType |
Assault detection, Smartphone sensing, Activity recognition, Machine learning | Aggravated assault,Feature vector,Activities of daily living,Activity recognition,Computer science,Computer security,Classification scheme,Extremely hard,Constant false alarm rate,Physical assault | Conference |
Volume | ISSN | Citations |
9204 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 12 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zehao Sun | 1 | 19 | 4.07 |
Tang Shaojie | 2 | 2224 | 157.73 |
He Huang | 3 | 829 | 65.14 |
Liusheng Huang | 4 | 1082 | 123.52 |
Zhenyu Zhu | 5 | 9 | 1.89 |
Hansong Guo | 6 | 4 | 1.77 |
Yu-E Sun | 7 | 67 | 9.60 |