Early warning strategies for corporate operational risk: A study by an improved random forest algorithm using FCM clustering.

Image segmentation plays an important role in machine vision, image recognition, and imaging applications. Based on the fuzzy c-means clustering algorithm, a kernel-distance-based intuitionistic fuzzy c-means clustering (KIFCM) algorithm is proposed. First, a fuzzy complement operator is used to generate the membership degree whereby the hesitation degree of intuitionistic fuzzy set is generated; second, a kernel-induced function is used to calculate the distance from each point to the cluster center instead of the Euclidean distance; third, a new objective function that includes the hesitation degree is established, and the optimization of the objective function results in new iterative expressions for the membership degree and the cluster center. The proposed KIFCM algorithm is compared with the fuzzy c-means clustering (FCM) algorithm, the kernel fuzzy c-means clustering (KFCM) algorithm, and the intuitionistic fuzzy c-means clustering (IFCM) algorithm in segmenting five images. The experimental results verify the effectiveness and superiority of our proposed KIFCM algorithm.

Abstract: Fuzzy C-Means Clustering (FCM) has been widely known as a technique for performing data clustering, such as image segmentation. This study will conduct a trial using the Normalized Cross Correlation method on the Fuzzy C-Means Clustering algorithm in determining the value of the initial fuzzy pseudo-partition matrix which was previously carried out by a random process. Clustering technique is a process of grouping data which is included in unsupervised learning. Data mining generally has two techniques in performing clustering, namely: hierarchical clustering and partitional clustering. The FCM algorithm has a working principle in grouping data by adding up the level of similarity between pairs of data groups. The method applied to measure the similarity of the data based on the correlation value is the Normalized Cross Correlation (NCC). The methodology in this research is the steps taken to measure clustering performance by adding the Normalized Cross Correlation (NCC) method in determining the initial fuzzy pseudo-partition matrix in the Fuzzy C-Means Clustering (FCM) algorithm. the results of data clustering using the Normalized Cross Correlation (NCC) method on the Fuzzy C-Means Clustering (FCM) algorithm gave better results than the ordinary Fuzzy C-Means Clustering (FCM) algorithm. The increase that occurs in the proposed method is 4.27% for the Accuracy, 4.73% for the rand index and 8.26% for the F-measure..

FCM 클러스터링 알고리즘은 대표적인 분할기반 군집화 알고리즘이며 다양한 분야에서 성공적으로 적용되어 왔다. 그러나 FCM 클러스터링 알고리즘은 잡음 및 지역 데이터에 대한 높은 민감도, 직관적인 결과와 상이한 결과 도출 가능성이 높은 문제, 초기 원형과 클러스터 개수 설정 문제 등이 존재한다. 본 논문에서는 FCM 알고리즘의 결과를 해당 속성의 데이터 축에 사상하여 퍼지구간을 결정하고, 결정된 퍼지구간을 FDT에 적용함으로써 FCM 알고리즘이 가지는 문제 중 잡음 및 데이터에 대한 높은 민감도, 직관적인 결과와 상이한 결과 도출 가능성이 높은 문제를 개선하는 시스템을 제안한다. 또한 실제 교통데이터와 강수량 데이터를 이용한 실험을 통하여 제안 모델과 FCM 클러스터링 알고리즘을 비교한다. 실험 결과를 통해 제안 모델은 잡음 및 데이터에 대한 민감도를 완화시킴으로써 보다 안정적인 결과를 제공하며, FCM 클러스터링 알고리즘을 적용한 시스템보다 직관적인 결과와의 일치율을 높여줌을 알 수 있다. FCM (Fuzzy C-Means) clustering algorithm, a typical split-based clustering algorithm, has been successfully applied to the various fields. Nonetheless, the FCM clustering algorithm has some problems, such as high sensitivity to noise and local data, the different clustering result from the intuitive grasp, and the setting of initial round and the number of clusters. To address these problems, in this paper, we determine fuzzy numbers which project the FCM clustering result on the axis with the specific attribute. And we propose a model that the fuzzy numbers apply to FDT (Fuzzy Decision Tree). This model improves the two problems of FCM clustering algorithm such as elevated sensitivity to data, and the difference of the clustering result from the intuitional decision. And also, this paper compares the effect of the proposed model and the result of FCM clustering algorithm through the experiment using real traffic and rainfall data. The experimental results indicate that the proposed model provides more reliable results by the sensitivity relief for data. And we can see that it has improved on the concordance of FCM clustering result with the intuitive expectation.

The mechanism of the sight control box of armored equipment is complex and the majority of signals are superimposed and integrated. It is difficult to evaluate the operating state from the perspective of analyzing a single signal. Establishing the state control system of the scope control box by using the rough set fusion FCM (Fuzzy C-Means) clustering algorithm. Firstly, the basic knowledge of rough set and FCM clustering algorithm is introduced, and the FCM clustering algorithm is improved. Since the signal index of the insertion and superposition in the scope control box is too large, only the output signal of the scope control box is selected as the evaluation feature quantity. Secondly, the FCM clustering algorithm is used to fuzzily divide the evaluation feature quantity and simultaneously generate the running state decision table. The rough set attribute reduction method of the difference matrix is used to attribute the attribute quantity of the extracted original data. Finally, through the blind deletion value reduction method, the reduction decision table is attributed to the attribute reduction to obtain a complete reduction decision table, and based on this, a state evaluation rule table is established. Through an example analysis, it is verified that the evaluation model established by the rough set fusion FCM clustering algorithm can accurately and effectively evaluate the operating state of the mirror control box.

As an important gas path performance parameter of gas turbine, exhaust gas temperature (EGT) can represent the thermal health condition of gas turbine. In order to monitor and diagnose the EGT effectively, a fusion approach based on fuzzy C-means (FCM) clustering algorithm and support vector machine (SVM) classification model is proposed in this paper. Considering the distribution characteristics of gas turbine EGT, FCM clustering algorithm is used to realize clustering analysis and obtain the state pattern, on the basis of which the preclassification of EGT is completed. Then, SVM multiclassification model is designed to carry out the state pattern recognition and fault diagnosis. As an example, the historical monitoring data of EGT from an industrial gas turbine is analyzed and used to verify the performance of the fusion fault diagnosis approach presented in this paper. The results show that this approach can make full use of the unsupervised feature extraction ability of FCM clustering algorithm and the sample classification generalization properties of SVM multiclassification model, which offers an effective way to realize the online condition recognition and fault diagnosis of gas turbine EGT.

In order to solve the problems of the fuzzy C-means (FCM) clustering algorithm when it is applied to the image segmentation such as making itself easily traps into local optimum and huge calculation, an image segmentation algorithm based on the modified particle swarm optimization(MPSO) and FCM clustering algorithm is proposed. The simulation results and the comparison between the proposed algorithm and FCM algorithm indicate that the proposed algorithm can obtain better segmentation effects and excel the existing FCM algorithm in several performance, such as the average dispersion, the maximum intra-distance between pixel and their cluster center, and the minimum inter-distance between any pair of clusters.

Cluster analysis refers to the process of grouping a collection of physical or abstract objects into multiple classes of similar objects. Determining the optimal classification number of a data set is the key to the clustering problem, that is to say whether the data set can be effectively partitioned. Cluster validity study is a process of establishing clustering effectiveness indicators, evaluating clustering quality and determining the optimal number of clusters. A validity function of fuzzy C-means (FCM) clustering algorithm is proposed by adopting the division of intra-class compactness and inter-class separation, whose minimum represents the best clustering. Then, the proposed validity function on FCM clustering algorithm is compared with the known typical validity functions by carrying out simulation experiments to compare the related clustering performance. Three data sets are adopted to carry out FCM clustering, which includes three classical data sets, two artificial data sets and six real data sets in UCI database. Simulation experimental results show that the proposed validity function can effectively partition the data set.

This paper expatiates on the improved fuzzy c-means (FCM) clustering algorithm. In the algorithm, the membership values are determined via the improved method, and the number of the centers of FCM clustering are determined via the number of the peaks of the two-dimensional histogram on the gray-level values of pixels and gradient values of pixel neighborhoods. The application to segmentation of a sonar image of a small underwater target shows that the improved FCM clustering algorithm can segment the image into the shadow and echo regions of the target, and that the improved algorithm is more intelligent and timesaving than the traditionary FCM clustering algorithm.

Through researching and analyzing self-adaptive strategy and fuzzy C-means (FCM) clustering algorithm, we put them together to form a self-adaptive FCM clustering algorithm. It is a good solution to the problem of local optimum as well as sensitivity to the initial value for the traditional FCM clustering algorithm. Finally, the new algorithm has been used in the regional division of police patrols in a city. In the division of the region, it has been proved by experiments that the sum of distance between a police vehicle and each possible accident scene can achieve the minimum value, which shows a significant effect of police patrols. And through the improved dijkstra algorithm to calculate shortest path length between a police vehicle and an accident scene, it proves that a police vehicle in the division of the region arrives at an accident scene within three minutes after accepting the warnings, whose proportion is 90.2%.

This paper presents the identification of fuzzy controller for rapid Nickel-Cadmium (Ni-Cd) batteries charger by applying fuzzy c-means (FCM) clustering algorithm on the input-output training data. The identification of fuzzy model using input-output data consists of two parts: structure identification and parameter estimation. Structure identification involves the determination of antecedent and consequent variables and in parameter estimation step, antecedents' membership functions and rule consequents are determined. Fuzzy clustering is used to partition the training data into regions that leads to creation of local linear models expressed by fuzzy rules. The data for the batteries charger has been obtained through experimentation with an objective to charge the batteries as fast as possible. For the premise part identification, the input space is partitioned by FCM clustering and the consequent parameters for each rule are calculated as least-square estimate. The Takagi-Sugeno-Kang (TSK) model obtained through FCM clustering algorithm is further fine tuned through hybrid learning.

Image segmentation is a primary work for machine vi11This work is funded by National Natural Science Foundation of China, grant number 41301371, 61502155, 61772180, Technological Innovation Project of Hubei Province 2019(2019AAA047), Green Industry Science and Technology Leadership Program of Hubei University of technology (No.CPYF2018005, YXQN2017002) sion and Fuzzy C-Means (FCM) clustering algorithm is one of the commonest methods. However, FCM is sensitive to the initial clustering center and easily falls into the local optimum solution, while the Krill Herd (KH) algorithm has strong global convergence and high stability. As a result, this paper proposes an image segmentation method based on improved Krill Herd algorithm and FCM (IKH-FCM). First of all, the method uses the K-Means algorithm to initialize the initial population of the krill herd, the improved KH algorithm is used to calculate the initial clustering center of FCM, and then FCM clustering is applied to implement image segmentation. Experiments show that the approach has strong global convergence and high stability compared to the original FCM, which is a favorable image segmentation approach for practical work.

Local segmentation of images using an improved fuzzy C-means clustering algorithm based on self-adaptive dictionary learning

An image segmentation method based on a modified local-information weighted intuitionistic Fuzzy C-means clustering and Gold-panning Algorithm

Traditional fuzzy C-means clustering (FCM) algorithm has the problem of large amount of calculation and too long operation time in medical image segmentation. In the case that sample set is not ideal, it can lead to bad clustering results. Against disadvantages of this algorithm, a kind of medical segmentation algorithm is put forward based on hybrid leapfrog optimized fuzzy c-means clustering. The step length of the frog directly affects the performance of the algorithm. Therefore, we propose the appropriate step update strategy. The experiment results show that the proposed algorithm can ensure the continuity of the image edge compared with fuzzy c-means clustering algorithm. It can provide certain reference for the design of real medical image segmentation system.

Diseases in tomato plants can cause economic losses in the agricultural industry. Identification of tomato plant diseases is important to choosing the right action to control their spread. In this research, we propose an approach to identify tomato plant diseases using a machine learning algorithm and lab colour space-based image segmentation using the fuzzy c-means (FCM) clustering algorithm. The segmentation method aims to separate the infected area, leaf image, and background in the tomato plant image. In the first step, the tomato image is represented in the Lab colour space, which allows for combining information on brightness (L), red-green colour components (a), and yellow-blue colour components (b). Then, the FCM algorithm is applied to segment the image. The segmentation results are then evaluated through an identification process using machine learning techniques such as k-Nearest Neighbors (kNN), Random Forest (RF), Support Vector Machine (SVM), and Naïve Bayes (NB) to measure the level of accuracy. The dataset used in this research is tomato images, which include various plant diseases obtained from the Kaggle dataset. The performance results of the proposed method show that the segmentation approach based on Lab colour space with the FCM clustering algorithm is able to identify infected areas well. The accuracy value of each machine learning method used is kNN of 85.40%, RF of 88.87%, SVM of 80.73%, and NB of 74.60%. The proposed method shows success in accurately identifying types of tomato plant diseases and obtains improvements compared to without using segmentation.