Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models

G.H. Lim; B. Chung; I.H. Suh

doi:10.1145/1957656.1957725

Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models

G.H. Lim, B. Chung, I.H. Suh

Machine Learning and Robotics

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior pattern is normal or not. The other model is the registered behavior threshold model to detect whether such behavior pattern is already learned. If a behavior patten is detected as a new one, an HMM is generated to represent the pattern, and then the HMM is used to update behavior clusters by hierarchical clustering process.

Original language	English
Title of host publication	HRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction
Pages	189-190
Number of pages	2
DOIs	https://doi.org/10.1145/1957656.1957725
Publication status	Published - 2011
Event	6th ACM/IEEE International Conference on Human-Robot Interaction - Lausanne, Switzerland Duration: 6 Mar 2011 → 9 Mar 2011 Conference number: 84437

Conference

Conference	6th ACM/IEEE International Conference on Human-Robot Interaction
Abbreviated title	HRI 2011
Country/Territory	Switzerland
City	Lausanne
Period	6/03/11 → 9/03/11

Access to Document

10.1145/1957656.1957725

Cite this

@inproceedings{a15792caa963486aa6fe183712f5d44b,

title = "Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models",

abstract = "Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior pattern is normal or not. The other model is the registered behavior threshold model to detect whether such behavior pattern is already learned. If a behavior patten is detected as a new one, an HMM is generated to represent the pattern, and then the HMM is used to update behavior clusters by hierarchical clustering process.",

author = "G.H. Lim and B. Chung and I.H. Suh",

year = "2011",

doi = "10.1145/1957656.1957725",

language = "English",

isbn = "978-145030561-7",

pages = "189--190",

booktitle = "HRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction",

note = "6th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2011 ; Conference date: 06-03-2011 Through 09-03-2011",

}

Lim, GH, Chung, B & Suh, IH 2011, Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models. in HRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction. pp. 189-190, 6th ACM/IEEE International Conference on Human-Robot Interaction, Lausanne, Switzerland, 6/03/11. https://doi.org/10.1145/1957656.1957725

TY - GEN

T1 - Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models

AU - Lim, G.H.

AU - Chung, B.

AU - Suh, I.H.

N1 - Conference code: 84437

PY - 2011

Y1 - 2011

N2 - Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior pattern is normal or not. The other model is the registered behavior threshold model to detect whether such behavior pattern is already learned. If a behavior patten is detected as a new one, an HMM is generated to represent the pattern, and then the HMM is used to update behavior clusters by hierarchical clustering process.

AB - Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior pattern is normal or not. The other model is the registered behavior threshold model to detect whether such behavior pattern is already learned. If a behavior patten is detected as a new one, an HMM is generated to represent the pattern, and then the HMM is used to update behavior clusters by hierarchical clustering process.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-79953151972&partnerID=MN8TOARS

U2 - 10.1145/1957656.1957725

DO - 10.1145/1957656.1957725

M3 - Conference contribution

SN - 978-145030561-7

SP - 189

EP - 190

BT - HRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction

T2 - 6th ACM/IEEE International Conference on Human-Robot Interaction

Y2 - 6 March 2011 through 9 March 2011

ER -

Recognition and incremental learning of scenario-oriented human behavior patterns by two threshold models

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this