Machine learning, particularly deep learning, typically achieves high facial emotion image recognition accuracy benefiting from multiple labeled data. However, the datasets usually contain insufficient labeled samples and numerous unlabeled data since human labeling is a costly endeavor. For semi-supervised learning of these datasets, self-training procedure solely based on the visual features of images fails to comprehensively understand the intricate high-level semantic features. Since EEG signals contain not only visual information related to the visual stimulus but also emotional information related to brain activity, they are highly suitable as supervisory signals for labeling unlabeled facial emotion images. In this study, we specifically employ EEG signals evoked by visual image stimuli in conjunction with EEGNet3D to learn a discriminative EEG class representation manifold of brain activity. The one-hot class label is replaced with the EEG class representation as the supervisory to train the base model. Then, better pseudo-labeling is achieved using the base model in the EEG class representation manifold. Based on pseudo-labeling results, the utilization of unlabeled data is further improved. Interestingly, our findings reveal that when utilizing EEG class representations as supervisory information for the base model, the base model demonstrates a learning pattern that involves focusing more on the eye area when making judgments about emotions. This behavior closely resembles how the human brain decodes emotions. Experiments show that the performance of the proposed method can be effectively enhanced by combining labeled and pseudo-labeled images. Further experiments demonstrate that our method exhibits strong generalization abilities when applied to new image datasets and other visual networks.

Camouflaged object detection (COD) aims to identify targets that visually blend into their surroundings, posing significant challenges due to low contrast between targets and backgrounds, diverse target appearances, and limited annotated training samples. A critical yet often overlooked subtask in COD is object presence detection, which determines whether a camouflaged object actually exists in an image. This step is essential as it underpins accurate localization and segmentation and enables timely decisions in practical applications such as disaster rescue and wildlife monitoring. However, most existing methods assume the target is always present and focus mainly on localization, limiting their robustness and reliability in complex scenarios. Inspired by the human brain's remarkable ability to perceive camouflaged objects by integrating edge and contextual cues, we propose a cognitive-visual coupling learning framework to enhance object presence detection. Specifically, electroencephalogram (EEG) signals are incorporated during training to embed human cognitive patterns into the model's visual feature learning through coupled representation learning. Notably, during inference, our framework relies solely on visual input, effectively leveraging cognitive insights acquired during training to improve detection performance. Extensive experiments demonstrate that our approach achieves superior accuracy compared to state-of-the-art methods and exhibits strong generalization across diverse visual backbone architectures and unseen cross-dataset scenarios.

Biometric recognition using visually evoked potentials (VEPs), a type of neural response to visual stimuli recorded via electroencephalography (EEG), has shown great promise. However, the non-stationary nature of EEG signals poses a major challenge in cross-session scenarios, where data collected on different days often leads to performance degradation. To address this, we propose the Discriminative Robust Feature Network (DRFNet) to enhance the robustness and inter-subject discriminability of identity representations across sessions. DRFNet incorporates two key components: (1) A log-power transformation that amplifies inter-individual differences by capturing non-linear energy patterns from VEP features via signal squaring and logarithmic scaling; and (2) A hierarchical normalization strategy with adaptive attention to balance discriminative identity cues with inter-session invariance by stabilizing feature distributions across multiple levels (feature map, batch, and sample). On two public multi-session SSVEP datasets (Dataset A: 30 subjects, 6 s trials; Dataset B: 54 subjects, 4 s trials), our model outperformed state-of-the-art methods, achieving identification accuracies of 92.92% and 86.30%, and equal error rates of 3.92% and 4.09%, respectively. Further analysis demonstrates that filter bank processing and a reduced set of parietal-occipital electrodes can provide more discriminative features while offering a practical path toward system lightweighting.

T-cell acute lymphoblastic leukemia (T-ALL) is a malignant neoplastic disease. Accurate identification of core genes helps to explore the pathogenesis of T-ALL and develop relevant targeted drugs. In this paper, we first screened the RNA-seq, CTCF ChIP-seq and DNA methylation datasets of T-ALL for intersecting differentially expressed genes (DEGs) using bioinformatics software. As such, candidate genes screening is transformed into a semi-supervised classification problem given all known T-ALL related genes. It is clear that there are no labelled negative samples but a few labelled positive samples in the dataset, motivating us to employ the PU bagging method based on Positive-unlabeled (PU) learning to discover the T-ALL related candidate genes, in which a multi-layer perceptron (MLP) classifier was employed to accomplish the classification task. On this ground, a protein-protein interaction (PPI) network was built with the candidate genes, and core genes were screened. Finally, the core genes were subjected to GO and KEGG functional enrichment analysis, search of CTD and review of relevant literature to validate the proposed method. The validation results showed that the proposed method is able to effectively predict T-ALL related core genes, and all core genes have the potential to become candidates in T-ALL biomarker studies in the future.

Recent works on visual classification tasks have leveraged EEG signals to provide additional supervisory information, further improving the performance of the models on natural images. However, previous methods often force machine models to directly match EEG signals, which involves the transfer of modal-specific representations, leading to potentially distorted alignment of modal-shared representations. Moreover, focusing solely on aligning individual sample features neglects the alignment of relationships between samples, making it difficult to capture the potential relational reasoning capabilities in EEG signals. This relational reasoning ability is key to the human brain’s outstanding performance in visual classification tasks. Similarly, for a machine model, the complex relationships between instances are more critical than individual instances. Inspired by this, our idea is to enhance machine visual classification capabilities by imparting human-like relational reasoning, encouraging machine models to focus on the relational structure within EEG signals. To this end, we propose a brain-machine relation alignment method that constructs a cognitive model and a visual model to process EEG signals and visual images, respectively. Instead of forcing the visual model to mimic the output of an individual EEG data sample represented by the cognitive model, we encourage it to learn the mutual relations of EEG data samples. By penalizing the difference in relational structures between EEG signals and visual images, we facilitate the transfer of relational knowledge. Experiments demonstrate that the proposed method significantly improves the classification performance of the visual model. This highlights the potential of relational alignment as a robust mechanism for integrating human relational reasoning into machine learning models.

Multimodal sarcasm analysis is one of the most challenging research branch of the sentiment analysis area, due to the presence of cross-modality incongruity. However, existing works mainly attend to the coarse-grained incongruity analysis, and totally ignore the sentiment semantic coupling issue. This indeed limits the discriminate capability and robustness of the sarcasm analysis model. In order to address the above issue, we propose a novel Fine-grained Semantic Disentanglement Network (FSDN). Specifically, the intra-modality semantic disentanglement is performed to investigate the more intrinsic semantic cues of the same modality. Additionally, the inter-modality semantic disentanglement is leveraged to simultaneously facilitate the common and intrinsic semantic cues across modalities. Furthermore, the dual-spatial semantic interaction block is presented to explore the long-range cross-spatial semantic context between the obtained verbal and non-verbal semantic space with the global view. The above semantic disentanglement processes with both local and global views significantly unleash much more robustness even for the sarcasm case consisting of multiple semantic message. Various experiments indicate that the FSDN can receive state-of-the-art or competitive performance.

Identifying essential genes in an organism is crucial for bioinformatics and genomics research. In this paper, we propose a new computational method for gene similarity prediction, named GT-KGCN, which combines the advantages of the Graph Transformer (GT), Graph Convolutional Network (GCN), and Kolmogorov-Arnold Network (KAN). Specifically, GT-KGCN utilizes graph transformers for feature embedding and multi-head attention aggregation, GCN for hierarchical aggregation of information from neighboring nodes, and KAN for optimizing feature learning through learnable activation functions. Model inputs include Protein-Protein Interaction (PPI) networks, gene expression profiles, subcellular localization, and orthologs information. We evaluated the performance of GT-KGCN on two different PPI network databases (BioGRID and STRING) using multi-omics datasets of Escherichia coli, Saccharomyces cerevisiae, Drosophila melanogaster, and Homo sapiens. The experimental results show that GT-KGCN achieves a prediction accuracy of 99.12% for Escherichia coli, 98.47% for Saccharomyces cerevisiae, 92.22% for Drosophila melanogaster, and 92.30% for Homo sapiens. The GT-KGCN model outperforms traditional shallow machine learning methods and other deep learning methods in essential gene prediction. The ablation study verifies the positive effects of multi-omics datasets as well as different convolutional layers on the prediction performance of the model, with gene expression data showing the most significant performance improvement and demonstrating the model’s superiority.

EEG-based brainprint recognition with deep learning models has garnered much attention in biometric identification. Yet, studies have indicated vulnerability to adversarial attacks in deep learning models with EEG inputs. In this paper, we introduce a novel adversarial attack method that jointly attacks time-domain and frequency-domain EEG signals by employing wavelet transform. Different from most existing methods which only target time-domain EEG signals, our method not only takes advantage of the time-domain attack’s potent adversarial strength but also benefits from the imperceptibility inherent in frequency-domain attack, achieving a better balance between attack performance and imperceptibility. Extensive experiments are conducted in both white- and grey-box scenarios and the results demonstrate that our attack method achieves state-of-the-art attack performance on three datasets and three deep-learning models. In the meanwhile, the perturbations in the signals attacked by our method are barely perceptible to the human visual system.

Proteins are among the most essential molecules in the living body and are irreplaceable in various biological processes that sustain life. Predicting their functions is essential for understanding the molecular mechanisms of cellular life activities. With the widespread use of second-generation highthroughput sequencing technologies, more and more protein sequence data are being rapidly sequenced and shared. The rapid accumulation and update of these data provide a more substantial and diverse data foundation for protein function prediction research. Traditisonal biological experimental methods are the most reliable way to determine protein function. However, relying solely on manual experimental methods to test unknown protein functions individually suffers from a high workload and long lead time. Therefore, a deep learning-based protein function prediction model called DeepLA was proposed in this paper. Firstly, the model encodes protein sequences in One-hot and uses the Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST) algorithm to perform a comparative search to obtain a Position-Specific Scoring Matrix (PSSM) containing protein evolutionary information. Next, the protein feature vectors were fed into a multi-channel model consisting of a convolutional neural network, a bidirectional long- and short-term memory network, and a self-attentive mechanism for feature extraction to achieve the protein function prediction task. The results showed that DeepLA exhibited good performance in the Molecular Function(MF) and Biological Process (BP) categories with values of 0.556 and 0.488 on the publicly available dataset CAFA3, respectively, which were 5.8% and 8.0% higher than other models.

Neural network models of machine learning have shown promising prospects for visual tasks, such as facial emotion recognition (FER). However, the generalization of the model trained from a dataset with a few samples is limited. Unlike the machine, the human brain can effectively realize the required information from a few samples to complete the visual tasks. To learn the generalization ability of the brain, in this article, we propose a novel brain-machine coupled learning method for facial emotion recognition to let the neural network learn the visual knowledge of the machine and cognitive knowledge of the brain simultaneously. The proposed method utilizes visual images and electroencephalogram (EEG) signals to couple training the models in the visual and cognitive domains. Each domain model consists of two types of interactive channels, common and private. Since the EEG signals can reflect brain activity, the cognitive process of the brain is decoded by a model following reverse engineering. Decoding the EEG signals induced by the facial emotion images, the common channel in the visual domain can approach the cognitive process in the cognitive domain. Moreover, the knowledge specific to each domain is found in each private channel using an adversarial strategy. After learning, without the participation of the EEG signals, only the concatenation of both channels in the visual domain is used to classify facial emotion images based on the visual knowledge of the machine and the cognitive knowledge learned from the brain. Experiments demonstrate that the proposed method can produce excellent performance on several public datasets. Further experiments show that the proposed method trained from the EEG signals has good generalization ability on new datasets and can be applied to other network models, illustrating the potential for practical applications.

Attention-based networks currently identify their effectiveness in multimodal sentiment analysis. However, existing methods ignore the redundancy of auxiliary modalities. More importantly, existing methods only attend to top-down attention (static process) or down-top attention (implicit process), leading to the coarse-grained multimodal sentiment context. In this paper, during the preprocessing period, we first propose the multimodal dynamic enhanced block to capture the intra-modality sentiment context. This can effectively decrease the intra-modality redundancy of auxiliary modalities. Furthermore, the bi-direction attention block is proposed to capture fine-grained multimodal sentiment context via the novel bi-direction multimodal dynamic routing mechanism. Specifically, the bi-direction attention block first highlights the explicit and low-level multimodal sentiment context. Then, the low-level multimodal context is transmitted to a carefully designed bi-direction multimodal dynamic routing procedure. This allows us to dynamically update and investigate high-level and much more fine-grained multimodal sentiment contexts. The experiments demonstrate that our fusion network can achieve state-of-the-art performance. Notably, our model outperforms the best baseline on the metric ‘Acc-7’ with an improvement of 6.9%.