Infrared Image Quality Estimation with Node-to-Graph Regression

Molecular carcinogenicity is a crucial factor in the development of cancer, and accurate prediction of it is vital for cancer prevention, treatment, and drug development. In recent years, deep learning has been applied to predict molecular carcinogenicity, but due to limitations in data quality and feature richness, these methods still need improvement in terms of accuracy, robustness, and interpretability. In this article, we propose a deep transfer learning model based on multimodal information fusion, called MMF-MCP, for molecular feature extraction and carcinogenicity prediction. We extract molecular graph features and fingerprint features using graph attention networks and convolutional neural networks, respectively, and process molecular images through a deep residual network, SE-ResNet18, equipped with a squeeze-and-excitation module. To more effectively utilize limited carcinogenicity data and enhance the model's predictive performance and generalization ability, we further apply a transfer learning strategy by pretraining the model on a molecular mutagenicity data set and then fine-tuning it on the carcinogenicity data set, enabling knowledge transfer and significant improvement in model performance. MMF-MCP achieves average ACC, AUC, SE, and SP scores of 0.8452, 0.8513, 0.8571, and 0.8333 on benchmark data sets for molecular carcinogenicity, significantly outperforming state-of-the-art molecular carcinogenicity prediction methods. Additionally, the visualization results of MMF-MCP on molecular images demonstrate its strong interpretability, providing significant assistance in visually observing and understanding the critical structures and features of molecular carcinogenicity. The source code for MMF-MCP is available at https://github.com/liuliwei1980/MCP.

The automatic identification of disease types of edible mushroom crops and poisonous crops is of great significance for improving crop yield and quality. Based on the graph convolutional neural network theory, this paper constructs a graph convolutional network model for the identification of poisonous crops and edible fungi. By constructing 6 graph convolutional networks with different depths, the model uses the training mechanism of graph convolutional networks to analyze the results of disease identification and completes the automatic extraction of the disease characteristics of the poisonous crops by overfitting problem. During the simulation, firstly, the relevant PlantVillage dataset is used to obtain the pretrained model, and the parameters are adjusted to fit the dataset. The network framework is trained and parameterized with prior knowledge learned from large datasets and finally synthesized by training multiple neural network models and using direct averaging and weighting to synthesize their predictions. The experimental results show that the graph convolutional neural network model that integrates multi-scale category relationships and dense links can use dense connection technology to improve the representation ability and generalization ability of the model, and the accuracy rate generally increases by 1%–10%. The average recognition rate is about 91%, which greatly promotes the ability to identify the diseases of poisonous crops.

Blind image quality assessment (BIQA) that can directly evaluate image quality without perfect-quality reference has been a long-standing research topic. Although the existing BIQA models have achieved very encouraging performance, the lack of explainability and generalization ability limits their real-world applications to a great extent. People usually assess image quality according to semantic attributes, e.g., brightness, color, contrast, noise and sharpness. Furthermore, judgment on image quality is also impacted by the scene presented in the image. Therefore, the inherent relationship between semantic attributes and scenes is crucial for image quality assessment, which has rarely been explored yet. With this motivation, this paper presents a Semantic Attribute Reasoning based image QUality Evaluator (SARQUE). Specifically, we propose a two-stream network to predict semantic attributes and scene categories from distorted images. To investigate the inherent relationship between the semantic attributes and scene category, a semantic reasoning module is further proposed based on the graph convolution network (GCN), producing the final quality score. Extensive experiments conducted on five in-the-wild image quality databases demonstrate the superiority of the proposed SARQUE model over the state-of-the-arts. Furthermore, the proposed model features better explainability and generalization ability due to the use of semantic attributes.

The increasing age of the population and the acceleration of urbanisation are giving rise to a growing emphasis on the layout and functional optimisation of medical facilities. To address this challenge, this study proposes a model for optimising the structure and function of medical facilities based on a Graph Convolutional Network (GCN). This combines existing deep learning and graph convolution methods to enhance the capabilities of traditional optimisation models by integrating the advantages of graph convolutional networks in modelling spatial and functional relationships. In this model, a graph representation of medical facilities is first constructed, with nodes representing facilities and edges representing spatial and functional connections between facilities. These relationships are then learned through a graph convolutional network, with the objective of capturing the distribution and demand characteristics of medical resources. Secondly, in order to enhance the model's adaptability to diverse scenarios, an adaptive graph convolution mechanism is introduced on the basis of the traditional GCN. This improves the model's generalisation ability in different medical environments by dynamically adjusting the graph structure and weights. Ultimately, the model optimises the allocation of medical resources through end-to-end training, thereby maximising the coverage and efficiency of medical services. The experimental results demonstrate that the proposed model enhances the efficiency and quality of medical resource allocation in comparison to existing optimisation methods.

A fully automated segmentation of substantia nigra (SN) is an essential task for the development of an explainable computer-aided diagnosis system of Parkinson's disease (PD). Since anatomical alterations of SN are vital information in PD diagnosis, a precise segmentation model should have generalization ability against spatiotemporal changes. To satisfy these requirements, we propose a fully automated pipeline with several new techniques for a volumetric image obtained by neuromelanin magnetic resonance imaging. We develop a pipeline by integrating SN-prior probability estimation into the decision of the SN-contained region of interest. An estimated SN-prior probability is further fed into a new priority attention mechanism as a gating signal in our segmentation model. Furthermore, we introduce test-time dropout to improve a segmentation model's accuracy and generalization ability. To evaluate the model's generalization ability, we collected principal and external datasets with longitudinal scans of the same PD patients. Our segmentation model achieved averaged Dice scores of 0.845 and 0.851 for SN hyperintense regions in the principal and external datasets, respectively. These results demonstrated the best generalization ability in our comparative evaluations. Thresholding the number of voxels in the SN hyperintense regions, we also evaluated the segmentation results in automated PD identification. The PD identification achieved the areas under the receiver operating characteristic curves of 0.755 and 0.726 by our pipeline's output and the ground truth, respectively. The proposed pipeline, where we integrated SN-prior probability estimation, priority attention mechanism and test-time dropout to our segmentation model, achieved accurate SN segmentation with high generalization ability for our longitudinal data: the principal and external datasets. As demonstrated in the validation with the automated PD identification, our pipeline has the potential for improving the performance of PD diagnosis via further large-scale longitudinal analysis.

<p>Forecasting weather systems are capable to model atmospheric phenomena at various space-time scales. At very short space-time nowcasting techniques are still relying on measured data processing from ground-based microwave radars and satellite-based geostationary spectrometers. In this respect, precipitation field nowcasting from a few minutes up to a few hours is one of the most challenging goals to provide rapid and accurate updated features for civil prevention and protection decision-makers (e.g., from emergency services, marine services, sport, and cultural events, air traffic control, emergency management, agricultural sector and moreover flood early-warning system). Deep learning precipitation nowcasting models, based on weather radar network reflectivity measurements, have recently exceeded the overall performance of traditional extrapolation models, becoming one of the hottest topics in this field. This work proposes a novel network architecture to increase the performance of deep learning mesoscale precipitation prediction. Since precipitation nowcasting can be viewed as a video prediction problem, we present an architecture based on Graph Convolutional Neural Network (GCNN) for video frame prediction. Our solution exploits, as a cornerstone, the topology of Space-Time-Separable Graph-Convolutional- Network (STS-GCN), originally used for posing forecasting. We have applied our model on the TAASRAD19 radar data set with the aim of comparing our performance with other models, namely the Stacked Generalization (SG) Trajectory Gated Recurrent Unit (TrajGRU) and S-PROG Spectral Lagrangian extrapolation program (S-PROG).</p><p>The proposed model, named STSU-GCN (Space-Time-Separable Unet3d Graph Convolutional Network), has a structure composed of an encoder, decoder, and forecaster. The role of the encoder and decoder are accomplished by a Unet3d a structure borrowed with the specific purpose of modifying the spatial component, but not the temporal component. In the bottleneck of this Unet3D network, we use a graph-based forecaster. The performance of the STSU-GCN has been quantified using conventional metrics, such as the Critical Success Index (CSI), widely used in the meteorological community for the nowcasting task. Using TAASRAD19 radar data set and literature data, these CSI metrics have been applied to 4 different classes of rain rate, that is 5, 10, 20, 30 mm/h. Our STSU-GCN model has overperformed both TrajGRU and S-PROG in the classes 10 mm/h and 20 mm/h obtaining a CSI respectively of 0.148 and 0.097. On the other hand, STSU-GCN is underperforming in class 5mm per hour getting a CSI respectively of 0.099. Our STSU-GCN model is aligned with the results of the S-PROG benchmark, for the class 30 mm/h confirming a model skillful for classes with a high rain rate. In this work, we will also illustrate the results of the proposed STSU-GCN algorithm using case studies in the area of interest of the Italian Central Apennines during the summer of 2021. Statistical performances, potential developments, and critical issues of the STSU-GCN algorithm will be also discussed.</p>

In this study, we propose a novel method for identifying lithology using an attention mechanism-enhanced graph convolutional neural network (AGCN). The aim of this method is to address the limitations of traditional approaches that evaluate unbalanced lithology by improving the identification of thin layers and small samples, while providing reliable data support for reservoir evaluation. To achieve this goal, we begin by using Principal Component Analysis (PCA) with maximum and minimum distance clustering (Max-min-distance) to correct the logging curves, which compensates for the low resolution of thin layers and enhances the accuracy of stratigraphic representation. Subsequently, we transform the logging data into graph-structured data by connecting distance similarity points and feature similarity points of the logging samples. We then use the graph convolutional network (GCN) to identify lithology, leveraging both labeled and unlabeled data to enhance the ability to identify lithology in small sample datasets. Additionally, our model incorporates a channel and spatial attention mechanism that assigns weights to the graph structure during lithology identification, improving the model’s capability to discern differences across samples. To evaluate the performance of our model, we constructed a lithology dataset comprising five wells and conducted experiments. The results indicate that our approach achieves a maximum accuracy of 97.67%, surpassing the performance of a singlestructure model in lithology identification. In conclusion, our proposed method provides a promising and effective approach for unbalanced lithology identification, significantly improving accuracy levels.

In the digital age, the proliferation of health-related information online has heightened the risk of misinformation, posing substantial threats to public well-being. This research conducts a meticulous comparative analysis of classification models, focusing on detecting health misinformation. The study evaluates the performance of traditional machine learning models and advanced graph convolutional networks (GCN) across critical algorithmic metrics. The results comprehensively understand each algorithm's effectiveness in identifying health misinformation and provide valuable insights for combating the pervasive spread of false health information in the digital landscape. GCN with TF-IDF gives the best result, as shown in the result section.•The research method involves a comparative analysis of classification algorithms to detect health misinformation, exploring traditional machine learning models and graph convolutional networks.•This research used algorithms such as Passive Aggressive Classifier, Random Forest, Decision Tree, Logistic Regression, Light GBM, GCN, GCN with BERT, GCN with TF-IDF, and GCN with Word2Vec were employed. Performance Metrics: Accuracy: for Passive Aggressive Classifier: 85.75 %, Random Forest: 86 %, Decision Tree: 81.30 %, Light BGM: 83.29 %, normal GCN: 84.53 %, GCN with BERT: 85.00 %, GCN with TR-IDF: 93.86 % and GCN with word2Vec: 81.00 %•Algorithmic performance metrics, including accuracy, precision, recall, and F1-score, were systematically evaluated to assess the efficacy of each model in detecting health misinformation, focusing on understanding the strengths and limitations of different approaches. The superior performance of Graph Convolutional Networks (GCNs) with TF-IDF embedding, achieving an accuracy of 93.86 %

Traffic forecasting is considered a cornerstone of smart city development. A key challenge is capturing the long-term spatiotemporal dependencies of traffic data while improving the model's generalization ability. To address these issues, various sophisticated modules are embedded into different models. However, this approach increases the computational cost of the model. Additionally, adding or replacing datasets in a trained model requires retraining, which decreases prediction accuracy and increases time cost. To address the challenges faced by existing models in handling long-term spatiotemporal dependencies and high computational costs, this study proposes an enhanced pre-training method called the Improved Spatiotemporal Diffusion Graph (ImPreSTDG). While existing traffic prediction models, particularly those based on Graph Convolutional Networks (GCNs) and deep learning, are effective at capturing short-term spatiotemporal dependencies, they often experience accuracy degradation and increased computational demands when dealing with long-term dependencies. To overcome these limitations, we introduce a Denoised Diffusion Probability Model (DDPM) as part of the pre-training process, which enhances the model's ability to learn from long-term spatiotemporal data while significantly reducing computational costs. During the pre-training phase, ImPreSTDG employs a data masking and recovery strategy, with DDPM facilitating the reconstruction of masked data segments, thereby enabling the model to capture long-term dependencies in the traffic data. Additionally, we propose the Mamba module, which leverages the Selective State Space Model (SSM) to effectively capture long-term multivariate spatiotemporal correlations. This module enables more efficient processing of long sequences, extracting essential patterns while minimizing computational resource consumption. By improving computational efficiency, the Mamba module addresses the challenge of modeling long-term dependencies without compromising accuracy in capturing extended spatiotemporal trends. In the fine-tuning phase, the decoder is replaced with a forecasting header, and the pre-trained parameters are frozen. The forecasting header includes a meta-learning fusion module and a spatiotemporal convolutional layer, which facilitates the integration of both long-term and short-term traffic data for accurate forecasting. The model is then trained and adapted to the specific forecasting task. Experiments conducted on three real-world traffic datasets demonstrate that the proposed pre-training method significantly enhances the model's ability to handle long-term dependencies, missing data, and high computational costs, providing a more efficient solution for traffic prediction.

Air passenger carbon offset and carbon neutrality strategies: Implementation mechanism by convolutional neural network

Knowledge Graph is an important research field that involves the storage and management of knowledge, but the incompleteness and sparsity of Knowledge Graphs hinder their application in many fields. Knowledge Graph Reasoning aims to alleviate this problem by completing missing paths or identifying wrong paths between entities. Graph Convolution Network (GCN) based methods are one of the state-of-the-art approaches to this work. However, it is difficult to directly generalize to unknown nodes and utilizes valid information from the local neighborhood which results in poor flexibility and extensibility and will loss of important information. This paper presents EG-KGR, a plug-and-play knowledge reasoning model based on enhanced graph sampling and aggregate inductive learning algorithm to relieve the above problems and enhance existing GCN-based methods. Specifically, EG-KGR supports incremental characteristics, uses inductive learning to replace transductive learning, and designs random sampling and local information sampling optimization methods to improve the model's generalization ability, prediction accuracy, and running speed. Extensive experimental results show that our EG-KGR can achieve optimal results.

Graph neural networks (GNNs) have demonstrated significant potential in analyzing complex graph-structured data. However, conventional GNNs encounter challenges in effectively incorporating global and local features. Therefore, this paper introduces a novel approach for GNN called multichannel adaptive data mixture augmentation (MAME-GNN). It enhances a GNN by adopting a multi-channel architecture and interactive learning to effectively capture and coordinate the interrelationships between local and global graph structures. Additionally, this paper introduces the polynomial–Gaussian mixture graph interpolation method to address the problem of single and sparse graph data, which generates diverse and nonlinear transformed samples, improving the model's generalization ability. The proposed MAME-GNN is validated through extensive experiments on publicly available datasets, showcasing its effectiveness. Compared to existing GNN models, the MAME-GNN exhibits superior performance, significantly enhancing the model's robustness and generalization ability.

Multi-source visual information fusion and quality improvement can help the robotic system to perceive the real world. Image fusion is a computational technique fusing multisource images from multiple sensors into a synthesized image that provides a comprehensive or reliable description. Quality improvement techniques can be used to address the challenge of low-quality image analysis tasks [1][2][3][4][5][6]. At present, a lot of brain-inspired algorithm methods (or models) are aggressively proposed to accomplish these two tasks, and the artificial neural network has become one of the most popular techniques in processing image fusion and quality improvement techniques in this decade, especially deep convolutional neural networks [4][5][6][7][8]. This is an exciting research field for the research community of image fusion, and many interesting issues remain to be explored, such as deep few-shot learning, unsupervised learning, application of embodied neural systems, and industrial applications.How to develop a sound biological neural network and embedded system to extract the multiple features of source images are two key questions that need to be addressed in the fields of image fusion and quality improvement. Hence, studies in this field can be divided into two aspects: new end-to-end neural network models for merging constituent parts during the image fusion process and the embodiment of artificial neural networks for image processing systems. In addition, current booming techniques, including deep neural systems and embodied artificial intelligence systems, are considered potential future trends for reinforcing image fusion performance and quality improvement.The paper of Zhang et al. introduces a palmprint recognition method based on a gating mechanism and adaptive feature fusion. They propose a new network structure, GLGAnet, for extracting local and global features of palmprints. The method incorporates a gating mechanism to control features extracted by deep convolutional layers and Transformer modules, along with an adaptive convolution fusion module for multi-level feature fusion. Experimental results demonstrate that their method outperforms existing approaches on two datasets.Many previous works overlooked the crucial support-query set interaction and the deeper information that needs to be explored. Zeng et al. propose a duplex network model utilizing the suppression and focus concept to address this issue. Their network includes dynamic convolution, prototype matching structure, and a hybrid attention module called DAAConv. The DPMCN model demonstrates superior performance over traditional prototype-based methods in dataset experiments.In the third work, Peng et al. proposed a network structure called Context-Aware Lightweight Super-Resolution Network, which enhances the resolution of remote sensing images. This network combines local and global features and includes a Dynamic Weight Generation Branch to improve image quality while maintaining computational efficiency. Compared to existing methods, the proposed approach can reconstruct highquality images at a lower cost.In the fourth study, titled "Feature fusion network based on few-shot fine-grained classification," Yang et al. introduced the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes while utilizing local measures to consolidate intra-class data, greatly enhancing the model's generalization ability. The method proposed in this paper has been validated to be effective.In

Deep neural networks (DNNs) require large amounts of labeled data for model training. However, label noise is a common problem in datasets due to the difficulty of classification and high cost of labeling processes. Introducing the concepts of curriculum learning and progressive learning, this paper presents a novel solution that is able to handle massive noisy labels and improve model generalization ability. It proposes a new network model training strategy that considers mislabeled samples directly in the network training process. The new learning curriculum is designed to measures the complexity of the data with their distribution density in a feature space. The sample data in each category are then divided into easy-to-classify (clean samples), relatively easy-to-classify, and hard-to-classify (noisy samples) subsets according to the smallest intra-class local density with each cluster. On this basis, DNNs are trained progressively in three stages, from easy to hard, i.e., from clean to noisy samples. The experimental results demonstrate that the accuracy of image classification can be improved through data augmentation, and the classification accuracy of the proposed method is clearly higher than that of standard Inception_v2 for the NEU dataset after data augmentation, when the proportion of noisy labels in the training set does not exceed 60%. With 50% noisy labels in the training set, the classification accuracy of the proposed method outperformed recent state-of-the-art label noise learning methods, CleanNet and MentorNet. The proposed method also performed well in practical applications, where the number of noisy labels was uncertain and unevenly distributed. In this case, the proposed method not only can alleviate the adverse effects of noisy labels, but it can also improve the generalization ability of standard deep networks and their overall capability.

Biomarkers discovery for endometrial cancer: A graph convolutional sample network method