期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到27篇文章
< 1 2 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Unknown Application Layer Protocol Recognition Method Based on Deep Clustering 认领 引用 被引量：1
1
作者 Wu Jisheng Hong Zheng +1 位作者 Ma Tiantian Si Jianpeng 《China Communications》 SCIE CSCD 2024年第12期275-296,共22页
In recent years,many unknown protocols are constantly emerging,and they bring severe challenges to network security and network management.Existing unknown protocol recognition methods suffer from weak feature extract... In recent years,many unknown protocols are constantly emerging,and they bring severe challenges to network security and network management.Existing unknown protocol recognition methods suffer from weak feature extraction ability,and they cannot mine the discriminating features of the protocol data thoroughly.To address the issue,we propose an unknown application layer protocol recognition method based on deep clustering.Deep clustering which consists of the deep neural network and the clustering algorithm can automatically extract the features of the input and cluster the data based on the extracted features.Compared with the traditional clustering methods,deep clustering boasts of higher clustering accuracy.The proposed method utilizes network-in-network(NIN),channel attention,spatial attention and Bidirectional Long Short-term memory(BLSTM)to construct an autoencoder to extract the spatial-temporal features of the protocol data,and utilizes the unsupervised clustering algorithm to recognize the unknown protocols based on the features.The method firstly extracts the application layer protocol data from the network traffic and transforms the data into one-dimensional matrix.Secondly,the autoencoder is pretrained,and the protocol data is compressed into low dimensional latent space by the autoencoder and the initial clustering is performed with K-Means.Finally,the clustering loss is calculated and the classification model is optimized according to the clustering loss.The classification results can be obtained when the classification model is optimal.Compared with the existing unknown protocol recognition methods,the proposed method utilizes deep clustering to cluster the unknown protocols,and it can mine the key features of the protocol data and recognize the unknown protocols accurately.Experimental results show that the proposed method can effectively recognize the unknown protocols,and its performance is better than other methods. 展开更多
关键词 attention mechanism clustering loss deep clustering network traffic unknown protocol recognition
暂未订购 下载PDF
Improved Dragonfly Optimizer for Intrusion Detection Using Deep Clustering CNN-PSO Classifier 认领 引用 被引量：3
2
作者 K.S.Bhuvaneshwari K.Venkatachalam +2 位作者 S.Hubalovsky P.Trojovsky P.Prabu 《Computers, Materials & Continua》 SCIE EI 2022年第3期5949-5965,共17页
With the rapid growth of internet based services and the data generated on these services are attracted by the attackers to intrude the networking services and information.Based on the characteristics of these intrude... With the rapid growth of internet based services and the data generated on these services are attracted by the attackers to intrude the networking services and information.Based on the characteristics of these intruders,many researchers attempted to aim to detect the intrusion with the help of automating process.Since,the large volume of data is generated and transferred through network,the security and performance are remained an issue.IDS(Intrusion Detection System)was developed to detect and prevent the intruders and secure the network systems.The performance and loss are still an issue because of the features space grows while detecting the intruders.In this paper,deep clustering based CNN have been used to detect the intruders with the help of Meta heuristic algorithms for feature selection and preprocessing.The proposed system includes three phases such as preprocessing,feature selection and classification.In the first phase,KDD dataset is preprocessed by using Binning normalization and Eigen-PCA based discretization method.In second phase,feature selection is performed by using Information Gain based Dragonfly Optimizer(IGDFO).Finally,Deep clustering based Convolutional Neural Network(CCNN)classifier optimized with Particle Swarm Optimization(PSO)identifies intrusion attacks efficiently.The clustering loss and network loss can be reduced with the optimization algorithm.We evaluate the proposed IDS model with the NSL-KDD dataset in terms of evaluation metrics.The experimental results show that proposed system achieves better performance compared with the existing system in terms of accuracy,precision,recall,f-measure and false detection rate. 展开更多
关键词 Intrusion detection system binning normalization deep clustering convolutional neural network information gain dragonfly optimizer
暂未订购 下载PDF
A multi-scale fracture prediction method based on improved deep embedded clustering 认领 引用
3
作者 Yu-jia Lu Chao Chen +2 位作者 Zhu-jiang Liu Fu-bin Wei Zhe-ge Liu 《Applied Geophysics》 SCIE CSCD 2026年第2期571-590,867,共20页
Accurately characterizing the distribution and scale characteristics of fractures in subsurface media is a crucial step for quantitatively evaluating shale gas sweet spots and guiding reservoir fracturing stimulation.... Accurately characterizing the distribution and scale characteristics of fractures in subsurface media is a crucial step for quantitatively evaluating shale gas sweet spots and guiding reservoir fracturing stimulation.However,a single seismic attribute is often used to identify fracture features of a specifi c scale,making it diffi cult to achieve detailed characterization of fractures across multiple scales simultaneously.Multi-attribute fusion algorithms often focus on statistical correlations,lacking in-depth exploration of the spatial topological relationships and intrinsic physical connections among fractures of diff erent scales,resulting in reduced accuracy in complex structural areas.To address this challenge,we propose a multi-scale integrated fracture prediction method based on an improved deep embedded clustering(DEC)framework,using the marine shale reservoir of the Wufeng–Longmaxi Formation in southeastern Sichuan Basin as a case study.Specifically,(1)an improved DEC objective function integrating fracture topology constraints and cluster-balancing mechanisms is developed to enhance the model’s adaptability to complex geological structures;(2)an“expand–then–contract”stacked autoencoder architecture is designed to better capture nonlinear relationships among multi-attribute data and decouple multi-scale fracture features;and(3)an integrated workfl ow from multi-attribute optimization,intelligent fusion clustering to geological interpretation is established,enabling diff erentiated and high-precision characterization of multi-scale fractures.Furthermore,based on the geological characteristics of the study area,we systematically analyze the spatial mapping relationships of the autoencoder’s multi-layer features and elucidate their implicit geophysical signifi cance.This analysis reveals the intrinsic processes through which the proposed model performs fracture attribute optimization,noise separation,and multi-scale feature extraction.Finally,by integrating intelligent fault identifi cation,micro-fracture amplitude variation with azimuth(AVAZ)inversion,and conventional geometric attributes,high-precision spatial characterization of the fracture system is achieved,spanning from large-scale faults to micro-fractures.The prediction results show strong agreement with geological understanding. 展开更多
关键词 Multi-scale fractures Deep embedded clustering Deep learning Autoencoding Marine shale
暂未订购 下载PDF
Deep Fuzzy C-Means Clustering in a Federated Heterogeneous Scenario 认领 引用
4
作者 Longmei Li Wei Lu Witold Pedrycz 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期633-646,共14页
In federated deep Fuzzy C-Means(FCM)clustering,conventional federated averaging(FedAvg)struggles with nonindependent and identically distributed(non-IID)data and dynamic device participation,leading to model drift and... In federated deep Fuzzy C-Means(FCM)clustering,conventional federated averaging(FedAvg)struggles with nonindependent and identically distributed(non-IID)data and dynamic device participation,leading to model drift and performance degradation during global aggregation.To address this challenge,we propose FedFCD,a federated deep FCM clustering method featuring a novel aggregation mechanism.FedFCD equips each client with a hybrid architecture comprising a contrastive autoencoder(CtAE)and an FCM network(FCMNet),which collaboratively learn stable low-dimensional embeddings and refine soft clustering assignments iteratively.At the server side,we design a two-phase aggregation strategy integrating Bayesian ensemble learning and knowledge distillation(KD).First,the Bayesian aggregation mechanism probabilistically fuses heterogeneous local models'inferences into a consensus assignment by treating each client's model as a candidate hypothesis,thereby constructing a posterior distribution over the global model space through iterative evidence accumulation.Subsequently,dual-source distillation harmonizes pseudo-labels derived from the Bayesian consensus with ground-truth labels from limited shared data,enabling the global model to align its predictions with both semantic anchors and aggregated soft assignments while preserving privacy through distillation loss.Comparative experiments on benchmark datasets demonstrate that Fed FCD outperforms baseline methods in clustering accuracy and exhibits enhanced stability under varying conditions,including data heterogeneity,device numbers,and device dropout. 展开更多
关键词 Bayesian inference data distillation deep embedding clustering federated learning fuzzy C-means(FCM) model aggregation
暂未订购 下载PDF
EDESC-IDS:An Efficient Deep Embedded Subspace Clustering-Based Intrusion Detection System for the Internet of Vehicles 认领 引用
5
作者 Lixing Tan Liusiyu Chen +2 位作者 Yang Wang Zhenyu Song Zenan Lu 《Computers, Materials & Continua》 SCIE EI 2026年第5期997-1020,共24页
Anomaly detection is a vibrant research direction in controller area networks,which provides the fundamental real-time data transmission underpinning in-vehicle data interaction for the internet of vehicles.However,ex... Anomaly detection is a vibrant research direction in controller area networks,which provides the fundamental real-time data transmission underpinning in-vehicle data interaction for the internet of vehicles.However,existing unsupervised learning methods suffer from insufficient temporal and spatial constraints on shallow features,resulting in fragmented feature representations that compromise model stability and accuracy.To improve the extraction of valuable features,this paper investigates the influence of clustering constraints on shallow feature convergence paths at the model level and further proposes an end-to-end intrusion detection system based on efficient deep embedded subspace clustering(EDESC-IDS).Following the standard learning approach,continuous messages are encoded into two-dimensional data frames via a frame builder,which are then input into an extended convolutional autoencoder for extracting shallow features from high-dimensional data.On this basis,the dual constraints of these output features and the embedding clustering module facilitate end-to-end training of the EDESC-IDS in various attack scenarios.Extensive experimental results show that such a system exhibits significant detection performance on four types of attack datasets,including DoS,Gear,Fuzzy,and RPM,with precision,recall,and F1 scores consistently above 97.79%,while maintaining a false negative rate(FNR)and an error rate(ER)below 2.22%. 展开更多
关键词 Internet of vehicles control area network anomaly detection unsupervised learning deep embedded subspace clustering extended convolutional autoencoder
暂未订购 下载PDF
Multi-Order Neighborhood Fusion Based Multi-View Deep Subspace Clustering 认领 引用 被引量：1
6
作者 Kai Zhou Yanan Bai +1 位作者 Yongli Hu Boyue Wang 《Computers, Materials & Continua》 SCIE EI 2025年第3期3873-3890,共18页
Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin s... Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between samples.To overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering model.We creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion module.By this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one cluster.In addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering methods.The code is available at http://gffzz188fe103f8f1460aspob9fb9p99o066xb.ffgz.tsg.suse.edu.cn/songzuolong/MNF-MDSC(accessed on 25 December 2024). 展开更多
关键词 Multi-view subspace clustering subspace clustering deep clustering multi-order graph structure
暂未订购 下载PDF
Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework 认领 引用
7
作者 Fengyun LÜ Yanmei ZHANG +1 位作者 Hongtao LIANG Luyang SUN 《Journal of Oceanology and Limnology》 SCIE CAS CSCD 2026年第2期728-742,共15页
The development of microfluidic-based Raman devices has enabled the acquisition of thousands of single-cell Raman spectra from complex microbial populations,offering new avenues for characterizing environmental bacter... The development of microfluidic-based Raman devices has enabled the acquisition of thousands of single-cell Raman spectra from complex microbial populations,offering new avenues for characterizing environmental bacteria.We proposed and validated the convolutional deep embedded clustering(CDEC)model,a clustering framework designed for the unsupervised classification of marine microbial Raman spectra.A four-stage analytical framework was employed to systematically assess the performance of the CDEC model,with increasing dataset complexity ranging from mock communities of pure bacterial cultures to natural microbial populations isolated from seawater.The CDEC algorithm consistently distinguished bacterial species across all stages,achieving an average accuracy of 97.27%,and surpassed the baseline methods in performance.In natural microbial communities,the model resolved eight distinct clusters with unique Raman spectral markers,revealing underlying metabolic heterogeneity.These results highlight the scalability and utility of the CDEC model for studying marine microbial diversity and characterizing microbial composition and metabolic traits at single-cell resolution. 展开更多
关键词 marine microbe Raman spectroscopy deep clustering convolutional network
暂未订购 下载PDF
Representation Then Augmentation:Wide Graph Clustering Network With Multi-Order Filter Fusion and Double-Level Contrastive Learning 认领 引用
8
作者 Youqing Wang Tianxiang Zhao +3 位作者 Mingliang Cui Junbin Gao Li Liang Jipeng Guo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期421-435,共15页
Deep graph contrastive clustering has attracted widespread attentions due to its self-supervised representation learning paradigm and superior clustering performance.Although,two challenges emerge and result in high c... Deep graph contrastive clustering has attracted widespread attentions due to its self-supervised representation learning paradigm and superior clustering performance.Although,two challenges emerge and result in high computational costs.Most existing contrastive methods adopt the data augmentation and then representation learning strategy,where representation learning with trainable graph convolution is coupled with complex and fixed data augmentation,inevitably limiting the efficiency and flexibility.The similarity metric between positive-negative sample pairs is complex and contrastive objective is partial,limiting the discriminability of representation learning.To solve these challenges,a novel wide graph clustering network(WGCN)adhering to representation and then augmentation framework is proposed,which mainly consists of multiorder filter fusion(MFF)and double-level contrastive learning(DCL)modules.Specifically,the MFF module integrates multiorder low-pass filters to extract smooth and multi-scale topological features,utilizing self-attention fusion to reduce redundancy and obtain comprehensive embedding representation.Further,the DCL module constructs two augmented views by the parallel parameter-unshared Siamese encoders rather than complex augmentations on graph.To achieve simple yet effective self-supervised learning,representation self-supervision and structural consistency oriented double-level contrastive loss is designed,where representation self-supervision maximizes the agreement between pairwise augmented embedding representations and structural consistency promotes the mutual information correlation between appending neighborhoods with similar semantics.Extensive experiments on six benchmark datasets demonstrate the superiority of the proposed WGCN,especially highlighting its time-saving characteristic.The code could be available in the http://gffzz188fe103f8f1460aspob9fb9p99o066xb.ffgz.tsg.suse.edu.cn/Tianxiang Zhao0474/WGCN. 展开更多
关键词 Deep graph clustering(DGC) double-level contrastive learning(DCL) multi-order low-pass filter self-supervised representation learning structural consistency
暂未订购 下载PDF
Identification of High-Risk Scenarios for Cascading Failures in New Energy Power Grids Based on Deep Embedding Clustering Algorithms 认领 引用 被引量：1
9
作者 Xueting Cheng Ziqi Zhang +1 位作者 Yueshuang Bao Huiping Zheng 《Energy Engineering》 EI 2023年第11期2517-2529,共13页
At present,the proportion of new energy in the power grid is increasing,and the random fluctuations in power output increase the risk of cascading failures in the power grid.In this paper,we propose a method for ident... At present,the proportion of new energy in the power grid is increasing,and the random fluctuations in power output increase the risk of cascading failures in the power grid.In this paper,we propose a method for identifying high-risk scenarios of interlocking faults in new energy power grids based on a deep embedding clustering(DEC)algorithm and apply it in a risk assessment of cascading failures in different operating scenarios for new energy power grids.First,considering the real-time operation status and system structure of new energy power grids,the scenario cascading failure risk indicator is established.Based on this indicator,the risk of cascading failure is calculated for the scenario set,the scenarios are clustered based on the DEC algorithm,and the scenarios with the highest indicators are selected as the significant risk scenario set.The results of simulations with an example power grid show that our method can effectively identify scenarios with a high risk of cascading failures from a large number of scenarios. 展开更多
关键词 New energy power system deep embedding clustering algorithms cascading failures
暂未订购 下载PDF
Automatic clustering of single-molecule break junction data through task-oriented representation learning 认领 引用
10
作者 Yi-Heng Zhao Shen-Wen Pang +4 位作者 Heng-Zhi Huang Shao-Wen Wu Shao-Hua Sun Zhen-Bing Liu Zhi-Chao Pan 《Rare Metals》 SCIE EI CAS CSCD 2025年第5期3244-3257,共14页
Clustering is a pivotal data analysis method for deciphering the charge transport properties of single molecules in break junction experiments.However,given the high dimensionality and variability of the data,feature ... Clustering is a pivotal data analysis method for deciphering the charge transport properties of single molecules in break junction experiments.However,given the high dimensionality and variability of the data,feature extraction remains a bottleneck in the development of efficient clustering methods.In this regard,extensive research over the past two decades has focused on feature engineering and dimensionality reduction in break junction conductance.However,extracting highly relevant features without expert knowledge remains an unresolved challenge.To address this issue,we propose a deep clustering method driven by task-oriented representation learning(CTRL)in which the clustering module serves as a guide for the representation learning(RepL)module.First,we determine an optimal autoencoder(AE)structure through a neural architecture search(NAS)to ensure efficient RepL;second,the RepL process is guided by a joint training strategy that combines AE reconstruction loss with the clustering objective.The results demonstrate that CTRL achieves excellent performance on both the generated and experimental data.Further inspection of the RepL step reveals that joint training robustly learns more compact features than the unconstrained AE or traditional dimensionality reduction methods,significantly reducing misclustering possibilities.Our method provides a general end-to-end automatic clustering solution for analyzing single-molecule break junction data. 展开更多
关键词 Single-molecule conductance Break junction Deep clustering Representation learning Neural architecture search
暂未订购 下载PDF
Unsupervised side-channel power analysis based on invariant information clustering 认领 引用
11
作者 Ning Yang Long-De Yan +4 位作者 Bi-Yang Liu Xiang Li Ai-Dong Chen Lu Zeng Wei-Feng Liu 《Journal of Electronic Science and Technology》 EI CAS CSCD 2025年第4期1-13,共13页
Side-channel analysis(SCA)has emerged as a research hotspot in the field of cryptanalysis.Among various approaches,unsupervised deep learning-based methods demonstrate powerful information extraction capabilities with... Side-channel analysis(SCA)has emerged as a research hotspot in the field of cryptanalysis.Among various approaches,unsupervised deep learning-based methods demonstrate powerful information extraction capabilities without requiring labeled data.However,existing unsupervised methods,particularly those represented by differential deep learning analysis(DDLA)and its improved variants,while overcoming the dependency on labeled data inherent in template analysis,still suffer from high time complexity and training costs when handling key byte difference comparisons.To address this issue,this paper introduces invariant information clustering(IIC)into SCA for the first time,and thus proposes a novel unsupervised learning-based SCA method,named IIC-SCA.By leveraging mutual information maximization techniques for automatic feature extraction of power leakage data,our approach achieves key recovery through a single training session,eliminating the prohibitive computational overhead of traditional methods that require separate training for all possible key bytes.Experimental results on the ASCAD dataset demonstrate successful key extraction using only 50000 training traces and 2000 attack traces.Furthermore,compared with DDLA,the proposed method reduces training time by approximately 93.40%and memory consumption by about 6.15%,significantly decreasing the temporal and resource costs of unsupervised SCA.This breakthrough provides new insights for developing low-cost,high-efficiency cryptographic attack methodologies. 展开更多
关键词 Deep clustering Mutual information maximization Non-profiled analysis Side-channel analysis Unsupervised learning
暂未订购 下载PDF
Neighbor Dual-Consistency Constrained Attribute-Graph Clustering 认领 引用
12
作者 Tian Tian Boyue Wang +2 位作者 Xiaxia He Wentong Wang Meng Wang 《Computers, Materials & Continua》 SCIE EI 2025年第12期4885-4898,共14页
Attribute-graph clustering aims to divide the graph nodes into distinct clusters in an unsupervised manner,which usually encodes the node attribute feature and the corresponding graph structure into a latent feature s... Attribute-graph clustering aims to divide the graph nodes into distinct clusters in an unsupervised manner,which usually encodes the node attribute feature and the corresponding graph structure into a latent feature space.However,traditional attribute-graph clustering methods often neglect the effect of neighbor information on clustering,leading to suboptimal clustering results as they fail to fully leverage the rich contextual information provided by neighboring nodes,which is crucial for capturing the intrinsic relationships between nodes and improving clustering performance.In this paper,we propose a novel Neighbor Dual-Consistency Constrained Attribute-Graph Clustering that leverages information from neighboring nodes in two significant aspects:neighbor feature consistency and neighbor distribution consistency.To enhance feature consistency among nodes and their neighbors,we introduce a neighbor contrastive loss that encourages the embeddings of nodes to be closer to those of their similar neighbors in the feature space while pushing them further apart from dissimilar neighbors.This method helps the model better capture local feature information.Furthermore,to ensure consistent cluster assignments between nodes and their neighbors,we introduce a neighbor distribution consistency module,which combines structural information from the graph with similarity of attributes to align cluster assignments between nodes and their neighbors.By integrating both local structural information and global attribute information,our approach effectively captures comprehensive patterns within the graph.Overall,our method demonstrates superior performance in capturing comprehensive patterns within the graph and achieves state-of-the-art clustering results on multiple datasets. 展开更多
关键词 Graph convolution clustering deep clustering contrastive learning
暂未订购 下载PDF
Contrastive Consistency and Attentive Complementarity for Deep Multi-View Subspace Clustering 认领 引用
13
作者 Jiao Wang Bin Wu Hongying Zhang 《Computers, Materials & Continua》 SCIE EI 2024年第4期143-160,共18页
Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewpriv... Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness. 展开更多
关键词 Deep multi-view subspace clustering contrastive learning adaptive fusion self-expression learning
暂未订购 下载PDF
A Convolutional Deep Neural Network Approach for miRNA Clustering 认领 引用
14
作者 Ghada Ali Mohamed Shommo Hadia Abbas Mohammed Elsied +3 位作者 Amira Kamil Ibrahim Hassan Sara Elsir Mohamed Ahmed Lamia Hassan Rahmatalla Mohamed Wafa Faisal Mukhtar 《Communications and Network》 2024年第4期135-148,共14页
The regulatory role of the Micro-RNAs (miRNAs) in the messenger RNAs (mRNAs) gene expression is well understood by the biologists since some decades, even though the delving into specific aspects is in progress. Clust... The regulatory role of the Micro-RNAs (miRNAs) in the messenger RNAs (mRNAs) gene expression is well understood by the biologists since some decades, even though the delving into specific aspects is in progress. Clustering is a cornerstone in bioinformatics research, offering a potent computational tool for analyzing diverse types of data encountered in genomics and related fields. MiRNA clustering plays a pivotal role in deciphering the intricate regulatory roles of miRNAs in biological systems. It uncovers novel biomarkers for disease diagnosis and prognosis and advances our understanding of gene regulatory networks and pathways implicated in health and disease, as well as drug discovery. Namely, we have implemented clustering procedure to find interrelations among miRNAs within clusters, and their relations to diseases. Deep clustering (DC) algorithms signify a departure from traditional clustering methods towards more sophisticated techniques, that can uncover intricate patterns and relationships within gene expression data. Deep learning (DL) models have shown remarkable success in various domains, and their application in genomics, especially for tasks like clustering, holding immense promise. The deep convolutional clustering procedure used is different from other traditional methods, demonstrating unbiased clustering results. In the paper, we implement the procedure on a Multiple Myeloma miRNA dataset publicly available on GEO platform, as a template of a cancer instance analysis, and hazard some biological issues. 展开更多
关键词 miRNA Deep Clustering DeepTrust Convolutional Neural Network Recurrence Plot
暂未订购 下载PDF
Multiscale and Auto-Tuned Semi-Supervised Deep Subspace Clustering and Its Application in Brain Tumor Clustering 认领 引用
15
作者 Zhenyu Qian Yizhang Jiang +4 位作者 Zhou Hong Lijun Huang Fengda Li Khin Wee Lai Kaijian Xia 《Computers, Materials & Continua》 SCIE EI 2024年第6期4741-4762,共22页
In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world da... In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world data,particularly in the field of medical imaging.Traditional deep subspace clustering algorithms,which are mostly unsupervised,are limited in their ability to effectively utilize the inherent prior knowledge in medical images.Our MAS-DSC algorithm incorporates a semi-supervised learning framework that uses a small amount of labeled data to guide the clustering process,thereby enhancing the discriminative power of the feature representations.Additionally,the multi-scale feature extraction mechanism is designed to adapt to the complexity of medical imaging data,resulting in more accurate clustering performance.To address the difficulty of hyperparameter selection in deep subspace clustering,this paper employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters related to subspace clustering,prior knowledge constraints,and model loss weights.Extensive experiments on standard clustering datasets,including ORL,Coil20,and Coil100,validate the effectiveness of the MAS-DSC algorithm.The results show that with its multi-scale network structure and Bayesian hyperparameter optimization,MAS-DSC achieves excellent clustering results on these datasets.Furthermore,tests on a brain tumor dataset demonstrate the robustness of the algorithm and its ability to leverage prior knowledge for efficient feature extraction and enhanced clustering performance within a semi-supervised learning framework. 展开更多
关键词 Deep subspace clustering multiscale network structure automatic hyperparameter tuning semi-supervised medical image clustering
暂未订购 下载PDF
Deep Learning-Based Algorithm for Multi-Type Defects Detection in Solar Cells with Aerial EL Images for Photovoltaic Plants 认领 引用 被引量：2
16
作者 Wuqin Tang Qiang Yang Wenjun Yan 《Computer Modeling in Engineering & Sciences》 SCIE EI 2022年第3期1423-1439,共17页
Defects detection with Electroluminescence(EL)image for photovoltaic(PV)module has become a standard test procedure during the process of production,installation,and operation of solar modules.There are some typical d... Defects detection with Electroluminescence(EL)image for photovoltaic(PV)module has become a standard test procedure during the process of production,installation,and operation of solar modules.There are some typical defects types,such as crack,finger interruption,that can be recognized with high accuracy.However,due to the complexity of EL images and the limitation of the dataset,it is hard to label all types of defects during the inspection process.The unknown or unlabeled create significant difficulties in the practical application of the automatic defects detection technique.To address the problem,we proposed an evolutionary algorithm combined with traditional image processing technology,deep learning,transfer learning,and deep clustering,which can recognize the unknown or unlabeled in the original dataset defects automatically along with the increasing of the dataset size.Specifically,we first propose a deep learning-based features extractor and defects classifier.Then,the unlabeled defects can be classified by the deep clustering algorithm and stored separately to update the original database without human intervention.When the number of unknown images reaches the preset values,transfer learning is introduced to train the classifier with the updated database.The fine-tuned model can detect new defects with high accuracy.Finally,numerical results confirm that the proposed solution can carry out efficient and accurate defect detection automatically using electroluminescence images. 展开更多
关键词 Electroluminescence images deep clustering automatic defect classification transfer learning
暂未订购 下载PDF
Federated Deep Subspace Clustering 认领 引用
17
作者 Yu-Pei Zhang Rou-Jia Feng +2 位作者 Yi-Fei Wang Shu-Hui Liu Xue-Qun Shang 《Journal of Computer Science & Technology》 SCIE EI CSCD 2026年第2期609-620,共12页
This paper presents Federated Deep Subspace Clustering(FDSC),a privacy-preserving deep subspace clustering model built upon a federated learning framework.In FDSC,each client employs a dedicated deep subspace clusteri... This paper presents Federated Deep Subspace Clustering(FDSC),a privacy-preserving deep subspace clustering model built upon a federated learning framework.In FDSC,each client employs a dedicated deep subspace clustering network to process its locally isolated data.This network consists of an encoder,a self-expressive layer,and a decoder.To enable collaboration across clients,the encoder network is shared with a central server,allowing communication and model aggregation.Furthermore,FDSC enhances local clustering performance by preserving the neighborhood relationships among data samples within each client.By integrating federated learning with locality preservation,the encoder learns more expressive features,which in turn improve the self-expressiveness and clustering accuracy.Extensive experiments on public datasets show that FDSC outperforms existing methods,benefiting from both federated learning and locality preservation. 展开更多
关键词 federated learning deep subspace clustering private protection deep learning image clustering
暂未订购 下载PDF
Model adaptation via credible local context representation 认领 引用
18
作者 Song Tang Wenxin Su +2 位作者 Yan Yang Lijuan Chen Mao Ye 《CAAI Transactions on Intelligence Technology》 SCIE EI CSCD 2025年第3期638-651,共14页
Conventional model transfer techniques,requiring the labelled source data,are not applicable in the privacy-protected medical fields.For the challenging scenarios,recent source data-free domain adaptation(SFDA)has bec... Conventional model transfer techniques,requiring the labelled source data,are not applicable in the privacy-protected medical fields.For the challenging scenarios,recent source data-free domain adaptation(SFDA)has become a mainstream solution but losing focus on the inter-sample class information.This paper proposes a new Credible Local Context Representation approach for SFDA.Our main idea is to exploit the credible local context for more discriminative representation.Specifically,we enhance the source model's discrimination by information regulating.To capture the context,a discovery method is developed that performs fixed steps walking in deep space and takes the credible features in this path as the context.In the epoch-wise adaptation,deep clustering-like training is conducted with two major updates.First,the context for all target data is constructed and then the context-fused pseudo-labels providing semantic guidance are generated.Second,for each target data,a weighting fusion on its context forms the anchored neighbourhood structure;thus,the deep clustering is switched from individual-based to coarse-grained.Also,a new regularisation building is developed on the anchored neighbourhood to drive the deep coarse-grained learning.Experiments on three benchmarks indicate that the proposed method can achieve stateof-the-art results. 展开更多
关键词 credible local context deep clustering domain adaptation machine learning model transfer self-supervised learning
暂未订购 下载PDF
An unsupervised incremental learning model to predict geological conditions for earth pressure balance shield tunneling 认领 引用
19
作者 Jiajie Zhen Fengwen Lai +3 位作者 Jim S.Shiau Ming Huang Yao Lu Jinhua Lin 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2025年第11期6993-7006,共14页
Current machine learning models for predicting geological conditions during earth pressure balance(EPB)shield tunneling predominantly rely on accurate geological conditions as model label inputs.This study introduces ... Current machine learning models for predicting geological conditions during earth pressure balance(EPB)shield tunneling predominantly rely on accurate geological conditions as model label inputs.This study introduces an innovative approach for the real-time prediction of geological conditions in EPB shield tunneling by utilizing an unsupervised incremental learning model that integrates deep temporal clustering(DTC)with elastic weight consolidation(EWC).The model was trained and tested using data from an EPB shield tunneling project in Nanjing,China.Results demonstrate that the DTC model outperforms nine comparison models by clustering the entire dataset into four distinct groups representing various geological conditions without requiring labeled data.Additionally,integrating EWC into the DTC model significantly enhances its continuous learning capabilities,enabling automatic parameter updates with incoming data and facilitating the real-time recognition of geological conditions.Feature importance was evaluated using the feature elimination method and the Shapley additive explanations(SHAP)method,underscoring the critical roles of earth chamber pressure and cutterhead rotation speed in predicting geological conditions.The proposed EWC-DTC model demonstrates practical utility for EPB shield tunneling in complex environments. 展开更多
关键词 Deep temporal clustering Geological condition perception Incremental learning Shield tunnel
暂未订购 下载PDF
Intraslab seismicity characteristics of northern Chile 认领 引用
20
作者 Zixin Chen Lei Gao +3 位作者 Haijiang Zhang Shaobo Yang Ying Liu Diana Comte 《Earthquake Science》 CAS CSCD 2025年第4期273-287,共15页
The Chilean subduction zone is one of the most seismically active regions globally,characterized by extensive intermediatedepth seismicity in the slab.In this study,we construct a new earthquake catalog for northern C... The Chilean subduction zone is one of the most seismically active regions globally,characterized by extensive intermediatedepth seismicity in the slab.In this study,we construct a new earthquake catalog for northern Chile using seismic waveforms assembled for the period of 2014-2019,from which 320,070 P-wave and 232,907 S-wave first arrivals are obtained for 25,763 earthquakes.Grid search location method NonLinLoc is applied to determine initial earthquake locations and double-difference location method is used to improve relative event locations.The distribution of earthquakes exhibits distinct patterns to the north and south of 21°S.There are many more earthquakes deeper than~150 km to the south of 21°S,while relatively fewer to the north.The intraslab earthquakes shallower than~80 km generally reveal a distinct double seismic zone,and the gap between the two seismic planes disappears at a depth of approximately~80 km,followed by a concentration of seismicity in the depth range of~80-150 km.In the deeper slab,there exist several seismicity clusters with distinct earthquake activities down to~300 km.These characteristics shown in slab seismicity are likely caused by different mechanisms and can be helpful for understanding the subduction process. 展开更多
关键词 seismic location Chile subduction zone double seismic zone deep seismicity cluster
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈