Wei Zheng

To address cross-subject domain shift and insufficient complementary fusion of time-frequency information in EEG-based emotion recognition, this paper proposes a multi-task adversarial network: Path Adversarial Dual-Branch Network for EEG Emotion Recognition (PADB-Net). The model adopts a dual-branch parallel architecture for time and frequency domains, processing raw EEG waveforms and differential entropy features respectively, and extracts discriminative features using lightweight depthwise separable convolutions and channel attention. A path adversarial module is introduced for the first time in emotion recognition to align time-domain and frequency-domain feature distributions, solving the single-branch dominance problem in dual-branch fusion. Together with a domain adversarial module, the overall distributions of source and target domains as well as the internal distributions of the two modality branches are aligned within a unified framework. Experiments on a dataset containing healthy subjects and patients with major depressive disorder show that the full model significantly outperforms single-adversarial and non-adversarial baselines in accuracy, AUC, F1-score, sensitivity, and specificity, verifying the synergistic gain of the dual-adversarial mechanism. On the HybridBCI dataset, PADB-Net achieves 77.80% accuracy, 84.50% AUC, and 79.40% F1-score with only 6.45 K trainable parameters. When transferred to the public SEED dataset for three-class emotion recognition, the model attains F1-scores of 71.83% (negative), 68.99% (neutral), and 73.37% (positive), demonstrating strong cross-dataset generalizability.

Neonatal seizures are a critical early indicator of neurological injury, yet effective automated detection is challenged by significant inter-subject variability in electroencephalogram (EEG) signals. To address this generalization gap, this study introduces the Domain-Adversarial Spatiotemporal Network (DA-STNet) for robust cross-subject seizure detection. Utilizing Short-Time Fourier Transform (STFT) spectrograms, the architecture employs a hierarchical backbone comprising a Channel-Independent CNN (CI-CNN) for local texture extraction, a Spatial Bidirectional Long Short-Term Memory (Bi-LSTM) for modeling topological dependencies, and Attention Pooling to dynamically prioritize pathological channels while suppressing noise. Crucially, a Gradient Reversal Layer (GRL) is integrated to enforce domain-adversarial training, decoupling pathological features from subject-specific identity to ensure domain invariance. Under rigorous 5-fold cross-validation, the model achieves State-of-the-Art performance with an average Area Under the Curve (AUC) of 0.9998 and an F1-score of 0.9952. Data scaling experiments further reveal that optimal generalization is attainable using only 80% of source data, highlighting the model’s superior data efficiency. These findings demonstrate the proposed method’s capability to reduce reliance on extensive clinical annotations while maintaining high diagnostic precision in complex clinical scenarios.

Neonatal epilepsy is an early postnatal brain disorder, and automatic seizure detection is crucial for timely diagnosis and treatment to reduce potential brain damage. This work proposes a novel Lightweight Multi-Attention Network, LMA-EEGNet, for diagnosing neonatal epileptic seizures from multi-channel EEG signals employing dilated depthwise separable convolution (DDS Conv) for feature extraction and using pointwise convolution followed by global average pooling for classification. The proposed approach substantially reduces the model size, number of parameters, and computational complexity, which are crucial for real-time detection and clinical diagnosis of neonatal epileptic seizures. LMA-EEGNet integrates temporal and spectral features through distinct temporal and spectral branches. The temporal branch uses DDS Conv to extract temporal features, enhanced by a channel attention mechanism. The spectral branch utilizes similar convolutions alongside a spatial attention mechanism to highlight key frequency components. Outputs from both branches are merged and processed through a pointwise convolution layer and a global average pooling layer for efficient neonatal seizure detection. Experimental results show that our model, with only 2471 parameters and a size of 23 KB, achieves an accuracy of 95.71% and an AUC of 0.9862, demonstrating its potential for practical deployment. This study provides an effective deep learning solution for the early detection of neonatal epileptic seizures, improving diagnostic accuracy and timeliness.

This paper presents a local field potential (LFP)/action potential (AP) mode reconfigurable analog front-end (AFE) dedicated for the closed-loop vagus nerve stimulator (VNS). It combines an inverse electrical model of the intracranial electroencephalogram (iEEG) conducting in the brain tissues and been recorded at scalp as the extended electroencephalogram (EEEG). The AFE contains a LFP/AP mode reconfigurable EEEG preamplifier, a tunable integrator to compensate the effect of either the recording electrodes or head tissues, and an adder. The LFP/AP mode reconfigurable EEEG preamplifier consists of a tunable chopper-stabilized amplifier (CSA) and a 2 ^nd -order tunable low pass filter (LPF). For better separation of LFP and AP signals, a high-order DC servo loop (DSL) characterized as a 2 ^nd -order DSL in parallel with a 1st-order DSL is exploited in the tunable CSA to achieve a tunable high-pass frequency with a stopband attenuation slope (SAS) of +40dB/dec. In addition, the tunable LPF can obtain a tunable low-pass frequency with a SAS of -40dB/dec and provide additional 20dB gain for AP signals. Fabricated in a SMIC 180nm CMOS technology, and in the LFP band (0.5Hz-200Hz) and AP band (300Hz-5kHz), the measured mid-band gains of the LFP/AP mode reconfigurable EEEG preamplifier are 39.6dB and 59.5dB, the input-referred noises (IRNs) are 2.2μVrms and 6.3μVrms, the DC/in-band input impedances are 1.27/1.26GΩ and 0.3/0.22GΩ, respectively. The power consumption per channel AFE is 6.3μW, and the die area is 1.4mm 0.25mm.

Emotion recognition plays an important role in the field of human-computer interaction (HCI). Automatic emotion recognition based on EEG is an important topic in brain-computer interface (BCI) applications. Currently, deep learning has been widely used in the field of EEG emotion recognition and has achieved remarkable results. However, due to the cost of data collection, most EEG datasets have only a small amount of EEG data, and the sample categories are unbalanced in these datasets. These problems will make it difficult for the deep learning model to predict the emotional state. In this paper, we propose a new sample generation method using generative adversarial networks to solve the problem of EEG sample shortage and sample category imbalance. In experiments, we explore the performance of emotion recognition with the frequency band correlation and frequency band separation computational models before and after data augmentation on standard EEG-based emotion datasets. Our experimental results show that the method of generative adversarial networks for data augmentation can effectively improve the performance of emotion recognition based on the deep learning model. And we find that the frequency band correlation deep learning model is more conducive to emotion recognition.