Kernel Fuzzy C-means Research Articles

Stochastic configuration networks for short-term power load forecasting

The accuracy of power load forecasting can enhance the operational efficacy and economic efficiency of the power system. This paper utilizes the stochastic configuration network (SCN) and improved marine predator algorithm (IMPA) for power systems short-term load forecasting. First, the daily load data is clustered using the kernel fuzzy C-means (KFCM), and the clustering results are utilized as training input data for the load forecasting model. Then, load forecasting is performed using SCN. Next, IMPA is developed by integrating the opposite-based differential evolution (ODE) and normal mutation perturbation strategy for the purpose of preventing the algorithm from converging to local minima. Finally, IMPA is employed to optimize the critical parameters of the load forecasting model. The experimental results clearly demonstrate that the proposed algorithm performs favorably in terms of the prediction accuracy compared to other modeling algorithms.

Motion Clutter Suppression for Non-Cooperative Target Identification Based on Frequency Correlation Dual-SVD Reconstruction.

Non-cooperative targets, such as birds and unmanned aerial vehicles (UAVs), are typical low-altitude, slow, and small (LSS) targets with low observability. Radar observations in such scenarios are often complicated by strong motion clutter originating from sources like airplanes and cars. Hence, distinguishing between birds and UAVs in environments with strong motion clutter is crucial for improving target monitoring performance and ensuring flight safety. To address the impact of strong motion clutter on discriminating between UAVs and birds, we propose a frequency correlation dual-SVD (singular value decomposition) reconstruction method. This method exploits the strong power and spectral correlation characteristics of motion clutter, contrasted with the weak scattering characteristics of bird and UAV targets, to effectively suppress clutter. Unlike traditional clutter suppression methods based on SVD, our method avoids residual clutter or target loss while preserving the micro-motion characteristics of the targets. Based on the distinct micro-motion characteristics of birds and UAVs, we extract two key features: the sum of normalized large eigenvalues of the target's micro-motion component and the energy entropy of the time-frequency spectrum of the radar echoes. Subsequently, the kernel fuzzy c-means algorithm is applied to classify bird and UAV targets. The effectiveness of our proposed method is validated through results using both simulation and experimental data.

An intelligent interval forecasting system based on fuzzy time series and error distribution characteristics for air quality index

Due to the emergency environment pollution problems, it is imperative to understand the air quality and take effective measures for environmental governance. As a representative measure, the air quality index (AQI) is a single conceptual index value simplified by the concentrations of several routinely monitored air pollutants according to the proportion of various components in the air. With the gradual enhancement of awareness of environmental protection, air quality index forecasting is a key point of environment management. However, most of the traditional forecasting methods ignore the fuzziness of original data itself and the uncertainty of forecasting results which causes the unsatisfactory results. Thus, an innovative forecasting system combining data preprocessing technique, kernel fuzzy c-means (KFCM) clustering algorithm and fuzzy time series is successfully developed for air quality index forecasting. Concretely, the fuzzy time series that handle the fuzzy set is used for the main forecasting process. Then the complete ensemble empirical mode decomposition and KFCM are respectively developed for data denoising and interval partition. Furthermore, the interval forecasting method based on error distribution is developed to measure the forecasting uncertainty. Finally, the experimental simulation and evaluation system verify the great performance of proposed forecasting system and the promising applicability in a practical environment early warning system.

LIKFCM: Linear interpolation-based kernelized fuzzy C-means clustering imputation method for handling incomplete data

Addressing missing values is a persistent challenge in the field of data mining. The presence of incomplete data can significantly compromise the overall data quality. Consequently, it is crucial to handle incomplete data efficiently. This paper presents a novel approach for imputing missing values that incorporates Kernelized Fuzzy C-Means (KFCM) clustering and proposes a method termed LIKFCM, which combines its benefits with Linear Interpolation (LI). The proposed LIKFCM’s performance is assessed through a comparison against nine state-of-the-art imputation techniques (mean, median, LI, EMI, KNNI, KMI, FKMI, LIFCM, and LIPFCM) across ten widely used real-world datasets from the UCI repository with six combinations of missing ratios to assess the efficacy of the proposed imputation method. From the experimental results, it is evident that our proposed method outperforms the existing imputation methods with significant improvements in terms of RMSE & MAE for these datasets. Additionally, experiments examining the effect of missing values validate the robustness of the proposed approach by handling different missing ratios. The performance validation of the proposed approach against other state-of-the-art imputation methods has been conducted utilizing a Kendall’s W statistical test, involving a comparison of their mean ranks across different missing ratios. The outcomes indicate that LIKFCM has outperformed other imputation methods, attaining the highest rank in terms of different evaluation criteria.

Revolutionizing Missing Data Handling with RFKFCM: Random Forest-based Kernelized Fuzzy C-Means

Missing values are a prevalent issue, frequently leading to a considerable decline in the quality of data. Therefore, it becomes imperative to adeptly manage missing data. This study presents a technique for imputing missing values that incorporates Kernelized Fuzzy C-Means (KFCM) clustering. The technique introduced is termed RFKFCM, which combines the benefits of Random Forest (RF) and KFCM algorithms. The proposed RFKFCM's performance is evaluated through a comparative analysis with five state-of-the-art imputation techniques (mean, LI, KNN, FCM, and LIFCM) across four widely used real-world datasets obtained from the UCI repository. Additionally, experiments investigating the impact of missing values affirm the robustness of the proposed technique across different missing rates using Friedman's statistical test for each dataset by comparing their mean rank. The experimental results indicate that our proposed technique performs significantly better than the existing imputation techniques based on Root mean squared error (RMSE) & Mean absolute error (MAE) for these datasets.

Novel modified kernel fuzzy c-means algorithm used for cotton leaf spot detection

Image segmentation is a significant and difficult subject that is a prerequisite for both basic image analysis and sophisticated picture interpretation. In image analysis, picture segmentation is crucial. Several different applications, including those related to medicine, facial identification, Cotton disease diagnosis, and map object detection, benefit from image segmentation. In order to segment images, the clustering approach is used. The two types of clustering algorithms are Crisp and Fuzzy. Crisp clustering is superior to fuzzy clustering. Fuzzy clustering uses the well-known FCM approach to enhance the results of picture segmentation. KFCM technique for image segmentation can be utilized to overcome FCM’s shortcomings in noisy and nonlinear separable images. In the KFCM approach, the Gaussian kernel function transforms high-dimensional, nonlinearly separable data into linearly separable data before applying FCM to the data. KFCM is enhancing noisy picture segmentation results. KFCM increases the accuracy rate but ignores neighboring pixels. The Modified Kernel Fuzzy C-Means approach is employed to get over this problem. The NMKFCM approach enhances picture segmentation results by including neighboring pixel information into the objective function. This suggested technique is used to find “blackarm” spots on cotton leaves. A fungal leaf disease called “blackarm” leaf spot results in brown leaves with purple borders. The bacterium can harm cotton plants, causing angular leaf blotches that range in color from red to brown.

Brain tumor segmentation based on kernel fuzzy c-means and penguin search optimization algorithm

Brain tumor segmentation based on kernel fuzzy c-means and penguin search optimization algorithm

A generalized fuzzy clustering framework for incomplete data by integrating feature weighted and kernel learning.

Missing data presents a challenge to clustering algorithms, as traditional methods tend to pad incomplete data first before clustering. To combine the two processes of padding and clustering and improve the clustering accuracy, a generalized fuzzy clustering framework is proposed based on optimal completion strategy (OCS) and nearest prototype strategy (NPS) with four improved algorithms developed. Feature weights are introduced to reduce outliers' influence on the cluster centers, and kernel functions are used to solve the linear indistinguishability problem. The proposed algorithms are evaluated regarding correct clustering rate, iteration number, and external evaluation indexes with nine datasets from the UCI (University of California, Irvine) Machine Learning Repository. The results of the experiment indicate that the clustering accuracy of the feature weighted kernel fuzzy C-means algorithm with NPS (NPS-WKFCM) and feature weighted kernel fuzzy C-means algorithm with OCS (OCS-WKFCM) under varying missing rates is superior to that of seven conventional algorithms. Experiments demonstrate that the enhanced algorithm proposed for clustering incomplete data is superior.

Brain-like position measurement method based on improved optical flow algorithm

In this paper, a brain-like navigation scheme based on fuzzy kernel C-means (FKCM) clustering assisted pyramid Lucas Kanade (LK) optical flow algorithm is developed to measure the position of vehicle. The Speed Cell and Place Cell in animals’ brain are introduced to construct the brain-like navigation mechanism which involves the optical flow method and image template matching to imitate the cells above-mentioned separately. To eliminate the singular values during optical flow calculation, the output of pyramid LK algorithm is clustered by FKCM algorithm firstly. Then, the velocity is calculated and integrated to get the position of the vehicle, and the brain-like navigation scheme is introduced to correct the position measurement errors by eliminating the accumulated errors resulting from velocity integration. The prominent advantages of the presented method are: (i) a pure visual brain-like position measurement method based on the concept of speed cells and place cells is proposed, making visual navigation more accurate and intelligent; (ii) the FKCM algorithm is used to eliminate the singular value of the pyramid LK algorithm, which improves the calculated velocity accuracy. Also, experimental comparison with classical pyramid LK algorithm is given to illustrate the superiority of the proposed method in position measurement.

Multi‐model predictive control ofSCRflue gas denitrification system in coal‐fired power plant based on kernel fuzzy c‐means clustering and integrated model

AbstractA multi‐model predictive control strategy based on kernel fuzzy c‐means (KFCM) clustering and integrated model is proposed for the complex problem of rapid and accurate control of ammonia injection in selective catalytic reduction (SCR) denitrification systems of coal‐fired power plants under a wide range of variable load conditions. First, the SCR data samples are clustered using the KFCM clustering algorithm, and the number of clusters is determined by introducing the Xie‐Beni index. Second, the prediction model of the SCR denitrification system is established by an integrated modelling approach, and the sub‐learners of the integrated model are the genetic algorithm optimized back propagation (GA‐BP) neural network model and the least squares support vector machine (LSSVM) model. Third, a multi‐model prediction controller based on the particle swarm optimization (PSO) algorithm and the integrated model is designed and developed. To ensure the stability of the system, a model‐switching strategy based on the minimum Euclidean distance is proposed. Finally, simulation verification and industrial field application verification are fulfilled by comparing with proportion integral differential (PID) control and single model predictive control (MPC). The results show that the multi‐model predictive control method proposed in this paper can obtain higher control accuracy and better control stability and meet the control requirements for the long‐term operation of the SCR denitrification system.

Substation clustering based on improved KFCM algorithm with adaptive optimal clustering number selection

The premise and basis of load modeling are substation load composition inquiries and cluster analyses. However, the traditional kernel fuzzy C-means (KFCM) algorithm is limited by artificial clustering number selection and its convergence to local optimal solutions. To overcome these limitations, an improved KFCM algorithm with adaptive optimal clustering number selection is proposed in this paper. This algorithm optimizes the KFCM algorithm by combining the powerful global search ability of genetic algorithm and the robust local search ability of simulated annealing algorithm. The improved KFCM algorithm adaptively determines the ideal number of clusters using the clustering evaluation index ratio. Compared with the traditional KFCM algorithm, the enhanced KFCM algorithm has robust clustering and comprehensive abilities, enabling the efficient convergence to the global optimal solution

Gaussian kernel fuzzy c-means with width parameter computation and regularization

The conventional Gaussian kernel fuzzy c-means clustering algorithms require selecting the width hyper-parameter, which is data-dependent and fixed for the entire execution. Not only that, but these parameters are the same for every dataset variable. Therefore, the variables have the same importance in the clustering task, including irrelevant variables. This paper proposes a Gaussian kernel fuzzy c-means with kernelization of the metric and automated computation of width parameters. These width parameters change at each iteration of the algorithm and vary from each variable and from each cluster. Thus, this algorithm can re-scale the variables differently, thus highlighting those that are relevant to the clustering task. Fuzzy clustering algorithms with regularization have become popular due to their high performance in large-scale data clustering, robustness for initialization, and low computational complexity. Because the width parameters of the variables can also be controlled by entropy, this paper also proposes Gaussian kernel fuzzy c-means algorithms with kernelization of the metric and automated computation of width parameters through entropy regularization. To demonstrate their usefulness, the proposed algorithms are compared with the conventional KFCM-K algorithm and previous algorithms that automatically compute the width parameter of the Gaussian kernel.

Safe semi-supervised clustering based on Dempster–Shafer evidence theory

In this paper, we propose a safe semi-supervised clustering algorithm based on Dempster–Shafer (D–S) evidence theory. The motivation is that D–S evidence theory can be used to fuse multiple base clustering results and obtain robust confidence estimations of mislabeled samples. Firstly, the proposed algorithm constructs multiple base clusters using fuzzy c-means and kernel fuzzy c-means. Base clusters with good performance are selected according to a clustering validity function. Then, D–S evidence theory is used to fuse the results of the selected base clusters, and the confidence of labeled samples is calculated based on the fused results. Finally, we construct a p-nearest neighbor graph to limit the outputs of labeled samples with low confidence to be those of the p nearest unlabeled samples. It is desired to reduce the negative influence of labeled samples with low confidence and achieve safe exploitation. To verify the effectiveness of the proposed algorithm, we compare it to several unsupervised and semi-supervised clustering algorithms. The results demonstrate that our algorithm yields higher accuracy and is more stable.

Deep neighborhood structure driven interval type-2 kernel fuzzy c-means clustering with local versus non-local information

Deep neighborhood structure driven interval type-2 kernel fuzzy c-means clustering with local versus non-local information

IFCEM based recognition method for target with interval-overlapped hybrid attributes

When the attributes of unknown targets are not just numerical attributes, but hybrid attributes containing linguistic attributes, the existing recognition methods are not effective. In addition, it is more difficult to identify the unknown targets densely distributed in the feature space, especially when there is interval overlap between attribute measurements of different target classes. To address these problems, a novel method based on intuitionistic fuzzy comprehensive evaluation model (IFCEM) is proposed. For numerical attributes, targets in the database are divided into individual classes and overlapping classes, and for linguistic attributes, continuous interval-valued linguistic term set (CIVLTS) is used to describe target characteristic. A cloud model-based method and an area-based method are proposed to obtain intuitionistic fuzzy decision information of query target on numerical attributes and linguistic attributes respectively. An improved inverse weighted kernel fuzzy c-means (IWK-FCM) algorithm is proposed for solution of attribute weight vector. The possibility matrix is applied to determine the identity and category of query target. Finally, a case study composed of parameter sensitivity analysis, recognition accuracy analysis. and comparison with other methods, is taken to verify the superiority of the proposed method.

Retinal Blood-Vessel Extraction Using Weighted Kernel Fuzzy C-Means Clustering and Dilation-Based Functions.

Automated blood-vessel extraction is essential in diagnosing Diabetic Retinopathy (DR) and other eye-related diseases. However, the traditional methods for extracting blood vessels tend to provide low accuracy when dealing with difficult situations, such as extracting both micro and large blood vessels simultaneously with low-intensity images and blood vessels with DR. This paper proposes a complete preprocessing method to enhance original retinal images before transferring the enhanced images to a novel blood-vessel extraction method by a combined three extraction stages. The first stage focuses on the fast extraction of retinal blood vessels using Weighted Kernel Fuzzy C-Means (WKFCM) Clustering to draw the vessel feature from the retinal background. The second stage focuses on the accuracy of full-size images to achieve regional vessel feature recognition of large and micro blood vessels and to minimize false extraction. This stage implements the mathematical dilation operator from a trained model called Dilation-Based Function (DBF). Finally, an optimal parameter threshold is empirically determined in the third stage to remove non-vessel features in the binary image and improve the overall vessel extraction results. According to evaluations of the method via the datasets DRIVE, STARE, and DiaretDB0, the proposed WKFCM-DBF method achieved sensitivities, specificities, and accuracy performances of 98.12%, 98.20%, and 98.16%, 98.42%, 98.80%, and 98.51%, and 98.89%, 98.10%, and 98.09%, respectively.

Optimal placement and capacity sizing of energy storage systems via NSGA-II in active distribution network

In recent years, with the rapid development of renewable energy, the penetration rate of renewable energy generation in the active distribution network (ADN) has increased. Because of the instability of renewable energy generation, the operation stability of ADN has decreased. Due to the ability to cut peak load and fill valley load, battery energy storage systems (BESSs) can enhance the stability of the electric system. However, the placement and capacity of BESSs connected to ADN are extremely significant, otherwise, it will lead to a further decline in the stability of ADN. To ensure the effectiveness of the BESSs connected to the grid, this work uses the fuzzy kernel C-means (FKCM) method for scene clustering. Meanwhile, a multi-objective optimization model of BESS configuration is established with the objective of BESS configuration cost, voltage fluctuation, and load fluctuation, and solved by non-dominated sorting genetic algorithm-II (NSGA-II). In this work, the grey target decision method based on the entropy weight method (EWM) is used to obtain the optimal compromise solution from the Pareto non-dominated set. Moreover, the proposed method is tested and verified in the extended IEEE-33 node system and the extended IEEE-69 node system. The results show that the BESSs configuration scheme obtained by NSGA-II can effectively reduce the fluctuation of voltage and load, and improve the stability of ADN operation.

Brain Tumour Region Extraction Using Novel Self-Organising Map-Based KFCM Algorithm

Medical professionals need help finding tumours in the ground truth image of the brain because the tumours’ location, contrast, intensity, size, and shape vary between images because of different acquisition methods, modalities, and the patient’s age. The medical examiner has difficulty manually separating a tumour from other parts of a Magnetic Resonance Imaging (MRI) image. Many semi- and fully automated brain tumour detection systems have been written about in the literature, and they keep improving. The segmentation literature has seen several transformations throughout the years. An in-depth examination of these methods will be the focus of this investigation. We look at the most recent soft computing technologies used in MRI brain analysis through several review papers. This study looks at Self-Organising maps (SOM) with K-means and the kernel Fuzzy c-means (KFCM) method for segmenting them. The suggested SOM networks were first compared to K-means analysis in an experiment based on datasets with well-known cluster solutions. Later, the SOM is combined with KFCM, reducing time complexity and producing more accurate results than other methods. Experiments show that skewed data improves networks’ performance with more SOMs. Finally, performance measures in real-time datasets are analysed using machine learning approaches. The results show that the proposed algorithm has good sensitivity and better accuracy than k-means and other state-of-art methods.

Congestion Detection and Alleviation Mechanism Using a Multi-Level Cluster Based Cuckoo Hosted Rider Search Multi-Hop Hierarchical Routing Protocol in Wireless Sensor Networks

Wireless sensor networks congestion occurs easily due to its centralized traffic pattern. Normally, mono-sync wireless sensor network experiences multiple traffic flow congestion in the dense environment of the network, which leads to excess energy consumption and severe packet loss. To overcome these issues, a congestion detection and alleviation mechanism using cluster based heuristic optimized hierarchical routing protocol is proposed in this paper. Here, congestion detection and alleviation utilize the features of sensor nodes. The congestion is categorized into two types: (i) node level congestion and (ii) link level congestion. The node level congestion is detected by assessing the buffer utilization and the interval amid the consecutive data packets. The link level congestion is considered with computing link usage utilizing back-off step of round robin carrier sense multi-access with collision avoidance. Congestion detection and alleviation reactively affected node/link through cuckoo hosted rider search multi-hop routing algorithm. It has two phases: the cluster head selection and multi-path routing. Cluster head selection is performed through Taylor multiple random forest kernel fuzzy C-means clustering algorithm and multi-path routing is performed through cuckoo hosted rider search multi-hop routing algorithm. The simulation of the proposed method is done in network simulator tool. Here, the performance metrics, like packet delivery ratio, delay, energy consumption, packet drop, overhead, network lifetime and throughput are calculated. The experimental outcomes of the proposed technique shows 11.6%, 18.4% and 28.1% lower delay, 78.2%, 65.4% and 52.6% higher packet delivery ratio, and 29.2%, 37.4% and 40.8% lower packet drop compared with the existing methods, like congestion detection and alleviation using multi-attribute decision-making in optimization-based hybrid congestion alleviation routing protocol in wireless sensor networks, congestion detection and alleviation using hybrid K-means with greedy best first search algorithms in packet rate reduction utilizing adaptive weight firefly algorithm ant colony optimization based routing protocol in wireless sensor networks and congestion detection and alleviation using multi-input time on task optimization algorithm for altered gravitational search algorithm routing protocol in wireless sensor networks.

Fault diagnosis method of high voltage circuit breaker based on the combination of time-frequency multi-characteristics of acoustic signal

Aiming at the problem of accurately identifying the mechanical state of circuit breaker in the actual operation environment, a new fault diagnosis method of high voltage circuit breaker based on the combination of time-frequency multi-characteristics of acoustic signal was proposed. Firstly, the background noise database was established to remove the template noise. On this basis, the adaptive wavelet transform (AWT) was used to remove the residual noise. Then the kurtosis, crest factor and skewness indexes were extracted respectively to construct the time-domain characteristics. The acoustic signal was decomposed by variational mode decomposition (VMD) to obtain the IMF component. The power spectrum of the IMF was converted to the polar coordinates of the divided sub-region. The sensitivity of the main peak region was improved by the divergence factor, and the spectral difference entropy characteristics were calculated. The two jointly constructed the time-frequency multi-characteristics. Finally, kernel fuzzy c means (KFCM) clustering was used to pre-classify the characteristics, and then support vector machine (SVM) was used to establish training models to realize mechanical state identification. The diagnosis result shows that the accuracy of time-frequency multi-characteristics combined with KFCM-SVM diagnosis method is 98.75 %. It can reflect the status information of circuit breaker from multiple dimensions, and has high practical popularization value.