文献类型：期刊文献

英文题名：A Socially Inspired Framework for Human State Inference Using Expert Opinion Integration

作者：Modi, Shrey[1];Lin, Yingzi[2];Cheng, Long[3];Yang, Guosheng[4];Liu, Lizhi[1];Zhang, W. J.[1,5]

机构：[1]Univ Saskatchewan, Adv Engn Design Lab, Saskatoon, SK S7N 5A9, Canada;[2]Northeastern Univ, Dept Mech & Ind Engn, Boston, MA 02115 USA;[3]Chinese Acad Sci, Inst Automat, Key Lab Complex Syst & Intelligence Sci, Beijing 100190, Peoples R China;[4]Minzu Univ China, Sch Informat Engn, Beijing 475001, Peoples R China;[5]E China Univ Sci & Technol, Complex Syst Res Lab, Shanghai 200237, Peoples R China

年份：2011

卷号：16

期号：5

起止页码：874

外文期刊名：IEEE-ASME TRANSACTIONS ON MECHATRONICS

收录：;EI(收录号：20113614310085);WOS:【SCI-EXPANDED(收录号:WOS:000294550100012)】；

基金：The work of Y. Lin was supported in part by the National Science Foundation under NSF CAREER Award 0954579. The work of L. Cheng was supported by the National Natural Science Foundation of China under Grant 61004099. The work of W. J. Zhang was supported by the Natural Sciences and Engineering Research Council of Canada Discovery under Grant RGPIN-203437-20.

语种：英文

外文关键词：Expert opinion elicitation; fatigue inference; human state inference; integrated framework

摘要：A complete biosensing involves two processes: data acquisition or collection and information inference. In this paper, a socially inspired framework to infer the human state using multiple cues or signals and inference techniques or "experts" is presented. A general idea with the proposed framework is that conventional inference algorithms are viewed as inference experts and then the inference problem can take advantage of the knowledge in expert opinion elicitation. The sense of the socially inspired lies in that 1) there are multiple cues, 2) there are multiple experts, 3) different experts have different expertise levels on different cues in association with different human states, and 4) there are different procedures to come up with a consensus or agreed opinion (i.e., human state in this case). To demonstrate the effectiveness of the proposed framework, inference of the fatigue state is taken as an example. The result is compared with that in a previous study in the literature and overall, it has been found that the proposed framework can deliver better results in terms of the inferring accuracy.