The Implementation of EEG Transfer Learning Method Using Integrated Selection for Motor Imagery Signal

Ramadhani, Aris; Fauzi, Hilman; Wijayanto, Inung; Rizal, Achmad; Shapiai, Mohd Ibrahim

doi:10.1007/978-981-33-6926-9_39

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Affes et al [ 30 ] proposed a cascading deep learning model called CAtt-MLP for channel selection, consisting of convolutional blocks, an attention neural network, and a multi-layer perceptron (MLP). Ramadhani et al [ 31 ] applied integrated selection to remove irrelevant channels, improving brain–computer interface performance. Dura and Wosiak [ 32 ] used a reversed correlation algorithm (RCA) to automatically select optimal EEG electrodes.…”

Section: Methodsmentioning

confidence: 99%

Optimizing 1D-CNN-Based Emotion Recognition Process through Channel and Feature Selection from EEG Signals

Aldawsari,

Al-Ahmadi,

Muhammad

2023

Diagnostics

View full text Add to dashboard Cite

EEG-based emotion recognition has numerous real-world applications in fields such as affective computing, human-computer interaction, and mental health monitoring. This offers the potential for developing IOT-based, emotion-aware systems and personalized interventions using real-time EEG data. This study focused on unique EEG channel selection and feature selection methods to remove unnecessary data from high-quality features. This helped improve the overall efficiency of a deep learning model in terms of memory, time, and accuracy. Moreover, this work utilized a lightweight deep learning method, specifically one-dimensional convolutional neural networks (1D-CNN), to analyze EEG signals and classify emotional states. By capturing intricate patterns and relationships within the data, the 1D-CNN model accurately distinguished between emotional states (HV/LV and HA/LA). Moreover, an efficient method for data augmentation was used to increase the sample size and observe the performance deep learning model using additional data. The study conducted EEG-based emotion recognition tests on SEED, DEAP, and MAHNOB-HCI datasets. Consequently, this approach achieved mean accuracies of 97.6, 95.3, and 89.0 on MAHNOB-HCI, SEED, and DEAP datasets, respectively. The results have demonstrated significant potential for the implementation of a cost-effective IoT device to collect EEG signals, thereby enhancing the feasibility and applicability of the data.

show abstract

Section: Methodsmentioning

confidence: 99%

Optimizing 1D-CNN-Based Emotion Recognition Process through Channel and Feature Selection from EEG Signals

Aldawsari,

Al-Ahmadi,

Muhammad

2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The study by Daoud and Bayoumi (2019) uses channel selection methods to identify relevant EEG channels using a semisupervised approach based on transfer learning. In order to simplify the training model, the authors of Ramadhani et al (2021) used integrated selection (IS) to remove irrelevant EEG channel signals which further improved the performance of an aBCI system. The article by Basar et al (2020) used welch power spectral density-based analysis to see the effects of CSP algorithms on EEG band and channel relationship, its neural efficacy, and emotional stimuli types.…”

Section: Eeg Channel Selectionmentioning

confidence: 99%

Not All Electrode Channels Are Needed: Knowledge Transfer From Only Stimulated Brain Regions for EEG Emotion Recognition

et al. 2022

View full text Add to dashboard Cite

Emotion recognition from affective brain-computer interfaces (aBCI) has garnered a lot of attention in human-computer interactions. Electroencephalographic (EEG) signals collected and stored in one database have been mostly used due to their ability to detect brain activities in real time and their reliability. Nevertheless, large EEG individual differences occur amongst subjects making it impossible for models to share information across. New labeled data is collected and trained separately for new subjects which costs a lot of time. Also, during EEG data collection across databases, different stimulation is introduced to subjects. Audio-visual stimulation (AVS) is commonly used in studying the emotional responses of subjects. In this article, we propose a brain region aware domain adaptation (BRADA) algorithm to treat features from auditory and visual brain regions differently, which effectively tackle subject-to-subject variations and mitigate distribution mismatch across databases. BRADA is a new framework that works with the existing transfer learning method. We apply BRADA to both cross-subject and cross-database settings. The experimental results indicate that our proposed transfer learning method can improve valence-arousal emotion recognition tasks.

show abstract

“…One practical approach is subject-specific models, as each individual may have unique self-regulation evoked responses in diverse frequency bands [ 14 ]. As a result, most MI-BCI systems are based on subject-specific temporal and spectral features [ 15 , 16 ], typically calculated on a single-trial basis. One example is the Filter Bank-Common Spatial Patterns (FBCSP) method, which leverages task-related brain rhythms primarily localized in the sensorimotor area [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

García-Murillo

Álvarez-Meza

Castellanos-Domínguez

2023

Diagnostics

View full text Add to dashboard Cite

This paper uses EEG data to introduce an approach for classifying right and left-hand classes in Motor Imagery (MI) tasks. The Kernel Cross-Spectral Functional Connectivity Network (KCS-FCnet) method addresses these limitations by providing richer spatial-temporal-spectral feature maps, a simpler architecture, and a more interpretable approach for EEG-driven MI discrimination. In particular, KCS-FCnet uses a single 1D-convolutional-based neural network to extract temporal-frequency features from raw EEG data and a cross-spectral Gaussian kernel connectivity layer to model channel functional relationships. As a result, the functional connectivity feature map reduces the number of parameters, improving interpretability by extracting meaningful patterns related to MI tasks. These patterns can be adapted to the subject’s unique characteristics. The validation results prove that introducing KCS-FCnet shallow architecture is a promising approach for EEG-based MI classification with the potential for real-world use in brain–computer interface systems.

show abstract

The Implementation of EEG Transfer Learning Method Using Integrated Selection for Motor Imagery Signal

Cited by 4 publications

References 21 publications

Optimizing 1D-CNN-Based Emotion Recognition Process through Channel and Feature Selection from EEG Signals

Optimizing 1D-CNN-Based Emotion Recognition Process through Channel and Feature Selection from EEG Signals

Not All Electrode Channels Are Needed: Knowledge Transfer From Only Stimulated Brain Regions for EEG Emotion Recognition

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

Contact Info

Product

Resources

About