1
|
Ahuja C, Sethia D. Harnessing Few-Shot Learning for EEG signal classification: a survey of state-of-the-art techniques and future directions. Front Hum Neurosci 2024; 18:1421922. [PMID: 39050382 PMCID: PMC11266297 DOI: 10.3389/fnhum.2024.1421922] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Accepted: 05/31/2024] [Indexed: 07/27/2024] Open
Abstract
This paper presents a systematic literature review, providing a comprehensive taxonomy of Data Augmentation (DA), Transfer Learning (TL), and Self-Supervised Learning (SSL) techniques within the context of Few-Shot Learning (FSL) for EEG signal classification. EEG signals have shown significant potential in various paradigms, including Motor Imagery, Emotion Recognition, Visual Evoked Potentials, Steady-State Visually Evoked Potentials, Rapid Serial Visual Presentation, Event-Related Potentials, and Mental Workload. However, challenges such as limited labeled data, noise, and inter/intra-subject variability have impeded the effectiveness of traditional machine learning (ML) and deep learning (DL) models. This review methodically explores how FSL approaches, incorporating DA, TL, and SSL, can address these challenges and enhance classification performance in specific EEG paradigms. It also delves into the open research challenges related to these techniques in EEG signal classification. Specifically, the review examines the identification of DA strategies tailored to various EEG paradigms, the creation of TL architectures for efficient knowledge transfer, and the formulation of SSL methods for unsupervised representation learning from EEG data. Addressing these challenges is crucial for enhancing the efficacy and robustness of FSL-based EEG signal classification. By presenting a structured taxonomy of FSL techniques and discussing the associated research challenges, this systematic review offers valuable insights for future investigations in EEG signal classification. The findings aim to guide and inspire researchers, promoting advancements in applying FSL methodologies for improved EEG signal analysis and classification in real-world settings.
Collapse
Affiliation(s)
- Chirag Ahuja
- Department of Computer Science and Engineering, Delhi Technological University, New Delhi, India
| | - Divyashikha Sethia
- Department of Software Engineering, Delhi Technology University, New Delhi, India
| |
Collapse
|
2
|
Chen A, Sun D, Gao X, Zhang D. A novel feature extraction method PSS-CSP for binary motor imagery - based brain-computer interfaces. Comput Biol Med 2024; 177:108619. [PMID: 38796879 DOI: 10.1016/j.compbiomed.2024.108619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2023] [Revised: 05/07/2024] [Accepted: 05/14/2024] [Indexed: 05/29/2024]
Abstract
In order to improve the performance of binary motor imagery (MI) - based brain-computer interfaces (BCIs) using electroencephalography (EEG), a novel method (PSS-CSP) is proposed, which combines spectral subtraction with common spatial pattern. Spectral subtraction is an effective denoising method which is initially adopted to process MI-based EEG signals for binary BCIs in this work. On this basis, we proposed a novel feature extraction method called power spectral subtraction-based common spatial pattern (PSS-CSP) , which calculates the differences in power spectrum between binary classes of EEG signals and uses the differences in the feature extraction process. Additionally, support vector machine (SVM) algorithm is used for signal classification. Results show the proposed method (PSS-CSP) outperforms certain existing methods, achieving a classification accuracy of 76.8% on the BCIIV dataset 2b, and 76.25% and 77.38% on the OpenBMI dataset session 1 and session 2, respectively.
Collapse
Affiliation(s)
- Ao Chen
- College of Communication Engineering, Jilin University, Changchun 130012, China
| | - Dayang Sun
- College of Communication Engineering, Jilin University, Changchun 130012, China.
| | - Xin Gao
- Centre for Autonomous Robotics (CENTAUR), Department of Electronic Electrical Engineering, University of Bath, Bath BA2 7AY, United Kingdom
| | - Dingguo Zhang
- Centre for Autonomous Robotics (CENTAUR), Department of Electronic Electrical Engineering, University of Bath, Bath BA2 7AY, United Kingdom
| |
Collapse
|
3
|
Mirjalili S, Duarte A. More than the sum of its parts: investigating episodic memory as a multidimensional cognitive process. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.04.22.590651. [PMID: 38712266 PMCID: PMC11071378 DOI: 10.1101/2024.04.22.590651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/08/2024]
Abstract
Why do we remember some events but forget others? Previous studies attempting to decode successful vs. unsuccessful brain states to investigate this question have met with limited success, potentially due, in part, to assessing episodic memory as a unidimensional process, despite evidence that multiple domains contribute to episodic encoding. Using a novel machine learning algorithm known as "transfer learning", we leveraged visual perception, sustained attention, and selective attention brain states to better predict episodic memory performance from trial-to-trial encoding electroencephalography (EEG) activity. We found that this multidimensional treatment of memory decoding improved prediction performance compared to traditional, unidimensional, methods, with each cognitive domain explaining unique variance in decoding of successful encoding-related neural activity. Importantly, this approach could be applied to cognitive domains outside of memory. Overall, this study provides critical insight into the underlying reasons why some events are remembered while others are not.
Collapse
|
4
|
Nagarajan A, Robinson N, Ang KK, Chua KSG, Chew E, Guan C. Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain-computer interface. J Neural Eng 2024; 21:016007. [PMID: 38091617 DOI: 10.1088/1741-2552/ad152f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 12/13/2023] [Indexed: 01/18/2024]
Abstract
Objective.Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients.Approach.We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients.Main results.Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects' data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p<0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p<0.001) and 5.55% (p<0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p>0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients.Significance.Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.
Collapse
Affiliation(s)
- Aarthy Nagarajan
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| | - Neethu Robinson
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| | - Kai Keng Ang
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
- Institute for Infocomm Research, Agency of Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Singapore 138632, Singapore
| | - Karen Sui Geok Chua
- Department of Rehabilitation Medicine, Tan Tock Seng Hospital, 11 Jln Tan Tock Seng, Singapore 308433, Singapore
| | - Effie Chew
- National University Health System, 1E Kent Ridge Road, Singapore 119228, Singapore
| | - Cuntai Guan
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| |
Collapse
|
5
|
Yang L, Shi T, Lv J, Liu Y, Dai Y, Zou L. A multi-feature fusion decoding study for unilateral upper-limb fine motor imagery. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:2482-2500. [PMID: 36899543 DOI: 10.3934/mbe.2023116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/18/2023]
Abstract
To address the fact that the classical motor imagination paradigm has no noticeable effect on the rehabilitation training of upper limbs in patients after stroke and the corresponding feature extraction algorithm is limited to a single domain, this paper describes the design of a unilateral upper-limb fine motor imagination paradigm and the collection of data from 20 healthy people. It presents a feature extraction algorithm for multi-domain fusion and compares the common spatial pattern (CSP), improved multiscale permutation entropy (IMPE) and multi-domain fusion features of all participants through the use of decision tree, linear discriminant analysis, naive Bayes, a support vector machine, k-nearest neighbor and ensemble classification precision algorithms in the ensemble classifier. For the same subject, the average classification accuracy improvement of the same classifier for multi-domain feature extraction relative to CSP feature results went up by 1.52%. The average classification accuracy improvement of the same classifier went up by 32.87% relative to the IMPE feature classification results. This study's unilateral fine motor imagery paradigm and multi-domain feature fusion algorithm provide new ideas for upper limb rehabilitation after stroke.
Collapse
Affiliation(s)
- Liangyu Yang
- The School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
| | - Tianyu Shi
- The School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
| | - Jidong Lv
- The School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
| | - Yan Liu
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Department of Medical Image, Suzhou 215163, China
- Suzhou Guokekangcheng Medical Technique Co., Ltd., Suzhou 215163, China
| | - Yakang Dai
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Department of Medical Image, Suzhou 215163, China
- Suzhou Guokekangcheng Medical Technique Co., Ltd., Suzhou 215163, China
| | - Ling Zou
- The School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
- Key Laboratory of Brain Machine Collaborative Intelligence Foundation of Zhejiang Province, Hangzhou, Zhejiang 310018, China
| |
Collapse
|
6
|
Korda A, Ventouras E, Asvestas P, Toumaian M, Matsopoulos G, Smyrnis N. Convolutional neural network propagation on electroencephalographic scalograms for detection of schizophrenia. Clin Neurophysiol 2022; 139:90-105. [DOI: 10.1016/j.clinph.2022.04.010] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Revised: 02/11/2022] [Accepted: 04/01/2022] [Indexed: 11/28/2022]
|
7
|
Huang X, Xu Y, Hua J, Yi W, Yin H, Hu R, Wang S. A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain-Computer Interface. Front Neurosci 2021; 15:733546. [PMID: 34489636 PMCID: PMC8417074 DOI: 10.3389/fnins.2021.733546] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Accepted: 07/30/2021] [Indexed: 11/26/2022] Open
Abstract
In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.
Collapse
Affiliation(s)
- Xin Huang
- Software College, Jiangxi Normal University, Nanchang, China
| | - Yilu Xu
- School of Software, Jiangxi Agricultural University, Nanchang, China
| | - Jing Hua
- School of Software, Jiangxi Agricultural University, Nanchang, China
| | - Wenlong Yi
- School of Software, Jiangxi Agricultural University, Nanchang, China
| | - Hua Yin
- School of Software, Jiangxi Agricultural University, Nanchang, China
| | - Ronghua Hu
- School of Mechatronics Engineering, Nanchang University, Nanchang, China
| | - Shiyi Wang
- Youth League Committee, Jiangxi University of Traditional Chinese Medicine, Nanchang, China
| |
Collapse
|
8
|
田 贵, 陈 俊, 丁 鹏, 龚 安, 王 帆, 罗 建, 董 煜, 赵 磊, 党 彩, 伏 云. [Execution, assessment and improvement methods of motor imagery for brain-computer interface]. SHENG WU YI XUE GONG CHENG XUE ZA ZHI = JOURNAL OF BIOMEDICAL ENGINEERING = SHENGWU YIXUE GONGCHENGXUE ZAZHI 2021; 38:434-446. [PMID: 34180188 PMCID: PMC9927765 DOI: 10.7507/1001-5515.202101037] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Revised: 03/09/2021] [Indexed: 11/03/2022]
Abstract
Motor imagery (MI) is an important paradigm of driving brain computer interface (BCI). However, MI is not easy to control or acquire, and the performance of MI-BCI depends heavily on the performance of the subjects' MI. Therefore, the correct execution of MI mental activities, ability evaluation and improvement methods play important and even critical roles in the improvement and application of MI-BCI system's performance. However, in the research and development of MI-BCI, the existing researches mainly focus on the decoding algorithm of MI, but do not pay enough attention to the above three aspects of MI mental activities. In this paper, these problems of MI-BCI are discussed in detail, and it is pointed out that the subjects tend to use visual motor imagery as kinesthetic motor imagery. In the future, we need to develop some objective, quantitatively visualized MI ability evaluation methods, and develop some effective and less time-consumption training methods to improve MI ability. It is also necessary to solve the differences and commonness of MI problems between and within individuals and MI-BCI illiteracy to a certain extent.
Collapse
Affiliation(s)
- 贵鑫 田
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 俊杰 陈
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 鹏 丁
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 安民 龚
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 帆 王
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 建功 罗
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 煜阳 董
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 磊 赵
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 彩萍 党
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
| | - 云发 伏
- 昆明理工大学 信息工程与自动化学院(昆明 650500)School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 昆明理工大学 脑认知与脑机智能融合创新团队(昆明 650500)Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming 650500, P.R.China
- 武警工程大学 信息工程学院(西安 710000)College of Information Engineering, Engineering University of PAP, Xi’an 710000, P.R.China
| |
Collapse
|