The goal of this study was to determine the spatiotemporal characteristics of mangrove distribution and fragmentation patterns from 1988 through 2019 in Dongzhaigang.Land cover datasets were generated for Dongzhaigang...The goal of this study was to determine the spatiotemporal characteristics of mangrove distribution and fragmentation patterns from 1988 through 2019 in Dongzhaigang.Land cover datasets were generated for Dongzhaigang for multiple years via a decision tree method based on a classification and regression tree(CART)algorithm using Landsat time series images.Spatiotemporal transform and fragmentation patterns of mangrove distribution were separately assessed with a transfer matrix of land cover types and a landscape pattern index.The classification method combined with multi-band images showed good accuracy,with overall accuracy higher than 90%.Mangrove areas in 1988,1999,2009,and 2019 were 2050,1875,1818,and 1750 ha,respectively,with decreases mainly due to conversion to aquaculture ponds and farmland.A mangrove growth index(MGI)was proposed,reflecting the water-mangrove relationship,showing positive mangrove growth from 1988–2009 and negative growth from 2009–2019.Study results indicated anthropogenic factors play a leading role in the extent and scale of mangrove effects over the past 30 years.According to the analysis results,corresponding management and protection measures are proposed to provide reference for the sustainable development of Dongzhaigang Mangrove Wetland ecosystem.展开更多
Transit managers can use Intelligent Transportation System technologies to access large amounts of data to monitor network status.However,the presentation of the data lacks structural information.Existing single-netwo...Transit managers can use Intelligent Transportation System technologies to access large amounts of data to monitor network status.However,the presentation of the data lacks structural information.Existing single-network description technologies are ineffective in representing the temporal and spatial characteristics simultaneously.Therefore,there is a need for complementary methods to address these deficiencies.To address these limitations,this paper proposes an approach that combines Network Snapshots and Temporal Paths for the scheduled system.A dual information network is constructed to assess the degree of operational deviation considering the planning tasks.To validate the effectiveness,discussions are conducted through a modified cosine similarity calculation on theoretical analysis,delay level description,and the ability to identify abnormal dates.Compared to some state-of-the-art methods,the proposed method achieves an average Spearman delay correlation of 0.847 and a relative distance of 3.477.Furthermore,case analyses are invested in regions of China's Mainland,Europe,and the United States,investigating both the overall and sub-regional network fluctuations.To represent the impact of network fluctuations in sub-regions,a response loss value was developed.The times that are prone to fluctuations are also discussed through the classification of time series data.The research can offer a novel approach to system monitoring,providing a research direction that utilizes individual data combined to represent macroscopic states.Our code will be released at https://github.com/daozhong/STPN.git.展开更多
As large-scale astronomical surveys,such as the Sloan Digital Sky Survey(SDSS)and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST),generate increasingly complex datasets,clustering algorithms have...As large-scale astronomical surveys,such as the Sloan Digital Sky Survey(SDSS)and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST),generate increasingly complex datasets,clustering algorithms have become vital for identifying patterns and classifying celestial objects.This paper systematically investigates the application of five main categories of clustering techniques-partition-based,density-based,model-based,hierarchical,and“others”-across a range of astronomical research over the past decade.This review focuses on the six key application areas of stellar classification,galaxy structure analysis,detection of galactic and interstellar features,highenergy astrophysics,exoplanet studies,and anomaly detection.This paper provides an in-depth analysis of the performance and results of each method,considering their respective suitabilities for different data types.Additionally,it presents clustering algorithm selection strategies based on the characteristics of the spectroscopic data being analyzed.We highlight challenges such as handling large datasets,the need for more efficient computational tools,and the lack of labeled data.We also underscore the potential of unsupervised and semi-supervised clustering approaches to overcome these challenges,offering insight into their practical applications,performance,and results in astronomical research.展开更多
Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique bas...Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique based on low rank tensor approximation is proposed for multichannel monitoring signal processing and utilization.Firstly,the affinity relationship of multichannel signals can be acquired based on the clustering results of each channel signal.Wherein an affinity tensor is constructed to integrate the diverse and consistent information of the clustering information among multichannel signals.Secondly,a low-rank tensor optimization model is built and the joint affinity matrix is optimized with the assistance of the strong confidence affinity matrix.Through solving the optimization model,the fused affinity relationship graph of multichannel signals can be obtained.Finally,the multichannel fused clustering results can be acquired though the updated joint affinity relationship graph.The multichannel signal utilization examples in health state assessment with public datasets and microwave detection with actual echoes verify the advantages and effectiveness of the proposed method.展开更多
With the popularization of smart devices,Location-Based Services(LBS)greatly facilitates users’life,but at the same time brings the risk of users’location privacy leakage.Existing location privacy protection methods...With the popularization of smart devices,Location-Based Services(LBS)greatly facilitates users’life,but at the same time brings the risk of users’location privacy leakage.Existing location privacy protection methods are deficient,failing to reasonably allocate the privacy budget for non-outlier location points and ignoring the critical location information that may be contained in the outlier points,leading to decreased data availability and privacy exposure problems.To address these problems,this paper proposes a Mix Location Privacy Preservation Method Based on Differential Privacy with Clustering(MLDP).The method first utilizes the DBSCAN clustering algorithm to classify location points into non-outliers and outliers.For non-outliers,the scoring function is designed by combining geographic information and semantic information,and the privacy budget is allocated according to the heat intensity of the hotspot area;for outliers,the scoring function is constructed to allocate the privacy budget based on their correlation with the hotspot area.By comprehensively considering the geographic information,semantic information,and correlation with hotspot areas of the location points,a reasonable privacy budget is assigned to each location point,andfinallynoise is added throughthe Laplacemechanismto realizeprivacyprotection.Experimental results on tworeal trajectory datasets,Geolife and T-Drive,show that the MLDP approach significantly improves data availability while effectively protecting location privacy.Compared with the comparison methods,the maximum available data ratio of MLDP is 1.Moreover,compared with the RandomNoise method,its execution time is 0.056–0.061 s longer,and the logRE is 0.12951–0.62194 lower;compared with KemeansDP,QTK-DP,DPK-F,IDP-SC,and DPK-Means-up methods,it saves 0.114–0.296 s in execution time,and the logRE is 0.01112–0.38283 lower.展开更多
With the rapid development of the aviation industry,air travel has become one of the most important modes.Improving the service quality of civil aviation airports is crucial to their competitiveness.This study intends...With the rapid development of the aviation industry,air travel has become one of the most important modes.Improving the service quality of civil aviation airports is crucial to their competitiveness.This study intends to develop a scientific and rational evaluation methodology and framework for assessing service quality in civil aviation airports,thereby providing a theoretical foundation and practical guidance for enhancing service standards in the aviation industry.First,the study constructs a CRITIC-bidirectional grey possibility clustering model,which uses the CRITIC method to determine the weights of indicators and integrates the forward grey possibility clustering model and the inverse grey possibility clustering model to determine possibility functions from two perspectives.Second,a service quality evaluation index system for civil airports is constructed from four dimensions,and the weights of each index within the system are subsequently calculated.Finally,the constructed model is applied to evaluate the service quality of nine domestic civil airports.Based on the clustering results,targeted countermeasures and suggestions are proposed.Empirical results demonstrate that,compared to the traditional grey possibility clustering model,the proposed model balances the objectivity of indicator weighting,the objectivity of possibility function construction,and the simplicity of the computational process,thereby possessing significant theoretical and practical implications.展开更多
This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the compl...This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the complexities,simulation time cost and convergence problems of detailed PV power station models.First,the amplitude–frequency curves of different filter parameters are analyzed.Based on the results,a grouping parameter set for characterizing the external filter characteristics is established.These parameters are further defined as clustering parameters.A single PV inverter model is then established as a prerequisite foundation.The proposed equivalent method combines the global search capability of PSO with the rapid convergence of KMC,effectively overcoming the tendency of KMC to become trapped in local optima.This approach enhances both clustering accuracy and numerical stability when determining equivalence for PV inverter units.Using the proposed clustering method,both a detailed PV power station model and an equivalent model are developed and compared.Simulation and hardwarein-loop(HIL)results based on the equivalent model verify that the equivalent method accurately represents the dynamic characteristics of PVpower stations and adapts well to different operating conditions.The proposed equivalent modeling method provides an effective analysis tool for future renewable energy integration research.展开更多
Satellite image segmentation plays a crucial role in remote sensing,supporting applications such as environmental monitoring,land use analysis,and disaster management.However,traditional segmentation methods often rel...Satellite image segmentation plays a crucial role in remote sensing,supporting applications such as environmental monitoring,land use analysis,and disaster management.However,traditional segmentation methods often rely on large amounts of labeled data,which are costly and time-consuming to obtain,especially in largescale or dynamic environments.To address this challenge,we propose the Semi-Supervised Multi-View Picture Fuzzy Clustering(SS-MPFC)algorithm,which improves segmentation accuracy and robustness,particularly in complex and uncertain remote sensing scenarios.SS-MPFC unifies three paradigms:semi-supervised learning,multi-view clustering,and picture fuzzy set theory.This integration allows the model to effectively utilize a small number of labeled samples,fuse complementary information from multiple data views,and handle the ambiguity and uncertainty inherent in satellite imagery.We design a novel objective function that jointly incorporates picture fuzzy membership functions across multiple views of the data,and embeds pairwise semi-supervised constraints(must-link and cannot-link)directly into the clustering process to enhance segmentation accuracy.Experiments conducted on several benchmark satellite datasets demonstrate that SS-MPFC significantly outperforms existing state-of-the-art methods in segmentation accuracy,noise robustness,and semantic interpretability.On the Augsburg dataset,SS-MPFC achieves a Purity of 0.8158 and an Accuracy of 0.6860,highlighting its outstanding robustness and efficiency.These results demonstrate that SSMPFC offers a scalable and effective solution for real-world satellite-based monitoring systems,particularly in scenarios where rapid annotation is infeasible,such as wildfire tracking,agricultural monitoring,and dynamic urban mapping.展开更多
This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid ag...This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid aggregation and often discard fine-grained boundary information.In contrast,our method computes soft membershipswithin each receptive field and aggregates cluster-wise responses throughmembership-weighted pooling,thereby preserving informative structure while reducing dimensionality.Being differentiable,the proposed layer operates as standard two-dimensional pooling.We evaluate our approach across various CNN backbones and open datasets,including CIFAR-10/100,STL-10,LFW,and ImageNette,and further probe small training set restrictions on MNIST and Fashion-MNIST.In these settings,the proposed pooling consistently improves accuracy and weighted F1 over conventional baselines,with particularly strong gains when training data are scarce.Even with less than 1%of the training set,ourmethodmaintains reliable performance,indicating improved sample efficiency and robustness to noisy or ambiguous local patterns.Overall,integrating soft memberships into the pooling operator provides a practical and generalizable inductive bias that enhances robustness and generalization in modern CNN pipelines.展开更多
The Intrusion Detection System(IDS)is a security mechanism developed to observe network traffic and recognize suspicious or malicious activities.Clustering algorithms are often incorporated into IDS;however,convention...The Intrusion Detection System(IDS)is a security mechanism developed to observe network traffic and recognize suspicious or malicious activities.Clustering algorithms are often incorporated into IDS;however,conventional clustering-based methods face notable drawbacks,including poor scalability in handling high-dimensional datasets and a strong dependence of outcomes on initial conditions.To overcome the performance limitations of existing methods,this study proposes a novel quantum-inspired clustering algorithm that relies on a similarity coefficient-based quantum genetic algorithm(SC-QGA)and an improved quantum artificial bee colony algorithm hybrid K-means(IQABC-K).First,the SC-QGA algorithmis constructed based on quantum computing and integrates similarity coefficient theory to strengthen genetic diversity and feature extraction capabilities.For the subsequent clustering phase,the process based on the IQABC-K algorithm is enhanced with the core improvement of adaptive rotation gate and movement exploitation strategies to balance the exploration capabilities of global search and the exploitation capabilities of local search.Simultaneously,the acceleration of convergence toward the global optimum and a reduction in computational complexity are facilitated by means of the global optimum bootstrap strategy and a linear population reduction strategy.Through experimental evaluation with multiple algorithms and diverse performance metrics,the proposed algorithm confirms reliable accuracy on three datasets:KDD CUP99,NSL_KDD,and UNSW_NB15,achieving accuracy of 98.57%,98.81%,and 98.32%,respectively.These results affirm its potential as an effective solution for practical clustering applications.展开更多
Deformation prediction for extra-high arch dams is highly important for ensuring their safe operation.To address the challenges of complex monitoring data,the uneven spatial distribution of deformation,and the constru...Deformation prediction for extra-high arch dams is highly important for ensuring their safe operation.To address the challenges of complex monitoring data,the uneven spatial distribution of deformation,and the construction and optimization of a prediction model for deformation prediction,a multipoint ultrahigh arch dam deformation prediction model,namely,the CEEMDAN-KPCA-GSWOA-KELM,which is based on a clustering partition,is pro-posed.First,the monitoring data are preprocessed via variational mode decomposition(VMD)and wavelet denoising(WT),which effectively filters out noise and improves the signal-to-noise ratio of the data,providing high-quality input data for subsequent prediction models.Second,scientific cluster partitioning is performed via the K-means++algorithm to precisely capture the spatial distribution characteristics of extra-high arch dams and ensure the consistency of deformation trends at measurement points within each partition.Finally,CEEMDAN is used to separate monitoring data,predict and analyze each component,combine the KPCA(Kernel Principal Component Analysis)and the KELM(Kernel Extreme Learning Machine)optimized by the GSWOA(Global Search Whale Optimization Algorithm),integrate the predictions of each component via reconstruction methods,and precisely predict the overall trend of ultrahigh arch dam deformation.An extra high arch dam project is taken as an example and validated via a comparative analysis of multiple models.The results show that the multipoint deformation prediction model in this paper can combine data from different measurement points,achieve a comprehensive,precise prediction of the deformation situation of extra high arch dams,and provide strong technical support for safe operation.展开更多
AIM:To evaluate long-term visual field(VF)prediction using K-means clustering in patients with primary open angle glaucoma(POAG).METHODS:Patients who underwent 24-2 VF tests≥10 were included in this study.Using 52 to...AIM:To evaluate long-term visual field(VF)prediction using K-means clustering in patients with primary open angle glaucoma(POAG).METHODS:Patients who underwent 24-2 VF tests≥10 were included in this study.Using 52 total deviation values(TDVs)from the first 10 VF tests of the training dataset,VF points were clustered into several regions using the hierarchical ordered partitioning and collapsing hybrid(HOPACH)and K-means clustering.Based on the clustering results,a linear regression analysis was applied to each clustered region of the testing dataset to predict the TDVs of the 10th VF test.Three to nine VF tests were used to predict the 10th VF test,and the prediction errors(root mean square error,RMSE)of each clustering method and pointwise linear regression(PLR)were compared.RESULTS:The training group consisted of 228 patients(mean age,54.20±14.38y;123 males and 105 females),and the testing group included 81 patients(mean age,54.88±15.22y;43 males and 38 females).All subjects were diagnosed with POAG.Fifty-two VF points were clustered into 11 and nine regions using HOPACH and K-means clustering,respectively.K-means clustering had a lower prediction error than PLR when n=1:3 and 1:4(both P≤0.003).The prediction errors of K-means clustering were lower than those of HOPACH in all sections(n=1:4 to 1:9;all P≤0.011),except for n=1:3(P=0.680).PLR outperformed K-means clustering only when n=1:8 and 1:9(both P≤0.020).CONCLUSION:K-means clustering can predict longterm VF test results more accurately in patients with POAG with limited VF data.展开更多
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
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 https://github.com/Tianxiang Zhao0474/WGCN.展开更多
Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous...Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous.Considering the challenge mentioned,this article proposes a clustering-based machine learning(ML)framework to enhance the stability of EPS networks by suppressing LFOs through real-time tuning of key power system stabilizer(PSS)parameters.To validate the proposed strategy,two distinct EPS networks are selected:the single-machine infinite-bus(SMIB)with a single-stage PSS and the unified power flow controller(UPFC)coordinated SMIB with a double-stage PSS.To generate data under various loading conditions for both networks,an efficient but offline meta-heuristic algorithm,namely the grey wolf optimizer(GWO),is used,with the loading conditions as inputs and the key PSS parameters as outputs.The generated loading conditions are then clustered using the fuzzy k-means(FKM)clustering method.Finally,the group method of data handling(GMDH)and long short-term memory(LSTM)ML models are developed for clustered data to predict PSS key parameters in real time for any loading condition.A few well-known statistical performance indices(SPI)are considered for validation and robustness of the training and testing procedure of the developed FKM-GMDH and FKM-LSTM models based on the prediction of PSS parameters.The performance of the ML models is also evaluated using three stability indices(i.e.,minimum damping ratio,eigenvalues,and time-domain simulations)after optimally tuned PSS with real-time estimated parameters under changing operating conditions.Besides,the outputs of the offline(GWO-based)metaheuristic model,proposed real-time(FKM-GMDH and FKM-LSTM)machine learning models,and previously reported literature models are compared.According to the results,the proposed methodology outperforms the others in enhancing the stability of the selected EPS networks by damping out the observed unwanted LFOs under various loading conditions.展开更多
Background:Brucellosis is a major public health issue in China,while its temporal and spatial distribution have not been studied in depth.This study aims to better understand the epidemiology of brucellosis in the mai...Background:Brucellosis is a major public health issue in China,while its temporal and spatial distribution have not been studied in depth.This study aims to better understand the epidemiology of brucellosis in the mainland of China,by investigating the human,temporal and spatial distribution and clustering characteristics of the disease.Methods:Human brucellosis data from the mainland of China between 2012 and 2016 were obtained from the China Information System for Disease Control and Prevention.The spatial autocorrelation analysis of ArcGIS10.6 and the spatial-temporal scanning analysis of SaTScan software were used to identify potential changes in the spatial and temporal distribution of human brucellosis in the mainland of China during the study period.Results:A total of 244348 human brucellosis cases were reported during the study period of 2012-2016.The average incidence of human brucellosis was higher in the 40-65 age group.The temporal clustering analysis showed that the high incidence of brucellosis occurred between March and July.The spatial clustering analysis showed that the location of brucellosis clustering in the mainland of China remained relatively fixed,mainly concentrated in most parts of northern China.The results of the spatial-temporal clustering analysis showed that Heilongjiang represents a primary clustering area,and the Tibet,Shanxi and Hubei provinces represent three secondary clustering areas.Conclusions:Human brucellosis remains a widespread challenge,particularly in northern China.The clustering analysis highlights potential high-risk human groups,time frames and areas,which may require special plans and resources to monitor and control the disease.展开更多
Earthquakes exhibit clear clustering on the earth. It is important to explore the spatial-temporal characteristics of seismicity clusters and their spatial heterogeneity. We analyze effects of plate space, tectonic st...Earthquakes exhibit clear clustering on the earth. It is important to explore the spatial-temporal characteristics of seismicity clusters and their spatial heterogeneity. We analyze effects of plate space, tectonic style, and their interaction on characteristic of cluster.Based on data of earthquakes not less than moment magnitude(M_w) 5.6 from 1960 to 2014, this study used the spatial-temporal scan method to identify earthquake clusters. The results indicate that seismic spatial-temporal clusters can be classified into two types based on duration: persistent clusters and burst clusters. Finally, we analysed the spatial heterogeneity of the two types. The main conclusions are as follows: 1) Ninety percent of the persistent clusters last for 22-38 yr and show a high clustering likelihood;ninety percent of the burst clusters last for 1-1.78 yr and show a high relative risk. 2) The persistent clusters are mainly distributed in interplate zones, especially along the western margin of the Pacific Ocean. The burst clusters are distributed in both intraplate and interplate zones, slightly concentrated in the India-Eurasia interaction zone. 3) For the persistent type, plate interaction plays an important role in the distribution of the clusters’ likelihood and relative risk. In addition, the tectonic style further enhances the spatial heterogeneity. 4) For the burst type,neither plate activity nor tectonic style has an obvious effect on the distribution of the clusters’ likelihood and relative risk. Nevertheless,interaction between these two spatial factors enhances the spatial heterogeneity, especially in terms of relative risk.展开更多
Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the cho...Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the choice of data augmentation,which usually limits the capacity of network generalization.Besides,most existing methods characterize positive and negative samples based on the nodes themselves,ignoring the influence of neighbors with different hop numbers on the node.In this study,a novel self-cumulative contrastive graph clustering(SC-CGC)method is devised,which is capable of dynamically adjusting the influence of neighbors with different hops.Our intuition is that better neighbors are closer and distant ones are further away in their feature space,thus we can perform neighbor contrasting without data augmentation.To be specific,SC-CGC relies on two neural networks,i.e.,autoencoder network(AE)and graph autoencoder network(GAE),to encode the node information and graph structure,respectively.To make these two networks interact and learn from each other,a dynamic fusion mechanism is devised to transfer the knowledge learned by AE to the corresponding GAE layer by layer.Then,a self-cumulative contrastive loss function is designed to characterize the structural information by dynamically accumulating the influence of the nodes with different hops.Finally,our approach simultaneously refines the representation learning and clustering assignments in a self-supervised manner.Extensive experiments on 8 realistic datasets demonstrate that SC-CGC consistently performs better over SOTA techniques.The code is available at https://github.com/Xiaoqiang-Yan/JAS-SCCGC.展开更多
As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limite...As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limited research in recent years on the spatial-temporal distribution and emission of its atmospheric pollutants.To address this,this study conducted mobile observations of urban roads using the Mobile-DOAS instrument from June 2021 to May 2022.The monitoring results exhibit a favourable consistent with TROPOMI satellite data and ground monitoring station data.Temporally,there were pronounced seasonal variations in air pollutants.Spatially,high concentration of HCHO and NO_(2)were closely associated with traffic congestion on roadways,while heightened SO_(2)levels were attributed to winter heating and industrial emissions.The study also revealed that with the implementation of road policies,the average vehicle speed increased by 95.4%,while the NO concentration decreased by 54.4%.In the estimation of urban NO_(x)emission flux,it was observed that in temporal terms,compared with inventory data,the emissions calculated viamobile measurements exhibitedmore distinct seasonal patterns,with the highest emission rate of 349 g/sec in winter and the lowest of 142 g/sec in summer.In spatial terms,the significant difference in emissions between the inner and outer ring roads also suggests the presence of the city’s primary NO_(x)emission sources in the area between these two rings.This study offers data support for formulating the next phase of air pollution control measures in urban areas.展开更多
Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy cl...Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.展开更多
基金financially supported by the National Natural Science Foundation of China(Nos.U2244225 and 42020104005)the Ministry of Education of China(111 Project)the Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)and China Geological Survey(No.DD20211391)。
文摘The goal of this study was to determine the spatiotemporal characteristics of mangrove distribution and fragmentation patterns from 1988 through 2019 in Dongzhaigang.Land cover datasets were generated for Dongzhaigang for multiple years via a decision tree method based on a classification and regression tree(CART)algorithm using Landsat time series images.Spatiotemporal transform and fragmentation patterns of mangrove distribution were separately assessed with a transfer matrix of land cover types and a landscape pattern index.The classification method combined with multi-band images showed good accuracy,with overall accuracy higher than 90%.Mangrove areas in 1988,1999,2009,and 2019 were 2050,1875,1818,and 1750 ha,respectively,with decreases mainly due to conversion to aquaculture ponds and farmland.A mangrove growth index(MGI)was proposed,reflecting the water-mangrove relationship,showing positive mangrove growth from 1988–2009 and negative growth from 2009–2019.Study results indicated anthropogenic factors play a leading role in the extent and scale of mangrove effects over the past 30 years.According to the analysis results,corresponding management and protection measures are proposed to provide reference for the sustainable development of Dongzhaigang Mangrove Wetland ecosystem.
文摘Transit managers can use Intelligent Transportation System technologies to access large amounts of data to monitor network status.However,the presentation of the data lacks structural information.Existing single-network description technologies are ineffective in representing the temporal and spatial characteristics simultaneously.Therefore,there is a need for complementary methods to address these deficiencies.To address these limitations,this paper proposes an approach that combines Network Snapshots and Temporal Paths for the scheduled system.A dual information network is constructed to assess the degree of operational deviation considering the planning tasks.To validate the effectiveness,discussions are conducted through a modified cosine similarity calculation on theoretical analysis,delay level description,and the ability to identify abnormal dates.Compared to some state-of-the-art methods,the proposed method achieves an average Spearman delay correlation of 0.847 and a relative distance of 3.477.Furthermore,case analyses are invested in regions of China's Mainland,Europe,and the United States,investigating both the overall and sub-regional network fluctuations.To represent the impact of network fluctuations in sub-regions,a response loss value was developed.The times that are prone to fluctuations are also discussed through the classification of time series data.The research can offer a novel approach to system monitoring,providing a research direction that utilizes individual data combined to represent macroscopic states.Our code will be released at https://github.com/daozhong/STPN.git.
基金supported by the National Natural Science Foundation of China (12473105 and 12473106)the central government guides local funds for science and technology development (YDZJSX2024D049)the Graduate Student Practice and Innovation Program of Shanxi Province (2024SJ313)
文摘As large-scale astronomical surveys,such as the Sloan Digital Sky Survey(SDSS)and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST),generate increasingly complex datasets,clustering algorithms have become vital for identifying patterns and classifying celestial objects.This paper systematically investigates the application of five main categories of clustering techniques-partition-based,density-based,model-based,hierarchical,and“others”-across a range of astronomical research over the past decade.This review focuses on the six key application areas of stellar classification,galaxy structure analysis,detection of galactic and interstellar features,highenergy astrophysics,exoplanet studies,and anomaly detection.This paper provides an in-depth analysis of the performance and results of each method,considering their respective suitabilities for different data types.Additionally,it presents clustering algorithm selection strategies based on the characteristics of the spectroscopic data being analyzed.We highlight challenges such as handling large datasets,the need for more efficient computational tools,and the lack of labeled data.We also underscore the potential of unsupervised and semi-supervised clustering approaches to overcome these challenges,offering insight into their practical applications,performance,and results in astronomical research.
基金supported by Shanghai Aerospace Science and Technology Innovation Foundation(SAST2023-075)。
文摘Multichannel signals have the characteristics of information diversity and information consistency.To better explore and utilize the affinity relationship within multichannel signals,a new graph learning technique based on low rank tensor approximation is proposed for multichannel monitoring signal processing and utilization.Firstly,the affinity relationship of multichannel signals can be acquired based on the clustering results of each channel signal.Wherein an affinity tensor is constructed to integrate the diverse and consistent information of the clustering information among multichannel signals.Secondly,a low-rank tensor optimization model is built and the joint affinity matrix is optimized with the assistance of the strong confidence affinity matrix.Through solving the optimization model,the fused affinity relationship graph of multichannel signals can be obtained.Finally,the multichannel fused clustering results can be acquired though the updated joint affinity relationship graph.The multichannel signal utilization examples in health state assessment with public datasets and microwave detection with actual echoes verify the advantages and effectiveness of the proposed method.
基金supported in part by the National Natural Science Foundation of China(Grant No.61971291)the Basic Scientific Research Project of the Liaoning Provincial Department of Education(LJ212410144013)+2 种基金the Leading Talent of the‘Xing Liao Ying Cai Plan’(XLYC2202013)the Shenyang Natural Science Foundation(22-315-6-10)the Guangxuan Scholar of Shenyang Ligong University(SYLUGXXZ202205).
文摘With the popularization of smart devices,Location-Based Services(LBS)greatly facilitates users’life,but at the same time brings the risk of users’location privacy leakage.Existing location privacy protection methods are deficient,failing to reasonably allocate the privacy budget for non-outlier location points and ignoring the critical location information that may be contained in the outlier points,leading to decreased data availability and privacy exposure problems.To address these problems,this paper proposes a Mix Location Privacy Preservation Method Based on Differential Privacy with Clustering(MLDP).The method first utilizes the DBSCAN clustering algorithm to classify location points into non-outliers and outliers.For non-outliers,the scoring function is designed by combining geographic information and semantic information,and the privacy budget is allocated according to the heat intensity of the hotspot area;for outliers,the scoring function is constructed to allocate the privacy budget based on their correlation with the hotspot area.By comprehensively considering the geographic information,semantic information,and correlation with hotspot areas of the location points,a reasonable privacy budget is assigned to each location point,andfinallynoise is added throughthe Laplacemechanismto realizeprivacyprotection.Experimental results on tworeal trajectory datasets,Geolife and T-Drive,show that the MLDP approach significantly improves data availability while effectively protecting location privacy.Compared with the comparison methods,the maximum available data ratio of MLDP is 1.Moreover,compared with the RandomNoise method,its execution time is 0.056–0.061 s longer,and the logRE is 0.12951–0.62194 lower;compared with KemeansDP,QTK-DP,DPK-F,IDP-SC,and DPK-Means-up methods,it saves 0.114–0.296 s in execution time,and the logRE is 0.01112–0.38283 lower.
基金support supplied by the National Natural Science Foundation of China(Nos.72571136,72271120)the Ministry of Education of the People’s Republic of China Humanities and Social Science project(No.24YJA630087)。
文摘With the rapid development of the aviation industry,air travel has become one of the most important modes.Improving the service quality of civil aviation airports is crucial to their competitiveness.This study intends to develop a scientific and rational evaluation methodology and framework for assessing service quality in civil aviation airports,thereby providing a theoretical foundation and practical guidance for enhancing service standards in the aviation industry.First,the study constructs a CRITIC-bidirectional grey possibility clustering model,which uses the CRITIC method to determine the weights of indicators and integrates the forward grey possibility clustering model and the inverse grey possibility clustering model to determine possibility functions from two perspectives.Second,a service quality evaluation index system for civil airports is constructed from four dimensions,and the weights of each index within the system are subsequently calculated.Finally,the constructed model is applied to evaluate the service quality of nine domestic civil airports.Based on the clustering results,targeted countermeasures and suggestions are proposed.Empirical results demonstrate that,compared to the traditional grey possibility clustering model,the proposed model balances the objectivity of indicator weighting,the objectivity of possibility function construction,and the simplicity of the computational process,thereby possessing significant theoretical and practical implications.
基金supported by the Research Project of China Southern Power Grid(No.056200KK52222031).
文摘This paper proposes an equivalent modeling method for photovoltaic(PV)power stations via a particle swarm optimization(PSO)K-means clustering(KMC)algorithm with passive filter parameter clustering to address the complexities,simulation time cost and convergence problems of detailed PV power station models.First,the amplitude–frequency curves of different filter parameters are analyzed.Based on the results,a grouping parameter set for characterizing the external filter characteristics is established.These parameters are further defined as clustering parameters.A single PV inverter model is then established as a prerequisite foundation.The proposed equivalent method combines the global search capability of PSO with the rapid convergence of KMC,effectively overcoming the tendency of KMC to become trapped in local optima.This approach enhances both clustering accuracy and numerical stability when determining equivalence for PV inverter units.Using the proposed clustering method,both a detailed PV power station model and an equivalent model are developed and compared.Simulation and hardwarein-loop(HIL)results based on the equivalent model verify that the equivalent method accurately represents the dynamic characteristics of PVpower stations and adapts well to different operating conditions.The proposed equivalent modeling method provides an effective analysis tool for future renewable energy integration research.
基金funded by the Research Project:THTETN.05/24-25,VietnamAcademy of Science and Technology.
文摘Satellite image segmentation plays a crucial role in remote sensing,supporting applications such as environmental monitoring,land use analysis,and disaster management.However,traditional segmentation methods often rely on large amounts of labeled data,which are costly and time-consuming to obtain,especially in largescale or dynamic environments.To address this challenge,we propose the Semi-Supervised Multi-View Picture Fuzzy Clustering(SS-MPFC)algorithm,which improves segmentation accuracy and robustness,particularly in complex and uncertain remote sensing scenarios.SS-MPFC unifies three paradigms:semi-supervised learning,multi-view clustering,and picture fuzzy set theory.This integration allows the model to effectively utilize a small number of labeled samples,fuse complementary information from multiple data views,and handle the ambiguity and uncertainty inherent in satellite imagery.We design a novel objective function that jointly incorporates picture fuzzy membership functions across multiple views of the data,and embeds pairwise semi-supervised constraints(must-link and cannot-link)directly into the clustering process to enhance segmentation accuracy.Experiments conducted on several benchmark satellite datasets demonstrate that SS-MPFC significantly outperforms existing state-of-the-art methods in segmentation accuracy,noise robustness,and semantic interpretability.On the Augsburg dataset,SS-MPFC achieves a Purity of 0.8158 and an Accuracy of 0.6860,highlighting its outstanding robustness and efficiency.These results demonstrate that SSMPFC offers a scalable and effective solution for real-world satellite-based monitoring systems,particularly in scenarios where rapid annotation is infeasible,such as wildfire tracking,agricultural monitoring,and dynamic urban mapping.
文摘This paper introduces a fuzzy C-means-based pooling layer for convolutional neural networks that explicitly models local uncertainty and ambiguity.Conventional pooling operations,such as max and average,apply rigid aggregation and often discard fine-grained boundary information.In contrast,our method computes soft membershipswithin each receptive field and aggregates cluster-wise responses throughmembership-weighted pooling,thereby preserving informative structure while reducing dimensionality.Being differentiable,the proposed layer operates as standard two-dimensional pooling.We evaluate our approach across various CNN backbones and open datasets,including CIFAR-10/100,STL-10,LFW,and ImageNette,and further probe small training set restrictions on MNIST and Fashion-MNIST.In these settings,the proposed pooling consistently improves accuracy and weighted F1 over conventional baselines,with particularly strong gains when training data are scarce.Even with less than 1%of the training set,ourmethodmaintains reliable performance,indicating improved sample efficiency and robustness to noisy or ambiguous local patterns.Overall,integrating soft memberships into the pooling operator provides a practical and generalizable inductive bias that enhances robustness and generalization in modern CNN pipelines.
基金supported by the NSFC(Grant Nos.62176273,62271070,62441212)The Open Foundation of State Key Laboratory of Networking and Switching Technology(Beijing University of Posts and Telecommunications)under Grant SKLNST-2024-1-062025Major Project of the Natural Science Foundation of Inner Mongolia(2025ZD008).
文摘The Intrusion Detection System(IDS)is a security mechanism developed to observe network traffic and recognize suspicious or malicious activities.Clustering algorithms are often incorporated into IDS;however,conventional clustering-based methods face notable drawbacks,including poor scalability in handling high-dimensional datasets and a strong dependence of outcomes on initial conditions.To overcome the performance limitations of existing methods,this study proposes a novel quantum-inspired clustering algorithm that relies on a similarity coefficient-based quantum genetic algorithm(SC-QGA)and an improved quantum artificial bee colony algorithm hybrid K-means(IQABC-K).First,the SC-QGA algorithmis constructed based on quantum computing and integrates similarity coefficient theory to strengthen genetic diversity and feature extraction capabilities.For the subsequent clustering phase,the process based on the IQABC-K algorithm is enhanced with the core improvement of adaptive rotation gate and movement exploitation strategies to balance the exploration capabilities of global search and the exploitation capabilities of local search.Simultaneously,the acceleration of convergence toward the global optimum and a reduction in computational complexity are facilitated by means of the global optimum bootstrap strategy and a linear population reduction strategy.Through experimental evaluation with multiple algorithms and diverse performance metrics,the proposed algorithm confirms reliable accuracy on three datasets:KDD CUP99,NSL_KDD,and UNSW_NB15,achieving accuracy of 98.57%,98.81%,and 98.32%,respectively.These results affirm its potential as an effective solution for practical clustering applications.
基金supported by the National Natural Science Foundation of China(Grant Nos.52069029,52369026)the Belt and Road Special Foundation of National Key Laboratory of Water Disaster Preven-tion(Grant No.2023490411)+2 种基金the Yunnan Agricultural Basic Research Joint Special General Project(Grant Nos.202501BD070001-060,202401BD070001-071)Construction Project of the Yunnan Key Laboratory of Water Security(No.20254916CE340051)the Youth Talent Project of“Xingdian Talent Support Plan”in Yunnan Province(Grant No.XDYC-QNRC-2023-0412).
文摘Deformation prediction for extra-high arch dams is highly important for ensuring their safe operation.To address the challenges of complex monitoring data,the uneven spatial distribution of deformation,and the construction and optimization of a prediction model for deformation prediction,a multipoint ultrahigh arch dam deformation prediction model,namely,the CEEMDAN-KPCA-GSWOA-KELM,which is based on a clustering partition,is pro-posed.First,the monitoring data are preprocessed via variational mode decomposition(VMD)and wavelet denoising(WT),which effectively filters out noise and improves the signal-to-noise ratio of the data,providing high-quality input data for subsequent prediction models.Second,scientific cluster partitioning is performed via the K-means++algorithm to precisely capture the spatial distribution characteristics of extra-high arch dams and ensure the consistency of deformation trends at measurement points within each partition.Finally,CEEMDAN is used to separate monitoring data,predict and analyze each component,combine the KPCA(Kernel Principal Component Analysis)and the KELM(Kernel Extreme Learning Machine)optimized by the GSWOA(Global Search Whale Optimization Algorithm),integrate the predictions of each component via reconstruction methods,and precisely predict the overall trend of ultrahigh arch dam deformation.An extra high arch dam project is taken as an example and validated via a comparative analysis of multiple models.The results show that the multipoint deformation prediction model in this paper can combine data from different measurement points,achieve a comprehensive,precise prediction of the deformation situation of extra high arch dams,and provide strong technical support for safe operation.
基金Supported by the Korea Health Technology R&D Project through the Korea Health Industry Development Institute(KHIDI),the Ministry of Health&Welfare,Republic of Korea(No.RS-2020-KH088726)the Patient-Centered Clinical Research Coordinating Center(PACEN),the Ministry of Health and Welfare,Republic of Korea(No.HC19C0276)the National Research Foundation of Korea(NRF),the Korea Government(MSIT)(No.RS-2023-00247504).
文摘AIM:To evaluate long-term visual field(VF)prediction using K-means clustering in patients with primary open angle glaucoma(POAG).METHODS:Patients who underwent 24-2 VF tests≥10 were included in this study.Using 52 total deviation values(TDVs)from the first 10 VF tests of the training dataset,VF points were clustered into several regions using the hierarchical ordered partitioning and collapsing hybrid(HOPACH)and K-means clustering.Based on the clustering results,a linear regression analysis was applied to each clustered region of the testing dataset to predict the TDVs of the 10th VF test.Three to nine VF tests were used to predict the 10th VF test,and the prediction errors(root mean square error,RMSE)of each clustering method and pointwise linear regression(PLR)were compared.RESULTS:The training group consisted of 228 patients(mean age,54.20±14.38y;123 males and 105 females),and the testing group included 81 patients(mean age,54.88±15.22y;43 males and 38 females).All subjects were diagnosed with POAG.Fifty-two VF points were clustered into 11 and nine regions using HOPACH and K-means clustering,respectively.K-means clustering had a lower prediction error than PLR when n=1:3 and 1:4(both P≤0.003).The prediction errors of K-means clustering were lower than those of HOPACH in all sections(n=1:4 to 1:9;all P≤0.011),except for n=1:3(P=0.680).PLR outperformed K-means clustering only when n=1:8 and 1:9(both P≤0.020).CONCLUSION:K-means clustering can predict longterm VF test results more accurately in patients with POAG with limited VF data.
基金supported by the National Natural Science Foundation of China(Grant No.62172292).
文摘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%.
基金supported by the National Natural Science Foundation of China(62225303,62403043,62433004)the Beijing Natural Science Foundation(4244085)+1 种基金the Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(GZC20230203)the China Postdoctoral Science Foundation(2023M740201)。
文摘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 https://github.com/Tianxiang Zhao0474/WGCN.
基金supported by the Deanship of Research at the King Fahd University of Petroleum&Minerals,Dhahran,31261,Saudi Arabia,under Project No.EC241001.
文摘Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous.Considering the challenge mentioned,this article proposes a clustering-based machine learning(ML)framework to enhance the stability of EPS networks by suppressing LFOs through real-time tuning of key power system stabilizer(PSS)parameters.To validate the proposed strategy,two distinct EPS networks are selected:the single-machine infinite-bus(SMIB)with a single-stage PSS and the unified power flow controller(UPFC)coordinated SMIB with a double-stage PSS.To generate data under various loading conditions for both networks,an efficient but offline meta-heuristic algorithm,namely the grey wolf optimizer(GWO),is used,with the loading conditions as inputs and the key PSS parameters as outputs.The generated loading conditions are then clustered using the fuzzy k-means(FKM)clustering method.Finally,the group method of data handling(GMDH)and long short-term memory(LSTM)ML models are developed for clustered data to predict PSS key parameters in real time for any loading condition.A few well-known statistical performance indices(SPI)are considered for validation and robustness of the training and testing procedure of the developed FKM-GMDH and FKM-LSTM models based on the prediction of PSS parameters.The performance of the ML models is also evaluated using three stability indices(i.e.,minimum damping ratio,eigenvalues,and time-domain simulations)after optimally tuned PSS with real-time estimated parameters under changing operating conditions.Besides,the outputs of the offline(GWO-based)metaheuristic model,proposed real-time(FKM-GMDH and FKM-LSTM)machine learning models,and previously reported literature models are compared.According to the results,the proposed methodology outperforms the others in enhancing the stability of the selected EPS networks by damping out the observed unwanted LFOs under various loading conditions.
文摘Background:Brucellosis is a major public health issue in China,while its temporal and spatial distribution have not been studied in depth.This study aims to better understand the epidemiology of brucellosis in the mainland of China,by investigating the human,temporal and spatial distribution and clustering characteristics of the disease.Methods:Human brucellosis data from the mainland of China between 2012 and 2016 were obtained from the China Information System for Disease Control and Prevention.The spatial autocorrelation analysis of ArcGIS10.6 and the spatial-temporal scanning analysis of SaTScan software were used to identify potential changes in the spatial and temporal distribution of human brucellosis in the mainland of China during the study period.Results:A total of 244348 human brucellosis cases were reported during the study period of 2012-2016.The average incidence of human brucellosis was higher in the 40-65 age group.The temporal clustering analysis showed that the high incidence of brucellosis occurred between March and July.The spatial clustering analysis showed that the location of brucellosis clustering in the mainland of China remained relatively fixed,mainly concentrated in most parts of northern China.The results of the spatial-temporal clustering analysis showed that Heilongjiang represents a primary clustering area,and the Tibet,Shanxi and Hubei provinces represent three secondary clustering areas.Conclusions:Human brucellosis remains a widespread challenge,particularly in northern China.The clustering analysis highlights potential high-risk human groups,time frames and areas,which may require special plans and resources to monitor and control the disease.
基金Under the auspices of National Natural Science Foundation of China(No.41771537)Fundamental Research Funds for the Central Universities
文摘Earthquakes exhibit clear clustering on the earth. It is important to explore the spatial-temporal characteristics of seismicity clusters and their spatial heterogeneity. We analyze effects of plate space, tectonic style, and their interaction on characteristic of cluster.Based on data of earthquakes not less than moment magnitude(M_w) 5.6 from 1960 to 2014, this study used the spatial-temporal scan method to identify earthquake clusters. The results indicate that seismic spatial-temporal clusters can be classified into two types based on duration: persistent clusters and burst clusters. Finally, we analysed the spatial heterogeneity of the two types. The main conclusions are as follows: 1) Ninety percent of the persistent clusters last for 22-38 yr and show a high clustering likelihood;ninety percent of the burst clusters last for 1-1.78 yr and show a high relative risk. 2) The persistent clusters are mainly distributed in interplate zones, especially along the western margin of the Pacific Ocean. The burst clusters are distributed in both intraplate and interplate zones, slightly concentrated in the India-Eurasia interaction zone. 3) For the persistent type, plate interaction plays an important role in the distribution of the clusters’ likelihood and relative risk. In addition, the tectonic style further enhances the spatial heterogeneity. 4) For the burst type,neither plate activity nor tectonic style has an obvious effect on the distribution of the clusters’ likelihood and relative risk. Nevertheless,interaction between these two spatial factors enhances the spatial heterogeneity, especially in terms of relative risk.
基金supported by the National Natural Science Foundation of China(62371423,62450002,62425107)China Postdoctoral Science Foundation(2020M682357).
文摘Contrastive graph clustering(CGC)has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs.However,the performance of CGC methods critically depends on the choice of data augmentation,which usually limits the capacity of network generalization.Besides,most existing methods characterize positive and negative samples based on the nodes themselves,ignoring the influence of neighbors with different hop numbers on the node.In this study,a novel self-cumulative contrastive graph clustering(SC-CGC)method is devised,which is capable of dynamically adjusting the influence of neighbors with different hops.Our intuition is that better neighbors are closer and distant ones are further away in their feature space,thus we can perform neighbor contrasting without data augmentation.To be specific,SC-CGC relies on two neural networks,i.e.,autoencoder network(AE)and graph autoencoder network(GAE),to encode the node information and graph structure,respectively.To make these two networks interact and learn from each other,a dynamic fusion mechanism is devised to transfer the knowledge learned by AE to the corresponding GAE layer by layer.Then,a self-cumulative contrastive loss function is designed to characterize the structural information by dynamically accumulating the influence of the nodes with different hops.Finally,our approach simultaneously refines the representation learning and clustering assignments in a self-supervised manner.Extensive experiments on 8 realistic datasets demonstrate that SC-CGC consistently performs better over SOTA techniques.The code is available at https://github.com/Xiaoqiang-Yan/JAS-SCCGC.
基金supported by the National Natural Science Foundation of China(Nos.U19A2044,42105132,42030609,41975037,and 42105133)the National Key Research and Development Program of China(No.2022YFC3703502)+1 种基金the Plan for Anhui Major Provincial Science&Technology Project(No.202203a07020003)Hefei Ecological Environment Bureau Project(No.2020BFFFD01804).
文摘As a significant city in the Yangtze River Delta regions,Hefei has experienced rapid changes in the sources of air pollution due to its high-speed economic development and urban expansion.However,there has been limited research in recent years on the spatial-temporal distribution and emission of its atmospheric pollutants.To address this,this study conducted mobile observations of urban roads using the Mobile-DOAS instrument from June 2021 to May 2022.The monitoring results exhibit a favourable consistent with TROPOMI satellite data and ground monitoring station data.Temporally,there were pronounced seasonal variations in air pollutants.Spatially,high concentration of HCHO and NO_(2)were closely associated with traffic congestion on roadways,while heightened SO_(2)levels were attributed to winter heating and industrial emissions.The study also revealed that with the implementation of road policies,the average vehicle speed increased by 95.4%,while the NO concentration decreased by 54.4%.In the estimation of urban NO_(x)emission flux,it was observed that in temporal terms,compared with inventory data,the emissions calculated viamobile measurements exhibitedmore distinct seasonal patterns,with the highest emission rate of 349 g/sec in winter and the lowest of 142 g/sec in summer.In spatial terms,the significant difference in emissions between the inner and outer ring roads also suggests the presence of the city’s primary NO_(x)emission sources in the area between these two rings.This study offers data support for formulating the next phase of air pollution control measures in urban areas.
基金funded by the Research Project:THTETN.05/24-25,VietnamAcademy of Science and Technology.
文摘Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.
