Spatial Position Information Research Articles

Positional encoding-guided transformer-based multiple instance learning for histopathology whole slide images classification

Background and objectives:Whole slide image (WSI) classification is of great clinical significance in computer-aided pathological diagnosis. Due to the high cost of manual annotation, weakly supervised WSI classification methods have gained more attention. As the most representative, multiple instance learning (MIL) generally aggregates the predictions or features of the patches within a WSI to achieve the slide-level classification under the weak supervision of WSI labels. However, most existing MIL methods ignore spatial position relationships of the patches, which is likely to strengthen the discriminative ability of WSI-level features. Methods:In this paper, we propose a novel positional encoding-guided transformer-based multiple instance learning (PEGTB-MIL) method for histopathology WSI classification. It aims to encode the spatial positional property of the patch into its corresponding semantic features and explore the potential correlation among the patches for improving the WSI classification performance. Concretely, the deep features of the patches in WSI are first extracted and simultaneously a position encoder is used to encode the spatial 2D positional information of the patches into the spatial-aware features. After incorporating the semantic features and spatial embeddings, multi-head self-attention (MHSA) is applied to explore the contextual and spatial dependencies of the fused features. Particularly, we introduce an auxiliary reconstruction task to enhance the spatial-semantic consistency and generalization ability of features. Results:The proposed method is evaluated on two public benchmark TCGA datasets (TCGA-LUNG and TCGA-BRCA) and two in-house clinical datasets (USTC-EGFR and USTC-GIST). Experimental results validate it is effective in the tasks of cancer subtyping and gene mutation status prediction. In the test stage, the proposed PEGTB-MIL outperforms the other state-of-the-art methods and respectively achieves 97.13±0.34%, 86.74±2.64%, 83.25±1.65%, and 72.52±1.63% of the area under the receiver operating characteristic (ROC) curve (AUC). Conclusion:PEGTB-MIL utilizes positional encoding to effectively guide and reinforce MIL, leading to enhanced performance on downstream WSI classification tasks. Specifically, the introduced auxiliary reconstruction module adeptly preserves the spatial-semantic consistency of patch features. More significantly, this study investigates the relationship between position information and disease diagnosis and presents a promising avenue for further research.

NEON-SD: A 30-m Structural Diversity Product Derived from the NEON Discrete-Return LiDAR Point Cloud

Structural diversity (SD) characterizes the volume and physical arrangement of biotic components in an ecosystem which control critical ecosystem functions and processes. LiDAR data provides detailed 3-D spatial position information of components and has been widely used to calculate SD. However, the intensive computation of SD metrics from extensive LiDAR datasets is time-consuming and challenging for researchers who lack access to high-performance computing resources. Moreover, a lack of understanding of LiDAR data and algorithms could lead to inconsistent SD metrics. Here, we developed a SD product using the Discrete-Return LiDAR Point Cloud from the NEON Aerial Observation Platform. This product provides SD metrics detailing height, density, openness, and complexity at a spatial resolution of 30 m, aligned to the Landsat grids, for 211 site-years for 45 Terrestrial NEON sites from 2013 to 2022. To accommodate various ecosystems with different understory heights, it includes three different cut-off heights (0.5 m, 2 m, and 5 m). This structural diversity product can enable various applications such as ecosystem productivity estimation and disturbance monitoring.

Semi-automatic robotic puncture system based on deformable soft tissue point cloud registration.

Traditional surgical puncture robot systems based on computed tomography (CT) and infrared camera guidance have natural disadvantages for puncture of deformable soft tissues such as the liver. Liver movement and deformation caused by breathing are difficult to accurately assess and compensate by current technical solutions. We propose a semi-automatic robotic puncture system based on real-time ultrasound images to solve this problem. Real-time ultrasound images and their spatial position information can be obtained by robot in this system. By recognizing target tissue in these ultrasound images and using reconstruction algorithm, 3D real-time ultrasound tissue point cloud can be constructed. Point cloud of the target tissue in the CT image can be obtained by using developed software. Through the point cloud registration method based on feature points, two point clouds above are registered. The puncture target will be automatically positioned, then robot quickly carries the puncture guide mechanism to the puncture site and guides the puncture. It takes about just tens of seconds from the start of image acquisition to completion of needle insertion. Patient can be controlled by a ventilator to temporarily stop breathing, and patient's breathing state does not need to be the same as taking CT scan. The average operation time of 24 phantom experiments is 64.5 s, and the average error between the needle tip and the target point after puncture is 0.8mm. Two animal puncture surgeries were performed, and the results indicated that the puncture errors of these two experiments are 1.76mm and 1.81mm, respectively. Robot system can effectively carry out and implement liver tissue puncture surgery, and the success rate of phantom experiments and experiments is 100%. It also shows that the puncture robot system has high puncture accuracy, short operation time, and great clinical value.

Shower separation in five dimensions for highly granular calorimeters using machine learning

To achieve state-of-the-art jet energy resolution for Particle Flow, sophisticated energy clustering algorithms must be developed that can fully exploit available information to separate energy deposits from charged and neutral particles. Three published neural network-based shower separation models were applied to simulation and experimental data to measure the performance of the highly granular CALICE Analogue Hadronic Calorimeter (AHCAL) technological prototype in distinguishing the energy deposited by a single charged and single neutral hadron for Particle Flow. The performance of models trained using only standard spatial, energy and charged track position information from an event was compared to models trained using timing information available from AHCAL, which is expected to improve sensitivity to shower development and, therefore, aid in clustering. Both simulation and experimental data were used to train and test the models and their performances were compared. The best-performing neural network achieved significantly superior event reconstruction when timing information was utilised in training for the case where the charged hadron had more energy than the neutral one, motivating temporally sensitive calorimeters. All models under test were observed to tend to allocate energy deposited by the more energetic of the two showers to the less energetic one. Similar shower reconstruction performance was observed for a model trained on simulation and applied to data and a model trained and applied to data.

Research on high precision localization of space target with multi-sensor association

In response to the challenges of acquiring spatial target position information and achieving high precision in existing methods, this paper proposes a multi-dimensional high-precision positioning method for spatial targets through multi-sensor fusion. Utilizing optical detection technology, the method extracts two-dimensional positional information of spatial targets on the observation plane. By deriving a fusion positioning formula for visible light and infrared based on the Gaussian mixture TPHD, the proposed method enhances positioning accuracy by 0.2 m compared to using visible light or infrared alone. Additionally, by integrating laser ranging for distance dimension information, precise target positioning in the world coordinate system is achieved. Outdoor experiments for spatial target positioning validate the method's effectiveness, utilizing visible light and infrared cameras along with laser ranging. Comparative analysis with a binary star angular measurement-only method demonstrates 17.9 % improvement in positioning accuracy, with the proposed method achieving 0.12 m accuracy for 5 cm spatial targets at 5 km distance.

A continuous concrete vibration method for robots based on machine vision with integrated spatial features

The traditional manual concrete vibration work faces numerous limitations, necessitating efficient automated method to assist in this task. This study proposes a vision-based continuous concrete vibration method for vibrating robots. By enhancing the YOLOv8n model with attention mechanisms, our proposed method demonstrates a high AP of 93.31 % in identifying reinforcing grids, and an FPS of 25.6 on embedded systems. For the first time in concrete vibration tasks, this study utilizes spatial positional information to cluster coordinate data, transforming confidence-sorted data into spatially ordered sequences. Vibrating robot case test shows that the proposed method enhances the vibration speed by 22.18 % and improves the vibration success rate by 11.67 % compared to traditional strategies. Additionally, the on-site experiment conducted at four construction sites demonstrated the robustness of the proposed method. These findings advance automation in concrete vibration work, offering significant implications for the fields of robotics and construction engineering.

TDT-MIL: a framework with a dual-channel spatial positional encoder for weakly-supervised whole slide image classification.

The classic multiple instance learning (MIL) paradigm is harnessed for weakly-supervised whole slide image (WSI) classification. The spatial position relationship located between positive tissues is crucial for this task due to the small percentage of these tissues in billions of pixels, which has been overlooked by most studies. Therefore, we propose a framework called TDT-MIL. We first serially connect a convolutional neural network and transformer for basic feature extraction. Then, a novel dual-channel spatial positional encoder (DCSPE) module is designed to simultaneously capture the complementary local and global positional information between instances. To further supplement the spatial position relationship, we construct a convolutional triple-attention (CTA) module to attend to the inter-channel information. Thus, the spatial positional and inter-channel information is fully mined by our model to characterize the key pathological semantics in WSI. We evaluated TDT-MIL on two publicly available datasets, including CAMELYON16 and TCGA-NSCLC, with the corresponding classification accuracy and AUC up to 91.54%, 94.96%, and 90.21%, 94.36%, respectively, outperforming state-of-the-art baselines. More importantly, our model possesses a satisfactory capability in solving the imbalanced WSI classification task using an ingenious but interpretable structure.

A Novel Deep Learning Model for Breast Tumor Ultrasound Image Classification with Lesion Region Perception.

Multi-task learning (MTL) methods are widely applied in breast imaging for lesion area perception and classification to assist in breast cancer diagnosis and personalized treatment. A typical paradigm of MTL is the shared-backbone network architecture, which can lead to information sharing conflicts and result in the decline or even failure of the main task's performance. Therefore, extracting richer lesion features and alleviating information-sharing conflicts has become a significant challenge for breast cancer classification. This study proposes a novel Multi-Feature Fusion Multi-Task (MFFMT) model to effectively address this issue. Firstly, in order to better capture the local and global feature relationships of lesion areas, a Contextual Lesion Enhancement Perception (CLEP) module is designed, which integrates channel attention mechanisms with detailed spatial positional information to extract more comprehensive lesion feature information. Secondly, a novel Multi-Feature Fusion (MFF) module is presented. The MFF module effectively extracts differential features that distinguish between lesion-specific characteristics and the semantic features used for tumor classification, and enhances the common feature information of them as well. Experimental results on two public breast ultrasound imaging datasets validate the effectiveness of our proposed method. Additionally, a comprehensive study on the impact of various factors on the model's performance is conducted to gain a deeper understanding of the working mechanism of the proposed framework.

Advanced Global Prototypical Segmentation Framework for Few-Shot Hyperspectral Image Classification.

With the advancement of deep learning, related networks have shown strong performance for Hyperspectral Image (HSI) classification. However, these methods face two main challenges in HSI classification: (1) the inability to capture global information of HSI due to the restriction of patch input and (2) insufficient utilization of information from limited labeled samples. To overcome these challenges, we propose an Advanced Global Prototypical Segmentation (AGPS) framework. Within the AGPS framework, we design a patch-free feature extractor segmentation network (SegNet) based on a fully convolutional network (FCN), which processes the entire HSI to capture global information. To enrich the global information extracted by SegNet, we propose a Fusion of Lateral Connection (FLC) structure that fuses the low-level detailed features of the encoder output with the high-level features of the decoder output. Additionally, we propose an Atrous Spatial Pyramid Pooling-Position Attention (ASPP-PA) module to capture multi-scale spatial positional information. Finally, to explore more valuable information from limited labeled samples, we propose an advanced global prototypical representation learning strategy. Building upon the dual constraints of the global prototypical representation learning strategy, we introduce supervised contrastive learning (CL), which optimizes our network with three different constraints. The experimental results of three public datasets demonstrate that our method outperforms the existing state-of-the-art methods.

A deep learning-based cascade algorithm for pancreatic tumor segmentation.

Pancreatic tumors are small in size, diverse in shape, and have low contrast and high texture similarity with surrounding tissue. As a result, the segmentation model is easily confused by complex and changeable background information, leading to inaccurate positioning of small targets and false positives and false negatives. Therefore, we design a cascaded pancreatic tumor segmentation algorithm. In the first stage, we use a general multi-scale U-Net to segment the pancreas, and we exploit a multi-scale segmentation network based on non-local localization and focusing modules to segment pancreatic tumors in the second stage. The non-local localization module learns channel and spatial position information, searches for the approximate area where the pancreatic tumor is located from a global perspective, and obtains the initial segmentation results. The focusing module conducts context exploration based on foreground features (or background features), detects and removes false positive (or false negative) interference, and obtains more accurate segmentation results based on the initial segmentation. In addition, we design a new loss function to alleviate the insensitivity to small targets. Experimental results show that the proposed algorithm can more accurately locate pancreatic tumors of different sizes, and the Dice coefficient outperforms the existing state-of-the-art segmentation model. The code will be available at https://github.com/HeyJGJu/Pancreatic-Tumor-SEG.

A Novel Point Cloud Adaptive Filtering Algorithm for LiDAR SLAM in Forest Environments Based on Guidance Information

To address the issue of accuracy in Simultaneous Localization and Mapping (SLAM) for forested areas, a novel point cloud adaptive filtering algorithm is proposed in the paper, based on point cloud data obtained by backpack Light Detection and Ranging (LiDAR). The algorithm employs a K-D tree to construct the spatial position information of the 3D point cloud, deriving a linear model that is the guidance information based on both the original and filtered point cloud data. The parameters of the linear model are determined by minimizing the cost function using an optimization strategy, and a guidance point cloud filter is subsequently constructed based on these parameters. The results demonstrate that, comparing the diameter at breast height (DBH) and tree height before and after filtering with the measured true values, the accuracy of SLAM mapping is significantly improved after filtering. The Mean Absolute Error (MAE) of DBH before and after filtering are 2.20 cm and 1.16 cm; the Root Mean Square Error (RMSE) values are 4.78 cm and 1.40 cm; and the relative RMSE values are 29.30% and 8.59%. For tree height, the MAE before and after filtering are 0.76 m and 0.40 m; the RMSE values are 1.01 m and 0.50 m; the relative RMSE values are 7.33% and 3.65%. The experimental results validate that the proposed adaptive point cloud filtering method based on guided information is an effective point cloud preprocessing method for enhancing the accuracy of SLAM mapping in forested areas.

FreqSNet: a multiaxial integration of frequency and spatial domains for medical image segmentation

Objective. In recent years, convolutional neural networks, which typically focus on extracting spatial domain features, have shown limitations in learning global contextual information. However, frequency domain can offer a global perspective that spatial domain methods often struggle to capture. To address this limitation, we propose FreqSNet, which leverages both frequency and spatial features for medical image segmentation. Approach. To begin, we propose a frequency-space representation aggregation block (FSRAB) to replace conventional convolutions. FSRAB contains three frequency domain branches to capture global frequency information along different axial combinations, while a convolutional branch is designed to interact information across channels in local spatial features. Secondly, the multiplex expansion attention block extracts long-range dependency information using dilated convolutional blocks, while suppressing irrelevant information via attention mechanisms. Finally, the introduced Feature Integration Block enhances feature representation by integrating semantic features that fuse spatial and channel positional information. Main results. We validated our method on 5 public datasets, including BUSI, CVC-ClinicDB, CVC-ColonDB, ISIC-2018, and Luna16. On these datasets, our method achieved Intersection over Union (IoU) scores of 75.46%, 87.81%, 79.08%, 84.04%, and 96.99%, and Hausdorff distance values of 22.22 mm, 13.20 mm, 13.08 mm, 13.51 mm, and 5.22 mm, respectively. Compared to other state-of-the-art methods, our FreqSNet achieves better segmentation results. Significance. Our method can effectively combine frequency domain information with spatial domain features, enhancing the segmentation performance and generalization capability in medical image segmentation tasks.

Intelligent tongue diagnosis model for gastrointestinal diseases based on tongue images

BackgroundCurrently, the diagnosis of gastrointestinal diseases relies heavily on electronic endoscopy, which is not suitable for all individuals and insufficient for dynamic patient monitoring. Therefore, there is an urgent need for a convenient and noninvasive examination method to enhance the diagnosis and monitoring of gastrointestinal diseases. MethodsSince the tongue is a significant reflection of the digestive system and closely associated with gastrointestinal diseases, our study aims to develop a diagnostic framework based on tongue features. We have collected a dataset of 2,167 tongue coating images from 949 consecutive patients, including 905 images from healthy individuals and 1,262 images from patients with various gastrointestinal conditions. Notably, each patient sample may represent distinct gastrointestinal diseases. This study introduces a novel approach to information fusion detection, integrating hand-crafted and auto-encoded features, alongside disease detection employing Squeeze and Excitation (SE) and Slot attention mechanisms. These two branches respectively analyze image feature and spatial position information when utilizing tongue images for diagnosing gastrointestinal diseases. The amalgamation of predictions from both aspects yields the final detection outcome. ResultsFor both healthy and diseased cohorts, the optimal classification metrics were achieved: AUC = 0.886, ACC = 0.849, and TPR = 0.965, indicating satisfactory performance. Notably, our framework demonstrated promising results in detecting five common gastrointestinal diseases: Helicobacter pylori infection, bile reflux, reflux esophagitis, gastric erosion, and duodenal erosion. Ablation experiments underscored the efficacy of mixed features in multi-color space, showcasing an increase in AUC and ACC by 13.48 % and 12.05 % respectively. Furthermore, the attention mechanism, by focusing on the middle region of tongue images, contributed to a 6.12 % increase in AUC and a 6.35 % increase in ACC. ConclusionsIn this study, we successfully develop and validate a diagnosis framework for gastrointestinal diseases based on tongue image features. By utilizing tongue images, we achieve intelligent diagnosis of gastrointestinal diseases, establishing tongue diagnosis as a convenient, cost-effective, and noninvasive method for diagnosing and screening gastrointestinal diseases.

Deep Convolutional Network Based on Attention Mechanism for Matching Optical and SAR Images

Abstract. Complex geometric distortions and nonlinear radiation differences between optical and synthetic aperture radar (SAR) images present challenges for the matching of sufficient and evenly distributed corresponding points. To address this problem, this paper proposes a deep convolutional network based on an attention mechanism for matching optical and SAR images. In order to obtain robust feature points, we employ phase consistency instead of image intensity and gradient information for feature detection. A deep convolutional network (DCN) is designed to extract high-level semantic features between optical and SAR images, providing robustness to geometric distortion and nonlinear radiation changes. Notably, incorporating multiple inverted residual structures in the DCN facilitates efficient extraction of local and global features, promoting feature reuse, and reducing the loss of key features. Furthermore, a dense feature fusion module based on coordinate attention is designed, focusing on the spatial positional information of effective features, integrating key features into deep descriptors to enhance the robustness of deep descriptors to nonlinear radiometric differences. A coarse-to-fine strategy is then employed to enhance accuracy by eliminating mismatches. Experimental results demonstrate that the proposed network performs better than the manually designed descriptors-based methods and the stateof- the-art deep learning networks in both matching effectiveness and accuracy. Specifically, the number of matches achieved is approximately 2 times greater than that of other methods, with a 10% improvement in F-measure.

Automatic loading method for robot guided by 3D vision for scattered and stacked shoe soles

This paper primarily introduces a method for the automated feeding of scattered stacked shoe soles using a 3D visual-guided robot. Initially, addressing issues like slow speed in pose estimation and poor robustness during the robot sorting and feeding process, we introduce an enhanced pose estimation algorithm. This algorithm combines the improved Super 4-Point Congruent Sets (Super 4PCS) with the Truncated Least Squares Semidefinite Relaxation (TEASER) algorithm, significantly boosting the speed and robustness of pose estimation during sole sorting, and achieving precise target pose estimation. Building upon this foundation, we present a sorting strategy for disordered stacked shoe soles. This strategy integrates spatial positional information of each sole, employing multi-objective decision-making and recognition algorithms to determine optimal grasping targets. Finally, an experimental platform for automated sole feeding is designed to validate the proposed method. The experimental results indicate that the pose estimation method proposed in this paper achieves an average distance error of 2.04 mm and an average angular error of 2.72°, with the robot’s average success rate in grasping reaching 97.08%. Moreover, the average processing time of the vision algorithm is only 1.34 s, demonstrating good efficiency, precision, and robustness. This method effectively meets the automated feeding needs of scattered and stacked shoe soles in the actual production processes of shoemaking enterprises.

MR2CPPIS: Accurate prediction of protein–protein interaction sites based on multi-scale Res2Net with coordinate attention mechanism

Proteins play a vital role in various biological processes and achieve their functions through protein–protein interactions (PPIs). Thus, accurate identification of PPI sites is essential. Traditional biological methods for identifying PPIs are costly, labor-intensive, and time-consuming. The development of computational prediction methods for PPI sites offers promising alternatives. Most known deep learning (DL) methods employ layer-wise multi-scale CNNs to extract features from protein sequences. But, these methods usually neglect the spatial positions and hierarchical information embedded within protein sequences, which are actually crucial for PPI site prediction. In this paper, we propose MR2CPPIS, a novel sequence-based DL model that utilizes the multi-scale Res2Net with coordinate attention mechanism to exploit multi-scale features and enhance PPI site prediction capability. We leverage the multi-scale Res2Net to expand the receptive field for each network layer, thus capturing multi-scale information of protein sequences at a granular level. To further explore the local contextual features of each target residue, we employ a coordinate attention block to characterize the precise spatial position information, enabling the network to effectively extract long-range dependencies. We evaluate our MR2CPPIS on three public benchmark datasets (Dset 72, Dset 186, and PDBset 164), achieving state-of-the-art performance. The source codes are available at https://github.com/YyinGong/MR2CPPIS.

A three-dimensional human motion pose recognition algorithm based on graph convolutional networks

In the task of three-dimensional human motion posture recognition, there are problems such as target loss, inaccurate target positioning, and high computational complexity. This article designs a recognition evaluation algorithm to address these issues. Design a LiteHRNet model for extracting skeleton sequences from action videos, and propose a graph convolutional structure that combines residual networks and attention mechanisms. This network can effectively enhance the expression ability of node key features. Introducing second-order velocity information and spatial position information of joint points to improve positioning accuracy. Improve the TCN and Transformer network models to simultaneously extract local and long-term features throughout the entire model, and more accurately model the temporal correlation between nodes in the entire action sequence. The fusion of Transformer networks can reduce the computational complexity of the model while ensuring its accuracy. The experiment shows that the model has good evaluation performance on multiple datasets.

Slimmable transformer with hybrid axial-attention for medical image segmentation

The transformer architecture has achieved remarkable success in medical image analysis owing to its powerful capability for capturing long-range dependencies. However, due to the lack of intrinsic inductive bias in modeling visual structural information, the transformer generally requires a large-scale pre-training schedule, limiting the clinical applications over expensive small-scale medical data. To this end, we propose a slimmable transformer to explore intrinsic inductive bias via position information for medical image segmentation. Specifically, we empirically investigate how different position encoding strategies affect the prediction quality of the region of interest (ROI) and observe that ROIs are sensitive to different position encoding strategies. Motivated by this, we present a novel Hybrid Axial-Attention (HAA) that can be equipped with pixel-level spatial structure and relative position information as inductive bias. Moreover, we introduce a gating mechanism to achieve efficient feature selection and further improve the representation quality over small-scale datasets. Experiments on LGG and COVID-19 datasets prove the superiority of our method over the baseline and previous works. Internal workflow visualization with interpretability is conducted to validate our success better; the proposed slimmable transformer has the potential to be further developed into a visual software tool for improving computer-aided lesion diagnosis and treatment planning.

Modulated Memory Network for Video Object Segmentation

Existing video object segmentation (VOS) methods based on matching techniques commonly employ a reference set comprising historical segmented frames, referred to as ‘memory frames’, to facilitate the segmentation process. However, these methods suffer from the following limitations: (i) Inherent segmentation errors in memory frames can propagate and accumulate errors when utilized as templates for subsequent segmentation. (ii) The non-local matching technique employed in top-leading solutions often fails to incorporate positional information, potentially leading to incorrect matching. In this paper, we introduce the Modulated Memory Network (MMN) for VOS. Our MMN enhances matching-based VOS methods in the following ways: (i) Introducing an Importance Modulator, which adjusts memory frames using adaptive weight maps generated based on the segmentation confidence associated with each frame. (ii) Incorporating a Position Modulator that encodes spatial and temporal positional information for both memory frames and the current frame. The proposed modulator improves matching accuracy by embedding positional information. Meanwhile, the Importance Modulator mitigates error propagation and accumulation by incorporating confidence-based modulation. Through extensive experimentation, we demonstrate the effectiveness of our proposed MMN, which also achieves promising performance on VOS benchmarks.

EEG Emotion Recognition Based on Self-Distillation Convolutional Graph Attention Network

A convolution graph attention model based on self-distillation convolutional graph attention network (SDC-GAT) is proposed for multi-channel EEG emotion recognition. Firstly, two-dimensional feature matrix based on EEG time-domain features are constructed, and the matrix is fed into the graph attention neural network to learn the internal connections between electrical brain channels located in different brain regions. Meanwhile, the three-dimensional feature matrix is constructed according to the relative positions of the electrode channels, and the self-distillation network is employed to extract local high-level abstract features containing electrode spatial position information from the three-dimensional feature matrix. Finally, outputs of the two networks are integrated to determine the emotional states. Experiments were performed on the DEAP dataset. The experimental results show that the spatial domain information of the electrode channel and the internal connection relationship between different channels are beneficial for emotion recognition. In addition, the proposed model can effectively fuse these information to improve the performance of multi-channel EEG emotion recognition.