EEG Topography Amplification Using FastGAN-ASP Method
Electroencephalogram (EEG) signals are bioelectrical activities generated by the central nervous system. As a unique information factor, they are correlated with the genetic information of the subjects, exhibiting robustness against forgery. The development of biometric identity recognition based on...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/24/4944 |
| _version_ | 1797381307931557888 |
|---|---|
| author | Min Zhao Shuai Zhang Xiuqing Mao Lei Sun |
| author_facet | Min Zhao Shuai Zhang Xiuqing Mao Lei Sun |
| author_sort | Min Zhao |
| collection | DOAJ |
| description | Electroencephalogram (EEG) signals are bioelectrical activities generated by the central nervous system. As a unique information factor, they are correlated with the genetic information of the subjects, exhibiting robustness against forgery. The development of biometric identity recognition based on EEG signals has significantly improved the security and accuracy of biometric recognition. However, EEG signals obtained from incompatible acquisition devices have low universality and are prone to noise, making them challenging for direct use in practical identity recognition scenarios. Employing deep learning network models for data augmentation can address the issue of data scarcity. Yet, the time–frequency–space characteristics of EEG signals pose challenges for extracting features and efficiently generating data with deep learning models. To tackle these challenges, this paper proposes a data generation method based on channel attention normalization and spatial pyramid in a generative adversative network (FastGAN-ASP). The method introduces attention mechanisms in both the generator and discriminator to locate crucial feature information, enhancing the training performance of the generative model for EEG data augmentation. The EEG data used here are preprocessed EEG topographic maps, effectively representing the spatial characteristics of EEG data. Experiments were conducted using the BCI Competition IV-Ⅰ and BCI Competition IV-2b standard datasets. Quantitative and usability evaluations were performed using the Fréchet inception distance (FID) metric and ResNet-18 classification network, validating the quality and usability of the generated data from both theoretical and applied perspectives. The FID metric confirmed that FastGAN-ASP outperforms FastGAN, WGAN-GP, and WGAN-GP-ASP in terms of performance. Moreover, utilizing the dataset augmented with this method for classification recognition achieved an accuracy of 95.47% and 92.43%. |
| first_indexed | 2024-03-08T20:49:33Z |
| format | Article |
| id | doaj.art-39c549f18a39488fb8bbeb5aed694906 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T20:49:33Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-39c549f18a39488fb8bbeb5aed6949062023-12-22T14:04:59ZengMDPI AGElectronics2079-92922023-12-011224494410.3390/electronics12244944EEG Topography Amplification Using FastGAN-ASP MethodMin Zhao0Shuai Zhang1Xiuqing Mao2Lei Sun3School of Cryptography Engineering, Information Engineering University, Zhengzhou 450001, ChinaSchool of Cryptography Engineering, Information Engineering University, Zhengzhou 450001, ChinaSchool of Cryptography Engineering, Information Engineering University, Zhengzhou 450001, ChinaSchool of Cryptography Engineering, Information Engineering University, Zhengzhou 450001, ChinaElectroencephalogram (EEG) signals are bioelectrical activities generated by the central nervous system. As a unique information factor, they are correlated with the genetic information of the subjects, exhibiting robustness against forgery. The development of biometric identity recognition based on EEG signals has significantly improved the security and accuracy of biometric recognition. However, EEG signals obtained from incompatible acquisition devices have low universality and are prone to noise, making them challenging for direct use in practical identity recognition scenarios. Employing deep learning network models for data augmentation can address the issue of data scarcity. Yet, the time–frequency–space characteristics of EEG signals pose challenges for extracting features and efficiently generating data with deep learning models. To tackle these challenges, this paper proposes a data generation method based on channel attention normalization and spatial pyramid in a generative adversative network (FastGAN-ASP). The method introduces attention mechanisms in both the generator and discriminator to locate crucial feature information, enhancing the training performance of the generative model for EEG data augmentation. The EEG data used here are preprocessed EEG topographic maps, effectively representing the spatial characteristics of EEG data. Experiments were conducted using the BCI Competition IV-Ⅰ and BCI Competition IV-2b standard datasets. Quantitative and usability evaluations were performed using the Fréchet inception distance (FID) metric and ResNet-18 classification network, validating the quality and usability of the generated data from both theoretical and applied perspectives. The FID metric confirmed that FastGAN-ASP outperforms FastGAN, WGAN-GP, and WGAN-GP-ASP in terms of performance. Moreover, utilizing the dataset augmented with this method for classification recognition achieved an accuracy of 95.47% and 92.43%.https://www.mdpi.com/2079-9292/12/24/4944EEG classificationgenerating adversarial network (GAN)data augmentationEEG topographyattention mechanism |
| spellingShingle | Min Zhao Shuai Zhang Xiuqing Mao Lei Sun EEG Topography Amplification Using FastGAN-ASP Method Electronics EEG classification generating adversarial network (GAN) data augmentation EEG topography attention mechanism |
| title | EEG Topography Amplification Using FastGAN-ASP Method |
| title_full | EEG Topography Amplification Using FastGAN-ASP Method |
| title_fullStr | EEG Topography Amplification Using FastGAN-ASP Method |
| title_full_unstemmed | EEG Topography Amplification Using FastGAN-ASP Method |
| title_short | EEG Topography Amplification Using FastGAN-ASP Method |
| title_sort | eeg topography amplification using fastgan asp method |
| topic | EEG classification generating adversarial network (GAN) data augmentation EEG topography attention mechanism |
| url | https://www.mdpi.com/2079-9292/12/24/4944 |
| work_keys_str_mv | AT minzhao eegtopographyamplificationusingfastganaspmethod AT shuaizhang eegtopographyamplificationusingfastganaspmethod AT xiuqingmao eegtopographyamplificationusingfastganaspmethod AT leisun eegtopographyamplificationusingfastganaspmethod |