Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

Gong, Shu; Xing, Kaibo; Cichocki, Andrzej; Li, Junhua

doi:10.1109/tcds.2021.3079712

Cited by 54 publications

(21 citation statements)

References 274 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs are efficient in processing inputs of large dimensions thanks to their properties of weight-sharing and sparse connections [45]. These properties not only reduce the number of parameters but also reduce training time and enhance training effectiveness [24]. Data scarcity is one issue when it comes to using deep learning models for medical analysis.…”

Section: Discussionmentioning

confidence: 99%

“…Thanks to the availability of several successful deep learning models in the domain of image analysis and computer vision, transfer learning in EEG signals involves converting a one-dimensional EEG signal into a two-dimensional image and applying an existing portion from a learned model from the image domain for classification of the two-dimensional EEG images [22,23]. Gong et al [24] provide a detailed description of the evolution of EEG signal classification from simple statistical methods to deep learning in the last decade.…”

Section: Approaches In Eeg Signal Analysismentioning

confidence: 99%

“…While there have been a variety of tasks related to EEG signal analysis, the identification, analysis, and treatment of alcoholism have been given less attention by researchers. Several recent reviews in the last couple of years [10,19,24,25] covering the state of the art in EEG classification of brain-related activities have identified about a dozen domains of application. However, it seems that more efforts have been spent in EEG analyses in the other domains of neuroscience and neuronal activity classification as compared to alcoholism.…”

Section: Approaches In Eeg Signal Analysismentioning

confidence: 99%

“…Feature extraction is a time-consuming task and requires specific knowledge of the domain and expertise [24]. Moreover, when using traditional machine learning methods, one must experiment with a significant subset of machine learning classifiers before being able to identify the important features and the best-performing classifier.…”

Section: Feature Extraction and Machine Learningmentioning

confidence: 99%

“…In case of limited data, a number of data augmentation techniques are applied to generate synthetic data [59,60]. Deep learning methods are also known to require high computation and suffer from slow convergence [24]. However, the availability of advanced processing units such as the graphical processing units (GPU) and the tensor processing units (TPUs) have solved the computation issues to a large extent [61].…”

Section: Limitations Of the Studymentioning

confidence: 99%

See 4 more Smart Citations

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

Mukhtar

Qaisar

Zaguia

2021

Sensors

View full text Add to dashboard Cite

Alcoholism is attributed to regular or excessive drinking of alcohol and leads to the disturbance of the neuronal system in the human brain. This results in certain malfunctioning of neurons that can be detected by an electroencephalogram (EEG) using several electrodes on a human skull at appropriate positions. It is of great interest to be able to classify an EEG activity as that of a normal person or an alcoholic person using data from the minimum possible electrodes (or channels). Due to the complex nature of EEG signals, accurate classification of alcoholism using only a small dataset is a challenging task. Artificial neural networks, specifically convolutional neural networks (CNNs), provide efficient and accurate results in various pattern-based classification problems. In this work, we apply CNN on raw EEG data and demonstrate how we achieved 98% average accuracy by optimizing a baseline CNN model and outperforming its results in a range of performance evaluation metrics on the University of California at Irvine Machine Learning (UCI-ML) EEG dataset. This article explains the stepwise improvement of the baseline model using the dropout, batch normalization, and kernel regularization techniques and provides a comparison of the two models that can be beneficial for aspiring practitioners who aim to develop similar classification models in CNN. A performance comparison is also provided with other approaches using the same dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Approaches In Eeg Signal Analysismentioning

confidence: 99%

Section: Approaches In Eeg Signal Analysismentioning

confidence: 99%

Section: Feature Extraction and Machine Learningmentioning

confidence: 99%

Section: Limitations Of the Studymentioning

confidence: 99%

See 3 more Smart Citations

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

Mukhtar

Qaisar

Zaguia

2021

Sensors

View full text Add to dashboard Cite

show abstract

EEG‐based biometric authentication system using convolutional neural network for military applications

Vadher,

Patel,

Nair

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

In this technological era, as the need for security arises, the use of biometrics is increasing in authentication systems as a secure and convenient method of human identification and verification. Electroencephalogram (EEG) signals have gained significant attention among the various biometric modalities available because of their unique and unforgeable characteristics. In this study, we have proposed an EEG‐based multi‐subject and multi‐task biometric authentication system for the military applications that address the challenges associated with multi‐task variation in EEG signals. The proposed work considers the use of respective EEG signals for the access of artillery, entrance to highly confidential places for the military and so forth by authenticated personnel only. We have used a multi‐subject, multi‐session, and multi‐task () dataset. The dataset was partially preprocessed with basic signal processing techniques such as bad channel repairing, independent component analysis for artifact removal, downsampling to 250 Hz, and an audio filter of 0.01–200 Hz for signal improvisation. This partially preprocessed dataset was further processed and was used in our deep learning model (DL) architectures. For EEG‐based biometric authentication, convolutional neural network (CNN) outperforms many of the state‐of‐the‐art DL architectures with a validation accuracy of approximately 99.86%, training accuracy of 98.49% and precision, recall and F1‐score with values of 99.91% that makes this EEG‐based approach for authentication more reliable. The DL models were also compared based on training and inference time, where CNN used the most training time but took the least time to predict the output. We compared the performance of the CNN model for three preprocessing techniques by feeding mel spectrograms, chromagrams and mel frequency cepstral coefficients, out of which mel spectrograms provided better results. This proposed architecture proves to be robust and efficient for military applications.

show abstract

Trends in Machine Learning and Electroencephalogram (EEG): A Review for Undergraduate Researchers

Murungi,

Pham,

Dai

et al. 2023

HCI International 2023 – Late Breaking Papers

View full text Add to dashboard Cite

Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

Cited by 54 publications

References 274 publications

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

EEG‐based biometric authentication system using convolutional neural network for military applications

Trends in Machine Learning and Electroencephalogram (EEG): A Review for Undergraduate Researchers

Contact Info

Product

Resources

About