Graph Convolutional Neural Networks Research Articles

Learning spatiotemporal dependencies using adaptive hierarchical graph convolutional neural network for air quality prediction

Air quality prediction has garnered significant attention from both governmental bodies and the general public due to its close connection with people’s daily lives. Learning spatio-temporal dependencies within air quality data are crucial for accurate air quality forecasting. Graph Convolutional Network (GCN) has been widely utilized in spatiotemporal data prediction due to its remarkable ability of capturing non-Euclidean spatial dependencies among nodes. However, previous research on Spatiotemporal Graph Neural Networks (ST-GNNs) has either utilized graph adjacency matrices predefined by heuristic rules or learned through trainable parameters. These approaches fail to accurately represent the true spatial relationships between stations and adaptively capture the required multi-level spatial dependencies for prediction. To address these limitations, this paper proposes an Adaptive Hierarchical Graph Convolutional Neural Network (AHGCNN) for PM2.5 prediction. More specially, an adaptive hierarchical graph convolutional structure is initially developed for dynamically extracting multi-level spatial dependencies. Then, a hierarchical aggregation scheme is designed to consolidate the unique topological structures of graph neural networks across different levels. Finally, a unified Adaptive Hierarchical Graph Convolution Gated Recurrent Unit (AHGC-GRU) model is proposed by integrating Gated Recurrent Unit (GRU) with hierarchical graph convolution in an effort to capture spatiotemporal dependencies of air quality data. Extensive experiments are conducted on real-world datasets, and the results demonstrate that the proposed model outperforms existing models.

Research on power generation prediction of hydropower in river basin based on multi-head attention graph convolutional neural network

For the power generation prediction of traditional hydropower stations, most of them only use time series prediction and neglect to study the spatial topological relationship of hydropower stations in the river basin, so that it is difficult to fully explore the characteristic relationship of space power stations. In this paper, a research method for power generation prediction of hydropower in river basin hydropower stations based on multi-head attention map convolutional neural network is proposed. This method establishes a first-level node neighborhood feature map based on the spatial geographic distribution information of hydropower stations in the basin, and uses the method of graph convolution to carry out node feature mining and feature learning, so as to transform the power generation capacity evaluation problem of the hydropower station in the basin into the node prediction problem in the graph, which is different from the global normalization rule. the multi-head attention mechanism introduced further improves the information aggregation quality of the graph node, and uses the historical temperature, power generation, electricity price, unit status and other data of each hydropower station in the basin for training. The reasoning results show that the proposed method achieves higher accuracy than other schemes, and the power prediction method is conducive to the formulation of power plans of hydropower stations in the basin, and can also play a positive role in guiding the site selection of hydropower plants.

Learning complex predicates for cardinality estimation using recursive neural networks

Cardinality estimation is one of the most vital components in the query optimizer, which has been extensively studied recently. On one hand, traditional cardinality estimators, such as histograms and sampling methods, struggle to capture the correlations between multiple tables. On the other hand, current learning-based methods still suffer from the feature extraction of complex predicates and join relations, which will lead to inaccurate cost estimation, eventually a sub-optimal execution plan. To address these challenges, we present a novel end-to-end architecture leveraging deep learning to provide high-quality cardinality estimation. We exploit an effective feature extraction technique, which can fully make use of the structure of tables, join conditions and predicates. Besides, we use sampling-based technique to construct sample bitmaps for the tables and join conditions respectively. We also utilize the characteristics of predicate tree combined with recursive neural network to extract deep-level features of complex predicates. Finally, we embed these feature vectors into the model, which consists of three components: a recursive neural network, a graph convolutional neural network (GCN) and a multi-set convolutional neural network, to obtain the estimated cardinality. Extensive results conducted on real-world workloads demonstrate that our approach can achieve significant improvement in accuracy and be extended to queries with complex semantics.

Forecasting vaping health risks through neural network model prediction of flavour pyrolysis reactions

Vaping involves the heating of chemical solutions (e-liquids) to high temperatures prior to lung inhalation. A risk exists that these chemicals undergo thermal decomposition to new chemical entities, the composition and health implications of which are largely unknown. To address this concern, a graph-convolutional neural network (NN) model was used to predict pyrolysis reactivity of 180 e-liquid chemical flavours. The output of this supervised machine learning approach was a dataset of probability ranked pyrolysis transformations and their associated 7307 products. To refine this dataset, the molecular weight of each NN predicted product was automatically correlated with experimental mass spectrometry (MS) fragmentation data for each flavour chemical. This blending of deep learning methods with experimental MS data identified 1169 molecular weight matches that prioritized these compounds for further analysis. The average number of discrete matches per flavour between NN predictions and MS fragmentation was 6.4 with 92.8% of flavours having at least one match. Globally harmonized system classifications for NN/MS matches were extracted from PubChem, revealing that 127 acute toxic, 153 health hazard and 225 irritant classifications were predicted. This approach may reveal the longer-term health risks of vaping in advance of clinical diseases emerging in the general population.

Machine learning-enabled chemical space exploration of all-inorganic perovskites for photovoltaics

The vast compositional and configurational spaces of multi-element metal halide perovskites (MHPs) result in significant challenges when designing MHPs with promising stability and optoelectronic properties. In this paper, we propose a framework for the design of B-site-alloyed ABX3 MHPs by combining density functional theory (DFT) and machine learning (ML). We performed generalized gradient approximation with Perdew–Burke–Ernzerhof functional for solids (PBEsol) on 3,159 B-site-alloyed perovskite structures using a compositional step of 1/4. Crystal graph convolution neural networks (CGCNNs) were trained on the 3159 DFT datasets to predict the decomposition energy, bandgap, and types of bandgaps. The trained CGCNN models were used to explore the compositional and configurational spaces of 41,400 B-site-alloyed ABX3 MHPs with a compositional step of 1/16, by accessing all possible configurations for each composition. The electronic band structures of the selected compounds were calculated using the hybrid functional (PBE0). Then, we calculated the optical absorption spectra and spectroscopic limited maximum efficiency of the selected compounds. Based on the DFT/ML-combined screening, 10 promising compounds with optimal bandgaps were selected, and from among these 10 compounds, CsGe0.3125Sn0.6875I3 and CsGe0.0625Pb0.3125Sn0.625Br3 were suggested as photon absorbers for single-junction and tandem solar cells, respectively. The design framework presented herein is a good starting point for the design of mixed MHPs for optoelectronic applications.

Solvatochromism and halochromism in nitro lophine derivatives: Photophysical study, computational calculations and applications as pH sensing material

Nitro Lophines were readily synthesized via multicomponent reaction of benzil, nitro benzaldehyde and ammonium acetate. All three nitro Lophines were isolated in good yields and were also characterized by various analytical and spectroscopic techniques. A distinctive solvatochromism was observed in case of ortho and para nitro containing Lophines in their absorbance spectra. In particular, naked eye solvatochromism was observed, in case of para nitro Lophine, in the form of yellow and red coloured solution in methanol and DMSO respectively. Halochromism studies revealed the hypsochromic shift under acidic pH while bathochromic shift under alkaline pH for both nitro Lophines. Again the para nitro Lophine demonstrated wonderful distinctive colour change under acidic and alkaline pH in both methanol and DMSO as solvents. The measurement of absorbance at different pH values was carried out and the data obtained were used for calculation of dissociation constants employing several graphical methods. Computational calculations were carried out using TD-DFT for UV–Vis absorption calculation while graph-convolutional neural network model was utilized for calculation of dissociation constants. Ultimately, a reusable naked eye pH detection paper could be developed using para nitro Lophine as a sole indicator.

AI-Empowered Multimodal Hierarchical Graph-Based Learning for Situation Awareness on Enhancing Disaster Responses

Situational awareness (SA) is crucial in disaster response, enhancing the understanding of the environment. Social media, with its extensive user base, offers valuable real-time information for such scenarios. Although SA systems excel in extracting disaster-related details from user-generated content, a common limitation in prior approaches is their emphasis on single-modal extraction rather than embracing multi-modalities. This paper proposed a multimodal hierarchical graph-based situational awareness (MHGSA) system for comprehensive disaster event classification. Specifically, the proposed multimodal hierarchical graph contains nodes representing different disaster events and the features of the event nodes are extracted from the corresponding images and acoustic features. The proposed feature extraction modules with multi-branches for vision and audio features provide hierarchical node features for disaster events of different granularities, aiming to build a coarse-granularity classification task to constrain the model and enhance fine-granularity classification. The relationships between different disaster events in multi-modalities are learned by graph convolutional neural networks to enhance the system’s ability to recognize disaster events, thus enabling the system to fuse complex features of vision and audio. Experimental results illustrate the effectiveness of the proposed visual and audio feature extraction modules in single-modal scenarios. Furthermore, the MHGSA successfully fuses visual and audio features, yielding promising results in disaster event classification tasks.

Enhancing human behavior recognition with spatiotemporal graph convolutional neural networks and skeleton sequences

ObjectivesThis study aims to enhance supervised human activity recognition based on spatiotemporal graph convolutional neural networks by addressing two key challenges: (1) extracting local spatial feature information from implicit joint connections that is unobtainable through standard graph convolutions on natural joint connections alone. (2) Capturing long-range temporal dependencies that extend beyond the limited temporal receptive fields of conventional temporal convolutions.MethodsTo achieve these objectives, we propose three novel modules integrated into the spatiotemporal graph convolutional framework: (1) a connectivity feature extraction module that employs attention to model implicit joint connections and extract their local spatial features. (2) A long-range frame difference feature extraction module that captures extensive temporal context by considering larger frame intervals. (3) A coordinate transformation module that enhances spatial representation by fusing Cartesian and spherical coordinate systems.FindingsEvaluation across multiple datasets demonstrates that the proposed method achieves significant improvements over baseline networks, with the highest accuracy gains of 2.76%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} on the NTU-RGB+D 60 dataset (Cross-subject), 4.1%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} on NTU-RGB+D 120 (Cross-subject), and 4.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} on Kinetics (Top-1), outperforming current state-of-the-art algorithms. This paper delves into the realm of behavior recognition technology, a cornerstone of autonomous systems, and presents a novel approach that enhances the accuracy and precision of human activity recognition.

Multi-scale relational graph convolutional network for multiple instance learning in histopathology images

Graph convolutional neural networks have shown significant potential in natural and histopathology images. However, their use has only been studied in a single magnification or multi-magnification with either homogeneous graphs or only different node types. In order to leverage the multi-magnification information and improve message passing with graph convolutional networks, we handle different embedding spaces at each magnification by introducing the Multi-Scale Relational Graph Convolutional Network (MS-RGCN) as a multiple instance learning method. We model histopathology image patches and their relation with neighboring patches and patches at other scales (i.e., magnifications) as a graph. We define separate message-passing neural networks based on node and edge types to pass the information between different magnification embedding spaces. We experiment on prostate cancer histopathology images to predict the grade groups based on the extracted features from patches. We also compare our MS-RGCN with multiple state-of-the-art methods with evaluations on several source and held-out datasets. Our method outperforms the state-of-the-art on all of the datasets and image types consisting of tissue microarrays, whole-mount slide regions, and whole-slide images. Through an ablation study, we test and show the value of the pertinent design features of the MS-RGCN.

Low-complexity collaborative caching strategy based on spatio-temporal graph convolutional model

To meet the low delay requirements for data content access in industrial IoT, efficient content caching strategies need to be designed in the Mobile Edge Computing (MEC). Most existing caching policies reduce access delay by predicting content popularity and caching popular content earlier during off-peak traffic, but these strategies only focus on the temporal order of content popularity without fully considering the graph topology of MEC servers and ignore the spatial correlation of content popularity. This paper proposes a low-complexity collaborative caching strategy based on spatio-temporal graph convolutional model (STCC). We integrate graph convolutional neural network and gated recurrent unit to construct spatio-temporal graph convolutional model, which mines the spatio-temporal correlation features of content popularity and make effective predictions on the MEC server graph topology constructed by proximity and semantic relations. Furthermore, we use hierarchical clustering to classify MEC servers into collaborative domains and design a low-complexity heuristic collaborative caching content placement algorithm to minimize the average access delay. Compared with the existing MEC server caching strategy, simulation experiments show that STCC has a better prediction effect of content popularity, and achieves better performance in the two indicators of the cache hit ratio and average access delay.

RPI-GGCN: Prediction of RNA-Protein Interaction Based on Interpretability Gated Graph Convolution Neural Network and Co-Regularized Variational Autoencoders.

RNA-protein interactions (RPIs) play an important role in several fundamental cellular physiological processes, including cell motility, chromosome replication, transcription and translation, and signaling. Predicting RPI can guide the exploration of cellular biological functions, intervening in diseases, and designing drugs. Given this, this study proposes the RPI-gated graph convolutional network (RPI-GGCN) method for predicting RPI based on the gated graph convolutional neural network (GGCN) and co-regularized variational autoencoder (Co-VAE). First, different types of feature information were extracted from RNA and protein sequences by nine feature extraction methods. Second, Co-VAEs are used to eliminate the redundancy of fused features and generate optimal features. Finally, this study introduces gated cyclic units into graph convolutional networks (GCNs) to construct a model for RPI prediction, which efficiently extracts topological information and improves the model's interpretable feature learning and expression capabilities. In the fivefold cross-validation test, the RPI-GGCN method achieved prediction accuracies of 97.27%, 97.32%, 96.54%, 95.76%, and 94.98% on the RPI369, RPI488, RPI1446, RPI1807, and RPI2241 datasets. To test the generalization performance of the model, we used the model trained on RPI369 to predict the independent NPInter v3.0 dataset and achieved excellent performance in all six independent validation sets. By visualizing the RPI network graph based on the prediction results, we aim to provide a new perspective and reference for studying RPI mechanisms and exploring new RPIs. Extensive experimental results demonstrate that RPI-GGCN can provide an efficient, accurate, and stable RPI prediction method.

A graph-based cardiac arrhythmia classification methodology using one-lead ECG recordings

In this study, we present a novel graph-based methodology for an accurate classification of cardiac arrhythmia diseases using a single-lead electrocardiogram (ECG). The proposed approach employs the visibility graph technique to generate graphs from time signals. Subsequently, informative features are extracted from each graph and then fed into classifiers to match the input ECG signal with the appropriate target arrhythmia class. The six target classes in this study are normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), atrial premature contraction (A), and fusion (F) beats. Three classification models were explored, including graph convolutional neural network (GCN), multi-layer perceptron (MLP), and random forest (RF). ECG recordings from the MIT-BIH arrhythmia database were utilized to train and evaluate these classifiers. The results indicate that the multi-layer perceptron model attains the highest performance, showcasing an average accuracy of 99.02%. Following closely, the random forest achieves a strong performance as well, with an accuracy of 98.94% while providing critical intuitions.

Employing Graph Neural Networks for Predicting Electrode Average Voltages and Screening High-Voltage Sodium Cathode Materials.

For many years, humans have been relentlessly focused on enhancing battery longevity and boosting energy storage capacities. The performance and durability of a battery depend significantly on the material used for its electrodes. In this context, merging machine learning with density functional theory (DFT) calculations has emerged as a pivotal approach to advancing the exploration of battery crystal structures. We present a new method that combines a graph convolutional neural network (GNN) with a Transformer convolutional layer, which we call Transformer-GNN. To underscore its efficacy, we benchmarked Transformer-GNN against three established statistical machine learning models: Support Vector Machine, Random Forest, and XGBoost. We also developed a standard GNN, which we refer to as Basic-GNN. Additionally, we compared Basic-GNN with Transformer-GNN to highlight the improvements brought about by incorporating the Transformer convolutional layer. The Transformer-GNN model outperforms the other models, achieving the highest R2 value of 0.82 and the lowest mean squared error of 0.3161. Our findings demonstrate that the Transformer-GNN can profoundly understand battery crystal structures, thus forging the path toward more sophisticated and durable battery systems. Leveraging the GNN model's voltage predictions in tandem with the capacity data sourced from the database, we screened and pinpointed Na(NiO2)2 as a high-voltage (higher than 5 V), high-capacity sodium cathode material. We conducted DFT calculations on Na(NiO2)2 and revealed the migration mechanism of the Na ions.

Meta graph network recommendation based on multi-behavior encoding

As traditional recommendation systems ignore the hidden information among different user behaviors (such as clicks, add-to-favorites, add-to-cart, and purchases), this often leads to low accuracy in recommendation results. We propose a meta-graph network recommendation system via multi-behavior encoding (MBGR). Firstly, the graph convolutional neural network is used to extract features from various interactive behavior heterogeneous graphs of user-items for behavior heterogeneous modeling. Secondly, matrix decomposition algorithm and meta-knowledge learner are used respectively to process the semantic information of user behavior, and then attention mechanism is used to learn and distinguish the importance of different types of user item interaction behaviors. Finally, meta-knowledge transfer network is used to combine meta-learning paradigm and neural network framework to establish user target behavior recommendation. We conducted comparative experiments comparing MBGR with 7 different baseline models such as NCF and DMF. Extensive experiments on three real datasets (Tmall, Yelp, ML10M) demonstrate that the proposed MBGR method outperforms the baselines. The performance of MBGR is improved by 10.97 % on average with the metric of HR@10 and 10.96 % with the metric of NDCG@10. Under different top-N value evaluation conditions (HR@10, HR@7, NDCG@10, NDCG@7, etc.), the proposed model's performance can also be improved by more than 10 %, which proves the rationality and effectiveness of the proposed MBGR method.

AAGCN: a graph convolutional neural network with adaptive feature and topology learning

In recent years, there has been a growing prevalence of deep learning in various domains, owing to advancements in information technology and computing power. Graph neural network methods within deep learning have shown remarkable capabilities in processing graph-structured data, such as social networks and traffic networks. As a result, they have garnered significant attention from researchers.However, real-world data often face challenges like data sparsity and missing labels, which can hinder the performance and generalization ability of graph convolutional neural networks. To overcome these challenges, our research aims to effectively extract the hidden features and topological information of graph convolutional neural networks. We propose an innovative model called Adaptive Feature and Topology Graph Convolutional Neural Network (AAGCN). By incorporating an adaptive layer, our model preprocesses the data and integrates the hidden features and topological information with the original data’s features and structure. These fused features are then utilized in the convolutional layer for training, significantly enhancing the expressive power of graph convolutional neural networks.To evaluate the effectiveness of the adaptive layer in the AAGCN model, we conducted node classification experiments on real datasets. The results validate its ability to address data sparsity and improve the classification performance of graph convolutional neural networks.In conclusion, our research primarily focuses on addressing data sparsity and missing labels in graph convolutional neural networks. The proposed AAGCN model, which incorporates an adaptive layer, effectively extracts hidden features and topological information, thereby enhancing the expressive power and classification performance of these networks.

Ship Ballast Water System Fault Diagnosis Method Based on Multi-Feature Fusion Graph Convolution

To tackle the issues of limited fault data, inadequate information availability, and subpar fault diagnosis within the realm of ship ballast water system condition monitoring, this paper presents a novel fault diagnosis methodology known as the Probabilistic Similarity and Linear Similarity-based Graph Convolutional Neural Network (PCGCN) model. PCGCN initially converts the ship’s ballast water system dataset into two distinct graph structures: a probabilistic topology graph and a correlation topology graph. It delves into data similarity by employing T-SNE for probabilistic similarity and Pearson’s correlation coefficient for linear similarity to establish the inter-sample neighbor relationships. Subsequently, an early fusion of these two graph structures is conducted to extract more profound multi-scale feature information. Following this step, the graph convolutional neural network (GCN) is introduced to amalgamate the feature information from neighboring nodes in addition to its inherent features. This is aimed at enhancing the available information for the classification task and addressing the issues of limited fault data and inadequate label information. In conclusion, we employ a simulated ship fault dataset for testing experiments, and the PCGCN model demonstrates superior classification accuracy, reaching 97.49%, outperforming traditional diagnostic methods. These experimental outcomes underscore the applicability of the model introduced in this study to the realm of ship ballast water system fault diagnosis, even under challenging conditions characterized by limited sample sizes and insufficient labeling information.

A brain topography graph embedded convolutional neural network for EEG-based motor imagery classification

Brain-computer interface (BCI) based on motor imagery EEG (MI-EEG) has been used extensively in health care, device control, entertainment, and other fields. MI-EEG signals consist of multiple channels that exhibit a specific topological relationship. However, many existing methods based on deep learning do not make good use of the multi-electrode characteristics of EEG signals. To further improve the decoding performance of MI-EEG, this study proposes a novel method combining the brain topology graph embedding and convolutional neural network (CNN) for MI-EEG classification. Specifically, mutual information is used to measure the relationship between EEG channels. A graph convolutional network (GCN) is employed to embed the topological relationship. Following this, a convolutional block using depth-wise convolution is built to extract spatial–temporal features, while a temporal convolutional network (TCN) is used to extract advanced temporal features. The model’s performance is evaluated on BCICIV-2a and HGD datasets. The experimental results show that the classification accuracy of the proposed model is 80.46% and 94.38%, respectively, outperforming existing methods. Moreover, ablation experiments and feature visualization show that graph embedding can significantly improve the decoding performance of MI-EEG.

Drug-target Interaction Prediction By Combining Transformer and Graph Neural Networks

Background: The prediction of drug-target interactions (DTIs) plays an essential role in drug discovery. Recently, deep learning methods have been widely applied in DTI prediction. However, most of the existing research does not fully utilize the molecular structures of drug compounds and the sequence structures of proteins, which makes these models unable to obtain precise and effective feature representations. Methods: In this study, we propose a novel deep learning framework combining transformer and graph neural networks for predicting DTIs. Our model utilizes graph convolutional neural networks to capture the global and local structure information of drugs, and convolutional neural networks are employed to capture the sequence feature of targets. In addition, the obtained drug and protein representations are input to multi-layer transformer encoders, respectively, to integrate their features and generate final representations. Results: The experiments on benchmark datasets demonstrated that our model outperforms previous graph-based and transformer-based methods, with 1.5% and 1.8% improvement in precision and 0.2% and 1.0% improvement in recall, respectively. The results indicate that the transformer encoders effectively extract feature information of both drug compounds and proteins. Conclusion: Overall, our proposed method validates the applicability of combining graph neural networks and transformer architecture in drug discovery, and due to the attention mechanisms, it can extract deep structure feature data of drugs and proteins.

Complex-Value Spatiotemporal Graph Convolutional Neural Networks and Its Applications to Electric Power Systems AI

Complex-Value Spatiotemporal Graph Convolutional Neural Networks and Its Applications to Electric Power Systems AI

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis.

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.