Density Peaks Clustering Algorithm Research Articles

Density peaks clustering based on superior nodes and fuzzy correlation

The Density Peaks Clustering (DPC) algorithm is simple and efficient, but still has a few limitations. For example, DPC needs manual selection of clustering centers and may miss the correct cluster when searching for denser nearest neighbors, which may cause incorrect allocation of data points. To address these limitations, this work proposes a novel density peaks clustering algorithm based on superior nodes and fuzzy correlation (DPC-SNFC). Reverse nearest neighbors are used first to find the nearest point with a higher density as the superior node. Fuzzy correlation is then applied to construct connectivity subgraphs without using clustering centers. The connectivity subgraphs can identify the different clusters. Extensive experiments are conducted using 12 synthetic datasets and 10 real datasets and using 6 state-of-the-art baseline algorithms. The experimental results show that the proposed DPC-SNFC algorithm outperforms the baseline algorithms, which validates its efficiency.

ANN-DPC: Density peak clustering by finding the adaptive nearest neighbors

DPC(clustering by fast search and find of density peaks) is an efficient clustering algorithm. However, DPC and its variations usually cannot detect the appropriate cluster centers for a dataset containing sparse and dense clusters simultaneously, resulting in the unique clustering within a dataset cannot being found. To remedy these limitations, we propose an Adaptive Nearest Neighbor Density Peak Clustering algorithm, referred to as ANN-DPC. It introduces the adaptive nearest neighbors for a point, so as to define the accurate local density of the point. Moreover, it partitions points into super-score, core, linked and slave points, and proposes techniques to detect appropriate cluster centers through introducing super-core point with higher local density to absorb the other super-core points sharing adaptive nearest neighbors with it and the dependency vector for finding next cluster center. Furthermore, novel assignment strategies are proposed by leveraging the adaptive nearest neighbors combing with breadth first search and fuzzy weighted adaptive nearest neighbors, so as to assign non-center points to the most appropriate clusters. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of the proposed ANN-DPC algorithm over the counterparts in precisely detecting the cluster centers and the unique clustering within a dataset.

An Improved Density Peaks Clustering Algorithm Based On Density Ratio

Abstract Density peaks clustering (DPC) is a relatively new density clustering algorithm. It is based on the idea that cluster centers always have relatively high local densities and are relatively far from the points with higher densities. With the aforementioned idea, a decision graph can be drawn, and cluster centers will be chosen easily with the aid of the decision graph. However, the algorithm has its own weaknesses. Because the algorithm calculates local density and allocates points based on the distances between certain points, the algorithm has difficulty in classifying points into proper groups with varying densities or nested structures. This paper proposes an improved density peaks clustering algorithm called Dratio-DPC to overcome this weakness. First, Dratio-DPC adjusts the original local density with a coefficient calculated with the density ratio. Second, Dratio-DPC takes density similarity into consideration to calculate the distances between one point and other points with higher local densities. We design and perform experiments on different benchmark datasets and compare the clustering results of Dratio-DPC, traditional clustering algorithms and three improved DPC algorithms. Comparison results show that Dratio-DPC is effective and applicable to a wider range of scenarios.

A novel tree structure-based multi-prototype clustering algorithm

Density-peak clustering (DPC) is a novel clustering algorithm that has received much attention from researchers. Its principle is to identify the cluster center of the data by density and distance. However, the density-peak clustering algorithm still suffers from poor clustering results due to irrational choices of cluster centers and misallocating samples. To tackle these problems, a novel tree structure-based multi-prototype clustering algorithm (MPCTS) is proposed in this paper. Firstly, a division-merger method is adopted to divide the dataset into multiple peak clusters based on multi-prototype clustering, which could minimize the impact of high-density sample points on the subsequent sample point assignments. Secondly, the KNN nearest-neighbor search strategy is improved to quickly obtain the sub-cluster center in each peak cluster to overcome the defect of irrational selection of initial cluster centers. Afterward, a tree-based decay strategy is designed to evaluate the correlation between sample points, and a tree-based association strategy is designed to achieve the merging of multiple peak clusters to tackle the sample points misallocation problem. Finally, the extensive experiments on clustering task are conducted over several benchmark synthetic and real datasets to verify the efficiency and superiority of the proposed MPCTS.

User profiling for Chinese super-new generation wine consumers based on improved density peak clustering algorithm

PurposeFor a better understanding of the preferences and differences of young consumers in emerging wine markets, this study aims to propose a clustering method to segment the super-new generation wine consumers based on their sensitivity to wine brand, origin and price and then conduct user profiles for segmented consumer groups from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences.Design/methodology/approachWe first proposed a consumer clustering perspective based on their sensitivity to wine brand, origin and price and then conducted an adaptive density peak and label propagation layer-by-layer (ADPLP) clustering algorithm to segment consumers, which improved the issues of wrong centers' selection and inaccurate classification of remaining sample points for traditional DPC (DPeak clustering algorithm). Then, we built a consumer profile system from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences for segmented consumer groups.FindingsIn this study, 10 typical public datasets and 6 basic test algorithms are used to evaluate the proposed method, and the results showed that the ADPLP algorithm was optimal or suboptimal on 10 datasets with accuracy above 0.78. The average improvement in accuracy over the base DPC algorithm is 0.184. As an outcome of the wine consumer profiles, sensitive consumers prefer wines with medium prices of 100–400 CNY and more personalized brands and origins, while casual consumers are fond of popular brands, popular origins and low prices within 50 CNY. The wine sensory attributes preferred by super-new generation consumers are red, semi-dry, semi-sweet, still, fresh tasting, fruity, floral and low acid.Practical implicationsYoung Chinese consumers are the main driver of wine consumption in the future. This paper provides a tool for decision-makers and marketers to identify the preferences of young consumers quickly which is meaningful and helpful for wine marketing.Originality/valueIn this study, the ADPLP algorithm was introduced for the first time. Subsequently, the user profile label system was constructed for segmented consumers to highlight their characteristics and demand partiality from three aspects: demographic characteristics, consumers' eating habits and consumers' preferences for wine attributes. Moreover, the ADPLP algorithm can be considered for user profiles on other alcoholic products.

Fuzzy Regional Co-Location Pattern Mining Based on Efficient Density Peak Clustering and Maximal Fuzzy Grid Cliques

Due to the heterogeneity of data distribution in real life and the spatial autocorrelation among spatial instances, traditional spatial co-location pattern mining methods tend to ignore valuable information specific to local regions. To address the limitation, regional co-location pattern mining has been proposed to find patterns that may be hidden within local regions. In this paper, a fuzzy regional co-location pattern mining framework based on efficient density peak clustering and maximal fuzzy grid cliques is presented. By incorporating a grid-splitting method and fuzzy theory, an efficient density peak clustering algorithm is proposed to divide the global area into distinct local regions. Furthermore, we propose a method to materialize the neighbor relationships between instances based on the maximal fuzzy grid cliques, and parallelize the clustering process to improve the algorithm efficiency. Experimental results show that the proposed algorithm can not only reduce the time consumption by about 40%, but also mine meaningful patterns with tighter instance distributions.

Multi-scale fusion public gathering recognition based on residual network

With the rapid economic development and high concentration of urban population, people’s income level and quality of life continue to improve, resulting in more and more crowded scenes caused by people going out. Especially in urban commercial centers, transportation hubs, sports venues during important events, tourist attractions, etc., crowd gatherings occur frequently. However, accidents involving crowd gatherings in public places occur frequently, causing heavy casualties and property losses. Therefore, for crowd recognition, this paper proposes a new method to accurately estimate the number of dense crowds. In this method, a density map with accurate pedestrian locations is first generated using the focal inverse distance transform and used as ground truth labels for network training. Then, a multi-scale feature fusion algorithm based on residual network is designed, combining spatial and channel attention mechanisms to improve the accuracy and stability of crowd density estimation. In dense crowds, the phenomenon of overlapping and occlusion of people is very common and serious, making it difficult for existing pedestrian detection methods to distinguish each individual and accurately count the flow of people. To solve this problem, this paper proposes a density map-based method that uses a local maximum detection strategy and a K-nearest neighbor algorithm to convert the density map into the corresponding dense head bounding box. This method can effectively reduce the impact of occlusion and improve the accuracy of people counting. In order to further improve the estimation accuracy, a pattern recognition density peak clustering algorithm is introduced to study the clustered crowds. By treating the head bounding box as an element point, the distance between each element point is calculated, and the density of each point is calculated. Then perform clustering to find the cluster center with the highest density in each class. Finally, by comparing the density of each cluster center with the corresponding density threshold and adopting the corresponding decision-making method, the accuracy of people counting is further improved.

Advancing 6G-IoT networks: Willow catkin packet transmission scheduling with AI and bayesian game-theoretic approach-based resource allocation.

The rapid expansion of mobile broadband networks and the proliferation of Internet of Things (IoT) applications have substantially increased data transmission and processing demands. However, the application domains of IoT-enabled models often face resource limitations, requiring rapid responses, low latency, and large bandwidth, surpassing their inherent capabilities. To address these challenges, we propose a fishnet approach-based packet scheduling and resource allocation system, termed Fishnet-6G, to optimize network resource allocation in the proposed 6G networks. Initially, we constructed a Sierpinski Triangle-based network in a 6G-IoT environment, enhancing device connectivity. We utilize the Quantum Density Peak Clustering (QDPC) algorithm to perform clustering for IoT devices, establishing Cluster Head (CH) and Substitute CH (SUB CH) based on actual metrics. Furthermore, traffic prediction is achieved through two processes, grouping, and fair queue status, using the Improved Deep Deterministic Policy Gradient (IMPDDPG) algorithm with a variable sampling rate, resulting in well-organized packet scheduling. Subsequently, we perform optimal packet scheduling by employing the Willow Catkin Optimization (WCO) algorithm, and the scheduled packets are managed within a Fishing Net Topology to reduce energy consumption and system complexity. Finally, we allocate the scheduled packets to the desired resource blocks using the Bayesian Game-Theoretic Approach (BGTA). The proposed approach is implemented using Network Simulator-3.26, and the performance of the Fishnet-6G model is evaluated based on time, transmission rate, energy efficiency, average throughput, latency, and Packet loss rate. Numerical analysis demonstrates that Fishnet-6G outperforms existing approaches across these metrics, showcasing its effectiveness in addressing the challenges of 6G-IoT networks.

Fast Automatic Fuzzy C-Means Knitting Pattern Color-Separation Algorithm Based on Superpixels.

Patterns entered into knitting CAD have thousands or tens of thousands of different colors, which need to be merged by color-separation algorithms. However, for degraded patterns, the current color-separation algorithms cannot achieve the desired results, and the clustering quantity parameter needs to be managed manually. In this paper, we propose a fast and automatic FCM color-separation algorithm based on superpixels, which first uses the Real-ESRGAN blind super-resolution network to clarify the degraded patterns and obtain high-resolution images with clear boundaries. Then, it uses the improved MMGR-WT superpixel algorithm to pre-separate the high-resolution images and obtain superpixel images with smooth and accurate edges. Subsequently, the number of superpixel clusters is automatically calculated by the improved density peak clustering (DPC) algorithm. Finally, the superpixels are clustered using fast fuzzy c-means (FCM) based on a color histogram. The experimental results show that not only is the algorithm able to automatically determine the number of colors in the pattern and achieve the accurate color separation of degraded patterns, but it also has lower running time. The color-separation results for 30 degraded patterns show that the segmentation accuracy of the color-separation algorithm proposed in this paper reaches 95.78%.

A Fast Granular-Ball-Based Density Peaks Clustering Algorithm for Large-Scale Data.

Density peaks clustering algorithm (DP) has difficulty in clustering large-scale data, because it requires the distance matrix to compute the density and δ -distance for each object, which has O(n2) time complexity. Granular ball (GB) is a coarse-grained representation of data. It is based on the fact that an object and its local neighbors have similar distribution and they have high possibility of belonging to the same class. It has been introduced into supervised learning by Xia et al. to improve the efficiency of supervised learning, such as support vector machine, k -nearest neighbor classification, rough set, etc. Inspired by the idea of GB, we introduce it into unsupervised learning for the first time and propose a GB-based DP algorithm, called GB-DP. First, it generates GBs from the original data with an unsupervised partitioning method. Then, it defines the density of GBs, instead of the density of objects, according to the centers, radius, and distances between its members and centers, without setting any parameters. After that, it computes the distance between the centers of GBs as the distance between GBs and defines the δ -distance of GBs. Finally, it uses GBs' density and δ -distance to plot the decision graph, employs DP algorithm to cluster them, and expands the clustering result to the original data. Since there is no need to calculate the distance between any two objects and the number of GBs is far less than the scale of a data, it greatly reduces the running time of DP algorithm. By comparing with k -means, ball k -means, DP, DPC-KNN-PCA, FastDPeak, and DLORE-DP, GB-DP can get similar or even better clustering results in much less running time without setting any parameters. The source code is available at https://github.com/DongdongCheng/GB-DP.

Optimization of Density Peak Clustering Algorithm Based on Improved Black Widow Algorithm.

Clustering is an unsupervised learning method. Density Peak Clustering (DPC), a density-based algorithm, intuitively determines the number of clusters and identifies clusters of arbitrary shapes. However, it cannot function effectively without the correct parameter, referred to as the cutoff distance (dc). The traditional DPC algorithm exhibits noticeable shortcomings in the initial setting of dc when confronted with different datasets, necessitating manual readjustment. To solve this defect, we propose a new algorithm where we integrate DPC with the Black Widow Optimization Algorithm (BWOA), named Black Widow Density Peaks Clustering (BWDPC), to automatically optimize dc for maximizing accuracy, achieving automatic determination of dc. In the experiment, BWDPC is used to compare with three other algorithms on six synthetic data and six University of California Irvine (UCI) datasets. The results demonstrate that the proposed BWDPC algorithm more accurately identifies density peak points (cluster centers). Moreover, BWDPC achieves superior clustering results. Therefore, BWDPC represents an effective improvement over DPC.

Optimal Capacity Configuration of Pumped-Storage Units Used to Retrofit Cascaded Hydropower Stations

As flexible resources, cascaded hydropower stations can regulate the fluctuations caused by wind and photovoltaic power. Constructing pumped-storage units between two upstream and downstream reservoirs is an effective method to further expand the capacity of flexible resources. This method transforms cascaded hydropower stations into a cascaded pumped-hydro-energy storage system. In this paper, a flexibility reformation planning model of cascaded hydropower stations retrofitted with pumped-storage units under a hybrid system composed of thermal, wind, and photovoltaic power is established with the aim of investigating the optimal capacity of pumped-storage units. First, a generative adversarial network and a density peak clustering algorithm are utilized to generate typical scenarios to deal with the seasonal fluctuation of renewable energy generation, natural water inflow, and loads. Then, a full-scenario optimization method is proposed to optimize the operation costs of multiple scenarios considering the variable-speed operation characteristics of pumped storage and to obtain a scheme with better comprehensive economy. Meanwhile, the proposed model is retransformed into a mixed-integer linear programming problem to simplify the solution. Case studies in Sichuan province are used to demonstrate the effectiveness of the proposed model.

Molecular-Clump Detection Based on an Improved YOLOv5 Joint Density Peak Clustering

The detection and analysis of molecular clumps can lead to a better understanding of star formation in the Milky Way. Herein, we present a molecular-clump-detection method based on improved YOLOv5 joint Density Peak Clustering (DPC). The method employs a two-dimensional (2D) detection and three-dimensional (3D) stitching strategy to accomplish the molecular-clump detection. In the first stage, an improved YOLOv5 is used to detect the positions of molecular clumps on the Galactic plane, obtaining their spatial information. In the second stage, the DPC algorithm is used to combine the detection results in the velocity direction. In the end, the clump candidates are positioned in the 3D position-position-velocity (PPV) space. Experiments show that the method can achieve a high recall of 98.41% in simulated data made up of Gaussian clumps added to observational data. The efficiency of the strategy has also been demonstrated in experiments utilizing observational data from the Milky Way Imaging Scroll Painting (MWISP) project.

Soft Sensor Modeling Method for the Marine Lysozyme Fermentation Process Based on ISOA-GPR Weighted Ensemble Learning.

Due to the highly nonlinear, multi-stage, and time-varying characteristics of the marine lysozyme fermentation process, the global soft sensor models established using traditional single modeling methods cannot describe the dynamic characteristics of the entire fermentation process. Therefore, this study proposes a weighted ensemble learning soft sensor modeling method based on an improved seagull optimization algorithm (ISOA) and Gaussian process regression (GPR). First, an improved density peak clustering algorithm (ADPC) was used to divide the sample dataset into multiple local sample subsets. Second, an improved seagull optimization algorithm was used to optimize and transform the Gaussian process regression model, and a sub-prediction model was established. Finally, the fusion strategy was determined according to the connectivity between the test samples and local sample subsets. The proposed soft sensor model was applied to the prediction of key biochemical parameters of the marine lysozyme fermentation process. The simulation results show that the proposed soft sensor model can effectively predict the key biochemical parameters with relatively small prediction errors in the case of limited training data. According to the results, this model can be expanded to the soft sensor prediction applications in general nonlinear systems.

SFKNN-DPC: Standard deviation weighted distance based density peak clustering algorithm

DPC (Clustering by fast search and find of Density Peaks) algorithm and its variations typically employ Euclidean distance, overlooking the diverse contributions of individual feature to similarity and subsequent clustering. To address this limitation, the standard deviation weighted distance is proposed in this paper to enhance the Euclidean distance. This weighted distance takes into account the specific contribution of each feature to the distance (similarity) between data points. By utilizing this weighted distance, the local density ρi and distance δi of point i are defined, thereby capturing the local pattern of point i to the fullest extent possible. Outliers are defined using this innovative weighted distance. The divide and conquer assignment strategy is proposed based on this proposed weighted distance and the semi-supervised learning and the mutual K-nearest neighbor assumption. Consequently, the SFKNN-DPC (Standard deviation weighted distance and Fuzzy weighted K-Nearest Neighbors based Density Peak Clustering) algorithm is proposed, aiming to effectively uncover the hidden clusters within a dataset. Extensive experiments conducted on benchmark datasets demonstrate the superiority of SFKNN-DPC over DPC, its variations, and other benchmark clustering algorithms. Moreover, statistical significance tests indicate that SFKNN-DPC exhibits notable differences when compared to its counterparts.

Density peaks clustering algorithm with connected local density and punished relative distance

Density peaks clustering algorithm with connected local density and punished relative distance

Density peak clustering based on improved dung beetle optimization and mahalanobis metric

The density peak clustering algorithm (DPC) quickly divides each cluster based on high-density peak points and shows better clustering performance. In order to address the issue that the local density is constrained by the preset cut-off distance in DPC and the Euclidean distance cannot capture the possible correlation between different features, a DPC algorithm based on improved dung beetle optimization (IDBO) and Mahalanobis metric is proposed, called IDBO-MDDPC. The IDBO algorithm enhances the ball dung beetle individual by incorporating nonlinear dynamic factors to increase the search and development capabilities of the algorithm and by incorporating an adaptive cosine wave inertial weight strategy to more precisely determine the optimal position of the thief dung beetle in order to improve the convergence speed and accuracy of the algorithm. The IDBO algorithm is simulated on eight benchmark functions, and the results demonstrate that it is superior to other comparison algorithms in terms of convergence speed and accuracy. In the DPC algorithm, the Mahalanobis metric is used to capture the correlation between features to improve clustering performance. The IDBO algorithm is integrated with the DPC algorithm, and the F-Measure evaluation index is used to design the objective function so that the optimal value of the cut-off distance can be automatically selected. In order to evaluate the efficiency of the algorithm, three sets of artificially synthesized datasets and five sets of UCI standard datasets were chosen for studies. Experimental results show that the IDBO-MDDPC algorithm can automatically determine a better cut-off distance value and ensure higher clustering accuracy.

Fast density peaks clustering algorithm based on improved mutual K-nearest-neighbor and sub-cluster merging

Density peaks clustering (DPC) has had an impact in many fields, as it can quickly select centers and effectively process complex data. However, it also has low operational efficiency and a “Domino” effect. To solve these defects, we propose a fast density peaks clustering algorithm based on improved mutual K-nearest-neighbor and sub-cluster merging (KS-FDPC). The new algorithm adopts a partitioning-merging strategy. By dividing the data into multiple sub-clusters, the impact range of high-density points on subsequent allocation points can be reduced. And the fast nearest neighbors search improves the speed of DPC. In the experiment, KS-FDPC is used to compare with eight improved DPC algorithms on eight synthetic data and eight UCI data. The results indicate that the overall clustering performance of KS-FDPC is superior to other algorithms. Moreover, KS-FDPC runs faster than other algorithms. Therefore, KS-FDPC is an effective improvement of DPC.

Efficient Density-peaks Clustering Algorithms on Static and Dynamic Data in Euclidean Space

Clustering multi-dimensional points is a fundamental task in many fields, and density-based clustering supports many applications because it can discover clusters of arbitrary shapes. This article addresses the problem of Density-Peaks Clustering (DPC) in Euclidean space. DPC already has many applications, but its straightforward implementation incurs O ( n 2 ) time, where n is the number of points, thereby does not scale to large datasets. To enable DPC on large datasets, we first propose empirically efficient exact DPC algorithm, Ex-DPC. Although this algorithm is much faster than the straightforward implementation, it still suffers from O ( n 2 ) time theoretically. We hence propose a new exact algorithm, Ex-DPC++, that runs in o ( n 2 ) time. We accelerate their efficiencies by leveraging multi-threading. Moreover, real-world datasets may have arbitrary updates (point insertions and deletions). It is hence important to support efficient cluster updates. To this end, we propose D-DPC for fully dynamic DPC. We conduct extensive experiments using real datasets, and our experimental results demonstrate that our algorithms are efficient and scalable.

A method for constructing word sense embeddings based on word sense induction

Polysemy is an inherent characteristic of natural language. In order to make it easier to distinguish between different senses of polysemous words, we propose a method for encoding multiple different senses of polysemous words using a single vector. The method first uses a two-layer bidirectional long short-term memory neural network and a self-attention mechanism to extract the contextual information of polysemous words. Then, a K-means algorithm, which is improved by optimizing the density peaks clustering algorithm based on cosine similarity, is applied to perform word sense induction on the contextual information of polysemous words. Finally, the method constructs the corresponding word sense embedded representations of the polysemous words. The results of the experiments demonstrate that the proposed method produces better word sense induction than Euclidean distance, Pearson correlation, and KL-divergence and more accurate word sense embeddings than mean shift, DBSCAN, spectral clustering, and agglomerative clustering.