IEICE TRANSACTIONS on Information
Open Access
Feature Selection of Deep Learning Models for EEG-Based RSVP Target Detection
-
Full Text Views
23
- Cite this
- Free PDF (1.2MB)
Summary :
Most recent work used raw electroencephalograph (EEG) data to train deep learning (DL) models, with the assumption that DL models can learn discriminative features by itself. It is not yet clear what kind of RSVP specific features can be selected and combined with EEG raw data to improve the RSVP classification performance of DL models. In this paper, we tried to extract RSVP specific features and combined them with EEG raw data to capture more spatial and temporal correlations of target or non-target event and improve the EEG-based RSVP target detection performance. We tested on X2 Expertise RSVP dataset to show the experiment results. We conducted detailed performance evaluations among different features and feature combinations with traditional classification models and different CNN models for within-subject and cross-subject test. Compared with state-of-the-art traditional Bagging Tree (BT) and Bayesian Linear Discriminant Analysis (BLDA) classifiers, our proposed combined features with CNN models achieved 1.1% better performance in within-subject test and 2% better performance in cross-subject test. This shed light on the ability for the combined features to be an efficient tool in RSVP target detection with deep learning models and thus improved the performance of RSVP target detection.
- Publication
- IEICE TRANSACTIONS on Information Vol.E102-D No.4 pp.836-844
- Publication Date
- 2019/04/01
- Publicized
- 2019/01/22
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2018EDP7095
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Jingxia CHEN
Shaanxi University of Science and Technology
Zijing MAO
University of Texas at San Antonio
Ru ZHENG
Shaanxi University of Science and Technology
Yufei HUANG
University of Texas at San Antonio
Lifeng HE
Shaanxi University of Science and Technology,Aichi Prefectural University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jingxia CHEN, Zijing MAO, Ru ZHENG, Yufei HUANG, Lifeng HE, "Feature Selection of Deep Learning Models for EEG-Based RSVP Target Detection" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 4, pp. 836-844, April 2019, doi: 10.1587/transinf.2018EDP7095.
Abstract: Most recent work used raw electroencephalograph (EEG) data to train deep learning (DL) models, with the assumption that DL models can learn discriminative features by itself. It is not yet clear what kind of RSVP specific features can be selected and combined with EEG raw data to improve the RSVP classification performance of DL models. In this paper, we tried to extract RSVP specific features and combined them with EEG raw data to capture more spatial and temporal correlations of target or non-target event and improve the EEG-based RSVP target detection performance. We tested on X2 Expertise RSVP dataset to show the experiment results. We conducted detailed performance evaluations among different features and feature combinations with traditional classification models and different CNN models for within-subject and cross-subject test. Compared with state-of-the-art traditional Bagging Tree (BT) and Bayesian Linear Discriminant Analysis (BLDA) classifiers, our proposed combined features with CNN models achieved 1.1% better performance in within-subject test and 2% better performance in cross-subject test. This shed light on the ability for the combined features to be an efficient tool in RSVP target detection with deep learning models and thus improved the performance of RSVP target detection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7095/_p
Copy
@ARTICLE{e102-d_4_836,
author={Jingxia CHEN, Zijing MAO, Ru ZHENG, Yufei HUANG, Lifeng HE, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Selection of Deep Learning Models for EEG-Based RSVP Target Detection},
year={2019},
volume={E102-D},
number={4},
pages={836-844},
abstract={Most recent work used raw electroencephalograph (EEG) data to train deep learning (DL) models, with the assumption that DL models can learn discriminative features by itself. It is not yet clear what kind of RSVP specific features can be selected and combined with EEG raw data to improve the RSVP classification performance of DL models. In this paper, we tried to extract RSVP specific features and combined them with EEG raw data to capture more spatial and temporal correlations of target or non-target event and improve the EEG-based RSVP target detection performance. We tested on X2 Expertise RSVP dataset to show the experiment results. We conducted detailed performance evaluations among different features and feature combinations with traditional classification models and different CNN models for within-subject and cross-subject test. Compared with state-of-the-art traditional Bagging Tree (BT) and Bayesian Linear Discriminant Analysis (BLDA) classifiers, our proposed combined features with CNN models achieved 1.1% better performance in within-subject test and 2% better performance in cross-subject test. This shed light on the ability for the combined features to be an efficient tool in RSVP target detection with deep learning models and thus improved the performance of RSVP target detection.},
keywords={},
doi={10.1587/transinf.2018EDP7095},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Feature Selection of Deep Learning Models for EEG-Based RSVP Target Detection
T2 - IEICE TRANSACTIONS on Information
SP - 836
EP - 844
AU - Jingxia CHEN
AU - Zijing MAO
AU - Ru ZHENG
AU - Yufei HUANG
AU - Lifeng HE
PY - 2019
DO - 10.1587/transinf.2018EDP7095
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2019
AB - Most recent work used raw electroencephalograph (EEG) data to train deep learning (DL) models, with the assumption that DL models can learn discriminative features by itself. It is not yet clear what kind of RSVP specific features can be selected and combined with EEG raw data to improve the RSVP classification performance of DL models. In this paper, we tried to extract RSVP specific features and combined them with EEG raw data to capture more spatial and temporal correlations of target or non-target event and improve the EEG-based RSVP target detection performance. We tested on X2 Expertise RSVP dataset to show the experiment results. We conducted detailed performance evaluations among different features and feature combinations with traditional classification models and different CNN models for within-subject and cross-subject test. Compared with state-of-the-art traditional Bagging Tree (BT) and Bayesian Linear Discriminant Analysis (BLDA) classifiers, our proposed combined features with CNN models achieved 1.1% better performance in within-subject test and 2% better performance in cross-subject test. This shed light on the ability for the combined features to be an efficient tool in RSVP target detection with deep learning models and thus improved the performance of RSVP target detection.
ER -
English
