Situation Inference by Fusion of Opportunistically Available Contexts

Computing and Communications

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

Published

Standard

Situation Inference by Fusion of Opportunistically Available Contexts. / Wang, Jiangtao; Wang, Yasha; Ren, Hongru et al.
2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops. IEEE, 2014. p. 10-17.

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

Harvard

Wang, J, Wang, Y, Ren, H & Zhang, D 2014, Situation Inference by Fusion of Opportunistically Available Contexts. in 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops. IEEE, pp. 10-17. https://doi.org/10.1109/UIC-ATC-ScalCom.2014.82

APA

Wang, J., Wang, Y., Ren, H., & Zhang, D. (2014). Situation Inference by Fusion of Opportunistically Available Contexts. In 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (pp. 10-17). IEEE. https://doi.org/10.1109/UIC-ATC-ScalCom.2014.82

Vancouver

Wang J, Wang Y, Ren H, Zhang D. Situation Inference by Fusion of Opportunistically Available Contexts. In 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops. IEEE. 2014. p. 10-17 doi: 10.1109/UIC-ATC-ScalCom.2014.82

Author

Wang, Jiangtao ; Wang, Yasha ; Ren, Hongru et al. / Situation Inference by Fusion of Opportunistically Available Contexts. 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops. IEEE, 2014. pp. 10-17

Bibtex

@inproceedings{cca196cd0be749ebb0171dbb1377c2c3,

title = "Situation Inference by Fusion of Opportunistically Available Contexts",

abstract = "In many ubiquitous intelligent systems, high-level situations are often required to be inferred by fusing several contexts, which is referred to as situation inference. As opportunistic sensing becomes widely accepted, new challenges are brought into situation inference. In the opportunistic sensing paradigm, applications make the best use of the sensors that happen to be available in a certain location, and those sensors do not necessarily need to be pre-deployed. In this way, opportunistic sensing effectively expands the scope of ubiquitous intelligent applications, but meanwhile brings uncertainty of sensed contexts to the situation inference as well. In this paper, we propose a learning-based approach for situation inference by fusion of opportunistically available contexts. In the offline training phase, in order to reduce the computation load, it only pre-computes some reduced-feature models (RFMs) with higher utility for situation inference, rather than training all possible ones. In the online classification phase, if the input context combination matches one of the pre-computed RFMs, then the model is used to infer the situation, otherwise a less accurate but more general method, the imputation-based method is applied. We evaluate our approach using an open dataset with various degrees of incompleteness and inaccuracy introduced.",

keywords = "Situation Inference, Context Fusion, Opportunistic Sensing",

author = "Jiangtao Wang and Yasha Wang and Hongru Ren and Daqing Zhang",

year = "2014",

doi = "10.1109/UIC-ATC-ScalCom.2014.82",

language = "English",

pages = "10--17",

booktitle = "2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops",

publisher = "IEEE",

}

RIS

TY - GEN

T1 - Situation Inference by Fusion of Opportunistically Available Contexts

AU - Wang, Jiangtao

AU - Wang, Yasha

AU - Ren, Hongru

AU - Zhang, Daqing

PY - 2014

Y1 - 2014

N2 - In many ubiquitous intelligent systems, high-level situations are often required to be inferred by fusing several contexts, which is referred to as situation inference. As opportunistic sensing becomes widely accepted, new challenges are brought into situation inference. In the opportunistic sensing paradigm, applications make the best use of the sensors that happen to be available in a certain location, and those sensors do not necessarily need to be pre-deployed. In this way, opportunistic sensing effectively expands the scope of ubiquitous intelligent applications, but meanwhile brings uncertainty of sensed contexts to the situation inference as well. In this paper, we propose a learning-based approach for situation inference by fusion of opportunistically available contexts. In the offline training phase, in order to reduce the computation load, it only pre-computes some reduced-feature models (RFMs) with higher utility for situation inference, rather than training all possible ones. In the online classification phase, if the input context combination matches one of the pre-computed RFMs, then the model is used to infer the situation, otherwise a less accurate but more general method, the imputation-based method is applied. We evaluate our approach using an open dataset with various degrees of incompleteness and inaccuracy introduced.

AB - In many ubiquitous intelligent systems, high-level situations are often required to be inferred by fusing several contexts, which is referred to as situation inference. As opportunistic sensing becomes widely accepted, new challenges are brought into situation inference. In the opportunistic sensing paradigm, applications make the best use of the sensors that happen to be available in a certain location, and those sensors do not necessarily need to be pre-deployed. In this way, opportunistic sensing effectively expands the scope of ubiquitous intelligent applications, but meanwhile brings uncertainty of sensed contexts to the situation inference as well. In this paper, we propose a learning-based approach for situation inference by fusion of opportunistically available contexts. In the offline training phase, in order to reduce the computation load, it only pre-computes some reduced-feature models (RFMs) with higher utility for situation inference, rather than training all possible ones. In the online classification phase, if the input context combination matches one of the pre-computed RFMs, then the model is used to infer the situation, otherwise a less accurate but more general method, the imputation-based method is applied. We evaluate our approach using an open dataset with various degrees of incompleteness and inaccuracy introduced.

KW - Situation Inference

KW - Context Fusion

KW - Opportunistic Sensing

U2 - 10.1109/UIC-ATC-ScalCom.2014.82

DO - 10.1109/UIC-ATC-ScalCom.2014.82

M3 - Conference contribution/Paper

SP - 10

EP - 17

BT - 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops

PB - IEEE

ER -

Research

Associated organisational unit

Links

Text available via DOI:

Keywords