To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-f...To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-feature local difference.Firstly,an improved high-boost filter is used for preprocessing to eliminate background clutter and high-brightness interference,thereby increasing the probability of capturing real targets in the density peak search.Secondly,a triple-layer window is used to extract features from the area surrounding candidate targets,addressing the uncertainty of small target sizes.By calculating multi-feature local differences between the triple-layer windows,the problems of blurred target edges and low contrast are resolved.To balance the contribution of different features,intra-class distance is used to calculate weights,achieving weighted fusion of multi-feature local differences to obtain the weighted multi-feature local differences of candidate targets.The real targets are then extracted using the interquartile range.Experiments on datasets such as SIRST and IRSTD-IK show that the proposed method is suitable for various complex types and demonstrates good robustness and detection performance.展开更多
Cluster-basedmodels have numerous application scenarios in vehicular ad-hoc networks(VANETs)and can greatly help improve the communication performance of VANETs.However,the frequent movement of vehicles can often lead...Cluster-basedmodels have numerous application scenarios in vehicular ad-hoc networks(VANETs)and can greatly help improve the communication performance of VANETs.However,the frequent movement of vehicles can often lead to changes in the network topology,thereby reducing cluster stability in urban scenarios.To address this issue,we propose a clustering model based on the density peak clustering(DPC)method and sparrow search algorithm(SSA),named SDPC.First,the model constructs a fitness function based on the parameters obtained from the DPC method and deploys the SSA for iterative optimization to select cluster heads(CHs).Then,the vehicles that have not been selected as CHs are assigned to appropriate clusters by comprehensively considering the distance parameter and link-reliability parameter.Finally,cluster maintenance strategies are considered to tackle the changes in the clusters’organizational structure.To verify the performance of the model,we conducted a simulation on a real-world scenario for multiple metrics related to clusters’stability.The results show that compared with the APROVE and the GAPC,SDPC showed clear performance advantages,indicating that SDPC can effectively ensure VANETs’cluster stability in urban scenarios.展开更多
AlAs/GaAs/In0.1Ga0.9As/GaAs/AlAs double-barrier resonant tunneling diodes （DBRTDs） grown on a semi-insulated GaAs substrate with molecular beam epitaxy is demonstrated. By sandwiching the In0.1 Ga0.9 As layer betwee...AlAs/GaAs/In0.1Ga0.9As/GaAs/AlAs double-barrier resonant tunneling diodes （DBRTDs） grown on a semi-insulated GaAs substrate with molecular beam epitaxy is demonstrated. By sandwiching the In0.1 Ga0.9 As layer between GaAs layers, potential wells beside the two sides of barrier are deepened, resulting in an increase of the peak-to-valley current ratio （PVCR） and a peak current density. A special shape of collector is designed in order to reduce contact resistance and non-uniformity of the current;as a result the total chrrent density in the device is increased. The use of thin barriers is also helpful for the improvement of the PVCR and the peak current density in DBRTDs. The devices exhibit a maximum PVCR of 13.98 and a peak current density of 89kA/cm^2 at room temperature.展开更多
Modeling of energy consumption(EC) and effluent quality(EQ) are very essential problems that need to be solved for the multiobjective optimal control in the wastewater treatment process(WWTP). To address this issue, a...Modeling of energy consumption(EC) and effluent quality(EQ) are very essential problems that need to be solved for the multiobjective optimal control in the wastewater treatment process(WWTP). To address this issue, a density peaks-based adaptive fuzzy neural network(DP-AFNN) is proposed in this study. To obtain suitable fuzzy rules, a DP-based clustering method is applied to fit the cluster centers to process nonlinearity.The parameters of the extracted fuzzy rules are fine-tuned based on the improved Levenberg-Marquardt algorithm during the training process. Furthermore, the analysis of convergence is performed to guarantee the successful application of the DPAFNN. Finally, the proposed DP-AFNN is utilized to develop the models of EC and EQ in the WWTP. The experimental results show that the proposed DP-AFNN can achieve fast convergence speed and high prediction accuracy in comparison with some existing methods.展开更多
We report a simultaneous observation of two band electromagnetic ion cyclotron(EMIC)waves and toroidal Alfvén waves by the Van Allen Probe mission.Through wave frequency analyses,the mass densityρis found to be ...We report a simultaneous observation of two band electromagnetic ion cyclotron(EMIC)waves and toroidal Alfvén waves by the Van Allen Probe mission.Through wave frequency analyses,the mass densityρis found to be locally peaked at the magnetic equator.Perpendicular fluxes of ions(<100 eV)increase simultaneously with the appearances of EMIC waves,indicating a heating of these ions by EMIC waves.In addition,the measured ion distributions also support the equatorial peak formation,which accords with the result of the frequency analyses.The formation of local mass density peaks at the equator should be due to enhancements of equatorial ion concentrations,which are triggered by EMIC waves’perpendicular heating on low energy ions.展开更多
This study deals with Peak of electron density in F2-layer sensibility scale during quiet time on solar minimum. Peaks of electron density in F2-layer (NmF2) values at the quietest days are compared to those carried o...This study deals with Peak of electron density in F2-layer sensibility scale during quiet time on solar minimum. Peaks of electron density in F2-layer (NmF2) values at the quietest days are compared to those carried out from the two nearest days (previous and following of quietest day). The study uses International Reference Ionosphere (IRI) for ionosphere modeling. The located station is Ouagadougou, in West Africa. Solar minimum of phase 22 is considered in this study. Using three core principles of ionosphere modeling under IRI running conditions, the study enables to carry out Peak of electron density in F2-layer values during the quietest days of the characteristic months for the four different seasons. These parameters are compared to those of the previous and the following of the quietest days (the day before and following each quietest selected day) at the same hour. The knowledge of NmF2 values at the quietest days and at the two nearest days enables to calculate the relative error that can be made on this parameter. This calculation highlights insignificant relative errors. This means that NmF2 values at the two nearest days of each quietest day on solar minimum can be used for simulating the quietest days’ behavior. NmF2 values obtained by running IRI model have good correlation with those carried out by Thermosphere-Ionosphere-Electrodynamics-General Circulation Model (TIEGCM).展开更多
Performing cluster analysis on molecular conformation is an important way to find the representative conformation in the molecular dynamics trajectories.Usually,it is a critical step for interpreting complex conformat...Performing cluster analysis on molecular conformation is an important way to find the representative conformation in the molecular dynamics trajectories.Usually,it is a critical step for interpreting complex conformational changes or interaction mechanisms.As one of the density-based clustering algorithms,find density peaks(FDP)is an accurate and reasonable candidate for the molecular conformation clustering.However,facing the rapidly increasing simulation length due to the increase in computing power,the low computing efficiency of FDP limits its application potential.Here we propose a marginal extension to FDP named K-means find density peaks(KFDP)to solve the mass source consuming problem.In KFDP,the points are initially clustered by a high efficiency clustering algorithm,such as K-means.Cluster centers are defined as typical points with a weight which represents the cluster size.Then,the weighted typical points are clustered again by FDP,and then are refined as core,boundary,and redefined halo points.In this way,KFDP has comparable accuracy as FDP but its computational complexity is reduced from O(n^(2))to O(n).We apply and test our KFDP method to the trajectory data of multiple small proteins in terms of torsion angle,secondary structure or contact map.The comparing results with K-means and density-based spatial clustering of applications with noise show the validation of the proposed KFDP.展开更多
The key challenge of the extended target probability hypothesis density (ET-PHD) filter is to reduce the computational complexity by using a subset to approximate the full set of partitions. In this paper, the influen...The key challenge of the extended target probability hypothesis density (ET-PHD) filter is to reduce the computational complexity by using a subset to approximate the full set of partitions. In this paper, the influence for the tracking results of different partitions is analyzed, and the form of the most informative partition is obtained. Then, a fast density peak-based clustering (FDPC) partitioning algorithm is applied to the measurement set partitioning. Since only one partition of the measurement set is used, the ET-PHD filter based on FDPC partitioning has lower computational complexity than the other ET-PHD filters. As FDPC partitioning is able to remove the spatially close clutter-generated measurements, the ET-PHD filter based on FDPC partitioning has good tracking performance in the scenario with more clutter-generated measurements. The simulation results show that the proposed algorithm can get the most informative partition and obviously reduce computational burden without losing tracking performance. As the number of clutter-generated measurements increased, the ET-PHD filter based on FDPC partitioning has better tracking performance than other ET-PHD filters. The FDPC algorithm will play an important role in the engineering realization of the multiple extended target tracking filter.展开更多
In this paper, using the MSISE-90 model as the reference atmosphere, we discuss the feasibility and method of deducing the peak densities of the undisturbed atomic oxygen profiles in the MLT region (the mesosphere and...In this paper, using the MSISE-90 model as the reference atmosphere, we discuss the feasibility and method of deducing the peak densities of the undisturbed atomic oxygen profiles in the MLT region (the mesosphere and lower thermosphere region) from OI (557.7 nm) night airglow intersities. The peak densities for different seasons, latitudes and longitudes are deduced from OI (557.7nm) airglow intensities through this expression. We analyze the features of inversion relative errors and discuss the influence of the variations in temperature on inversion errors. The results indicate that all inversion errors are less than 5% except for those at high altitudes in the summer hemisphere. And the impact of the variations in temperature on errors is not significant.展开更多
We present a novel unsupervised integrated score framework to generate generic extractive multi- document summaries by ranking sentences based on dynamic programming （DP） strategy. Considering that cluster-based met...We present a novel unsupervised integrated score framework to generate generic extractive multi- document summaries by ranking sentences based on dynamic programming （DP） strategy. Considering that cluster-based methods proposed by other researchers tend to ignore informativeness of words when they generate summaries, our proposed framework takes relevance, diversity, informativeness and length constraint of sentences into consideration comprehensively. We apply Density Peaks Clustering （DPC） to get relevance scores and diversity scores of sentences simultaneously. Our framework produces the best performance on DUC2004, 0.396 of ROUGE-1 score, 0.094 of ROUGE-2 score and 0.143 of ROUGE-SU4 which outperforms a series of popular baselines, such as DUC Best, FGB [7], and BSTM [10].展开更多
The principal resonance of Duffing random external excitation was investigated. oscillator to combined deterministic and The random excitation was taken to be white noise or harmonic with separable random amplitude an...The principal resonance of Duffing random external excitation was investigated. oscillator to combined deterministic and The random excitation was taken to be white noise or harmonic with separable random amplitude and phase. The method of multiple scales was used to determine the equations of modulation of amplitude and phase. The one peak probability density function of each of the two stable stationary solutions was calculated by the linearization method. These two one-peak-density functions were combined using the probability of realization of the two stable stationary solutions to obtain the double peak probability density function. The theoretical analysis are verified by numerical results.展开更多
The impact of the E×B flow shear stabilization on particle transport and density peaking at JET is analyzed in the framework of integrated modelling with the CRONOS code.For that purpose,plasmas from a power scan...The impact of the E×B flow shear stabilization on particle transport and density peaking at JET is analyzed in the framework of integrated modelling with the CRONOS code.For that purpose,plasmas from a power scan which show a significant increasing of density peaking with the injected neutral beam injection power have been used as a modeling basis.By means of simulations with the quasilinear model GLF23 for the heat and particle transport,a strong link between the particle confinement and E×B flow shear stabilization is found.This is particularly important close to the pedestal region where the particle pinch direction becomes strongly inward for high E×B flow shear values.Such impact introduces some non-negligible deviation from the well-known collisonality dependence of the density peaking,whose general trend has been also obtained in the framework of this modelling by performing pedestal density scans.展开更多
There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of netwo...There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of network data is usually paired with clustering algorithms to solve the community detection problem.Meanwhile, there is always an unpredictable distribution of class clusters outputby graph representation learning. Therefore, we propose an improved densitypeak clustering algorithm (ILDPC) for the community detection problem, whichimproves the local density mechanism in the original algorithm and can betteraccommodate class clusters of different shapes. And we study the communitydetection in network data. The algorithm is paired with the benchmark modelGraph sample and aggregate (GraphSAGE) to show the adaptability of ILDPCfor community detection. The plotted decision diagram shows that the ILDPCalgorithm is more discriminative in selecting density peak points compared tothe original algorithm. Finally, the performance of K-means and other clusteringalgorithms on this benchmark model is compared, and the algorithm is proved tobe more suitable for community detection in sparse networks with the benchmarkmodel on the evaluation criterion F1-score. The sensitivity of the parameters ofthe ILDPC algorithm to the low-dimensional vector set output by the benchmarkmodel GraphSAGE is also analyzed.展开更多
为解决路侧毫米波雷达数据分布不均匀、噪点较多,导致雷达在多目标跟踪方面准确性下降的问题,本文在密度峰值聚类(density peaks clustering,DPC)算法的基础上,提出一种适用于毫米波雷达数据改进的DPC算法。该方法结合匈牙利匹配算法和...为解决路侧毫米波雷达数据分布不均匀、噪点较多,导致雷达在多目标跟踪方面准确性下降的问题,本文在密度峰值聚类(density peaks clustering,DPC)算法的基础上,提出一种适用于毫米波雷达数据改进的DPC算法。该方法结合匈牙利匹配算法和无迹卡尔曼滤波算法(unscented Kalman filter,UKF),实现77 GHz毫米波雷达在不同车流密度路面上的跟踪验证。实验结果表明:改进后的DPC算法能够在大幅度提高毫米波雷达数据聚类精度的同时,有效提高多目标跟踪算法的跟踪精度。展开更多
基金supported by the National Natural Science Foundation of China (No.52205548)。
文摘To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-feature local difference.Firstly,an improved high-boost filter is used for preprocessing to eliminate background clutter and high-brightness interference,thereby increasing the probability of capturing real targets in the density peak search.Secondly,a triple-layer window is used to extract features from the area surrounding candidate targets,addressing the uncertainty of small target sizes.By calculating multi-feature local differences between the triple-layer windows,the problems of blurred target edges and low contrast are resolved.To balance the contribution of different features,intra-class distance is used to calculate weights,achieving weighted fusion of multi-feature local differences to obtain the weighted multi-feature local differences of candidate targets.The real targets are then extracted using the interquartile range.Experiments on datasets such as SIRST and IRSTD-IK show that the proposed method is suitable for various complex types and demonstrates good robustness and detection performance.
文摘Cluster-basedmodels have numerous application scenarios in vehicular ad-hoc networks(VANETs)and can greatly help improve the communication performance of VANETs.However,the frequent movement of vehicles can often lead to changes in the network topology,thereby reducing cluster stability in urban scenarios.To address this issue,we propose a clustering model based on the density peak clustering(DPC)method and sparrow search algorithm(SSA),named SDPC.First,the model constructs a fitness function based on the parameters obtained from the DPC method and deploys the SSA for iterative optimization to select cluster heads(CHs).Then,the vehicles that have not been selected as CHs are assigned to appropriate clusters by comprehensively considering the distance parameter and link-reliability parameter.Finally,cluster maintenance strategies are considered to tackle the changes in the clusters’organizational structure.To verify the performance of the model,we conducted a simulation on a real-world scenario for multiple metrics related to clusters’stability.The results show that compared with the APROVE and the GAPC,SDPC showed clear performance advantages,indicating that SDPC can effectively ensure VANETs’cluster stability in urban scenarios.
文摘AlAs/GaAs/In0.1Ga0.9As/GaAs/AlAs double-barrier resonant tunneling diodes （DBRTDs） grown on a semi-insulated GaAs substrate with molecular beam epitaxy is demonstrated. By sandwiching the In0.1 Ga0.9 As layer between GaAs layers, potential wells beside the two sides of barrier are deepened, resulting in an increase of the peak-to-valley current ratio （PVCR） and a peak current density. A special shape of collector is designed in order to reduce contact resistance and non-uniformity of the current;as a result the total chrrent density in the device is increased. The use of thin barriers is also helpful for the improvement of the PVCR and the peak current density in DBRTDs. The devices exhibit a maximum PVCR of 13.98 and a peak current density of 89kA/cm^2 at room temperature.
基金supported by the National Science Foundation for Distinguished Young Scholars of China(61225016)the State Key Program of National Natural Science of China(61533002)
文摘Modeling of energy consumption(EC) and effluent quality(EQ) are very essential problems that need to be solved for the multiobjective optimal control in the wastewater treatment process(WWTP). To address this issue, a density peaks-based adaptive fuzzy neural network(DP-AFNN) is proposed in this study. To obtain suitable fuzzy rules, a DP-based clustering method is applied to fit the cluster centers to process nonlinearity.The parameters of the extracted fuzzy rules are fine-tuned based on the improved Levenberg-Marquardt algorithm during the training process. Furthermore, the analysis of convergence is performed to guarantee the successful application of the DPAFNN. Finally, the proposed DP-AFNN is utilized to develop the models of EC and EQ in the WWTP. The experimental results show that the proposed DP-AFNN can achieve fast convergence speed and high prediction accuracy in comparison with some existing methods.
基金the National Natural Science Foundation of China(41925018,41874194).
文摘We report a simultaneous observation of two band electromagnetic ion cyclotron(EMIC)waves and toroidal Alfvén waves by the Van Allen Probe mission.Through wave frequency analyses,the mass densityρis found to be locally peaked at the magnetic equator.Perpendicular fluxes of ions(<100 eV)increase simultaneously with the appearances of EMIC waves,indicating a heating of these ions by EMIC waves.In addition,the measured ion distributions also support the equatorial peak formation,which accords with the result of the frequency analyses.The formation of local mass density peaks at the equator should be due to enhancements of equatorial ion concentrations,which are triggered by EMIC waves’perpendicular heating on low energy ions.
文摘This study deals with Peak of electron density in F2-layer sensibility scale during quiet time on solar minimum. Peaks of electron density in F2-layer (NmF2) values at the quietest days are compared to those carried out from the two nearest days (previous and following of quietest day). The study uses International Reference Ionosphere (IRI) for ionosphere modeling. The located station is Ouagadougou, in West Africa. Solar minimum of phase 22 is considered in this study. Using three core principles of ionosphere modeling under IRI running conditions, the study enables to carry out Peak of electron density in F2-layer values during the quietest days of the characteristic months for the four different seasons. These parameters are compared to those of the previous and the following of the quietest days (the day before and following each quietest selected day) at the same hour. The knowledge of NmF2 values at the quietest days and at the two nearest days enables to calculate the relative error that can be made on this parameter. This calculation highlights insignificant relative errors. This means that NmF2 values at the two nearest days of each quietest day on solar minimum can be used for simulating the quietest days’ behavior. NmF2 values obtained by running IRI model have good correlation with those carried out by Thermosphere-Ionosphere-Electrodynamics-General Circulation Model (TIEGCM).
基金Professor Hong Yu at Intelligent Fishery Innovative Team(No.C202109)in School of Information Engineering of Dalian Ocean University for her support of this workfunded by the National Natural Science Foundation of China(No.31800615 and No.21933010)。
文摘Performing cluster analysis on molecular conformation is an important way to find the representative conformation in the molecular dynamics trajectories.Usually,it is a critical step for interpreting complex conformational changes or interaction mechanisms.As one of the density-based clustering algorithms,find density peaks(FDP)is an accurate and reasonable candidate for the molecular conformation clustering.However,facing the rapidly increasing simulation length due to the increase in computing power,the low computing efficiency of FDP limits its application potential.Here we propose a marginal extension to FDP named K-means find density peaks(KFDP)to solve the mass source consuming problem.In KFDP,the points are initially clustered by a high efficiency clustering algorithm,such as K-means.Cluster centers are defined as typical points with a weight which represents the cluster size.Then,the weighted typical points are clustered again by FDP,and then are refined as core,boundary,and redefined halo points.In this way,KFDP has comparable accuracy as FDP but its computational complexity is reduced from O(n^(2))to O(n).We apply and test our KFDP method to the trajectory data of multiple small proteins in terms of torsion angle,secondary structure or contact map.The comparing results with K-means and density-based spatial clustering of applications with noise show the validation of the proposed KFDP.
基金supported by the National Natural Science Foundation of China(61401475)
文摘The key challenge of the extended target probability hypothesis density (ET-PHD) filter is to reduce the computational complexity by using a subset to approximate the full set of partitions. In this paper, the influence for the tracking results of different partitions is analyzed, and the form of the most informative partition is obtained. Then, a fast density peak-based clustering (FDPC) partitioning algorithm is applied to the measurement set partitioning. Since only one partition of the measurement set is used, the ET-PHD filter based on FDPC partitioning has lower computational complexity than the other ET-PHD filters. As FDPC partitioning is able to remove the spatially close clutter-generated measurements, the ET-PHD filter based on FDPC partitioning has good tracking performance in the scenario with more clutter-generated measurements. The simulation results show that the proposed algorithm can get the most informative partition and obviously reduce computational burden without losing tracking performance. As the number of clutter-generated measurements increased, the ET-PHD filter based on FDPC partitioning has better tracking performance than other ET-PHD filters. The FDPC algorithm will play an important role in the engineering realization of the multiple extended target tracking filter.
基金Supported by the National Science Foundation of China (40225011, 40336054)National Research Project (G2000078407)project of CAS (KZCX3-SW-217)International Collaboration Research Team Program of the Chinese Academy of Sciencesthe China-Russia Joint Research Center on Space WeatherChinese Academy of Sciences
文摘In this paper, using the MSISE-90 model as the reference atmosphere, we discuss the feasibility and method of deducing the peak densities of the undisturbed atomic oxygen profiles in the MLT region (the mesosphere and lower thermosphere region) from OI (557.7 nm) night airglow intersities. The peak densities for different seasons, latitudes and longitudes are deduced from OI (557.7nm) airglow intensities through this expression. We analyze the features of inversion relative errors and discuss the influence of the variations in temperature on inversion errors. The results indicate that all inversion errors are less than 5% except for those at high altitudes in the summer hemisphere. And the impact of the variations in temperature on errors is not significant.
文摘We present a novel unsupervised integrated score framework to generate generic extractive multi- document summaries by ranking sentences based on dynamic programming （DP） strategy. Considering that cluster-based methods proposed by other researchers tend to ignore informativeness of words when they generate summaries, our proposed framework takes relevance, diversity, informativeness and length constraint of sentences into consideration comprehensively. We apply Density Peaks Clustering （DPC） to get relevance scores and diversity scores of sentences simultaneously. Our framework produces the best performance on DUC2004, 0.396 of ROUGE-1 score, 0.094 of ROUGE-2 score and 0.143 of ROUGE-SU4 which outperforms a series of popular baselines, such as DUC Best, FGB [7], and BSTM [10].
基金Project supported by the National Natural Science Foundation of China (Key Program) (No.10332030)the Natural Science Foundation of Guangdong Province of China (No.04011640)
文摘The principal resonance of Duffing random external excitation was investigated. oscillator to combined deterministic and The random excitation was taken to be white noise or harmonic with separable random amplitude and phase. The method of multiple scales was used to determine the equations of modulation of amplitude and phase. The one peak probability density function of each of the two stable stationary solutions was calculated by the linearization method. These two one-peak-density functions were combined using the probability of realization of the two stable stationary solutions to obtain the double peak probability density function. The theoretical analysis are verified by numerical results.
基金supported by The Franco-Thai scholarship program and Development and Promotion of Science and Technology Talents Projectbeen carried out within the framework of the EUROfusion Consortium and has received funding from the Euratom research and training programme 2014-2018 under grant agreement No.633053。
文摘The impact of the E×B flow shear stabilization on particle transport and density peaking at JET is analyzed in the framework of integrated modelling with the CRONOS code.For that purpose,plasmas from a power scan which show a significant increasing of density peaking with the injected neutral beam injection power have been used as a modeling basis.By means of simulations with the quasilinear model GLF23 for the heat and particle transport,a strong link between the particle confinement and E×B flow shear stabilization is found.This is particularly important close to the pedestal region where the particle pinch direction becomes strongly inward for high E×B flow shear values.Such impact introduces some non-negligible deviation from the well-known collisonality dependence of the density peaking,whose general trend has been also obtained in the framework of this modelling by performing pedestal density scans.
基金The National Natural Science Foundation of China(No.61762031)The Science and Technology Major Project of Guangxi Province(NO.AA19046004)The Natural Science Foundation of Guangxi(No.2021JJA170130).
文摘There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of network data is usually paired with clustering algorithms to solve the community detection problem.Meanwhile, there is always an unpredictable distribution of class clusters outputby graph representation learning. Therefore, we propose an improved densitypeak clustering algorithm (ILDPC) for the community detection problem, whichimproves the local density mechanism in the original algorithm and can betteraccommodate class clusters of different shapes. And we study the communitydetection in network data. The algorithm is paired with the benchmark modelGraph sample and aggregate (GraphSAGE) to show the adaptability of ILDPCfor community detection. The plotted decision diagram shows that the ILDPCalgorithm is more discriminative in selecting density peak points compared tothe original algorithm. Finally, the performance of K-means and other clusteringalgorithms on this benchmark model is compared, and the algorithm is proved tobe more suitable for community detection in sparse networks with the benchmarkmodel on the evaluation criterion F1-score. The sensitivity of the parameters ofthe ILDPC algorithm to the low-dimensional vector set output by the benchmarkmodel GraphSAGE is also analyzed.
