Modeling human activity semantics for improved recognition performance

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Modeling human activity semantics for improved recognition performance. / Kim, Eunju; Helal, Sumi.
8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011. ed. / C. H. Hsu; L. T. Yang; J. Ma; C. Zhu. Berlin: Springer, 2011. p. 514-528 (Lecture Notes in Computer Science; Vol. 6905).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Kim, E & Helal, S 2011, Modeling human activity semantics for improved recognition performance. in CH Hsu, LT Yang, J Ma & C Zhu (eds), 8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011. Lecture Notes in Computer Science, vol. 6905, Springer, Berlin, pp. 514-528. https://doi.org/10.1007/978-3-642-23641-9_41

APA

Kim, E., & Helal, S. (2011). Modeling human activity semantics for improved recognition performance. In C. H. Hsu, L. T. Yang, J. Ma, & C. Zhu (Eds.), 8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011 (pp. 514-528). (Lecture Notes in Computer Science; Vol. 6905). Springer. https://doi.org/10.1007/978-3-642-23641-9_41

Vancouver

Kim E, Helal S. Modeling human activity semantics for improved recognition performance. In Hsu CH, Yang LT, Ma J, Zhu C, editors, 8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011. Berlin: Springer. 2011. p. 514-528. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-23641-9_41

Author

Kim, Eunju ; Helal, Sumi. / Modeling human activity semantics for improved recognition performance. 8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011. editor / C. H. Hsu ; L. T. Yang ; J. Ma ; C. Zhu. Berlin : Springer, 2011. pp. 514-528 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{9a3ffd22048849c6ae6170d59421d34d,

title = "Modeling human activity semantics for improved recognition performance",

abstract = "Activity recognition performance is significantly dependent on the accuracy of the underlying activity model. Therefore, it is essential to examine and develop an activity model that can capture and represent the complex nature of human activities precisely. To address this issue, we introduce a new activity modeling technique, which utilizes simple yet often ignored activity semantics. Activity semantics are highly evidential knowledge that can identify an activity more accurately in ambiguous situations. We classify semantics into three types and apply them to generic activity framework, which is a refined hierarchical composition structure of the traditional activity theory. We compare the introduced activity model with the traditional model and the hierarchical models in terms of attainable recognition certainty. The comparison study shows superior performance of our semantic model using activities of daily living scenario. {\textcopyright} 2011 Springer-Verlag.",

keywords = "Accuracy and Certainty, Activity Modeling, Activity Recognition, Activity Semantic Knowledge, Generic Activity Framework, Activities of Daily Living, Activity models, Activity Theory, Comparison study, Complex nature, Hierarchical composition, Hierarchical model, Human activities, Modeling technique, Recognition performance, Semantic Model, Accuracy and certainty, Activity modeling, Activity recognition, Generic activity framework, Semantic knowledge, Activity coefficients, Hierarchical systems, Ubiquitous computing, Computation theory, Pattern recognition, Semantics",

author = "Eunju Kim and Sumi Helal",

year = "2011",

doi = "10.1007/978-3-642-23641-9_41",

language = "English",

isbn = "9783642236402 ",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "514--528",

editor = "Hsu, {C. H.} and Yang, {L. T.} and J. Ma and C. Zhu",

booktitle = "8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011",

}

RIS

TY - GEN

T1 - Modeling human activity semantics for improved recognition performance

AU - Kim, Eunju

AU - Helal, Sumi

PY - 2011

Y1 - 2011

N2 - Activity recognition performance is significantly dependent on the accuracy of the underlying activity model. Therefore, it is essential to examine and develop an activity model that can capture and represent the complex nature of human activities precisely. To address this issue, we introduce a new activity modeling technique, which utilizes simple yet often ignored activity semantics. Activity semantics are highly evidential knowledge that can identify an activity more accurately in ambiguous situations. We classify semantics into three types and apply them to generic activity framework, which is a refined hierarchical composition structure of the traditional activity theory. We compare the introduced activity model with the traditional model and the hierarchical models in terms of attainable recognition certainty. The comparison study shows superior performance of our semantic model using activities of daily living scenario. © 2011 Springer-Verlag.

AB - Activity recognition performance is significantly dependent on the accuracy of the underlying activity model. Therefore, it is essential to examine and develop an activity model that can capture and represent the complex nature of human activities precisely. To address this issue, we introduce a new activity modeling technique, which utilizes simple yet often ignored activity semantics. Activity semantics are highly evidential knowledge that can identify an activity more accurately in ambiguous situations. We classify semantics into three types and apply them to generic activity framework, which is a refined hierarchical composition structure of the traditional activity theory. We compare the introduced activity model with the traditional model and the hierarchical models in terms of attainable recognition certainty. The comparison study shows superior performance of our semantic model using activities of daily living scenario. © 2011 Springer-Verlag.

KW - Accuracy and Certainty

KW - Activity Modeling

KW - Activity Recognition

KW - Activity Semantic Knowledge

KW - Generic Activity Framework

KW - Activities of Daily Living

KW - Activity models

KW - Activity Theory

KW - Comparison study

KW - Complex nature

KW - Hierarchical composition

KW - Hierarchical model

KW - Human activities

KW - Modeling technique

KW - Recognition performance

KW - Semantic Model

KW - Accuracy and certainty

KW - Activity modeling

KW - Activity recognition

KW - Generic activity framework

KW - Semantic knowledge

KW - Activity coefficients

KW - Hierarchical systems

KW - Ubiquitous computing

KW - Computation theory

KW - Pattern recognition

KW - Semantics

U2 - 10.1007/978-3-642-23641-9_41

DO - 10.1007/978-3-642-23641-9_41

M3 - Conference contribution/Paper

SN - 9783642236402

T3 - Lecture Notes in Computer Science

SP - 514

EP - 528

BT - 8th International Conference on Ubiquitous Intelligence and Computing, UIC 2011

A2 - Hsu, C. H.

A2 - Yang, L. T.

A2 - Ma, J.

A2 - Zhu, C.

PB - Springer

CY - Berlin

ER -

Research

Links

Text available via DOI:

Keywords