Microseismic monitoring and signal recognition constitute critical technologies for accurately assessing rockburst risks and ensuring the safe construction of underground rock engineering.This study developed a"S...Microseismic monitoring and signal recognition constitute critical technologies for accurately assessing rockburst risks and ensuring the safe construction of underground rock engineering.This study developed a"Surface+Underground"microseismic intelligent monitoring system to evaluate dynamic disaster risks during construction at the Beishan High-level Radioactive Waste Geological Disposal Laboratory in China.The datasets of four typical one-dimensional time-domain microseismic signals,including rock fracture,blasting,TBM tunneling,and drilling,were constructed,and the BO-CNN-LSTM model is developed to identify and classify these signals..Based on the classification results,the typical time-frequency domain characteristics of the four types of signals are analyzed.The classification results of BO-CNN-LSTM,CNN,LSTM and CNN-LSTM models show that the recognition accuracy of the four models is 98.0%,85.7%,66.7%and 91.0%,respectively.Among all types,the four models demonstrate the highest effectiveness in identifying rock fracture and borehole signals.The findings further confirm that the BO-CNN-LSTM model efficiently recognizes and extracts microseismic signal features,demonstrating superior performance and stability in the classification task.Finally,the study suggests several future research directions,particularly in the areas of raw signal denoising,and automation of feature extraction.展开更多
With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion det...With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion detection models,this paper proposes a Dual-Attention model for NID,which combines Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM)to design two modules:the FocusConV and the TempoNet module.The FocusConV module,which automatically adjusts and weights CNN extracted local features,focuses on local features that are more important for intrusion detection.The TempoNet module focuses on global information,identifies more important features in time steps or sequences,and filters and weights the information globally to further improve the accuracy and robustness of NID.Meanwhile,in order to solve the class imbalance problem in the dataset,the EQL v2 method is used to compute the class weights of each class and to use them in the loss computation,which optimizes the performance of the model on the class imbalance problem.Extensive experiments were conducted on the NSL-KDD,UNSW-NB15,and CIC-DDos2019 datasets,achieving average accuracy rates of 99.66%,87.47%,and 99.39%,respectively,demonstrating excellent detection accuracy and robustness.The model also improves the detection performance of minority classes in the datasets.On the UNSW-NB15 dataset,the detection rates for Analysis,Exploits,and Shellcode attacks increased by 7%,7%,and 10%,respectively,demonstrating the Dual-Attention CNN-BiLSTM model’s excellent performance in NID.展开更多
Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and ...Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.展开更多
In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in...In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.展开更多
宝鸡市滑坡灾害频发,但当前该区域滑坡编录数据样本较少,同时若仅采用滑坡点样本训练模型会导致模型的空间代表性不足,从而制约对该区域滑坡易发性评价的精度。针对此,结合卷积神经网络模型(convolutional neural net‐work,CNN)的局部...宝鸡市滑坡灾害频发,但当前该区域滑坡编录数据样本较少,同时若仅采用滑坡点样本训练模型会导致模型的空间代表性不足,从而制约对该区域滑坡易发性评价的精度。针对此,结合卷积神经网络模型(convolutional neural net‐work,CNN)的局部特征提取优势和注意力机制Transformer的全局建模能力,提出一种融合Transformer与CNN的正样本缓冲滑坡易发性评价模型。依据滑坡规模设置90~130 m动态缓冲区扩展正样本,并综合考虑地形地貌、地质条件、水文气象和人类工程等选取13类滑坡影响因子,通过多重共线性分析后构建了滑坡评价体系。研究结果显示,采用缓冲区将随机森林、CNN、Transformer、Transformer-CNN模型四者的ROC曲线下的面积(area under the curve,AUC)从0.834、0.852、0.847、0.875分别提升至0.883、0.913、0.926、0.959。此外,Transformer-CNN相较CNN、Transformer,未缓冲时AUC分别从0.852、0.847提升至0.875,进行缓冲时分别从0.913、0.926提升至0.959;基于夏普利加性解释算法可解释性分析进一步揭示出岩性、年降雨、坡向三类因子对滑坡易发性预测贡献度最大,贡献度分别达0.55、0.47、0.43,且三者交互效应显著,为锁定区域滑坡高易发区提供了可量化的依据。展开更多
Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiv...Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiveness of sinter quality prediction,an intelligent flare monitoring system for sintering machine tails that combines hybrid neural networks integrating convolutional neural network with long short-term memory(CNN-LSTM)networks was proposed.The system utilized a high-temperature thermal imager for image acquisition at the sintering machine tail and employed a zone-triggered method to accurately capture dynamic feature images under challenging conditions of high-temperature,high dust,and occlusion.The feature images were then segmented through a triple-iteration multi-thresholding approach based on the maximum between-class variance method to minimize detail loss during the segmentation process.Leveraging the advantages of CNN and LSTM networks in capturing temporal and spatial information,a comprehensive model for sinter quality prediction was constructed,with inputs including the proportion of combustion layer,porosity rate,temperature distribution,and image features obtained from the convolutional neural network,and outputs comprising quality indicators such as underburning index,uniformity index,and FeO content of the sinter.The accuracy is notably increased,achieving a 95.8%hit rate within an error margin of±1.0.After the system is applied,the average qualified rate of FeO content increases from 87.24%to 89.99%,representing an improvement of 2.75%.The average monthly solid fuel consumption is reduced from 49.75 to 46.44 kg,leading to a 6.65%reduction and underscoring significant energy saving and cost reduction effects.展开更多
Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empir...Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.展开更多
基金Project supported by the China Atomic Energy Authority(CAEA)through the Geological Disposal ProgramProjects(U24A20616,U24B2038)supported by the National Natural Science Foundation of ChinaProject(2025-05)supported by the Guangdong Provincial Water Conservancy Science and Technology Innovation Project,China。
摘要Microseismic monitoring and signal recognition constitute critical technologies for accurately assessing rockburst risks and ensuring the safe construction of underground rock engineering.This study developed a"Surface+Underground"microseismic intelligent monitoring system to evaluate dynamic disaster risks during construction at the Beishan High-level Radioactive Waste Geological Disposal Laboratory in China.The datasets of four typical one-dimensional time-domain microseismic signals,including rock fracture,blasting,TBM tunneling,and drilling,were constructed,and the BO-CNN-LSTM model is developed to identify and classify these signals..Based on the classification results,the typical time-frequency domain characteristics of the four types of signals are analyzed.The classification results of BO-CNN-LSTM,CNN,LSTM and CNN-LSTM models show that the recognition accuracy of the four models is 98.0%,85.7%,66.7%and 91.0%,respectively.Among all types,the four models demonstrate the highest effectiveness in identifying rock fracture and borehole signals.The findings further confirm that the BO-CNN-LSTM model efficiently recognizes and extracts microseismic signal features,demonstrating superior performance and stability in the classification task.Finally,the study suggests several future research directions,particularly in the areas of raw signal denoising,and automation of feature extraction.
基金supported by the High-Level Talent Foundation of Jinling Institute of Technology(grant number.JIT-B-202413).
摘要With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion detection models,this paper proposes a Dual-Attention model for NID,which combines Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM)to design two modules:the FocusConV and the TempoNet module.The FocusConV module,which automatically adjusts and weights CNN extracted local features,focuses on local features that are more important for intrusion detection.The TempoNet module focuses on global information,identifies more important features in time steps or sequences,and filters and weights the information globally to further improve the accuracy and robustness of NID.Meanwhile,in order to solve the class imbalance problem in the dataset,the EQL v2 method is used to compute the class weights of each class and to use them in the loss computation,which optimizes the performance of the model on the class imbalance problem.Extensive experiments were conducted on the NSL-KDD,UNSW-NB15,and CIC-DDos2019 datasets,achieving average accuracy rates of 99.66%,87.47%,and 99.39%,respectively,demonstrating excellent detection accuracy and robustness.The model also improves the detection performance of minority classes in the datasets.On the UNSW-NB15 dataset,the detection rates for Analysis,Exploits,and Shellcode attacks increased by 7%,7%,and 10%,respectively,demonstrating the Dual-Attention CNN-BiLSTM model’s excellent performance in NID.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01296).
摘要Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.
摘要In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.
摘要针对不同磁密幅值、频率、谐波组合等复杂激励工况下磁致伸缩建模面临的精准性问题,该文利用空间注意力机制(spatial attention mechanism,SAM)对传统的卷积神经网络(convolutional neural network,CNN)进行改进,将SAM嵌套入CNN网络中,建立SAMCNN改进型网络。再结合双向长短期记忆(bidirectional long short-term memory,BiLSTM)网络,提出电工钢片SAMCNN-BiLSTM磁致伸缩模型。首先,利用灰狼优化算法(grey wolf optimization,GWO)寻优神经网络结构的参数,实现复杂工况下磁致伸缩效应的准确表征;然后,建立中低频范围单频与叠加谐波激励等复杂工况下的磁致伸缩应变数据库,开展数据预处理与特征分析;最后,对SAMCNN-BiLSTM模型开展对比验证。对比叠加3次谐波激励下的磁致伸缩应变频谱主要分量,SAMCNN-BiLSTM模型计算值最大相对误差为3.70%,其比Jiles-Atherton-Sablik(J-A-S)、二次畴转等模型能更精确地表征电工钢片的磁致伸缩效应。
摘要宝鸡市滑坡灾害频发,但当前该区域滑坡编录数据样本较少,同时若仅采用滑坡点样本训练模型会导致模型的空间代表性不足,从而制约对该区域滑坡易发性评价的精度。针对此,结合卷积神经网络模型(convolutional neural net‐work,CNN)的局部特征提取优势和注意力机制Transformer的全局建模能力,提出一种融合Transformer与CNN的正样本缓冲滑坡易发性评价模型。依据滑坡规模设置90~130 m动态缓冲区扩展正样本,并综合考虑地形地貌、地质条件、水文气象和人类工程等选取13类滑坡影响因子,通过多重共线性分析后构建了滑坡评价体系。研究结果显示,采用缓冲区将随机森林、CNN、Transformer、Transformer-CNN模型四者的ROC曲线下的面积(area under the curve,AUC)从0.834、0.852、0.847、0.875分别提升至0.883、0.913、0.926、0.959。此外,Transformer-CNN相较CNN、Transformer,未缓冲时AUC分别从0.852、0.847提升至0.875,进行缓冲时分别从0.913、0.926提升至0.959;基于夏普利加性解释算法可解释性分析进一步揭示出岩性、年降雨、坡向三类因子对滑坡易发性预测贡献度最大,贡献度分别达0.55、0.47、0.43,且三者交互效应显著,为锁定区域滑坡高易发区提供了可量化的依据。
基金founded by the Open Project Program of Anhui Province Key Laboratory of Metallurgical Engineering and Resources Recycling(Anhui University of Technology)(No.SKF21-06)Research Fund for Young Teachers of Anhui University of Technology in 2020(No.QZ202001).
摘要Real-time prediction and precise control of sinter quality are pivotal for energy saving,cost reduction,quality improvement and efficiency enhancement in the ironmaking process.To advance,the accuracy and comprehensiveness of sinter quality prediction,an intelligent flare monitoring system for sintering machine tails that combines hybrid neural networks integrating convolutional neural network with long short-term memory(CNN-LSTM)networks was proposed.The system utilized a high-temperature thermal imager for image acquisition at the sintering machine tail and employed a zone-triggered method to accurately capture dynamic feature images under challenging conditions of high-temperature,high dust,and occlusion.The feature images were then segmented through a triple-iteration multi-thresholding approach based on the maximum between-class variance method to minimize detail loss during the segmentation process.Leveraging the advantages of CNN and LSTM networks in capturing temporal and spatial information,a comprehensive model for sinter quality prediction was constructed,with inputs including the proportion of combustion layer,porosity rate,temperature distribution,and image features obtained from the convolutional neural network,and outputs comprising quality indicators such as underburning index,uniformity index,and FeO content of the sinter.The accuracy is notably increased,achieving a 95.8%hit rate within an error margin of±1.0.After the system is applied,the average qualified rate of FeO content increases from 87.24%to 89.99%,representing an improvement of 2.75%.The average monthly solid fuel consumption is reduced from 49.75 to 46.44 kg,leading to a 6.65%reduction and underscoring significant energy saving and cost reduction effects.
基金supported by the Ministry of Education(MOE)Singapore,Academic Research Fund(AcRF)Tier 1(RG65/22)。
摘要Convolutional neural networks(CNNs)have shown remarkable success across numerous tasks such as image classification,yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements.In this paper,the first filter learning framework with convergence-guaranteed learning laws for end-to-end learning of deep CNNs is proposed.Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks.The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors.Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods.This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.