Graph neural networks(GNNs)have shown notable success in identifying security vulnerabilities within Ethereum smart contracts by capturing structural relationships encoded in control-and data-flow graphs.Despite their...Graph neural networks(GNNs)have shown notable success in identifying security vulnerabilities within Ethereum smart contracts by capturing structural relationships encoded in control-and data-flow graphs.Despite their effectiveness,most GNN-based vulnerability detectors operate as black boxes,making their decisions difficult to interpret and thus less suitable for critical security auditing.The information bottleneck(IB)principle provides a theoretical framework for isolating task-relevant graph components.However,existing IB-based implementations often encounter unstable optimization and limited understanding of code semantics.To address these issues,we introduce ContractGIB,an interpretable graph information bottleneck framework for function-level vulnerability analysis.ContractGIB introduces three main advances.First,ContractGIB introduces an Hilbert–Schmidt Independence Criterion(HSIC)based estimator that provides stable dependence measurement.Second,it incorporates a CodeBERT semantic module to improve node representations.Third,it initializes all nodes with pretrained CodeBERT embeddings,removing the need for hand-crafted features.For each contract function,ContractGIB identifies themost informative nodes forming an instance-specific explanatory subgraph that supports the model’s prediction.Comprehensive experiments on public smart contract datasets,including ESC andVSC,demonstrate thatContractGIB achieves superior performance compared to competitive GNN baselines,while offering clearer,instance-level interpretability.展开更多
BACKGROUND: Sepsis is a life-threatening inflammatory condition in which the invading pathogen avoids the host's defense mechanisms and continuously stimulates and damages host cells. Consequently, many immune res...BACKGROUND: Sepsis is a life-threatening inflammatory condition in which the invading pathogen avoids the host's defense mechanisms and continuously stimulates and damages host cells. Consequently, many immune responses initially triggered for protection become harmful because of the failure to restore homeostasis, resulting in ongoing hyperinflammation and immunosuppression. METHODS: A literature review was conducted to address bacterial sepsis, describe advances in understanding complex immunological reactions, critically assess diagnostic approaches, and emphasize the importance of studying bacterial bottlenecks in the detection and treatment of sepsis.RESULTS: Diagnosing sepsis via a single laboratory test is not feasible;therefore, multiple key biomarkers are typically monitored, with a focus on trends rather than absolute values. The immediate interpretation of sepsis-associated clinical signs and symptoms, along with the use of specific and sensitive laboratory tests, is crucial for the survival of patients in the early stages. However, long-term mortality associated with sepsis is now recognized, and alongside the progression of this condition, there is an in vivo selection of adapted pathogens.CONCLUSION: Bacterial sepsis remains a significant cause of mortality across all ages and societies. While substantial progress has been made in understanding the immunological mechanisms underlying the inflammatory response, there is growing recognition that the ongoing host-pathogen interactions, including the emergence of adapted virulent strains, shape both the acute and long-term outcomes in sepsis. This underscores the urgent need for novel high-throughput diagnostic methods and a shift toward more pre-emptive, rather than reactive, treatment strategies in sepsis care.展开更多
Tomato leaf diseases significantly reduce crop yield;therefore,early and accurate disease detection is required.Traditional detection methods are laborious and error-prone,particularly in large-scale farms,whereas exi...Tomato leaf diseases significantly reduce crop yield;therefore,early and accurate disease detection is required.Traditional detection methods are laborious and error-prone,particularly in large-scale farms,whereas existing hybrid deep learning models often face computational inefficiencies and poor generalization over diverse environmental and disease conditions.This study presents a unified U-Net-Vision Mamba Model with Hierarchical Bottleneck AttentionMechanism(U-net-Vim-HBAM),which integrates U-Net’s high-resolution segmentation,Vision Mamba’s efficient contextual processing,and a Hierarchical Bottleneck Attention Mechanism to address the challenges of disease detection accuracy,computational complexity,and efficiency in existing models.The model was trained on the Tomato Leaves and PlantVillage combined datasets from Kaggle and achieved 98.63% accuracy,98.24% precision,96.41% recall,and 97.31%F1 score,outperforming baselinemodels.Simulation tests demonstrated the model’s compatibility across devices with computational efficacy,ensuring its potential for integration into real-time mobile agricultural applications.The model’s adaptability to diverse datasets and conditions suggests that it is a versatile and high-precision instrument for disease management in agriculture,supporting sustainable agricultural practices.This offers a promising solution for crop health management and contributes to food security.展开更多
Diagnosing gastrointestinal tract diseases is a critical task requiring accurate and efficient methodologies.While deep learning models have significantly advanced medical image analysis,challenges such as imbalanced ...Diagnosing gastrointestinal tract diseases is a critical task requiring accurate and efficient methodologies.While deep learning models have significantly advanced medical image analysis,challenges such as imbalanced datasets and redundant features persist.This study proposes a novel framework that customizes two deep learning models,NasNetMobile and ResNet50,by incorporating bottleneck architectures,named as NasNeck and ResNeck,to enhance feature extraction.The feature vectors are fused into a combined vector,which is further optimized using an improved Whale Optimization Algorithm to minimize redundancy and improve discriminative power.The optimized feature vector is then classified using artificial neural network classifiers,effectively addressing the limitations of traditional methods.Data augmentation techniques are employed to tackle class imbalance,improving model learning and generalization.The proposed framework was evaluated on two publicly available datasets:Hyper-Kvasir and Kvasir v2.The Hyper-Kvasir dataset,comprising 23 gastrointestinal disease classes,yielded an impressive 96.0%accuracy.On the Kvasir v2 dataset,which contains 8 distinct classes,the framework achieved a remarkable 98.9%accuracy,further demonstrating its robustness and superior classification performance across different gastrointestinal datasets.The results demonstrate the effectiveness of customizing deep models with bottleneck architectures,feature fusion,and optimization techniques in enhancing classification accuracy while reducing computational complexity.展开更多
A bottleneck algebra is a linearly ordered set(B,≤)with two operations a⊕b=max{a,b}and a⊗b=min{a,b}.A finite nonempty set of vectors of order m over a bottleneck algebra B is said to be 2 B-independent if each vecto...A bottleneck algebra is a linearly ordered set(B,≤)with two operations a⊕b=max{a,b}and a⊗b=min{a,b}.A finite nonempty set of vectors of order m over a bottleneck algebra B is said to be 2 B-independent if each vector of order m over B can be expressed as a linear combination of vectors in this set in at most one way.In 1996,Cechlárováand Plávka posed an open problem:Find a necessary and sufficient condition for a finite nonempty set of vectors of order m over B to be 2 B-independent.In this paper,we derive some necessary and sufficient conditions for a finite nonempty set of vectors of order m over a bounded bottleneck algebra to be 2 B-independent and answer this open problem.展开更多
INTRODUCTION Contemporary human living environments present complex and pervasive health risks,and environmental health challenges are becoming increasingly prominent.These risks encompass diverse domains,such as chem...INTRODUCTION Contemporary human living environments present complex and pervasive health risks,and environmental health challenges are becoming increasingly prominent.These risks encompass diverse domains,such as chemical factors(e.g.,heavy metals,nanomaterials,per-and polyfluoroalkyl substances),physical factors(e.g.,noise,radiation,and extreme weather)biological factors(e.g.,pathogenic microorganisms and parasites),natural disasters(e.g.,earthquakes and floods),and anthropogenic incidents(e.g.,chemical spills,fires,and explosions).展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.52208424,52208416,52078091,and 52108399)the Shanghai Municipal Science and Technology Major Project(Grant No.2021SHZDZX0102).
文摘Graph neural networks(GNNs)have shown notable success in identifying security vulnerabilities within Ethereum smart contracts by capturing structural relationships encoded in control-and data-flow graphs.Despite their effectiveness,most GNN-based vulnerability detectors operate as black boxes,making their decisions difficult to interpret and thus less suitable for critical security auditing.The information bottleneck(IB)principle provides a theoretical framework for isolating task-relevant graph components.However,existing IB-based implementations often encounter unstable optimization and limited understanding of code semantics.To address these issues,we introduce ContractGIB,an interpretable graph information bottleneck framework for function-level vulnerability analysis.ContractGIB introduces three main advances.First,ContractGIB introduces an Hilbert–Schmidt Independence Criterion(HSIC)based estimator that provides stable dependence measurement.Second,it incorporates a CodeBERT semantic module to improve node representations.Third,it initializes all nodes with pretrained CodeBERT embeddings,removing the need for hand-crafted features.For each contract function,ContractGIB identifies themost informative nodes forming an instance-specific explanatory subgraph that supports the model’s prediction.Comprehensive experiments on public smart contract datasets,including ESC andVSC,demonstrate thatContractGIB achieves superior performance compared to competitive GNN baselines,while offering clearer,instance-level interpretability.
基金funded by the Deanship of Scientific Research (DSR) at King Abdulaziz UniversityJeddah+1 种基金Saudi Arabiaunder grant number G-150-248-1443。
文摘BACKGROUND: Sepsis is a life-threatening inflammatory condition in which the invading pathogen avoids the host's defense mechanisms and continuously stimulates and damages host cells. Consequently, many immune responses initially triggered for protection become harmful because of the failure to restore homeostasis, resulting in ongoing hyperinflammation and immunosuppression. METHODS: A literature review was conducted to address bacterial sepsis, describe advances in understanding complex immunological reactions, critically assess diagnostic approaches, and emphasize the importance of studying bacterial bottlenecks in the detection and treatment of sepsis.RESULTS: Diagnosing sepsis via a single laboratory test is not feasible;therefore, multiple key biomarkers are typically monitored, with a focus on trends rather than absolute values. The immediate interpretation of sepsis-associated clinical signs and symptoms, along with the use of specific and sensitive laboratory tests, is crucial for the survival of patients in the early stages. However, long-term mortality associated with sepsis is now recognized, and alongside the progression of this condition, there is an in vivo selection of adapted pathogens.CONCLUSION: Bacterial sepsis remains a significant cause of mortality across all ages and societies. While substantial progress has been made in understanding the immunological mechanisms underlying the inflammatory response, there is growing recognition that the ongoing host-pathogen interactions, including the emergence of adapted virulent strains, shape both the acute and long-term outcomes in sepsis. This underscores the urgent need for novel high-throughput diagnostic methods and a shift toward more pre-emptive, rather than reactive, treatment strategies in sepsis care.
文摘Tomato leaf diseases significantly reduce crop yield;therefore,early and accurate disease detection is required.Traditional detection methods are laborious and error-prone,particularly in large-scale farms,whereas existing hybrid deep learning models often face computational inefficiencies and poor generalization over diverse environmental and disease conditions.This study presents a unified U-Net-Vision Mamba Model with Hierarchical Bottleneck AttentionMechanism(U-net-Vim-HBAM),which integrates U-Net’s high-resolution segmentation,Vision Mamba’s efficient contextual processing,and a Hierarchical Bottleneck Attention Mechanism to address the challenges of disease detection accuracy,computational complexity,and efficiency in existing models.The model was trained on the Tomato Leaves and PlantVillage combined datasets from Kaggle and achieved 98.63% accuracy,98.24% precision,96.41% recall,and 97.31%F1 score,outperforming baselinemodels.Simulation tests demonstrated the model’s compatibility across devices with computational efficacy,ensuring its potential for integration into real-time mobile agricultural applications.The model’s adaptability to diverse datasets and conditions suggests that it is a versatile and high-precision instrument for disease management in agriculture,supporting sustainable agricultural practices.This offers a promising solution for crop health management and contributes to food security.
基金supported by Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia through the Researchers Supporting Project PNURSP2025R333.
文摘Diagnosing gastrointestinal tract diseases is a critical task requiring accurate and efficient methodologies.While deep learning models have significantly advanced medical image analysis,challenges such as imbalanced datasets and redundant features persist.This study proposes a novel framework that customizes two deep learning models,NasNetMobile and ResNet50,by incorporating bottleneck architectures,named as NasNeck and ResNeck,to enhance feature extraction.The feature vectors are fused into a combined vector,which is further optimized using an improved Whale Optimization Algorithm to minimize redundancy and improve discriminative power.The optimized feature vector is then classified using artificial neural network classifiers,effectively addressing the limitations of traditional methods.Data augmentation techniques are employed to tackle class imbalance,improving model learning and generalization.The proposed framework was evaluated on two publicly available datasets:Hyper-Kvasir and Kvasir v2.The Hyper-Kvasir dataset,comprising 23 gastrointestinal disease classes,yielded an impressive 96.0%accuracy.On the Kvasir v2 dataset,which contains 8 distinct classes,the framework achieved a remarkable 98.9%accuracy,further demonstrating its robustness and superior classification performance across different gastrointestinal datasets.The results demonstrate the effectiveness of customizing deep models with bottleneck architectures,feature fusion,and optimization techniques in enhancing classification accuracy while reducing computational complexity.
基金Supported by National Natural Science Foundation of China(Grant Nos.11771004 and 11971111).
文摘A bottleneck algebra is a linearly ordered set(B,≤)with two operations a⊕b=max{a,b}and a⊗b=min{a,b}.A finite nonempty set of vectors of order m over a bottleneck algebra B is said to be 2 B-independent if each vector of order m over B can be expressed as a linear combination of vectors in this set in at most one way.In 1996,Cechlárováand Plávka posed an open problem:Find a necessary and sufficient condition for a finite nonempty set of vectors of order m over B to be 2 B-independent.In this paper,we derive some necessary and sufficient conditions for a finite nonempty set of vectors of order m over a bounded bottleneck algebra to be 2 B-independent and answer this open problem.
基金supported by the commissioned project of the Department of Health and Immunization Planning under the National Disease Control and Prevention Administration(No.BX2024100800015)The preliminary study project on standardization of the Chinese Center for Disease Control and Prevention(No.BZ2025-Q155)The National Natural Science Foundation of China(No.82404299).
文摘INTRODUCTION Contemporary human living environments present complex and pervasive health risks,and environmental health challenges are becoming increasingly prominent.These risks encompass diverse domains,such as chemical factors(e.g.,heavy metals,nanomaterials,per-and polyfluoroalkyl substances),physical factors(e.g.,noise,radiation,and extreme weather)biological factors(e.g.,pathogenic microorganisms and parasites),natural disasters(e.g.,earthquakes and floods),and anthropogenic incidents(e.g.,chemical spills,fires,and explosions).
