Rough Fuzzy Clustering Research Articles

IFKC and Optimized DeTrac Deep Convolutional Neural Network Based Location Prediction in the Mobile IOT

Wireless Sensor Network (WSN) is a noteworthy technological advancement in the Internet of Things (IoT). Due to its severe resource constraints, this network necessitates the development of energy-efficient routing strategies. In the context of the Internet of Things, a cluster-based routing problems frequently struggle with unequal power usage. Therefore, this paper proposes an Improved Fractional Rough Fuzzy K-means Clustering and Optimized DeTraC Deep Convolutional Neural Network based Location Prediction in Mobile Internet of Things (IFKC-ODTN-LP-MIoT) system to address unequal power consumption in cluster-based IoT routing. By proposing Improved Fractional Rough Fuzzy K-means (IF-RFKM) for cluster head selection and an optimized DeTraC Deep Convolutional Neural Network (DT-DCNN) the system aims to enhance energy efficiency for location prediction. Then Adolescent Identity Search Algorithm (AISA) optimizes DT-DCNN parameters for improved accuracy. The experimental results demonstrate significant improvements in Computational efficiency, network lifetime and delay compared to the existing approaches.

Dynamic iterative imputation algorithm based on rough fuzzy C-Means clustering

Abstract Missing data is a very common phenomenon in daily life. To mitigate its adverse impact on data analysis, this paper proposes a dynamic iterative imputation algorithm based on the rough fuzzy C-means algorithm. The algorithm incorporates dynamic approximations to partition and iterate the cluster assignment of missing sample points, utilizing information from complete sample points within the same cluster for iterative imputation. The imputation results are evaluated by using MAE and RMSE metrics, and the optimal number of iterations and imputation values are determined by minimizing these metrics. To verify the effectiveness of the proposed algorithm, 6 UCI public datasets are selected for imputation tests, and the change curves of metric value with iterations are generated under different missing proportions in each dataset. The optimal imputation result is obtained based on the lowest point of the curve. Subsequently, the performance of the proposed algorithm is compared with three cluster-based and five machine learning-based imputation algorithms. The results demonstrate the significant superiority of the proposed algorithm over the other methods, achieving a more approximate imputation of missing values in the dataset.

Rough Fuzzy K-Means Clustering Based on Parametric Decision-Theoretic Shadowed Set with Three-Way Approximation

Rough Fuzzy K-Means Clustering Based on Parametric Decision-Theoretic Shadowed Set with Three-Way Approximation

A robust multi-view knowledge transfer-based rough fuzzy C-means clustering algorithm

Rough fuzzy clustering algorithms have received extensive attention due to the excellent ability to handle overlapping and uncertainty of data. However, existing rough fuzzy clustering algorithms generally consider single view clustering, which neglects the clustering requirements of multiple views and results in the failure to identify diverse data structures in practical applications. In addition, rough fuzzy clustering algorithms are always sensitive to the initialized cluster centers and easily fall into local optimum. To solve the above problems, the multi-view and transfer learning are introduced into rough fuzzy clustering and a robust multi-view knowledge transfer-based rough fuzzy c-means clustering algorithm (MKT-RFCCA) is proposed in this paper. First, multiple distance metrics are adopted as multiple views to effectively recognize different data structures, and thus positively contribute to clustering. Second, a novel multi-view transfer-based rough fuzzy clustering objective function is constructed by using fuzzy memberships as transfer knowledge. This objective function can fully explore and utilize the potential information between multiple views and characterize the uncertainty information. Then, combining the statistical information of color histograms, an initialized centroids selection strategy is presented for image segmentation to overcome the instability and sensitivity caused by the random distribution of the initialized cluster centers. Finally, to reduce manual intervention, a distance-based adaptive threshold determination mechanism is designed to determine the threshold parameter for dividing the lower approximation and boundary region of rough fuzzy clusters during the iteration process. Experiments on synthetic datasets, real-world datasets, and noise-contaminated Berkeley and Weizmann images show that MKT-RFCCA obtains favorable clustering results. Especially, it provides satisfactory segmentation results on images with different types of noise and preserves more specific detail information of images.

Ensemble CART surrogate-assisted automatic multi-objective rough fuzzy clustering algorithm for unsupervised image segmentation

Multi-objective clustering algorithms (MOCAs) are popular in unsupervised image segmentation due to their merit of meeting multiple segmentation requirements and the prospect of automatically estimating the number of clusters. However, most of them suffer from high time costs and are easily to be influenced by the uncertainty when handling real complex images. To address these issues, we propose an ensemble classification and regression tree (CART) surrogate-assisted automatic multi-objective rough fuzzy clustering (ECS-AMRFC) algorithm for unsupervised image segmentation. Firstly, a cluster medoid-based encoding scheme is employed to represent solutions with different number of clusters and meanwhile lessen the length of encoding. Then, we design an ensemble CART as the surrogate model to significantly reduce the computational burden. Moreover, a surrogate model management strategy is proposed to accelerate the optimization and enhance the quality of surrogate modeling. To handle the uncertainty in data, we extend the rough fuzzy clustering into MOCAs and construct three complementary objective functions to seek proper cluster medoids from multiple perspectives. In addition, the Gaussian kernel is introduced into the objective functions to handle image pixels that cannot separate linearly in the feature space. Finally, a kernelized rough fuzzy clustering validity index is defined to automatically select the optimal solution with no requirements of any prior knowledge. Experiments show that ECS-AMRFC not only identifies appropriate number of clusters on different kinds of images, but also obtains better segmentation results than state-of-the-art rough fuzzy clustering algorithms and automatic MOCAs.

A reliable region information driven kriging-assisted multiobjective rough fuzzy clustering algorithm for color image segmentation

Multiobjective clustering algorithms (MOCAs) are becoming increasingly popular with the merit of segmenting images from multiple perspectives. The performances of MOCAs highly depend on their fitness functions. However, most existing MOCAs adopt one pair of complementary fitness functions, which always measure intra-class compactness and inter-class separation, respectively. This may result in insufficient ability to recognize and mine feature structures from complex images. Moreover, information within color images, such as region information and uncertain information, can barely receive enough attention in MOCAs. To resolve these problems, we propose a reliable region information driven Kriging-assisted multiobjective rough fuzzy clustering algorithm (RRI-KMRFC). Firstly, a reliability-based region information extraction strategy (RRIES) is designed to obtain reliable image information with satisfactory regional homogeneity and abundant image details. Secondly, the derived region information is used to construct three complementary fitness functions, focusing on rough intra-class compactness, rough inter-class separation, and regional consistency, respectively. Such fitness functions can effectively identify the clustering structure, maintain contour details, and characterize uncertain information from color images. To efficiently optimize the proposed functions, an incremental Kriging-assisted evolutionary framework is presented to decrease the expensive function evaluations in which an improved infill sampling strategy is devised to assist in finding unexplored areas in the decision space. Finally, a rough fuzzy clustering validity index with reliable region information is proposed to select the optimal trade-off solution. Experiments performed on Berkeley and Weizmann images confirm the effectiveness and robustness of RRI-KMRFC.

Knee Point Guided Competitive Learning Approach to Surrogate Assisted Multi-Objective Rough Fuzzy Clustering for Image Segmentation

Knee Point Guided Competitive Learning Approach to Surrogate Assisted Multi-Objective Rough Fuzzy Clustering for Image Segmentation

A Reliable Region Information Driven Kriging-Assisted Multiobjective Rough Fuzzy Clustering Algorithm for Color Image Segmentation

A Reliable Region Information Driven Kriging-Assisted Multiobjective Rough Fuzzy Clustering Algorithm for Color Image Segmentation

Power Transformer Condition Assessment Method based on Improved Rough Fuzzy K-means Clustering

As an important equipment of power transmission and transformation, power transformer plays a direct role on the reliability of power supply. Considering the low proportion of power transformer fault data and the overlap boundary with normal data, an imbalance measurement of cluster size is introduced and a power transformer state assessment based on rough fuzzy k-means clustering is proposed. The developed method can not only judge the type of fault that has occurred, but also predict the possible future faults of power transformers. The effectiveness of the designed method is verified by experimental comparative analysis.

Partially Supervised Kernel Induced Rough Fuzzy Clustering for Brain Tissue Segmentation

In modern imaging diagnosis Magnetic Resonance Imaging (MRI) is possibly one of the widely used effective techniques particularly for brain tissue segmentation. Clustering techniques may not be perfect always. Clustering can be significantly improved by supervising partially. A novel partially supervised kernel induced rough fuzzy clustering is proposed for brain tissue segmentation by employing a small quantity of labeled pixels with constraint seeded policy. Labeled pixels act as the constraints which are utilized to initialize the clustering process and guide the method towards a more accurate partitioning. Kernel trick used here enhances the possibility of linear partition of different complex segments of brain which cannot separate linearly in its original feature space. Whereas, the rough and fuzzy set handles the overlappingness, vagueness and indiscernibility of different tissue regions. A variety of benchmark brain MRI datasets are used for the experiments. The ability of the method is compared with state-of-the-art clustering segmentation techniques and evaluated using different validity indices. Experimental results confirm that the technique considerably enhances the segmentation accuracy with a little quantity of supervision. Enhancement in accuracy gained by the method compared to the other techniques are 0.3, 0.37, 1.15, and 1.03% for IBSR datasets 144, 150, 155, and 167, respectively, and 1.02% for the BrainWeb dataset 85. Statistical impact of the method is confirmed from the paired t-test results.

A Shadowed Rough-fuzzy Clustering Algorithm Based on Mahalanobis Distance for Intrusion Detection

Intrusion detection has been widely used in many application domains; thus, it has caught significant attention in academic fields these years. Assembled with more and more sub-systems, the network is more vulnerable to multiple attacks aiming at the network security. Compared with the other issues such as complex environment and resources-constrained devices, network security has been the biggest challenge for Internet construction. To deal with this problem, a fundamental measure for safeguarding network security is to select an intrusion detection algorithm. As is known, it is less effective to determine the abnormal behavior as an intrusion and learn the entire scope of the normal behavior with the traditional anomaly-based algorithm for Internet intrusion detection. In this paper, we propose an intrusion-detecting algorithm of shadowed rough-fuzzy clustering based on Mahalanobis distance, named MSRFCM. It adopts dissimilarity measurement of Mahalanobis distance to identify the relevant variables that significantly influence the clustering performance and reduce the error rate in the process of partitioning clusters with high attribute correlation. And shadowed rough-fuzzy clustering (SRFCM) is applied to obtaining real value-approaching prototypes based on iteration and partitioning the data set into more meaningful clusters. Through simulation with the NSL-KDD intrusion data set and three other intrusion data sets, the Mahalanobis distance-based shadowed rough-fuzzy clustering algorithm has improved performance in intrusion detection.

InOvIn: A fuzzy-rough approach for detecting overlapping communities with intrinsic structures in evolving networks

Real-world networks, such as biological, biomedical and social networks, often contain overlapping and intrinsic communities. More significantly, such networks are growing or evolving over time, which leads to a continuous alteration of community structures. Detecting overlapping community together with intrinsic structures in evolving scenarios is one of the challenging tasks. Prior researches are limited in handling all the events together while designing a community detector.We propose an integrated solution, InOvIn (Intrinsic Overlapping Community Detection in Incremental Networks), for detecting overlapping, non-overlapping and intrinsic communities in evolving networks. Herein, we have explored a rough-fuzzy clustering approach for overlapping community detection. Fuzzy membership helps in soft decision making for deciding membership of a node towards a target community. While rough boundary of the communities decides the shared membership of a node in multiple communities. The node degree density variation measure is used to discover the existence of intrinsic community within a community.We assess the performance of InOvIn in light of twelve (12) popular real-world social networks. It may be noted that available real-world networks are lacking in labeled overlapping and intrinsic communities. Hence, we synthetically generate six (06) networks with both overlapping and intrinsic communities. We demonstrate the superiority of InOvIn over contemporary community detection methods using ten (10) different statistical assessment parameters. Interestingly, for the first time, our method detects intrinsic communities in PolBooks and Word Adjacencies networks.

Medical Image Segmentation by Partitioning Spatially Constrained Fuzzy Approximation Spaces

Image segmentation is an important prerequisite step for any automatic clinical analysis technique. It assists in visualization of human tissues, as accurate delineation of medical images requires involvement of expert practitioners, which is also time consuming. In this background, the rough-fuzzy clustering algorithm provides an effective approach for image segmentation. It handles uncertainties arising due to overlapping classes and incompleteness in class definition by partitioning the fuzzy approximation spaces. However, the existing rough-fuzzy clustering algorithms do not consider the spatial distribution of the image. They depend only on the distribution of pixels to determine their class labels. In this regard, this article introduces a new algorithm, termed as spatially constrained rough-fuzzy $c$ -means (sRFCM) for medical image segmentation. The proposed sRFCM algorithm combines wisely the merits of rough-fuzzy clustering and local neighborhood information. In the proposed algorithm, the labels of local neighbors influence in the determination of the label of center pixel. The effect of local neighbors acts as a regularizer. Moreover, the proposed sRFCM algorithm partitions each cluster in possibilistic lower approximation or core region and probabilistic boundary region. The cluster centroid depends on the core and boundary regions, weight parameter, and neighborhood regularizer. A novel segmentation validity index, termed as neighborhood Silhouette, is proposed to find out the optimum values of regularizer and weight parameter, controlling the performance of the sRFCM. The efficacy of the proposed sRFCM algorithm, as well as several existing segmentation algorithms, is demonstrated on four brain MR volume databases and one HEp-2 cell image data.

Rough Hypercuboid Based Generalized and Robust IT2 Fuzzy C-Means Algorithm.

One of the important issues in pattern recognition and machine learning is how to find natural groups present in a dataset. In this regard, this paper presents a novel clustering algorithm, called rough hypercuboid-based interval type-2 fuzzy c -means (RIT2FCM). It judiciously integrates the merits of the rough hypercuboid approach, c -means algorithm, and interval type-2 fuzzy set, to address the uncertainty associated with real-life datasets. Using the concept of hypercuboid equivalence partition matrix (HEM) of rough hypercuboid approach, the lower approximation and boundary region of each cluster are implicitly defined, without using any prespecified threshold parameter. The interval-valued fuzzifier is applied to address the uncertainty coupled with different parameters of rough-fuzzy clustering algorithms, where the determination of the appropriate value of fuzzifier is a difficult task. An analytical formulation on the convergence analysis of the proposed RIT2FCM algorithm, along with a theoretical bound of its fuzzifier, is also introduced. The efficacy of the proposed RIT2FCM method is extensively compared with that of several existing clustering algorithms, using some cluster validity and classification rate indices on various real-life datasets. The proposed algorithm performs better than the state-of-the-art c -means algorithms in 92.59% cases, with respect to different cluster validity indices, in lesser computation time.

Optimal rough fuzzy clustering for user profile ontology based web page recommendation analysis

Optimal rough fuzzy clustering for user profile ontology based web page recommendation analysis

Semi-Supervised Rough Fuzzy Clustering for Brain MRI Segmentation

Semi-Supervised Rough Fuzzy Clustering for Brain MRI Segmentation

Multigranulation rough-fuzzy clustering based on shadowed sets

In this study, a new technique of rough-fuzzy clustering based on multigranulation approximation regions is developed to tackle the uncertainty associated with the fuzzifier parameter m. According to shadowed set theory, the multigranulation approximation regions for each cluster can be formed based on fuzzy membership degrees under the multiple values of fuzzifier parameter with a partially ordered relation. The uncertainty generated by the fuzzifier parameter m can be captured and interpreted through the variations in approximation regions among different levels of granularity, rather than at a single level of granularity under a specific fuzzifier value. An ensemble strategy for updating prototypes is then presented based on the constructed multigranulation approximation regions, in which the prototype calculations that may be spoiled due to the uncertainty caused by a single fuzzifier value can be modified. Finally, a multilevel degranulation mechanism is introduced to evaluate the validity of clustering methods. By integrating the notions of shadowed sets and multigranulation into rough-fuzzy clustering approaches, the overall topology of data can be captured well and the uncertain information implicated in data can be effectively addressed, including the uncertainty generated by fuzzification coefficient, the vagueness arising in boundary regions and overlapping partitions. The essence of the proposed method is illustrated by comparative experiments in terms of several validity indices.

Integrated Rough Fuzzy Clustering for Categorical data Analysis

In recent times, advanced data mining research has been mostly focusing on clustering of categorical data, where a natural ordering in attribute values is missing. To address this fact the Rough Fuzzy K-Modes clustering technique has been recently developed in order to handle imperfect information, i.e. indiscernibility (coarseness) and vagueness within the dataset. However, it has been observed that the said technique suffers from the problem of local optima due to the random choice of initial cluster modes. Hence, in this paper, we have proposed an integrated clustering technique using multi-phase learning. In this regard, first, Simulated Annealing based Rough Fuzzy K-Modes and Genetic Algorithm based Rough Fuzzy K-Modes are proposed in order to perform the clustering better by considering clustering as an underlying optimization problem. These clustering methods individually produce clusters having set of central and peripheral points. Thereafter, for each case, final improved clustering results are obtained by assigning peripheral points to a particular crisp cluster using Random Forest, where central points are used as training set. Second, the varying cardinality of the training and testing sets produced by each clustering method further motivated us to propose a generalized technique called Integrated Rough Fuzzy Clustering using Random Forest, where, results of three aforementioned clustering techniques are used to compute the roughness measure. Based on this measure, three different sets namely best central points, semi-best central points and pure peripheral points are determined. Thereafter, using multi-phase learning, best central points are used to classify the semi-best central points and then using both of them, pure peripheral points are classified by Random Forest. Experimental results are reported quantitatively and visually to demonstrate the effectiveness of the proposed methods in comparison with well-known state-of-the-art methods for six synthetic and five real-life datasets. Finally, statistical significance tests are conducted to establish the superiority of the results produced by the proposed methods.

MIMPFC: Identifying miRNA-mRNA regulatory modules by combining phase-only correlation and improved rough-fuzzy clustering.

MicroRNAs (miRNAs) play a key role in gene expression and regulation in various organisms. They control a wide range of biological processes and are involved in several types of cancers by causing mRNA degradation or translational inhibition. However, the functions of most miRNAs and their precise regulatory mechanisms remain elusive. With the accumulation of the expression data of miRNAs and mRNAs, many computational methods have been proposed to predict miRNA-mRNA regulatory relationship. However, most existing methods require the number of modules predefined that may be difficult to determine beforehand. Here, we propose a novel computational method to discover miRNA-mRNA regulatory modules by combining Phase-only correlation and improved rough-Fuzzy Clustering (MIMPFC). The proposed method is evaluated on three heterogeneous datasets, and the obtained results are further validated through relevant literatures, biological significance and functional enrichment analysis. The analysis results show that the identified modules are highly correlated with the biological conditions. A large part of the regulatory relationships found by MIMPFC has been confirmed in the experimentally verified databases. It demonstrates that the modules found by MIMPFC are biologically significant.

Rough-Fuzzy Clustering Based on Two-Stage Three-Way Approximations

A general framework of rough-fuzzy clustering based on two-stage three-way approximations is presented in this paper. The proposed framework can deal with the uncertainties caused by the membership degree distributions of patterns. In the first stage (macro aspect), three-way approximations with respect to a fixed cluster can be formed from the global observation on data which can capture the data topology well about this cluster. In the second stage (micro aspect), the fuzziness of individual patterns over all clusters can be measured with De Luca and Termini’s method, based on which three-way approximations with respect to the whole data set can be generated such that the uncertainties of the locations of individual patterns can be detected. By integrating the approximation region partitions obtained in the two stages, i.e., using the partition results obtained in the second stage to modify the partition results obtained in the first stage, the misled prototype calculations can be verified and the obtained prototypes tend to their natural positions. Comparative experiments on a synthetic data set and some benchmark data sets demonstrate the improved performance of the proposed method.