TY - GEN
T1 - DAVE
T2 - 2nd IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017
AU - Salekin, Asif
AU - Wang, Hongning
AU - Williams, Kristine
AU - Stankovic, John
N1 - Funding Information:
VIII. ACKNOWLEDGEMENT This paper was supported, in part, by DGIST Research and Development Program (CPS Global center) funded by the Ministry of Science, ICT and Future Planning, NSF CNS-1319302 and, the National Institute of Nursing Research of the NIH under Award Number R01NR011455.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/14
Y1 - 2017/8/14
N2 - DAVE is a comprehensive set of event detection techniques to monitor and detect 5 important verbal agitations: Asking for help, verbal sexual advances, questions, cursing, and talking with repetitive sentences. The novelty of DAVE includes combining acoustic signal processing with three different text mining paradigms to detect verbal events (asking for help, verbal sexual advances, and questions) which need both lexical content and acoustic variations to produce accurate results. To detect cursing and talking with repetitive sentences we extend word sense disambiguation and sequential pattern mining algorithms. The solutions have applicability to monitoring dementia patients, for online video sharing applications, human computer interaction (HCI) systems, home safety, and other health care applications. A comprehensive performance evaluation across multiple domains includes audio clips collected from 34 real dementia patients, audio data from controlled environments, movies and Youtube clips, online data repositories, and healthy residents in real homes. The results show significant improvement over baselines and high accuracy for all 5 vocal events.
AB - DAVE is a comprehensive set of event detection techniques to monitor and detect 5 important verbal agitations: Asking for help, verbal sexual advances, questions, cursing, and talking with repetitive sentences. The novelty of DAVE includes combining acoustic signal processing with three different text mining paradigms to detect verbal events (asking for help, verbal sexual advances, and questions) which need both lexical content and acoustic variations to produce accurate results. To detect cursing and talking with repetitive sentences we extend word sense disambiguation and sequential pattern mining algorithms. The solutions have applicability to monitoring dementia patients, for online video sharing applications, human computer interaction (HCI) systems, home safety, and other health care applications. A comprehensive performance evaluation across multiple domains includes audio clips collected from 34 real dementia patients, audio data from controlled environments, movies and Youtube clips, online data repositories, and healthy residents in real homes. The results show significant improvement over baselines and high accuracy for all 5 vocal events.
KW - Acoustic signal processing
KW - Asking for help
KW - Cursing
KW - Monitoring dementia patients
KW - Verbal agitation
KW - Verbal sexual advances
UR - http://www.scopus.com/inward/record.url?scp=85029372225&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029372225&partnerID=8YFLogxK
U2 - 10.1109/CHASE.2017.74
DO - 10.1109/CHASE.2017.74
M3 - Conference contribution
AN - SCOPUS:85029372225
T3 - Proceedings - 2017 IEEE 2nd International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017
SP - 157
EP - 166
BT - Proceedings - 2017 IEEE 2nd International Conference on Connected Health
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 17 July 2017 through 19 July 2017
ER -