Cognitive emotion model for eldercare robot in smart home

Author

Han Jing ; Xie Lun ; Li Dan ; He Zhijie ; Wang Zhiliang

Author_Institution

Sch. of Comput. & Commun. Eng., Univ. of Sci. & Technol. Beijing, Beijing, China

Volume

12

Issue

4

fYear

2015

fDate

Apr-15

Firstpage

32

Lastpage

41

Abstract

Based on the smart home and facial expression recognition, this paper presents a cognitive emotional model for eldercare robot. By combining with Gabor filter, Local Binary Pattern algorithm (LBP) and k-Nearest Neighbor algorithm (KNN) are facial emotional features extracted and recognized. Meanwhile, facial emotional features put influence on robot´s emotion state, which is described in AVS emotion space. Then the optimization of smart home environment on the cognitive emotional model is specially analyzed using simulated annealing algorithm (SA). Finally, transition probability from any emotional state to a state of basic emotions is obtained based on the cognitive reappraisal strategy and Euclidean distance. The simulation and experiment have tested and verified the effective in reducing negative emotional state.

Keywords

Gabor filters; control engineering computing; emotion recognition; face recognition; feature extraction; geriatrics; medical robotics; probability; robot vision; simulated annealing; AVS emotion space; Euclidean distance; Gabor filter; KNN; LBP; SA; cognitive emotion model; cognitive reappraisal strategy; eldercare robot; emotional state; facial emotional feature extraction; facial expression recognition; k-nearest neighbor algorithm; local binary pattern algorithm; negative emotional state reduction; simulated annealing algorithm; smart home; transition probability; Analytical models; Computational modeling; Emotion recognition; Mouth; Robots; Senior citizens; Smart homes; AVS emotion space; cognitive emotion model; eldercare robot; emotional state transition; expression recognition; smart home;

fLanguage

English

Journal_Title

Communications, China

Publisher

ieee

ISSN

1673-5447

Type

jour

DOI

10.1109/CC.2015.7114067

Filename

7114067