fuzzy clustering

[1] Corresponding Author Human activities, such as mining, constructing highways, and building infrastructures like dams and industrial facilities, have caused significant damage to many natural ecosystems. In addition to disrupting the balance of these ecosystems, some of these activities have led to considerable pollution. Traditional methods, such as geostatistics and geophysics, while helpful info helpful in identifying contaminated areas and measuring the extent of pollution, are often costly, time-consuming, and come with helpful in identifying areas and measuring the extent of pollution, are often expensive, time-consuming and come with various limitations. To address these limitations, remote sensing data can provide an effective solution. The foundation of remote sensing lies in the spectral frequencies or images captured through satellite or drone equipment. Remote sensing data processing methods for identifying the type and estimating the extent of soil contamination fall into three main categories: physical models, mathematical models, and physics-based mathematical models. Given the various challenges associated with remote sensing of pollution in mining areas and their surroundings and the limited research conducted—particularly in Iran—this study addresses a critical important important important necessary conducted undertaken—particularly in Iran—this study addresses the essential gap. Iran hosts numerous mining sites in or near critical environmental ecosystems, making pollution management in these areas a pressing issue. This research proposes a method combining fuzzy clustering and edge-based features to identify surface and physical soil contamination caused by mining activities and coal-washing waste from the eastern Alborz coal preparation plant. This approach uses Sentinel-2 satellite imagery at a 1:100,000 scale for the studied mining area. The study focuses on the eastern Alborz coal mining region in Semnan Province, Iran. This area lies 140 kilometers from the provincial capital, 25 kilometers northeast of Damghan, and 75 kilometers from Shahroud.

The structure of operators in most traditional multi-objective evolutionary algorithms are based on fixed heuristics such as intersection and mutation, which are unable to learn the structures or properties of problems to create. To use evolutionary algorithms to learnability, news of evolutionary algorithms with the model is presented. In model evolutionary algorithms, innovative operators are replaced by machine learning models such as instructional and sample models. In this paper, a multi-objective evolutionary algorithm with a model is presented in which in each generation, a probable area of the search space deserves the model as a possible model. In the decision area in the search space, which are the dominant points, they are better ranked, we have clustered or different fuzzy methods, or on other points with the first order, it is a contest selection action. If you are missing, you take the form to be removed at close range, and the result is considered to be the center of the clusters, and then, clustering is done based on the nearest neighbors. The principal component analysis algorithm, which is the best method for reducing the given dimensions linearly, has been used for the models. New solutions are obtained from the model if it is a normal distribution. The proposed method is tested and the results are compared with the method of non-dominated sorting genetic algorithms. The results show that this method is faster than earlier methods and with fewer repetitions and evaluation of functions, the results are better and bold.

Recommender systems are a subset of intelligent information filtering systems that discovers user interests and provide user-friendly recommendations. User-based collaborative filtering recommender systems is one of the most important types of recommender systems. However, they are faced with voluminous data and sparsity problems that have negative effects on the performance of the systems. In the proposed method, fuzzy C-ordered means clustering algorithm is integrated with a chaotic self-adaptive particle swarm evolutionary algorithm for clustering users. The proposed method aims to improve the rating prediction in large sparse datasets and reduce the negative impact of outliers and noisy data. Experiments have been conducted on real-world datasets to evaluate and prove the efficiency of the proposed method. Experimental results show the superiority of the proposed method that the state-of-the-art methods based on prediction error criteria, accuracy rates, and the computational time.

High strength aluminum alloy pipes (AA7075-T6) has been widely used in various industries due to their favorable properties, Such as high strength to weight ratio, excellent machinability and proper forming. On the other hand, according to the susceptible to phenomenon of stress corrosion cracking, the evaluation and monitoring of mechanisms related to this issue is of considerable importance in the industry. In this research, Fuzzy clustering method (FCM) has been used to detect acoustic emission signals related to stress corrosion cracking mechanisms of aluminum pipe. Using this method, while revealing the clusters in an unsupervised method, leads to more appropriate classification and separation of data. In this regard, a laboratory system including waveguide, corrosive solution chamber, and arc-shaped aluminum samples according to ASTM-E399 standard along with acoustic emission equipment was designed and prepared. Then, using the slow strain rate test (SSRT) and receiving AE signals simultaneously, the AA7075-T6 aluminum sample was placed in two corrosive environments (HCL9% and HCL33%) to identify the two main mechanisms of stress corrosion cracking, including anodic dissolution and hydrogen embrittlement (cathodic). Five descriptive acoustic parameters including rise time, count, energy, amplitude and duration were used to analyze the obtained signals. In order to select the most effective acoustic characteristics and reduce the amount of information, principal component analysis was used. Subsequently, with the fuzzy method (FCM clustering) based on the optimized data from the analysis of the main components, it was possible to distinguish and separate these two types of corrosion mechanisms. According to the obtained results, it was found that the dominant mechanism in the phenomenon of stress corrosion cracking in HCL corrosive solution is the anodic dissolution mechanism, which in addition to increasing the corrosion current density, increases the dependence of stress corrosion on this mechanism by increasing the concentration of H+ and C- ions.

Detection of calcium particles in breast mammography images is important in the early detection of cancer. Identification of these particles is done manually by experts, which is associated with high cost and error. In this paper, a new method based on fuzzy clustering algorithm for fine-grained detection in mammographic images is proposed. In the proposed method, the low quality of mammographic images is improved with the help of preprocessing. By defining an appropriate membership function in fuzzy clustering, fine-grained regions are identified. Finally, the identified areas were classified into benign and malignant groups with the help of forward propagation neural network with error propagation training algorithm. The accuracy of identification of the desired area is 96.79% and the sensitivity of this identification is 97.20%. Compared to the previous method, the accuracy and sensitivity of fine-grained identification has been improved (95% of the desired area identification accuracy and 90.52% sensitivity).  In the classification of areas with the help of neural network, the accuracy was 97.5%. Evaluation criteria showed the superiority of the proposed method in the extraction of calcium particles and classification. The reason for the superiority of the proposed method is the high accuracy in extracting the desired area as well as the distinctive features extracted from the desired area.

The structure of operators in most traditional multi-objective evolutionary algorithms are based on fixed heuristics such as intersection and mutation, which are unable to learn the structures or properties of problems to create. To use evolutionary algorithms to learnability, news of evolutionary algorithms with the model is presented. In model evolutionary algorithms, innovative operators are replaced by machine learning models such as instructional and sample models. In this paper, a multi-objective evolutionary algorithm with a model is presented in which in each generation, a probable area of the search space deserves the model as a possible model. In the decision area in the search space, which are the dominant points, they are better ranked, we have clustered or different fuzzy methods, or on other points with the first order, it is a contest selection action. If you are missing, you take the form to be removed at close range, and the result is considered to be the center of the clusters, and then, clustering is done based on the nearest neighbors. The principal component analysis algorithm, which is the best method for reducing the given dimensions linearly, has been used for the models. New solutions are obtained from the model if it is a normal distribution. The proposed method is tested and the results are compared with the method of non-dominated sorting genetic algorithms. The results show that this method is faster than earlier methods and with fewer repetitions and evaluation of functions, the results are better and bold.

Nowadays, computer networks are being widely used in the world. Due to the widespread use of the internet, computer systems are prone to information theft and this has led to the emergence of intrusion detection systems (IDS). Thus, network security has become an essential subject in computer science responding to the increase of sensitive information. The current research has used fuzzy C-means (FCM) and Whale optimization algorithm (WOA) to propose an unsupervised machine learning intrusion identification system and has tested it with the KDD Cup 99 standard intrusion detection dataset. In this method, fuzzy C-means has been applied in order to distinguish intrusive activities from normal activities and Whale optimization algorithm has been used to achieve optimal separations among these activities. In order to help FCM, the WOA has been applied to start with suitable cluster centers rather than randomly initialized centers. Experimental results on KDD Cup 99 dataset showed that the proposed method offers higher detection accuracy and a lower false alarm rate compared to other similar algorithms. Therefore, the findings of the present study would be effective in solving complex problems related to IDS.

Many conventional e-Learning systems are based on static information and consider all learners the same, so they cannot meet their diverse needs and tastes. The main drawback of these systems is ignoring the previous interactions and interests of the learners. The e-learning recommender systems have been introduced with the aim of overcoming these problems and offering the most suitable personalized courses to each learner. The goal of this article is to propose a trust-based e-learning recommender system using fuzzy clustering while taking into account the learners' previous interactions and interests. For this purpose, the weighted association rules and rank prediction were used to produce a candidate list of learning courses and reclassification of the candidate list to generate the final recommendations list.

In this paper, a novel approach is proposed, which is based on combining the trust relationships among users and their common interests in order to calculate their similarities in an e-Learning recommender system while using fuzzy clustering and weighted association rules, which are aimed at recommending learning courses to the users. In the proposed method, after analyzing the similarities among users and constructing a trust matrix, the next stages are divided into two general phases: the clustering phase of the users and the phase of recommending suitable learning courses for the users. The clustering phase consists of two stages. In the first stage, the optimal number of clusters is obtained using the X-Means algorithm, and in the second stage, the fuzzy C-Means clustering is performed based on the number of clusters obtained. In the recommendation phase for the user, using the weighted association rules and the final clusters obtained for the users, the rank intended by the target user is predicted for each learning item according to the neighbors of the user’s cluster. Finally, based on the predicted rankings, N higher ranking course items are suggested as the target user's favorite items.

Implementation and evaluation of the proposed method on the Moodle dataset demonstrate that with the reduction of the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), the accuracy of the proposed recommendations is increased, utilizing trust relationships, and the coverage rate of the users and ranks has increased, using fuzzy clustering and weighted association rules, respectively, as compared with the other existing methods. These findings result from employing the fuzzy clustering of users based on their interests and the trust relationships among them, which make it possible for each user to join several clusters with different degrees of membership. Moreover, in utilizing weighted association rules, the association rules that are most compatible with the courses taken by the user are selected. Rules selection scores are calculated on the basis of not only the reliability factors but also a combination of the reliability factors and the user’s interest in learning courses.

Utilizing the criterion of trust among users increases the accuracy in choosing neighbors and limits the users' harmful effects and invalid opinions, which will ultimately lead to more accurate recommendations. Also, according to the fuzzy clustering of users, the prediction of the rating of different learning courses is done only based on the neighbors existing in the clusters of the target user. As a result, it will perform more efficiently for the massive volume of information available in an e-Learning system and it shall reduce the problem of data sparsity.

In this paper, a fuzzy rule extraction system is designed and the idea of ​​using this method in designing a fuzzy rule database is considered. First, the fuzzy backup vector machine is designed based on the clustering method. In this case, the backup vector machine will perform better in noise data or out-of-range data, and as a result, the rules extracted from it seem to be more accurate. The fuzzy backup vector machine model is simulated and then its backup vectors are used to derive fuzzy rules. The extracted rules are fuzzy rules that are obtained in the form of "if-then". The rules are extracted using two models of simple support vector machine and fuzzy support vector machine, which will show that the rules extracted from fuzzy backup vector machine in most cases have better accuracy in classification than ordinary backup vector machine. The number of extracted rules is an important parameter in the accuracy of the operation of this database, the number of rules extracted in the fuzzy method is less in most cases.

The complete knowledge of the cutting process and the performance of the sawing machine can help increase the efficiency and quality of the manufactured product.  During the field studies, 12 rock samples from two kinds of ornamental stones were collected and some major mechanical properties including uniaxial compressive strength (UCS), Mohs hardness (Mh), Schimazek’s F-abrasiveness factors (SF-a), and young modulus (YM) were measured. Also, Fuzzy C-means has been used as a soft computing technique in this study. All different studied rock samples are classified into 3, 4, and 5 classes. Then, the results of classification were compared with consumed energy values. Finally, it can be concluded that FCM could be a simple but efficient tool in the evaluation of the sawability of ornamental stone as one of the most important factors to estimation and prediction of production cost and productivity of processing plants.

The rock sawability and prediction of consumed energy is one of the most important factors in the estimation and prediction of production cost and productivity of processing plants. In this study, for laboratory tests, some rock blocks were collected from the studied quarries. Then, by using the fuzzy C-means clustering approached and considering laboratory results of rock samples, all of the rocks have been classified in 3, 4, and 5 separate clusters. The results clearly showed that the FCM algorithm was used as a reliable and efficient tool for classifying the ornamental stone.  

Nowadays, with the increasing growth of uncertain problems, the use of soft computing techniques with high ability in solving these kinds of problems has increased significantly. Assessment of the sawability of ornamental stone is the most important factor in the identification and prediction of production cost and productivity of processing plants. Given the unreliability of all experimental laboratory, one of the most important tasks in the sawability of ornamental stone’ classification is using a method with the highest possible accuracy. According to the importance of the issue, in this study, the Fuzzy C-means algorithm is used for the classification. Four important physical and mechanical characteristics of 12 rock samples are considered for the classification of sawability of ornamental stone from two kinds of ornamental stone, including hard and soft rock groups using Fuzzy C-means Optimization, including uniaxial compressive strength, Mohs hardness, Schmiazek F-abrasivity factor, and Young's modulus. Finally, in this study, the results of the classification are compared with consumed energy.

In this study employing Fuzzy C-means as soft computing technique and some major mechanical properties such as uniaxial compressive strength, Mohs hardness, Schmiazek F-abrasivity factor, and Young's modulus to evaluate the sawability of ornamental stone, 3 to 5 classes are considered. Generally, according to this research, the following remarks can be concluded: 1- The 12 rock samples from two kinds of ornamental stones, including hard and soft rock groups, are evaluated and tested. 2- A comparison was made between 3 different models (3 classes from 3 to 5 classes) with consumed energy of the sawing machine. The results show that all 12 rock samples are classified as very suitable. 3- In comparison to all classes, it can be concluded that FCM is a reliable technique for clustering the sawability of ornamental stone with highly acceptable degrees of robustness.

Wireless sensor networks are one of the most important tools for information acquisition and environment identification in many application areas. Recent advances in the field of electronics and wireless telecommunications have led to the design and manufacture of sensors with low power consumption, small size, reasonable price and various applications. Most research in the area of wireless sensor networks has focused on two dimensional sensor networks while in the real world, most of the applications are three dimensional. Some research in this area has focused on underwater, space, forestry, and environment applications. The main objective of the current research is increasing network lifetime by defining new parameters and embedding them in the fuzzy clustering or fuzzy C-means algorithm that has been adapted for three dimensional wireless sensor networks. One of the parameters that has been used in this research is limited movement of sensors. By adding this ability to the network, there is an expectation of improvement in network performance. The results of the experiments indicate the positive effect of this ability on network performance and lifetime.

Recommender systems are the systems that help users find and select their target items. Most of the available events for recommender systems are focused on recommending the most relevant items to the users and do not include any context information such as time, location . This paper is presented by the use of geographically tagged photo information which is highly accurate. The distinction point between this thesis and other similar articles is that this paper includes more context (weather conditions, users’ mental status, traffic level, etc.) than similar articles which include only time and location as context. This has brought the users close to each other in a cluster and has led to an increase in the accuracy. The proposed method merges the Colonial Competitive Algorithm and fuzzy clustering for a better and stronger processing against using merely the classic clustering and this has increased the accuracy of the recommendations. Flickr dataset is used to evaluate the presented method. Results of the evaluation indicate that the proposed method can provide location recommendations proportionate to the users’ preferences and their current visiting location.

Microarray datasets have an important role in identification and classification of the cancer tissues. In cancer researches, having a few samples of microarrays in cancer researches is one of the most concerns which lead to some problems in designing the classifiers. Moreover, due to the large number of features in microarrays, feature selection and classification are even more challenging for such datasets. Not all of these numerous features contribute to the classification task, and some even impede performance. Hence, appropriate gene selection method can significantly improve the performance of cancer classification. In this paper, a modified multi-objective cuckoo search algorithm is used to feature selection and sample selection to find the best available solutions. For accelerating the optimization process and preventing local optimum trapping, new heuristic approaches are included to the original algorithm. The proposed algorithm is applied on six cancer datasets and its results are compared with other existing methods. The results show that the proposed method has higher accuracy and validity in comparison to other existing approaches and is able to select the small subset of informative genes in order to increase the classification accuracy.

In this paper, an effective method for regression is presented in which a variety of fuzzy clustering methods and concepts of Hesitant fuzzy sets are used. First, the fuzzy clustering algorithm is applied to the data, and after projecting the cluster membership function on different features, the number of clusters of fuzzy sets is obtained on each dimension (or feature). We then consider these fuzzy sets as a hesitant fuzzy set on each feature, and we obtain the Hesitant Fuzzy Correlation Coefficient Matrix (HFCCM) for the attributes. Subsequently, a nonlinear mapping based on the principal components analysis of the HFCCM is used to convert the dataset's features into new features. Finally, the new extracted features are assigned to the fuzzy clustering algorithm and a Sugeno fuzzy regression system is fitted. The proposed method was compared with some other methods to several regression datasets. The results of the experiments indicate that the proposed method is successful in extracting and reducing the characteristics, as well as increasing the regression accuracy. Also, the number of rules of the fuzzy regression model in the proposed method is fairly low.