The Analysis of Emotion Recognition from GSR Based on PSO

Abstract

A method for recognizing the emotion states of subjects based on 30 features extracted from their Galvanic Skin Response (GSR) signals was proposed. GSR signals were acquired by means of experiments attended by those subjects. Next the data was normalized with the calm signal of the same subject after being de-noised. Then the normalized data were extracted features before the step of feature selection. Immune Hybrid Particle Swarm Optimization (IH-PSO) was proposed to select the feature subsets of different emotions. Classifier for feature selection was evaluated on the correct recognition as well as number of the selected features. At last, this paper verified the effectiveness of the feature subsets selected with another new data. All performed in this paper illustrate that IH-PSO can achieve much effective results, and further more, demonstrate that there is significant emotion information in GSR signal.

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 — 80 citations exist upstream.

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