Adaptive Clustering Method Research Articles

Fully automatic operational modal analysis method based on statistical rule enhanced adaptive clustering method

Timely monitoring of modal parameters is commonly adopted to keep in-service bridges safe. For fulfilling the demand, plenty of operational modal analysis (OMA) methods were developed in which only the structural response needs to be measured. However, when utilizing these methods, there are still some deficiencies, like mingled spurious modes and the hyper-parameters needing manual tuning. Although many studies have utilized clustering algorithms to solve these issues and promote the automatic level of the OMA method, some new hyper-parameters belonging to these algorithms would be introduced as well, which also need manual maneuvering. Meanwhile, the performance of various clustering algorithms on this issue also shows variety due to their distinct inductive biases. As a result, the prerequisite of relevant expertise still hinders the common users in their extraction and tracking of the bridge’s modal information. Under these circumstances, after conducting a comparison among representative clustering algorithms, this study proposed an applicable fully automatic OMA method by an adaptive clustering method, “K-average nearest neighbor density-based spatial clustering of applications with noise (KANN-DBSCAN)” enhanced by the five-number summary. This method’s performance was investigated via numerical analyses and the measured data from an actual bridge. The results illustrated that this method functions well in the tested scenarios and has the potential for wide application in actual engineering.

Low distortion and adaptive image steganography by enhancing DBSCAN, Sobel operator, and XOR coding

Image steganography is concealing digital messages in an image in a matter that the secret data is not revealed. An effective practice to reduce the variations between the cover and stego images is to hide the secret data in the edge areas. The clustering approach can be applied to detect the edge pixels of the cover image. DBSCAN is a density-based clustering algorithm and is applicable for this purpose. This algorithm, however, may fail to detect edge areas if its parameters are not tuned properly. Furthermore, to reduce the distortion of the stego image, coding techniques should be applied in the data embedding process. The existing coding schemes have low performance and there is still scope for improvement and to propose more promising approaches. In this paper, we propose an effective edge-based image steganography algorithm. The proposed method convolves the cover image using an enhanced Sobel operator prior to edge detection. This approach places more emphasis on the edge pixels. For detecting edge areas, an adaptive clustering method based on the DBSCAN algorithm is proposed, which adjusts its sensitivity against edge pixels according to the cover image structure and message size. As opposed to the traditional DBSCAN, this method is adaptive and can adjust the values of parameters dynamically. Additionally, a novel enhanced XOR coding technique for message concealment which reduces the variations of the edge pixels to 12.5%, is proposed. The experimental results demonstrate that the proposed method improves PSNR and wPSNR by 3.98db and 2.18db compared to other state-of-the-art schemes.

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Point cloud local feature extraction places an important part of point cloud deep learning neural networks. Accurate extraction of point cloud features is still a challenge for deep learning networks. Oversampling and feature loss of point cloud model are important problems in the accuracy of image point cloud deep learning network. In this paper, we propose an adaptive clustering method for point cloud feature extraction—adaptive optimal means clustering (AOMC)—and apply it to point cloud deep learning network tasks. This method solves the problem of determining the number of clustering centers in the process of point cloud feature extraction so that the feature points contain the whole point cloud model and avoid the problem of losing detail features. Specifically, according to the loss characteristics of point cloud clustering, AOMC selects a different number of clustering centers for various models. Moreover, in light of the density distribution of the point cloud, the radius of the clustering subset is determined. This method effectively improves the accuracy of the point cloud deep learning network on object classification and parts segmentation. Our method reaches demand on Modelnet10 and shapenetcore_partanno_segmentation_benchmark datasets. In terms of deep learning network optimization, it has good performance. Additionally, our method has high accuracy and low algorithm complexity.

Application of big data adaptive semi-supervised clustering method based on deep learning

In order to solve the problems of high computational complexity, poor dimensionality reduction, and reduced clustering effect when the clustering task faces a large amount of big data, the application of a large data adaptive semi-supervised clustering method based on deep learning is proposed. Through the self-encoder of the deep clustering network, the analysis of the confrontation network is generated, and the semi-supervised deep clustering algorithm and algorithm of the adaptive strategy are optimized. Through the encoder layer structure of the deep coding network, different parameters are set for all data sets for algorithm experimental analysis. The results show that the data obtained by this method is faster, more accurate and more optimized than the traditional clustering method, which proves the effectiveness of the method.

Adaptive neuro-fuzzy clustering of distorted data based on prototype-centroid strategy using evolutionary procedures

The problem of clustering is a very relevant area in Data Mining of different nature. To solve this problem, there are a large number of known methods and algorithms, most of which work in batch mode, in conditions when the entire of data set is known in advance and does not change over the time. These methods are complex in software implementa-tion and are not without drawbacks. The aim of the work is to develop an adaptive neuro-fuzzy clustering method of distorted data based on proto-type-centroid strategy using evolutionary procedures, that solves the problem in online mode, when data are fed se-quentially in real time and is characterized by numerical simplicity and high speed. The problem of adaptive fuzzy clustering of distorted data by outliers and emissions, which are presented in the form of vector arrays, based on the strategy of the nearest prototype - centroid using evolutionary procedures, is con-sidered. The proposed approach is based on the online probabilistic fuzzy clustering procedure with the membership function of special type and the evolutionary cat swarm algorithm. Proposed adaptive neuro-fuzzy clustering method of distorted data based on prototype-centroid strategy using evolutionary procedures characterized by computational simplicity, high speed and accuracy of the results based on experimental studies. The modification of optimization procedure that based on cat swarm algorithm was propose. The proposed method is simple in numerical implementation, workable in the case when the data is distorted and are fed sequentially in online mode, that is confirmed experimentally.

A Reinforcement Learning-Based Dynamic Clustering Algorithm for Compressive Data Gathering in Wireless Sensor Networks

Compressive data gathering (CDG) is an effective technique to handle large amounts of data transmissions in resource-constrained wireless sensor networks (WSNs). However, CDG with static clustering cannot adapt to time-varying environments in WSNs. In this paper, a reinforcement learning-based dynamic clustering algorithm (RLDCA) for CDG in WSNs is proposed. It is a dynamic and adaptive clustering method aiming to further reduce data transmissions and energy consumption in WSNs. Sensor nodes act as reinforcement learning (RL) agents which can observe the environment and dynamically select a cluster to join in. These RL agents are instructed by a well-designed reward scheme to join a cluster with strong data correlation and proper distance. It is also a distributed and lightweight learning method. All agents are independent and operate in parallel. Additional overheads introduced by RL are lightweight. Computations of a linear reward function and a few comparison operations are needed. It is implementable in WSNs. Simulations performed in MATLAB validate the effectiveness of the proposed method and simulation results show that the proposed algorithm achieves the desired effect as well as fine convergence. It decreases data transmissions by 16.6% and 54.4% and energy consumption by 6% and 29%, respectively, compared to the two contrastive schemes.

Subgroup-specific dose finding for phase I-II trials usingBayesian clustering.

In most models and algorithms for dose‐finding clinical trials, it is assumed that the trial participants are homogeneous—the optimal dose is the same for all those who qualify for the trial. However, if there are heterogeneous populations who may benefit from the same treatment, it is inefficient to conduct dose‐finding separately for each group, and assuming homogeneity across all subpopulations may lead to identification of the incorrect dose for some (or all) subgroups. To accommodate heterogeneity in dose‐finding trials when both efficacy and toxicity outcomes must be used to identify the optimal dose (as in immunotherapeutic oncology treatments), we utilize an adaptive Bayesian clustering method which borrows strength among similar subgroups and clusters truly homogeneous subgroups. Unlike methodology already described in the literature, our proposed methodology does not require the assumption of exchangeability between subgroups or a priori ordering of subgroups, but does allow for specification of different subgroup‐specific priors if prior information is available. We provide a comparison of operating characteristics between our method and Bayesian hierarchical models for subgroups in a variety of relevant scenarios. After simulation studies with four a priori subgroups, we observed that our method and the hierarchical models both outperform separate subgroup‐specific models when all subgroups have the same dose‐efficacy and dose‐toxicity curves. However, our method outperforms hierarchical models when one subgroup has a different dose‐efficacy or dose‐toxicity curve from the other three subgroups.

A structure similarity based adaptive sampling method for time-dependent graph embedding

Time-dependent graphs have been well researched in a wealth of fields, such as road network, bioinformatics network. Unlike in static graphs, relations among nodes will change by time in time-dependent graphs, which causes some for such special properties as temporal reachability and node dynamic local structure. And, for different kinds of time-dependent graphs, activity frequency of nodes may be greatly different. These properties should be taken into consideration while embedding nodes in time-dependent graphs into vectors for further research. So, in this work, we study the problem of time-dependent graph embedding and propose a structure similarity based adaptive sampling method, called ATDGEB (Adaptive Time-Dependent Graph Embedding), which aims to encode different kinds of time-dependent graph nodes into vectors based on node’s local structure and their special properties. Specifically, we first design a new method based on node’s local structure to compute visit probability between nodes, and then propose an adaptive clustering method for solving the problem that nodes’ active frequency is greatly different in different types of time-dependent graph. Meanwhile to get the walk paths as soon as possible, we design a novel walk strategy to get node’s walk paths. The sampled nodes in walk process will be stored in bidirectional multi-tree. Once the walk process is finished, we can get node’s walk path by reversely travelling​ the multi-tree from leaf nodes in the tree. Sufficient experiments conducted on real datasets demonstrate that our method outperforms the existing embedding methods with respect to node clustering, reachability prediction, and link prediction.

Subspace Decomposition Based Adaptive Density Peak Clustering for Radar Signals Sorting

Radar signal sorting (RSS) plays an important role in the electronic support measurement system. However, the existing clustering-based RSS methods depend heavily on prior knowledge to achieve excellent performance, which may bring severe challenges to RSS in actual scenarios. This letter proposes a novel subspace decomposition based adaptive density peak clustering (SD-ADPC) method to address the problems of low accuracy and high computational cost in RSS. First, the original complex radar signal data is directly decomposed into two-dimensional (2D) subspace by t-distributed random neighborhood embedding (t-SNE). Then, based on the outlier detection of the products between the peak density and the distance of the data points, ADPC is used to adaptively determine the optimal clustering centers of the original data in 2D subspace. Finally, the reminding data is assigned to its nearest cluster with Euclidean distance in one step. The experimental results of the simulated RSS dataset and the open baselines show that our proposed method does not require any knowledge and can achieve better or competitive performance in terms of accuracy and computational cost, compared to existing state-of-the-art methods.

Transferable network with Siamese architecture for anomaly detection in hyperspectral images

The purpose of hyperspectral anomaly detection is to distinguish abnormal objects from the surrounding background. In actual scenes, however, the complexity of ground objects, the high-dimensionality of data and the non-linear correlation of bands have high requirements for the generalizability, feature extraction ability and nonlinear expression ability of anomaly detection algorithms. In order to address the above problems, we propose a transferable network with Siamese architecture for hyperspectral image anomaly detection (TSN-HAD). The contribution of TSN-HAD is three-fold. First, we address the anomaly detection problem through similarity metric evaluation. The similarity scores are estimated with the proposed Siamese network, which is able to identify pixels that deviate from the neighboring pixels. Second, a spectral-angle-based contrastive constraint is proposed to compel the network to extract more discriminative features, which can enhance the generalizability of the network effectively. Third, to enhance the transfer capability of the network, an unsupervised adaptive clustering method is employed to fine-tune the network with pseudo-labels learned from the test image without any prior knowledge. Comparisons with the state-of-the-art methods on multiple datasets demonstrate the excellence of the proposed method.

A New Density-Based Clustering Method Considering Spatial Distribution of Lidar Point Cloud for Object Detection of Autonomous Driving

Lidar is a key sensor of autonomous driving systems, but the spatial distribution of its point cloud is uneven because of its scanning mechanism, which greatly degrades the clustering performance of the traditional density-based spatial clustering of application with noise (DSC). Considering the outline feature of detected objects for intelligent vehicles, a DSC-based adaptive clustering method (DAC) is proposed with the adoption of an elliptic neighborhood, which is designed according to the distribution properties of the point cloud. The parameters of the ellipse are adaptively adjusted with the location of the sample point to deal with the uniformity of points in different ranges. Furthermore, the dependence among different parameters of DAC is analyzed, and the parameters are numerically optimized with the KITTI dataset by considering comprehensive performance. To verify the effectiveness, a comparative experiment was conducted with a vehicle equipped with three IBEO LUX8 lidars on campus, and the results show that compared with DSC using a circular neighborhood, DAC has a better clustering performance and can notably reduce the rate of over-segmentation and under-segmentation.

An objective reduction method based on advanced clustering for many-objective optimization problems and its human-computer interaction visualization of pareto front

Many-objective optimization problems(MaOPs) are the most challenging problems among multi-objective optimization problems (MOPs). Objective reduction method has become one of the most important technique for MaOPs which can alleviate the difficulties of selection pressure, computational cost and the human-computer interaction visualization. In this paper, we propose an objective reduction algorithm based on adaptive propagating tree clustering for MaOPs. The advanced adaptive clustering method makes the number of clusters determined adaptively, and outliers can be clustered correctly. According to the clustering result, the algorithm uses an adaptive objective aggrega tion method which can preserve the structure of the original problem as much as possible. The algorithm is suitable for dealing with MaOPs with irregular shape of sample sets, and can improve the friendliness of human-computer interaction visualization of Pareto Front. Compared with different types of classical many-objective optimization algorithms, the simulation results of our algorithm has considerable advantages.

Brain tumor grade identification using deep Elman neural network with adaptive fuzzy clustering-based segmentation approach

A brain tumor is a collection of anomalous evolution of harmful and unnecessary nerve cells in the brain. For advanced treatment, it is essential to categorize the tumors from the MRI (magnetic resonance imaging). In this paper, develop the adaptive fuzzy Tsallis entropy (FTE) clustering with the improved cuckoo search optimization (ICS) procedure, and the effective feature selection mechanism is proposed in this paper. Initially, the input MRI is pre-processed using the anisotropic diffusion filter and non-parametric region-based techniques to eliminate noise removal and skull stripping. After that, the tumor regions are segmented using the adaptive FTE clustering method with the ICS algorithm. The robust features are attained using the first-order statistical, discrete wavelet transform (DWT), the histogram of oriented gradients (HOG), and intensity histogram. After that, the set of optimal features are selected from the mined features using the black widow optimization (BWO) algorithm in the feature selection (FS) process. Finally, a deep Elman neural network (DENN) structure is utilized to categorize the grade of brain tumor. The suggested approach is simulated using the Matlab environment using the BRATS 2012, BRATS 2019 and BRATS 2020 datasets. The different performances are evaluated, and it is related to other existing classifiers and other approaches. The simulation results verified that the accuracy of developed approach is 99.8% for BRATS 2012, 98.7% for BRATS 2019 and 98% for BRATS 2020 as compared to other classifiers and other existing approaches.

Crop Row Segmentation and Detection in Paddy Fields Based on Treble-Classification Otsu and Double-Dimensional Clustering Method

Visual navigation is developing rapidly and is of great significance to improve agricultural automation. The most important issue involved in visual navigation is extracting a guidance path from agricultural field images. Traditional image segmentation methods may fail to work in paddy field, for the colors of weed, duckweed, and eutrophic water surface are very similar to those of real rice seedings. To deal with these problems, a crop row segmentation and detection algorithm, designed for complex paddy fields, is proposed. Firstly, the original image is transformed to the grayscale image and then the treble-classification Otsu method classifies the pixels in the grayscale image into three clusters according to their gray values. Secondly, the binary image is divided into several horizontal strips, and feature points representing green plants are extracted. Lastly, the proposed double-dimensional adaptive clustering method, which can deal with gaps inside a single crop row and misleading points between real crop rows, is applied to obtain the clusters of real crop rows and the corresponding fitting line. Quantitative validation tests of efficiency and accuracy have proven that the combination of these two methods constitutes a new robust integrated solution, with attitude error and distance error within 0.02° and 10 pixels, respectively. The proposed method achieved better quantitative results than the detection method based on typical Otsu under various conditions.

Outlier Detection Method based on Adaptive Clustering Method and Density Peak

The outlier detection technique is widely used in the data analysis for the clustering of data. Many techniques have been applied in the outlier detection to increase the efficiency of the data analysis. The Local Projection based Outlier Detection (LPOD) method effectively identifies neighbouring values of data, but this has the drawback of random selection of the cluster centre that affects the overall clustering performance of the system. In this study, the Adaptive Clustering by Fast Search and Find of Density Peak (ACFSFDP) is proposed to select the clustering centre and density peak. This ACFSFDP method is implemented with the min-max algorithm to find the number of categories that measured the local density and distance information. The density and distance are used to select the cluster centre, but density is not calculated on the existing distance based clustering techniques. The ACFSFDP method calculates cluster centre based on the density and distance during the clustering process, whereas the existing techniques randomly select the data centre. The results indicated that the ACFSFDP method is provided effective outlier detection compared with existing Clustering by Fast Search and Find of Density Peak (CFSFDP) methods. The ACFSFDP is tested on two datasets Pen-digits and waveform datasets. The experiment results proved that Area Under Curve (AUC) of the ACFSFDP is 99.08% on the Pen-Digit dataset, while the existing distance classifier method k-Nearest Neighbour has achieved 68.7% of AUC.

Interactive Multimodal Television Media Adaptive Visual Communication Based on Clustering Algorithm

This article starts with the environmental changes in human cognition, analyzes the virtual as the main feature of visual perception under digital technology, and explores the transition from passive to active human cognitive activities. With the diversified understanding of visual information, human contradiction of memory also began to become prominent. Aiming at the problem that the existing multimodal TV media recognition methods have low recognition rate of unknown application layer protocols, an adaptive clustering method for identifying unknown application layer protocols is proposed. This method clusters application layer protocols based on similarity of the load characteristics of network stream application layer protocol data. The method divides the similarity calculation in the clustering algorithm to improve the clustering efficiency of the algorithm. Experimental results show that the proposed method can efficiently and accurately recognize unknown visual communication. This article proposes that, in the interactive multimodal visual information transmission, human visual perception experience has changed, the diversity of visual information content expression makes the aesthetic subject more personalized and stylized.

An Improved Cooperative Control Method for Hybrid Unmanned Aerial-Ground System in Multitasks

The cooperative control in complex multitasks using unmanned aerial vehicle and unmanned ground vehicle (UAV/UGV) is an important and challenging issue in the multirobot cooperative field. The main goal of the task studied in this paper is to minimize the time and energy consumed by the system to complete the assigned tasks. In this paper, a complex multitask problem using the hybrid UAV/UGV system is studied, which is divided into three stages, namely, the stage of finding the optimal locations of the relay stations for the UGV; the stage of solving the path planning problem for the UGV; and the stage of the task assignment for multi-UAVs. Furthermore, an improved integrated method is proposed to deal with the cooperative control problems in these three stages. Firstly, an adaptive clustering method is proposed to determine the locations of the UGV relay stations, and then an improved cuckoo search algorithm is used to find the shortest path for the UGV. Finally, a grouping method is presented to solve the multitask allocation problem of UAVs, based on an improved dynamic programming algorithm. In addition, some simulations are carried out and the results show that the proposed method has better performance when it comes to the time and energy consumption and can effectively guide the hybrid UAV/UGV system to carry out the complex multitasks.

Low-complexity point cloud denoising for LiDAR by PCA-based dimension reduction

Signals emitted by LiDAR sensors would often be negatively influenced during transmission by rain, fog, dust, atmospheric particles, scattering of light and other influencing factors, causing noises in point cloud images. To address this problem, this paper develops a new noise reduction method to filter LiDAR point clouds, i.e. an adaptive clustering method based on principal component analysis (PCA). Different from the traditional filtering methods that directly process three-dimension (3D) point cloud data, the proposed method uses dimension reduction to generate two-dimension (2D) data by extracting the first principal component and the second principal component of the original data with little information attrition. In the 2D space spanned by two principal components, the generated 2D data are clustered for noise reduction before being restored into 3D. Through dimension reduction and the clustering of the generated 2D data, this method derives low computational complexity, effectively removing noises while retaining details of environmental features. Compared with traditional filtering algorithms, the proposed method has higher precision and recall. Experimental results show a F-score as high as 0.92 with complexity reduced by 50% compared with traditional density-based clustering method.

Improving articulated hand pose detection for static finger sign recognition in RGB-D images

With the emergence of consumer RGB-D sensors, discriminative modeling has been shown to perform well in estimating human body pose. However, articulated hand pose estimation remains a challenging problem, mostly due to its high flexibility, occlusions, noisy data, and small area of the fingertips. In this paper, we present an efficient discriminative-based scheme to improve the performance of hand pose estimation from a single depth image. The proposed scheme is inspired by decision forest-based framework, but with several well-motivated modifications. Specifically, we propose a method to estimate 2D in-plane orientation of the hand, which is then utilized to enforce the depth comparison features and make them invariant to in-plane rotation. Subsequently, we investigate the use of random decision forests (RDF) and mean shift algorithm to predict a primary version of hand parts and joint locations. Based on this primary prediction, an adaptive spatial clustering method is applied to correct the misclassified regions, and to deliver the final estimation of hand pose. Along with the proposed scheme, we further develop a new set of highly-distinctive features for static finger sign recognition by utilizing the estimated hand pose configurations and RGB information. The proposed features are straightforward and can effectively capture different aspects of hand pose, such as links from each joint to the closest joints and orientation of each hand part. Extensive experiments on several challenging datasets demonstrate that our approach, compared to decision forest-based methods, is able to provide more precise estimation of hand poses (with up to 21% improvement in joint localization accuracy), and can efficiently recognize more complex static finger signs (93.85% mean recognition accuracy on a challenging 34-finger sign dataset). Our approach is also robust to illumination, inter-hand occlusion, scale, and rotation variance.

Principal component analysis (PCA) based hybrid models for the accurate estimation of reservoir water saturation

Water saturation is imperative in the evaluation of hydrocarbon reserves available. However, it is challenging to accurately determine the water saturation of complex reservoirs using conventional techniques. This is due to the fact that the conventional models are unable to fully account for the heterogeneity of the reservoir and their results are highly influenced by factors such as type of data, approach and shale distribution. Moreover, most computational intelligence methods developed to estimate water saturation have neglected the relationship that can exist between input variables and their impact on model performance. This is because well log parameters can exhibit relationships among each other which leads to the presence of multiple collinearities and increases the complexity of the model. Therefore, this paper for the first time adopted principal component analysis (PCA) as a dimensionality reduction method to improve the performance of optimized least squares support vector machine (LSSVM) and adaptive neuro-fuzzy inference system-subtractive clustering method (ANFIS-SCM). The experimental results clearly depicted a superior performance from PCA based LSSVM (PCA-LSSVM) during training and testing. Also, PCA minimized the overfitting experienced by ANFIS-SCM by improving the model's generalization ability. On the whole, PCA-LSSVM provided the least prediction error and outperformed PCA based ANFIS-SCM (PCA-ANFIS-SCM) when estimating water saturation.