A Socially Inspired Framework for Human State Inference Using Expert Opinion Integration

Abstract

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.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 83 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.