基于共空间模式和支持向量机算法的食物偏好脑电分类研究

doi:10.3969/j.issn.0258-8021.2022.03.002

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1605 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In this study an ERP experiment was conducted to investigate the difference of ERP evoked by individual food preferences. A new classification method was proposed. The oddball paradigm was adopted and 18 subjects participated in this experiment. After ranking 5 kinds of food, ERP was induced by different food stimulus, and the highest and lowest score were collected. The ERPs were analyzed to determine whether there were significant differences in the signals related to the different food. Next, common spatial pattern and support vector machines were used for feature extraction and single-trial ERP classification respectively. The leave-one-out method was used for cross validation. Results showed that P3 amplitudes for food with high or low score were different significantly and P3 amplitudes were larger in the former compared to the latter. The average amplitude increased by about 15%. A positive correlation between P3 amplitudes and food scores was seen. The averaged accuracy of classification could reach 93.16% when 4 single-trial ERP were used. These results suggested that brain reactivities responding to food preferences were quite different and the proposed method achieved expected results. In conclusion, ERP can be used as a new tool for food preference analysis and provides a new solution to food evaluation and assistant treatment about anorexia.

Key words： food preference event related potential (ERP) common spatial pattern (CSP) support vector machines (SVM)

Received: 16 August 2021

PACS:

R318

Corresponding Authors: ^*E-mail:heaven@tju.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Li Chunyu
	He Feng
	Qi Hongzhi
	Guo Xiaoyi
	Chen Long
	Ming Dong

Cite this article:

Li Chunyu,He Feng,Qi Hongzhi, et al. A Study for ERP Classification of Food Preference Based on CSP and SVM[J]. Chinese Journal of Biomedical Engineering, 2022, 41(3): 266-272.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2022.03.002 OR http://cjbme.csbme.org/EN/Y2022/V41/I3/266

[1] LaBar KS, Gitelman DR, Parrish TB, et al. Hunger selectively modulates corticolimbic activation to food stimuli in humans [J]. Behavioral Neuroscience, 2001, 115(2): 493-500.
[2] Ulrike T, Jean-François K, Julie H, et al. The brain tracks the energetic value in food images [J]. NeuroImage, 2009, 44(3): 967-974.
[3] Rebecca GB, Hedy K. Food cue reactivity and craving predict eating and weight gain: a meta-analytic review [J]. Obesity Reviews, 2016, 17(2): 159-177.
[4] Stockburger J, Weike AI, Hamm AO, et al. Deprivation selectively modulates brain potentials to food pictures [J]. Behavioral Neuroscience, 2008, 122(4): 936-942.
[5] Leland DS, Pineda JA. Effects of food-related stimuli on visual spatial attention in fasting and nonfasting normal subjects: behavior and electrophysiology [J]. Clinical Neurophysiology, 2006, 117(1): 67-84.
[6] Marc BA, Manuel MS, Toni C. Food is special by itself: Neither valence, arousal, food appeal, nor caloric content modulate the attentional bias induced by food images [J]. Appetite, 2021, 156: 104984.
[7] Han P, Roitzsch C, Horstmann A, et al. Increased Brain Reward Responsivity to Food-Related Odors in Obesity [J]. Obesity, 2021, 29(7): 1138-1145.
[8] Todd DW, Katherine TG. Neurocognitive correlates of processing food-related stimuli in a Go/No-go paradigm [J]. Appetite, 2013, 71: 40-47.
[9] Nachie T, Hisato S, Takashi I, et al. Effect of individual food preferences on oscillatory brain activity [J]. Brain and Behavior, 2019, 9(5): e01262.
[10] Anoushiravan Z, Aleksandra L, Werner S. Modification of food preferences by posthypnotic suggestions: An event-related brain potential study [J]. Appetite, 2020, 151:104713.
[11] Jessica S, Ralf S, Tobias F, et al. The impact of hunger on food cue processing: An event-related brain potential study [J]. NeuroImage, 2009, 47(4): 1819-1829.
[12] Mitsuo I, Munehisa K, Aki A, et al. Effect of negatively valenced words on deviant P3 during the three-stimulus oddball paradigm [J]. Neuroscience Letters, 2018, 683: 38-42.
[13] 张锐, 刘家俊, 陈明明, 等. 基于小波变换—集合经验模态分解的单通道脑电信号眼电伪迹自动去除研究 [J]. 生物医学工程学杂志, 2021, 38(3): 473-482.
[14] Carbine KA, Rodeback R, Modersitzki E, et al. The utility of event-related potentials (ERPs) in understanding food-related cognition: a systematic review and recommendations [J]. Appetite, 2018,128:58-78.
[15] Wang Yijun, Gao Shangkai, Gao Xiaorong. Common spatial pattern method for channel selelction in motor imagery based brain-computer interface [C]//Proceedings of Annual International Conference of the IEEE EMBS. Shanghai: IEEE,2005: 5392-5395.
[16] 汲继跃, 佘青山, 张启忠, 等. 最优区域共空间模式的运动想象脑电信号分类方法 [J]. 传感技术学报, 2020, 33(1):34-39.
[17] 李幼军, 钟宁, 黄佳进, 等. 基于高斯核函数支持向量机的脑电信号时频特征情感多类识别 [J]. 北京工业大学学报, 2018, 44(2):234-243.
[18] Wiebke H, Holger SR, Annekathrin S. Associated motivational salience impacts early sensory processing of human faces [J]. NeuroImage, 2017, 156: 466-474.
[19] Becker CA, Flaisch T, Renner B, et al. Neural Correlates of the Perception of Spoiled Food Stimuli [J]. Frontiers in Human Neuroscience, 2016, 10: 302.
[20] Qiu Ruyi, Qi Yuxuan, Wan Xiaoang, et al. An event-related potential study of consumers' responses to food bundles [J]. Appetite, 2020, 147: 104538.
[21] Nuria MB, María LM, Giulia T, et al. Clinical andneurophysiological correlates of emotion and food craving regulation inpatients with anorexia nervosa [J]. Journal of Clinical Medicine, 2020, 9(4): 960.