eCite Digital Repository

An evoked potential-guided deep learning brain representation for visual classification

Citation

Zheng, X and Cao, Z and Bai, Q, An evoked potential-guided deep learning brain representation for visual classification, Neural Information Processing: Proceedings of the 27th International Conference on Neural Information Processing. In: Communications in Computer and Information Science, vol 1333, 18-22 November 2020, Virtual Conference, Online (Bangkok, Thailand), pp. 54-61. ISBN 978-3-030-63822-1 (2020) [Refereed Conference Paper]

Copyright Statement

Copyright unknown

DOI: doi:10.1007/978-3-030-63823-8_7

Abstract

The new perspective in visual classification aims to decode the feature representation of visual objects from human brain activities. Recording electroencephalogram (EEG) from the brain cortex has been seen as a prevalent approach to understand the cognition process of an image classification task. In this study, we proposed a deep learning framework guided by the visual evoked potentials, called the Event-Related Potential (ERP)-Long short-term memory (LSTM) framework, extracted by EEG signals for visual classification. In specific, we first extracted the ERP sequences from multiple EEG channels to response image stimuli-related information. Then, we trained an LSTM network to learn the feature representation space of visual objects for classification. In the experiment, 10 subjects were recorded by over 50,000 EEG trials from an image dataset with 6 categories, including a total of 72 exemplars. Our results showed that our proposed ERP-LSTM framework could achieve classification accuracies of cross-subject of 66.81% and 27.08% for categories (6 classes) and exemplars (72 classes), respectively. Our results outperformed that of using the existing visual classification frameworks, by improving classification accuracies in the range of 12.62%-53.99%. Our findings suggested that decoding visual evoked potentials from EEG signals is an effective strategy to learn discriminative brain representations for visual classification.

Item Details

Item Type:Refereed Conference Paper
Keywords:vsual classification, EEG, ERP, LSTM network, deep learning, brain representation\
Research Division:Information and Computing Sciences
Research Group:Computer vision and multimedia computation
Research Field:Image processing
Objective Division:Expanding Knowledge
Objective Group:Expanding knowledge
Objective Field:Expanding knowledge in the environmental sciences
UTAS Author:Zheng, X (Mr Xialing Zheng)
UTAS Author:Cao, Z (Dr Zehong Cao)
UTAS Author:Bai, Q (Dr Quan Bai)
ID Code:141228
Year Published:2020
Deposited By:Information and Communication Technology
Deposited On:2020-10-06
Last Modified:2021-07-05
Downloads:0

Repository Staff Only: item control page