A novel EEG-based graph convolution network for depression detection: Incorporating secondary subject partitioning and attention mechanism

Zhang, Zhongyi; Meng, Qinghao; Jin, LiCheng; Wang, Hanguang; Hou, Huirang

doi:10.1016/j.eswa.2023.122356

Cited by 11 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhuang et al reported spinal cord stimulation may facilitate the recovery of consciousness, and they used an EEG test to predict the process [150]. Thanks to the boom in deep learning, many deep learning models are developed and combined with EEG to detect mental fatigue [151], Parkinson's disease [152], depression [153], schizophrenia [154,155], epilepsy [156][157][158], and neurocognitive disorders [159,160]. In addition to symptom detection, EEG is reported to localize the epileptogenic zone [161,162] and it has the potential to guide the surgery.…”

Section: Bioelectrical Sensorsmentioning

confidence: 99%

Recent Advances in Wearable Healthcare Devices: From Material to Application

Luo,

Tan,

Wen

2024

Bioengineering

View full text Add to dashboard Cite

In recent years, the proliferation of wearable healthcare devices has marked a revolutionary shift in the personal health monitoring and management paradigm. These devices, ranging from fitness trackers to advanced biosensors, have not only made healthcare more accessible, but have also transformed the way individuals engage with their health data. By continuously monitoring health signs, from physical-based to biochemical-based such as heart rate and blood glucose levels, wearable technology offers insights into human health, enabling a proactive rather than a reactive approach to healthcare. This shift towards personalized health monitoring empowers individuals with the knowledge and tools to make informed decisions about their lifestyle and medical care, potentially leading to the earlier detection of health issues and more tailored treatment plans. This review presents the fabrication methods of flexible wearable healthcare devices and their applications in medical care. The potential challenges and future prospectives are also discussed.

show abstract

Section: Bioelectrical Sensorsmentioning

confidence: 99%

Recent Advances in Wearable Healthcare Devices: From Material to Application

Luo,

Tan,

Wen

2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…As the EEG signals are discontinuous in the spatial domain, it is suggested that it may be not suitable to apply CNNs in this way on images. More recently, there is a trend to build models based on graph theory, where the graph is mainly designed or learnable, to describe the relation of multiple channels [25][26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Interaction in Multiscale Multichannel EEG Signals for Emotion Recognition

Guo,

Zhang,

Fan

et al. 2024

Mathematics

View full text Add to dashboard Cite

Electroencephalogram (EEG) is the most preferred and credible source for emotion recognition, where long-short range features and a multichannel relationship are crucial for performance because numerous physiological components function at various time scales and on different channels. We propose a cascade scale-aware adaptive graph convolutional network and cross-EEG transformer (SAG-CET) to explore the comprehensive interaction between multiscale and multichannel EEG signals with two novel ideas. First, to model the relationship of multichannel EEG signals and enhance signal representation ability, the multiscale EEG signals are fed into a scale-aware adaptive graph convolutional network (SAG) before the CET model. Second, the cross-EEG transformer (CET), is used to explicitly capture multiscale features as well as their correlations. The CET consists of two self-attention encoders for gathering features from long-short time series and a cross-attention module to integrate multiscale class tokens. Our experiments show that CET significantly outperforms a vanilla unitary transformer, and the SAG module brings visible gains. Our methods also outperform state-of-the-art methods in subject-dependent tasks with 98.89%/98.92% in accuracy for valence/arousal on DEAP and 99.08%/99.21% on DREAMER.

show abstract

“…The innovative method aimed to explore the enhanced interaction among subjects through multi-channel EEG signals, providing a unique perspective for analyzing brain activity patterns. Zhang et al (2024) employed attention mechanism-based GCNs and LSTM models to detect depression. The integration of existing research with GCNs has typically yielded promising and satisfactory classification outcomes.…”

Section: Introductionmentioning

confidence: 99%

“…The innovative method aimed to explore the enhanced interaction among subjects through multi-channel EEG signals, providing a unique perspective for analyzing brain activity patterns. Zhang et al (2024) The remainder of this article is structured as follows. Section 2 offers a comprehensive overview of the dataset and details the proposed framework.…”

Section: Introductionmentioning

confidence: 99%

Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology

Liu,

Jia,

Wang

2024

Front. Neurosci.

View full text Add to dashboard Cite

Depression has become the prevailing global mental health concern. The accuracy of traditional depression diagnosis methods faces challenges due to diverse factors, making primary identification a complex task. Thus, the imperative lies in developing a method that fulfills objectivity and effectiveness criteria for depression identification. Current research underscores notable disparities in brain activity between individuals with depression and those without. The Electroencephalogram (EEG), as a biologically reflective and easily accessible signal, is widely used to diagnose depression. This article introduces an innovative depression prediction strategy that merges time-frequency complexity and electrode spatial topology to aid in depression diagnosis. Initially, time-frequency complexity and temporal features of the EEG signal are extracted to generate node features for a graph convolutional network. Subsequently, leveraging channel correlation, the brain network adjacency matrix is employed and calculated. The final depression classification is achieved by training and validating a graph convolutional network with graph node features and a brain network adjacency matrix based on channel correlation. The proposed strategy has been validated using two publicly available EEG datasets, MODMA and PRED+CT, achieving notable accuracy rates of 98.30 and 96.51%, respectively. These outcomes affirm the reliability and utility of our proposed strategy in predicting depression using EEG signals. Additionally, the findings substantiate the effectiveness of EEG time-frequency complexity characteristics as valuable biomarkers for depression prediction.

show abstract

A novel EEG-based graph convolution network for depression detection: Incorporating secondary subject partitioning and attention mechanism

Cited by 11 publications

References 48 publications

Recent Advances in Wearable Healthcare Devices: From Material to Application

Recent Advances in Wearable Healthcare Devices: From Material to Application

A Comprehensive Interaction in Multiscale Multichannel EEG Signals for Emotion Recognition

Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology

Contact Info

Product

Resources

About