1
|
Adey B, Habib A, Karmakar C. Exploration of an intrinsically explainable self-attention based model for prototype generation on single-channel EEG sleep stage classification. Sci Rep 2024; 14:27612. [PMID: 39528813 PMCID: PMC11555387 DOI: 10.1038/s41598-024-79139-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2024] [Accepted: 11/05/2024] [Indexed: 11/16/2024] Open
Abstract
Prototype-based methods in deep learning offer interpretable explanations for decisions by comparing inputs to typical representatives in the data. This study explores the adaptation of SESM, a self-attention-based prototype method successful in electrocardiogram (ECG) tasks, for electroencephalogram (EEG) signals. The architecture is evaluated on sleep stage classification, exploring its efficacy in predicting stages with single-channel EEG. The model achieves comparable test accuracy compared to EEGNet, a state-of-the-art black-box architecture for EEG classification. The generated prototypical components are exaimed qualitatively and using the area over the perterbation curve (AOPC) indicate some alignment with expected bio-markers for different sleep stages such as alpha spindles and slow waves in non-REM sleep, but the results are severely limited by the model's ability to only extract and present information in the time-domain. Ablation studies are used to explore the impact of kernel size, number of heads, and diversity threshold on model performance and explainability. This study represents the first application of a self-attention based prototype method to EEG data and provides a step forward in explainable AI for EEG data analysis.
Collapse
Affiliation(s)
- Brenton Adey
- School of Information Technology, Deakin University, Geelong, 3225, Australia
| | - Ahsan Habib
- School of Information Technology, Deakin University, Geelong, 3225, Australia.
| | - Chandan Karmakar
- School of Information Technology, Deakin University, Geelong, 3225, Australia
| |
Collapse
|
2
|
K N V, Gupta CN. Systematic review of experimental paradigms and deep neural networks for electroencephalography-based cognitive workload detection. PROGRESS IN BIOMEDICAL ENGINEERING (BRISTOL, ENGLAND) 2024; 6:042004. [PMID: 39655862 DOI: 10.1088/2516-1091/ad8530] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/21/2024] [Accepted: 10/09/2024] [Indexed: 12/18/2024]
Abstract
This article summarizes a systematic literature review of deep neural network-based cognitive workload (CWL) estimation from electroencephalographic (EEG) signals. The focus of this article can be delineated into two main elements: first is the identification of experimental paradigms prevalently employed for CWL induction, and second, is an inquiry about the data structure and input formulations commonly utilized in deep neural networks (DNN)-based CWL detection. The survey revealed several experimental paradigms that can reliably induce either graded levels of CWL or a desired cognitive state due to sustained induction of CWL. This article has characterized them with respect to the number of distinct CWL levels, cognitive states, experimental environment, and agents in focus. Further, this literature analysis found that DNNs can successfully detect distinct levels of CWL despite the inter-subject and inter-session variability typically observed in EEG signals. Several methodologies were found using EEG signals in its native representation of a two-dimensional matrix as input to the classification algorithm, bypassing traditional feature selection steps. More often than not, researchers used DNNs as black-box type models, and only a few studies employed interpretable or explainable DNNs for CWL detection. However, these algorithms were mostly post hoc data analysis and classification schemes, and only a few studies adopted real-time CWL estimation methodologies. Further, it has been suggested that using interpretable deep learning methodologies may shed light on EEG correlates of CWL, but this remains mostly an unexplored area. This systematic review suggests using networks sensitive to temporal dependencies and appropriate input formulations for each type of DNN architecture to achieve robust classification performance. An additional suggestion is to utilize transfer learning methods to achieve high generalizability across tasks (task-independent classifiers), while simple cross-subject data pooling may achieve the same for subject-independent classifiers.
Collapse
Affiliation(s)
- Vishnu K N
- Neural Engineering Lab, Department of Biosciences and Bioengineering, Indian Institute of Technology Guwahati, Assam 781039, India
| | - Cota Navin Gupta
- Neural Engineering Lab, Department of Biosciences and Bioengineering, Indian Institute of Technology Guwahati, Assam 781039, India
| |
Collapse
|
3
|
Liao L, Lu J, Wang L, Zhang Y, Gao D, Wang M. CT-Net: an interpretable CNN-Transformer fusion network for fNIRS classification. Med Biol Eng Comput 2024; 62:3233-3247. [PMID: 38816665 DOI: 10.1007/s11517-024-03138-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Accepted: 05/23/2024] [Indexed: 06/01/2024]
Abstract
Functional near-infrared spectroscopy (fNIRS), an optical neuroimaging technique, has been widely used in the field of brain activity recognition and brain-computer interface. Existing works have proposed deep learning-based algorithms for the fNIRS classification problem. In this paper, a novel approach based on convolutional neural network and Transformer, named CT-Net, is established to guide the deep modeling for the classification of mental arithmetic (MA) tasks. We explore the effect of data representations, and design a temporal-level combination of two raw chromophore signals to improve the data utilization and enrich the feature learning of the model. We evaluate our model on two open-access datasets and achieve the classification accuracy of 98.05% and 77.61%, respectively. Moreover, we explain our model by the gradient-weighted class activation mapping, which presents a high consistent between the contributing value of features learned by the model and the mapping of brain activity in the MA task. The results suggest the feasibility and interpretability of CT-Net for decoding MA tasks.
Collapse
Affiliation(s)
- Lingxiang Liao
- School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China
| | - Jingqing Lu
- School of Life Sciences and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China
| | - Lutao Wang
- School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China
| | - Yongqing Zhang
- School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China
| | - Dongrui Gao
- School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China
| | - Manqing Wang
- School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China.
- School of Life Sciences and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, China.
| |
Collapse
|
4
|
Li D, Wang J, Xu J, Fang X, Ji Y. Cross-Channel Specific-Mutual Feature Transfer Learning for Motor Imagery EEG Signals Decoding. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:13472-13482. [PMID: 37220058 DOI: 10.1109/tnnls.2023.3269512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
In recent years, with the rapid development of deep learning, various deep learning frameworks have been widely used in brain-computer interface (BCI) research for decoding motor imagery (MI) electroencephalogram (EEG) signals to understand brain activity accurately. The electrodes, however, record the mixed activities of neurons. If different features are directly embedded in the same feature space, the specific and mutual features of different neuron regions are not considered, which will reduce the expression ability of the feature itself. We propose a cross-channel specific-mutual feature transfer learning (CCSM-FT) network model to solve this problem. The multibranch network extracts the specific and mutual features of brain's multiregion signals. Effective training tricks are used to maximize the distinction between the two kinds of features. Suitable training tricks can also improve the effectiveness of the algorithm compared with novel models. Finally, we transfer two kinds of features to explore the potential of mutual and specific features to enhance the expressive power of the feature and use the auxiliary set to improve identification performance. The experimental results show that the network has a better classification effect in the BCI Competition IV-2a and the HGD datasets.
Collapse
|
5
|
Zayed A, Belhadj N, Ben Khalifa K, Bedoui MH, Valderrama C. Efficient Generalized Electroencephalography-Based Drowsiness Detection Approach with Minimal Electrodes. SENSORS (BASEL, SWITZERLAND) 2024; 24:4256. [PMID: 39001037 PMCID: PMC11244425 DOI: 10.3390/s24134256] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/13/2024] [Revised: 06/21/2024] [Accepted: 06/27/2024] [Indexed: 07/16/2024]
Abstract
Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an electroencephalography (EEG)-based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM), the K nearest neighbor (KNN), the Naive Bayes (NB), the Decision Tree (DT), and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake and drowsy). Segmentation into 10 s intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries.
Collapse
Affiliation(s)
- Aymen Zayed
- Technology and Medical Imaging Laboratory, Faculty of Medicine Monastir, University of Monastir, Monastir 5019, Tunisia
- National Engineering School of Sousse, University of Sousse, BP 264 Erriyadh, Sousse 4023, Tunisia
- Department of Electronics and Microelectronics (SEMi), University of Mons, 7000 Mons, Belgium
| | - Nidhameddine Belhadj
- Laboratory of Electronics and Microelectronics, Faculty of Sciences of Monastir, Monsatir 5019, Tunisia
| | - Khaled Ben Khalifa
- Technology and Medical Imaging Laboratory, Faculty of Medicine Monastir, University of Monastir, Monastir 5019, Tunisia
- Higher Institute of Applied Science and Technology of Sousse, University of Sousse, Sousse 4003, Tunisia
| | - Mohamed Hedi Bedoui
- Technology and Medical Imaging Laboratory, Faculty of Medicine Monastir, University of Monastir, Monastir 5019, Tunisia
| | - Carlos Valderrama
- Department of Electronics and Microelectronics (SEMi), University of Mons, 7000 Mons, Belgium
| |
Collapse
|
6
|
Siddiqui HUR, Akmal A, Iqbal M, Saleem AA, Raza MA, Zafar K, Zaib A, Dudley S, Arambarri J, Castilla ÁK, Rustam F. Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence. SENSORS (BASEL, SWITZERLAND) 2024; 24:3754. [PMID: 38931541 PMCID: PMC11207316 DOI: 10.3390/s24123754] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/07/2024] [Revised: 06/01/2024] [Accepted: 06/05/2024] [Indexed: 06/28/2024]
Abstract
Driving while drowsy poses significant risks, including reduced cognitive function and the potential for accidents, which can lead to severe consequences such as trauma, economic losses, injuries, or death. The use of artificial intelligence can enable effective detection of driver drowsiness, helping to prevent accidents and enhance driver performance. This research aims to address the crucial need for real-time and accurate drowsiness detection to mitigate the impact of fatigue-related accidents. Leveraging ultra-wideband radar data collected over five minutes, the dataset was segmented into one-minute chunks and transformed into grayscale images. Spatial features are retrieved from the images using a two-dimensional Convolutional Neural Network. Following that, these features were used to train and test multiple machine learning classifiers. The ensemble classifier RF-XGB-SVM, which combines Random Forest, XGBoost, and Support Vector Machine using a hard voting criterion, performed admirably with an accuracy of 96.6%. Additionally, the proposed approach was validated with a robust k-fold score of 97% and a standard deviation of 0.018, demonstrating significant results. The dataset is augmented using Generative Adversarial Networks, resulting in improved accuracies for all models. Among them, the RF-XGB-SVM model outperformed the rest with an accuracy score of 99.58%.
Collapse
Affiliation(s)
- Hafeez Ur Rehman Siddiqui
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Ambreen Akmal
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Muhammad Iqbal
- Institute of Computer and Software Engineering, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan 64200, Punjab, Pakistan;
| | - Adil Ali Saleem
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Muhammad Amjad Raza
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Kainat Zafar
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Aqsa Zaib
- Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan; (A.A.); (A.A.S.); (M.A.R.); (K.Z.); (A.Z.)
| | - Sandra Dudley
- Bioengineering Research Centre, School of Engineering, London South Bank University, 103 Borough Road, London SE1 0AA, UK;
| | - Jon Arambarri
- Universidade Internacional do Cuanza, Cuito EN250, Angola; (J.A.); (Á.K.C.)
- Fundación Universitaria Internacional de Colombia, Bogotá 111321, Colombia
- Universidad Internacional Iberoamericana, Campeche 24560, Mexico
| | - Ángel Kuc Castilla
- Universidade Internacional do Cuanza, Cuito EN250, Angola; (J.A.); (Á.K.C.)
- Universidad de La Romana, La Romana 22000, Dominican Republic
- Universidad Europea del Atlántico, Isabel Torres 21, 39011 Santander, Spain
| | - Furqan Rustam
- School of Computing, National College of Ireland, Dublin D01 K6W2, Ireland
| |
Collapse
|
7
|
Gupta K. A robust deep learning system for screening of obstructive sleep apnea using T-F spectrum of ECG signals. Comput Methods Biomech Biomed Engin 2024:1-13. [PMID: 38829354 DOI: 10.1080/10255842.2024.2359635] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 05/20/2024] [Indexed: 06/05/2024]
Abstract
Obstructive sleep apnea (OSA) is a non-communicable sleep-related medical condition marked by repeated disruptions in breathing during sleep. It may induce various cardiovascular and neurocognitive complications. Electrocardiography (ECG) is a useful method for detecting numerous health-related disorders. ECG signals provide a less complex and non-invasive solution for the screening of OSA. Automated and accurate detection of OSA may enhance diagnostic performance and reduce the clinician's workload. Traditional machine learning methods typically involve several labor-intensive manual procedures, including signal decomposition, feature evaluation, selection, and categorization. This article presents the time-frequency (T-F) spectrum classification of de-noised ECG data for the automatic screening of OSA patients using deep convolutional neural networks (DCNNs). At first, a filter-fusion algorithm is used to eliminate the artifacts from the raw ECG data. Stock-well transform (S-T) is employed to change filtered time-domain ECG into T-F spectrums. To discriminate between apnea and normal ECG signals, the obtained T-F spectrums are categorized using benchmark Alex-Net and Squeeze-Net, along with a less complex DCNN. The superiority of the presented system is measured by computing the sensitivity, specificity, accuracy, negative predicted value, precision, F1-score, and Fowlkes-Mallows index. The results of comparing all three utilized DCNNs reveal that the proposed DCNN requires fewer learning parameters and provides higher accuracy. An average accuracy of 95.31% is yielded using the proposed system. The presented deep learning system is lightweight and faster than Alex-Net and Squeeze-Net as it utilizes fewer learnable parameters, making it simple and reliable.
Collapse
Affiliation(s)
- Kapil Gupta
- School of Computer Sciences, University of Petroleum and Energy Studies (UPES), Dehradun, India
| |
Collapse
|
8
|
Yuan L, Li R, Cui J, Siyal MY. SPARK: A High-Efficiency Black-Box Domain Adaptation Framework for Source Privacy-Preserving Drowsiness Detection. IEEE J Biomed Health Inform 2024; 28:3478-3488. [PMID: 38483803 DOI: 10.1109/jbhi.2024.3377373] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/07/2024]
Abstract
Developing an effective and efficient electroencephalography (EEG)-based drowsiness monitoring system is crucial for enhancing road safety and reducing the risk of accidents. For general usage, cross-subject evaluation is indispensable. Despite progress in unsupervised domain adaptation (UDA) and source-free domain adaptation (SFDA) methods, these often rely on the availability of labeled source data or white-box source models, posing potential privacy risks. This study explores a more challenging setting of UDA for EEG-based drowsiness detection, termed black-box domain adaptation (BBDA). In BBDA, adaptation in the target domain relies solely on a black-box source model, without access to the source data or parameters of the source model. Specifically, we propose a framework called Self-distillation and Pseudo-labelling for Ensemble Deep Random Vector Functional Link (edRVFL)-based Black-box Knowledge Adaptation (SPARK). SPARK employs entropy-based selection of high-confidence samples, which are then pseudo-labeled to train a student edRVFL network. Subsequently, ensemble self-distillation is performed to extract knowledge by training the edRVFL using refined labels introduced by ensemble learning. This process further improves the robustness of the student edRVFL network. The features of the edRVFL are beneficial for improving the computational efficiency of the framework, making it more suitable for tasks involving small datasets. The proposed SPARK framework is evaluated on two publicly available driver drowsiness datasets. Experimental results demonstrate its superior performance over strong baselines, while significantly reducing training time. These findings underscore the potential for practical integration of the proposed framework into drowsiness monitoring systems, thereby contributing substantially to the privacy preservation of source subjects.
Collapse
|
9
|
He L, Zhang L, Lin X, Qin Y. A novel deep-learning model based on τ-shaped convolutional network (τNet) with long short-term memory (LSTM) for physiological fatigue detection from EEG and EOG signals. Med Biol Eng Comput 2024; 62:1781-1793. [PMID: 38374416 DOI: 10.1007/s11517-024-03033-y] [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: 09/06/2023] [Accepted: 01/21/2024] [Indexed: 02/21/2024]
Abstract
In recent years, fatigue driving has become the main cause of traffic accidents, leading to increased attention towards fatigue detection systems. However, the pooling and strided convolutional operations in fatigue detection algorithm based on traditional deep learning methods may led to the loss of some useful information. This paper proposed a novel τ -shaped convolutional network ( τ Net ) aiming to address this issue. Unlike traditional network structures, τ Net incorporates the operations of upsampling features and concatenating high- and low-level features, enabling full utilization of useful information. Moreover, considering that the fatigue state is a mental state involving temporal evolution, we proposed the novel long short-term memory (LSTM)- τ -shaped convolutional network (LSTM- τ Net ), a parallel structure composed of LSTM and τ Net for fatigue detection, where τ Net extracts time-invariant features with location information, and LSTM extracts long temporal dependencies. We compared LSTM- τ Net with six competing methods based on two datasets. Results showed that the proposed algorithm achieved higher classification accuracy than the other methods, with 94.25% on EEG data (binary classification) and 82.19% on EOG data (triple classification). Additionally, the proposed algorithm exhibits low computational cost, good training stability, and robustness against insufficient training. Therefore, it is promising for further implementation of fatigue online detection systems.
Collapse
Affiliation(s)
- Le He
- State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing, 400044, People's Republic of China
| | - Li Zhang
- State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing, 400044, People's Republic of China.
| | - Xiangtian Lin
- State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing, 400044, People's Republic of China
| | - Yunfeng Qin
- State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing, 400044, People's Republic of China
| |
Collapse
|
10
|
Ludwig S, Bakas S, Adamos DA, Laskaris N, Panagakis Y, Zafeiriou S. EEGminer: discovering interpretable features of brain activity with learnable filters. J Neural Eng 2024; 21:036010. [PMID: 38684154 DOI: 10.1088/1741-2552/ad44d7] [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: 07/28/2023] [Accepted: 04/29/2024] [Indexed: 05/02/2024]
Abstract
Objective. The patterns of brain activity associated with different brain processes can be used to identify different brain states and make behavioural predictions. However, the relevant features are not readily apparent and accessible. Our aim is to design a system for learning informative latent representations from multichannel recordings of ongoing EEG activity.Approach: We propose a novel differentiable decoding pipeline consisting of learnable filters and a pre-determined feature extraction module. Specifically, we introduce filters parameterized by generalized Gaussian functions that offer a smooth derivative for stable end-to-end model training and allow for learning interpretable features. For the feature module, we use signal magnitude and functional connectivity estimates.Main results.We demonstrate the utility of our model on a new EEG dataset of unprecedented size (i.e. 721 subjects), where we identify consistent trends of music perception and related individual differences. Furthermore, we train and apply our model in two additional datasets, specifically for emotion recognition on SEED and workload classification on simultaneous task EEG workload. The discovered features align well with previous neuroscience studies and offer new insights, such as marked differences in the functional connectivity profile between left and right temporal areas during music listening. This agrees with the specialisation of the temporal lobes regarding music perception proposed in the literature.Significance. The proposed method offers strong interpretability of learned features while reaching similar levels of accuracy achieved by black box deep learning models. This improved trustworthiness may promote the use of deep learning models in real world applications. The model code is available athttps://github.com/SMLudwig/EEGminer/.
Collapse
Affiliation(s)
- Siegfried Ludwig
- Department of Computing, Imperial College London, London SW7 2RH, United Kingdom
- Cogitat Ltd, London, United Kingdom
| | - Stylianos Bakas
- Department of Computing, Imperial College London, London SW7 2RH, United Kingdom
- School of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece
- Cogitat Ltd, London, United Kingdom
| | - Dimitrios A Adamos
- Department of Computing, Imperial College London, London SW7 2RH, United Kingdom
- Cogitat Ltd, London, United Kingdom
| | - Nikolaos Laskaris
- School of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece
- Cogitat Ltd, London, United Kingdom
| | - Yannis Panagakis
- Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens 15784, Greece
- Cogitat Ltd, London, United Kingdom
| | - Stefanos Zafeiriou
- Department of Computing, Imperial College London, London SW7 2RH, United Kingdom
- Cogitat Ltd, London, United Kingdom
| |
Collapse
|
11
|
Gao D, Li P, Wang M, Liang Y, Liu S, Zhou J, Wang L, Zhang Y. CSF-GTNet: A Novel Multi-Dimensional Feature Fusion Network Based on Convnext-GeLU- BiLSTM for EEG-Signals-Enabled Fatigue Driving Detection. IEEE J Biomed Health Inform 2024; 28:2558-2568. [PMID: 37022236 DOI: 10.1109/jbhi.2023.3240891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
Electroencephalography (EEG) signal has been recognized as an effective fatigue detection method, which can intuitively reflect the drivers' mental state. However, the research on multi-dimensional features in existing work could be much better. The instability and complexity of EEG signals will increase the difficulty of extracting data features. More importantly, most current work only treats deep learning models as classifiers. They ignored the features of different subjects learned by the model. Aiming at the above problems, this paper proposes a novel multi-dimensional feature fusion network, CSF-GTNet, based on time and space-frequency domains for fatigue detection. Specifically, it comprises Gaussian Time Domain Network (GTNet) and Pure Convolutional Spatial Frequency Domain Network (CSFNet). The experimental results show that the proposed method effectively distinguishes between alert and fatigue states. The accuracy rates are 85.16% and 81.48% on the self-made and SEED-VIG datasets, respectively, which are higher than the state-of-the-art methods. Moreover, we analyze the contribution of each brain region for fatigue detection through the brain topology map. In addition, we explore the changing trend of each frequency band and the significance between different subjects in the alert state and fatigue state through the heat map. Our research can provide new ideas in brain fatigue research and play a specific role in promoting the development of this field.
Collapse
|
12
|
Miao M, Yang Z, Zeng H, Zhang W, Xu B, Hu W. Explainable cross-task adaptive transfer learning for motor imagery EEG classification. J Neural Eng 2023; 20:066021. [PMID: 37963394 DOI: 10.1088/1741-2552/ad0c61] [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: 07/17/2023] [Accepted: 11/14/2023] [Indexed: 11/16/2023]
Abstract
Objective. In the field of motor imagery (MI) electroencephalography (EEG)-based brain-computer interfaces, deep transfer learning (TL) has proven to be an effective tool for solving the problem of limited availability in subject-specific data for the training of robust deep learning (DL) models. Although considerable progress has been made in the cross-subject/session and cross-device scenarios, the more challenging problem of cross-task deep TL remains largely unexplored.Approach. We propose a novel explainable cross-task adaptive TL method for MI EEG decoding. Firstly, similarity analysis and data alignment are performed for EEG data of motor execution (ME) and MI tasks. Afterwards, the MI EEG decoding model is obtained via pre-training with extensive ME EEG data and fine-tuning with partial MI EEG data. Finally, expected gradient-based post-hoc explainability analysis is conducted for the visualization of important temporal-spatial features.Main results. Extensive experiments are conducted on one large ME EEG High-Gamma dataset and two large MI EEG datasets (openBMI and GIST). The best average classification accuracy of our method reaches 80.00% and 72.73% for OpenBMI and GIST respectively, which outperforms several state-of-the-art algorithms. In addition, the results of the explainability analysis further validate the correlation between ME and MI EEG data and the effectiveness of ME/MI cross-task adaptation.Significance. This paper confirms that the decoding of MI EEG can be well facilitated by pre-existing ME EEG data, which largely relaxes the constraint of training samples for MI EEG decoding and is important in a practical sense.
Collapse
Affiliation(s)
- Minmin Miao
- School of Information Engineering, Huzhou University, Huzhou, People's Republic of China
- Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou University, Huzhou, People's Republic of China
| | - Zhong Yang
- School of Information Engineering, Huzhou University, Huzhou, People's Republic of China
| | - Hong Zeng
- School of Instrument Science and Engineering, Southeast University, Nanjing, People's Republic of China
| | - Wenbin Zhang
- College of Computer and Information, Hohai University, Nanjing, People's Republic of China
| | - Baoguo Xu
- School of Instrument Science and Engineering, Southeast University, Nanjing, People's Republic of China
| | - Wenjun Hu
- School of Information Engineering, Huzhou University, Huzhou, People's Republic of China
- Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou University, Huzhou, People's Republic of China
| |
Collapse
|
13
|
Alreshidi I, Bisandu D, Moulitsas I. Illuminating the Neural Landscape of Pilot Mental States: A Convolutional Neural Network Approach with Shapley Additive Explanations Interpretability. SENSORS (BASEL, SWITZERLAND) 2023; 23:9052. [PMID: 38005440 PMCID: PMC10674947 DOI: 10.3390/s23229052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Revised: 10/31/2023] [Accepted: 11/07/2023] [Indexed: 11/26/2023]
Abstract
Predicting pilots' mental states is a critical challenge in aviation safety and performance, with electroencephalogram data offering a promising avenue for detection. However, the interpretability of machine learning and deep learning models, which are often used for such tasks, remains a significant issue. This study aims to address these challenges by developing an interpretable model to detect four mental states-channelised attention, diverted attention, startle/surprise, and normal state-in pilots using EEG data. The methodology involves training a convolutional neural network on power spectral density features of EEG data from 17 pilots. The model's interpretability is enhanced via the use of SHapley Additive exPlanations values, which identify the top 10 most influential features for each mental state. The results demonstrate high performance in all metrics, with an average accuracy of 96%, a precision of 96%, a recall of 94%, and an F1 score of 95%. An examination of the effects of mental states on EEG frequency bands further elucidates the neural mechanisms underlying these states. The innovative nature of this study lies in its combination of high-performance model development, improved interpretability, and in-depth analysis of the neural correlates of mental states. This approach not only addresses the critical need for effective and interpretable mental state detection in aviation but also contributes to our understanding of the neural underpinnings of these states. This study thus represents a significant advancement in the field of EEG-based mental state detection.
Collapse
Affiliation(s)
- Ibrahim Alreshidi
- Centre for Computational Engineering Sciences, Cranfield University, Cranfield MK43 0AL, UK;
- Machine Learning and Data Analytics Laboratory, Digital Aviation Research and Technology Centre (DARTeC), Cranfield University, Cranfield MK43 0AL, UK
- College of Computer Science and Engineering, University of Ha’il, Ha’il 81451, Saudi Arabia
| | - Desmond Bisandu
- Centre for Computational Engineering Sciences, Cranfield University, Cranfield MK43 0AL, UK;
- Machine Learning and Data Analytics Laboratory, Digital Aviation Research and Technology Centre (DARTeC), Cranfield University, Cranfield MK43 0AL, UK
| | - Irene Moulitsas
- Centre for Computational Engineering Sciences, Cranfield University, Cranfield MK43 0AL, UK;
- Machine Learning and Data Analytics Laboratory, Digital Aviation Research and Technology Centre (DARTeC), Cranfield University, Cranfield MK43 0AL, UK
| |
Collapse
|
14
|
Wang Q, Smythe D, Cao J, Hu Z, Proctor KJ, Owens AP, Zhao Y. Characterisation of Cognitive Load Using Machine Learning Classifiers of Electroencephalogram Data. SENSORS (BASEL, SWITZERLAND) 2023; 23:8528. [PMID: 37896621 PMCID: PMC10611194 DOI: 10.3390/s23208528] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 10/09/2023] [Accepted: 10/16/2023] [Indexed: 10/29/2023]
Abstract
A high cognitive load can overload a person, potentially resulting in catastrophic accidents. It is therefore important to ensure the level of cognitive load associated with safety-critical tasks (such as driving a vehicle) remains manageable for drivers, enabling them to respond appropriately to changes in the driving environment. Although electroencephalography (EEG) has attracted significant interest in cognitive load research, few studies have used EEG to investigate cognitive load in the context of driving. This paper presents a feasibility study on the simulation of various levels of cognitive load through designing and implementing four driving tasks. We employ machine learning-based classification techniques using EEG recordings to differentiate driving conditions. An EEG dataset containing these four driving tasks from a group of 20 participants was collected to investigate whether EEG can be used as an indicator of changes in cognitive load. The collected dataset was used to train four Deep Neural Networks and four Support Vector Machine classification models. The results showed that the best model achieved a classification accuracy of 90.37%, utilising statistical features from multiple frequency bands in 24 EEG channels. Furthermore, the Gamma and Beta bands achieved higher classification accuracy than the Alpha and Theta bands during the analysis. The outcomes of this study have the potential to enhance the Human-Machine Interface of vehicles, contributing to improved safety.
Collapse
Affiliation(s)
- Qi Wang
- School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK; (Q.W.); (D.S.); (J.C.); (Z.H.)
| | - Daniel Smythe
- School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK; (Q.W.); (D.S.); (J.C.); (Z.H.)
| | - Jun Cao
- School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK; (Q.W.); (D.S.); (J.C.); (Z.H.)
| | - Zhilin Hu
- School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK; (Q.W.); (D.S.); (J.C.); (Z.H.)
| | - Karl J. Proctor
- Jaguar Land Rover Research, Coventry CV4 7AL, UK; (K.J.P.); (A.P.O.)
| | - Andrew P. Owens
- Jaguar Land Rover Research, Coventry CV4 7AL, UK; (K.J.P.); (A.P.O.)
| | - Yifan Zhao
- School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK; (Q.W.); (D.S.); (J.C.); (Z.H.)
| |
Collapse
|
15
|
Yu Y, Bezerianos A, Cichocki A, Li J. Latent Space Coding Capsule Network for Mental Workload Classification. IEEE Trans Neural Syst Rehabil Eng 2023; 31:3417-3427. [PMID: 37607136 DOI: 10.1109/tnsre.2023.3307481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/24/2023]
Abstract
Mental workload can be monitored in real time, which helps us improve work efficiency by maintaining an appropriate workload level. Based on previous studies, we have known that features, such as band power and brain connectivity, can be utilized to classify the levels of mental workload. As band power and brain connectivity represent different but complementary information related to mental workload, it is helpful to integrate them together for workload classification. Although deep learning models have been utilized for workload classification based on EEG, the classification performance is not satisfactory. This is because the current models cannot well tackle variances in the features extracted from non-stationary EEG. In order to address this problem, we, in this study, proposed a novel deep learning model, called latent space coding capsule network (LSCCN). The features of band power and brain connectivity were fused and then modelled in a latent space. The subsequent convolutional and capsule modules were used for workload classification. The proposed LSCCN was compared to the state-of-the-art methods. The results demonstrated that the proposed LSCCN was superior to the compared methods. LSCCN achieved a higher testing accuracy with a relatively smaller standard deviation, indicating a more reliable classification across participants. In addition, we explored the distribution of the features and found that top discriminative features were localized in the frontal, parietal, and occipital regions. This study not only provides a novel deep learning model but also informs further studies in workload classification and promotes practical usage of workload monitoring.
Collapse
|
16
|
Statsenko Y, Babushkin V, Talako T, Kurbatova T, Smetanina D, Simiyu GL, Habuza T, Ismail F, Almansoori TM, Gorkom KNV, Szólics M, Hassan A, Ljubisavljevic M. Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach. Biomedicines 2023; 11:2370. [PMID: 37760815 PMCID: PMC10525492 DOI: 10.3390/biomedicines11092370] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Revised: 07/13/2023] [Accepted: 07/21/2023] [Indexed: 09/29/2023] Open
Abstract
Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the non-overlapping window technique, which we tested on the TUSZ dataset. The system accurately detects seizure episodes (87.7% Sn, 91.16% Sp) and carefully distinguishes eight seizure types (95-100% Acc). An increase in EEG sampling rate from 50 to 250 Hz boosted model performance: the precision of seizure detection rose by 5%, and seizure differentiation by 7%. A low sampling rate is a reasonable solution for training reliable models with EEG data. Decreasing the number of EEG electrodes from 21 to 8 did not affect seizure detection but worsened seizure differentiation significantly: 98.24 ± 0.17 vs. 85.14 ± 3.14% recall. In detecting epileptic episodes, all electrodes provided equally informative input, but in seizure differentiation, their informative value varied. We improved model explainability with interpretable ML. Activation maximization highlighted the presence of EEG patterns specific to eight seizure types. Cortical projection of epileptic sources depicted differences between generalized and focal seizures. Interpretable ML techniques confirmed that our system recognizes biologically meaningful features as indicators of epileptic activity in EEG.
Collapse
Affiliation(s)
- Yauhen Statsenko
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
- Medical Imaging Platform, ASPIRE Precision Medicine Research Institute Abu Dhabi, Al Ain P.O. Box 15551, United Arab Emirates
- Big Data Analytics Center, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Vladimir Babushkin
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Tatsiana Talako
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
- Department of Oncohematology, Minsk Scientific and Practical Center for Surgery, Transplantology and Hematology, 220089 Minsk, Belarus
| | - Tetiana Kurbatova
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Darya Smetanina
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Gillian Lylian Simiyu
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Tetiana Habuza
- Big Data Analytics Center, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
- Department of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Fatima Ismail
- Pediatric Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Taleb M. Almansoori
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Klaus N.-V. Gorkom
- Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Miklós Szólics
- Neurology Division, Medicine Department, Tawam Hospital, Al Ain P.O. Box 15258, United Arab Emirates
- Internal Medicine Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Ali Hassan
- Neurology Division, Medicine Department, Tawam Hospital, Al Ain P.O. Box 15258, United Arab Emirates
| | - Milos Ljubisavljevic
- Physiology Department, College of Medicine and Health Sciences, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates;
- Neuroscience Platform, ASPIRE Precision Medicine Research Institute Abu Dhabi, Al Ain P.O. Box 15551, United Arab Emirates
| |
Collapse
|
17
|
Cui J, Yuan L, Wang Z, Li R, Jiang T. Towards best practice of interpreting deep learning models for EEG-based brain computer interfaces. Front Comput Neurosci 2023; 17:1232925. [PMID: 37663037 PMCID: PMC10470463 DOI: 10.3389/fncom.2023.1232925] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Accepted: 07/24/2023] [Indexed: 09/05/2023] Open
Abstract
Introduction As deep learning has achieved state-of-the-art performance for many tasks of EEG-based BCI, many efforts have been made in recent years trying to understand what have been learned by the models. This is commonly done by generating a heatmap indicating to which extent each pixel of the input contributes to the final classification for a trained model. Despite the wide use, it is not yet understood to which extent the obtained interpretation results can be trusted and how accurate they can reflect the model decisions. Methods We conduct studies to quantitatively evaluate seven different deep interpretation techniques across different models and datasets for EEG-based BCI. Results The results reveal the importance of selecting a proper interpretation technique as the initial step. In addition, we also find that the quality of the interpretation results is inconsistent for individual samples despite when a method with an overall good performance is used. Many factors, including model structure and dataset types, could potentially affect the quality of the interpretation results. Discussion Based on the observations, we propose a set of procedures that allow the interpretation results to be presented in an understandable and trusted way. We illustrate the usefulness of our method for EEG-based BCI with instances selected from different scenarios.
Collapse
Affiliation(s)
- Jian Cui
- Research Center for Augmented Intelligence, Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China
| | - Liqiang Yuan
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore
| | - Zhaoxiang Wang
- Research Center for Augmented Intelligence, Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China
| | - Ruilin Li
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore
| | - Tianzi Jiang
- Research Center for Augmented Intelligence, Research Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou, China
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| |
Collapse
|
18
|
Aydemir E, Baygin M, Dogan S, Tuncer T, Barua PD, Chakraborty S, Faust O, Arunkumar N, Kaysi F, Acharya UR. Mental performance classification using fused multilevel feature generation with EEG signals. INTERNATIONAL JOURNAL OF HEALTHCARE MANAGEMENT 2022. [DOI: 10.1080/20479700.2022.2130645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/10/2022]
Affiliation(s)
- Emrah Aydemir
- Department of Management Information, College of Management, Sakarya University, Sakarya, Turkey
| | - Mehmet Baygin
- Department of Computer Engineering, College of Engineering, Ardahan University, Ardahan, Turkey
| | - Sengul Dogan
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey
| | - Turker Tuncer
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey
| | - Prabal Datta Barua
- School of Management & Enterprise, University of Southern Queensland, Darling Heights, Australia
- Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia
| | - Subrata Chakraborty
- School of Science and Technology, Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, Australia
- Center for Advanced Modelling and Geospatial Information Systems, Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia
| | - Oliver Faust
- School of Computing, Anglia Ruskin University, Cambridge, UK
| | - N. Arunkumar
- Department of Electronics and Instrumentation, SASTRA University, Thanjavur, India
| | - Feyzi Kaysi
- Department of Electronic and Automation, Vocational School of Technical Sciences, Istanbul University-Cerrahpasa, Istanbul, Turkey
| | - U. Rajendra Acharya
- Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore, Singapore
- Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore, Singapore
- Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan
| |
Collapse
|
19
|
An Efficient Hybrid Model for Patient-Independent Seizure Prediction Using Deep Learning. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12115516] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
Recently, many researchers have deployed different deep learning techniques to predict epileptic seizure, using electroencephalogram signals. However, most of this research requires very large amounts of memory and complicated feature extraction algorithms. In addition, they could not precisely examine EEG signal characteristics, which led to poor prediction performance. In this research, a non-patient-specific epileptic seizure prediction approach is proposed. The proposed model integrates Wavelet-based EEG signal processing with deep learning architectures for efficient prediction of pre-ictal and inter-ictal signals. The proposed system uses different models of one-dimensional convolutional neural networks to discriminate between inter-ictal signal and pre-ictal signals in order to enhance prediction performance. Experiments have been carried out on a benchmark dataset to validate the robustness of the proposed model. The experimental results showed that the proposed approach achieved 93.4% for 16 patients and 97.87% for 6 patients. Experiments showed that the proposed model can predict epileptic seizures effectively, which can have remarkable potential in clinical applications.
Collapse
|
20
|
Coupled Projection Transfer Metric Learning for Cross-Session Emotion Recognition from EEG. SYSTEMS 2022. [DOI: 10.3390/systems10020047] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
Distribution discrepancies between different sessions greatly degenerate the performance of video-evoked electroencephalogram (EEG) emotion recognition. There are discrepancies since the EEG signal is weak and non-stationary and these discrepancies are manifested in different trails in each session and even in some trails which belong to the same emotion. To this end, we propose a Coupled Projection Transfer Metric Learning (CPTML) model to jointly complete domain alignment and graph-based metric learning, which is a unified framework to simultaneously minimize cross-session and cross-trial divergences. By experimenting on the SEED_IV emotional dataset, we show that (1) CPTML exhibits a significantly better performance than several other approaches; (2) the cross-session distribution discrepancies are minimized and emotion metric graph across different trials are optimized in the CPTML-induced subspace, indicating the effectiveness of data alignment and metric exploration; and (3) critical EEG frequency bands and channels for emotion recognition are automatically identified from the learned projection matrices, providing more insights into the occurrence of the effect.
Collapse
|