Robust Clustering Algorithm Research Articles

Data-driven approaches for tau-PET imaging biomarkers in Alzheimer's disease.

Previous positron emission tomography (PET) studies have quantified filamentous tau pathology using regions-of-interest (ROIs) based on observations of the topographical distribution of neurofibrillary tangles in post-mortem tissue. However, such approaches may not take full advantage of information contained in neuroimaging data. The present study employs an unsupervised data-driven method to identify spatial patterns of tau-PET distribution, and to compare these patterns to previously published "pathology-driven" ROIs. Tau-PET patterns were identified from a discovery sample comprised of 123 normal controls and patients with mild cognitive impairment or Alzheimer's disease (AD) dementia from the Swedish BioFINDER cohort, who underwent [18 F]AV1451 PET scanning. Associations with cognition were tested in a separate sample of 90 individuals from ADNI. BioFINDER [18 F]AV1451 images were entered into a robust voxelwise stable clustering algorithm, which resulted in five clusters. Mean [18 F]AV1451 uptake in the data-driven clusters, and in 35 previously published pathology-driven ROIs, was extracted from ADNI [18 F]AV1451 scans. We performed linear models comparing [18 F]AV1451 signal across all 40 ROIs to tests of global cognition and episodic memory, adjusting for age, sex, and education. Two data-driven ROIs consistently demonstrated the strongest or near-strongest effect sizes across all cognitive tests. Inputting all regions plus demographics into a feature selection routine resulted in selection of two ROIs (one data-driven, one pathology-driven) and education, which together explained 28% of the variance of a global cognitive composite score. Our findings suggest that [18 F]AV1451-PET data naturally clusters into spatial patterns that are biologically meaningful and that may offer advantages as clinical tools.

TTClust: A Versatile Molecular Simulation Trajectory Clustering Program with Graphical Summaries.

It is extremely helpful to be able to partition the thousands of frames produced in molecular dynamics simulations into a limited number of most dissimilar conformations. While robust clustering algorithms are already available to do so, there is a distinct need for an easy-to-use clustering program with complete user control, taking as input a trajectory from any molecular dynamics (MD) package and outputting an intuitive display of results with plots allowing at-a-glance analysis. We present TTClust (for Trusty Trajectory Clustering), a python program that uses the MDTraj package to fill this need.

Significantly Fast and Robust Fuzzy C-Means Clustering Algorithm Based on Morphological Reconstruction and Membership Filtering

As fuzzy c-means clustering (FCM) algorithm is sensitive to noise, local spatial information is often introduced to an objective function to improve the robustness of the FCM algorithm for image segmentation. However, the introduction of local spatial information often leads to a high computational complexity, arising out of an iterative calculation of the distance between pixels within local spatial neighbors and clustering centers. To address this issue, an improved FCM algorithm based on morphological reconstruction and membership filtering (FRFCM) that is significantly faster and more robust than FCM is proposed in this paper. First, the local spatial information of images is incorporated into FRFCM by introducing morphological reconstruction operation to guarantee noise-immunity and image detail-preservation. Second, the modification of membership partition, based on the distance between pixels within local spatial neighbors and clustering centers, is replaced by local membership filtering that depends only on the spatial neighbors of membership partition. Compared with state-of-the-art algorithms, the proposed FRFCM algorithm is simpler and significantly faster, since it is unnecessary to compute the distance between pixels within local spatial neighbors and clustering centers. In addition, it is efficient for noisy image segmentation because membership filtering are able to improve membership partition matrix efficiently. Experiments performed on synthetic and real-world images demonstrate that the proposed algorithm not only achieves better results, but also requires less time than the state-of-the-art algorithms for image segmentation.

Time Series, Spectral Densities and Robust Functional Clustering

In this work, a robust clustering algorithm for stationary time series is proposed. The algorithm is based on the use of estimated spectral densities, which are considered as functional data, as the basic characteristic of stationary time series for clustering purposes. A robust algorithm for functional data is then applied to the set of spectral densities. Trimming techniques and restrictions on the scatter within groups reduce the effect of noise in the data and help to prevent the identification of spurious clusters. The procedure is tested in a simulation study and is also applied to a real data set.

Robust clustering by identifying the veins of clusters based on kernel density estimation

Clustering by fast search and find of density peaks(DPC) was an efficient clustering algorithm proposed by Rodriguez and Laio [49]. It adopts a concise but effective categorizing strategy which assigns data points to the same cluster as their nearest neighbors with higher densities. However, it suffers from the so-called “chain reaction” due to the simplistic strategy. What’s more, the accuracy of DPC badly depends on the selection of cut off distance dc when the data scale ranges. In order to take advantage of DPC whilst avoiding the drawbacks aforementioned, this paper proposed a robust clustering algorithm named IVDPC which provides a feasible approach for solving the classification problem of data with different shape and distribution. The local density is estimated through a non-parametric density estimation method first. Then, by calculating the similarity matrix of points and connecting the most resembled pairs continuously from high density regions to the edge of clusters, IVDPC identifies the main structure(veins) of clusters and classifies the rest of the samples precisely to the nearest vein. Having veins rather than one representative point to represent a cluster allows IVDPC to adjust well to the geometry of non-spherical shapes and decrease the chain reaction of DPC. The method proposed is benchmarked on artificial and real-world data sets against several baseline methods. The experimental results demonstrate that IVDPC can recognize the structure distribution of clusters and perform better in clustering accuracy over several state-of-art algorithms.

A robust gene clustering algorithm based on clonal selection in multiobjective optimization framework

Gene clustering is a prerequisite in the analysis of microarray data where sets of co-expressed genes are clustered. In this paper, a multi-objective clonal selection optimization algorithm (MCSOA) is developed based on the immune system behavior for gene clustering purposes in which the number of clusters can vary in a predefined range. To achieve a reliable clustering outcome on various gene expression (GE) datasets, the most effective clustering validity indexes are incorporated and represented in terms of two conflicting objective functions. For the sake of fast convergence to the optimal solutions, a new population updating mechanism is iteratively applied to select the less-dominate solutions of the previous iteration. The proposed clustering technique is implemented on various publicly available microarray datasets. Comparing the results with those of the widely used gene clustering techniques confirms the superiority and efficacy of the proposed technique.

Constraint-based clustering by fast search and find of density peaks

Clustering by fast search and find of density peaks (CFDP) algorithm first proposed on Science is based on assumptions that the cluster center has the highest density among its neighbors and keeps a distance from other cluster centers. In CFDP algorithm, a local density metric and a minimal distance vector are first calculated for constructing a decision graph to select cluster centers. However, CFDP's performance is quite sensitive to parameter selection and relies on other prior knowledge. To solve the problem, this paper proposed a new clustering algorithm named constraint-based clustering by fast search and find of density peaks (CCFDP). In the proposed algorithm, several potential cluster centers are automatically formed and the structural information from constraints could be made full use of. CCFDP adopts a new method to obtain the density metric and the decision graph. After that, the decision graph is analyzed from different perspectives to help complete the final clustering. CCFDP is a semi-supervised robust clustering algorithm, combining semi-supervised constraints, density clustering and hierarchical clustering. Three synthetic and seven open datasets are used for testing its performance and robustness. The final results show that CCFDP outperforms other well-known constraint-based clustering algorithms.

Effective Kernel-Based Fuzzy Clustering Systems in Analyzing Cancer Database

The greatest challenge in high-dimensional medical cancer databases is to differentiate the available subtypes due to uncertainty associated with the objects of the database. Recently, mathematical algorithm-based diagnosing system plays an increasingly important role in analyzing the high-dimensional medical cancer databases. Particularly, fuzzy clustering technique has taken a major role in clustering medical cancer databases. The fuzzy clustering techniques are not robust with high-dimensional databases which have more similar objects. Therefore, this paper tries to propose robust fuzzy clustering algorithms for effective analysis of high-dimensional medical database. This paper introduces the objective function of proposed robust fuzzy clustering techniques by incorporating Laplacian kernel-induced distance, Canberra distance, possibilistic memberships, and fuzzy memberships. The proposed methods have been implemented with high-dimensional breast cancer database containing three subclasses which are the leading causes of cancer deaths in the world. Benchmark datasets have been used to evaluate the performance of the proposed methods, and this paper has shown the effectiveness of the proposed methods through clustering accuracy.

An Efficient Method for Detection of Outliers in Tracer Curves Derived from Dynamic Contrast-Enhanced Imaging

Presence of outliers in tracer concentration-time curves derived from dynamic contrast-enhanced imaging can adversely affect the analysis of the tracer curves by model-fitting. A computationally efficient method for detecting outliers in tracer concentration-time curves is presented in this study. The proposed method is based on a piecewise linear model and implemented using a robust clustering algorithm. The method is noniterative and all the parameters are automatically estimated. To compare the proposed method with existing Gaussian model based and robust regression-based methods, simulation studies were performed by simulating tracer concentration-time curves using the generalized Tofts model and kinetic parameters derived from different tissue types. Results show that the proposed method and the robust regression-based method achieve better detection performance than the Gaussian model based method. Compared with the robust regression-based method, the proposed method can achieve similar detection performance with much faster computation speed.

A segmentation of pulmonary nodules based on improved fuzzy C-means clustering algorithm

According to reports, lung cancer is gradually becoming the first cancer that threatens human life. The early stage of lung cancer is in the form of pulmonary nodules. The key issue in computer-aided diagnosis of lung tumors is to correct and accelerate rapid segmentation of diseased tissue. Therefore, this paper proposes a robust fuzzy c-mean clustering algorithm for pulmonary nodules segmentation, which can effectively improve the adaptive degree of local domain pixels. Since the information of the domain pixels does not necessarily have a positive correlation with the central pixels, the reference mechanism of domain window pixel information needs to be redefined. The robust fuzzy c-means clustering algorithm redefines the grayscale of the spatial pixel points in the domain and selects different fuzzy factors according to the reference standard. Based on this, the weights of different fuzzy factors are updated according to the characteristics of pixel points and gray fluctuation in pixel domain. The experimental results show that this method is superior to other typical algorithms in the segmentation of pulmonary nodules.

Adaptive kernelized evidential clustering for automatic 3D tumor segmentation in FDG–PET images

Automatically and reliably delineating tumor contours in noisy and blurring PET images is a challenging work in clinical oncology. In this paper, we introduce a specific unsupervised learning method to this end. More specifically, a robust clustering algorithm with spatial knowledge enhancement is developed in the framework of belief functions, a formal and powerful tool for modeling and reasoning with uncertain and/or imprecise information. Diverse patch-based image features are extracted to comprehensively describe PET image voxels. Then, informative input features are iteratively selected to learn an adaptive kernel-induced metric in an unsupervised way, so as to precisely grouping voxels into different clusters. The effectiveness of the proposed method has been evaluated on FDG–PET images for lung tumor patients.

Robust clustering using a kNN mode seeking ensemble

In this paper we present a new algorithm for parameter-free clustering by mode seeking. Mode seeking, especially in the form of the mean shift algorithm, is a widely used strategy for clustering data, but at the same time prone to poor performance if the parameters are not chosen correctly. We propose to form a clustering ensemble consisting of repeated and bootstrapped runs of the recent kNN mode seeking algorithm, an algorithm which is faster than ordinary mean shift and more suited for high dimensional data. This creates a robust mode seeking clustering algorithm with respect to the choice of parameters and high dimensional input spaces, while at the same inheriting all other strengths of mode seeking in general. We demonstrate promising results on a number of synthetic and real data sets.

A robust automatic clustering algorithm for probability density functions with application to categorizing color images

ABSTRACTThis study develops a robust automatic algorithm for clustering probability density functions based on the previous research. Unlike other existing methods that often pre-determine the number of clusters, this method can self-organize data groups based on the original data structure. The proposed clustering method is also robust in regards to noise. Three examples of synthetic data and a real-world COREL dataset are utilized to illustrate the accurateness and effectiveness of the proposed approach.

A robust fuzzy clustering algorithm using mean-field-approximation based hidden Markov random field model for image segmentation

Although how to deal well with images corrupted with noise is a commonly encountered task in image segmentation, the design of efficient and robust segmentation algorithms still keeps a challenging research topic. In this paper, a robust fuzzy-clustering-based image segmentation algorithm is presen ted to effectively segment noisy images. The proposed algorithm is derived from both the conventional fuzzy c-means (FCM) clustering algorithm and the hidden Markov random field (HMRF) model with the capability of incorporating spatial information. The performance of the proposed algorithm is experimentally evaluated with the comparison algorithms. Experimental results on synthetic and real images demonstrate the effectiveness of the proposed algorithm.

Cluster Validation Method for Determining the Number of Clusters in Categorical Sequences.

Cluster validation, which is the process of evaluating the quality of clustering results, plays an important role for practical machine learning systems. Categorical sequences, such as biological sequences in computational biology, have become common in real-world applications. Different from previous studies, which mainly focused on attribute-value data, in this paper, we work on the cluster validation problem for categorical sequences. The evaluation of sequences clustering is currently difficult due to the lack of an internal validation criterion defined with regard to the structural features hidden in sequences. To solve this problem, in this paper, a novel cluster validity index (CVI) is proposed as a function of clustering, with the intracluster structural compactness and intercluster structural separation linearly combined to measure the quality of sequence clusters. A partition-based algorithm for robust clustering of categorical sequences is also proposed, which provides the new measure with high-quality clustering results by the deterministic initialization and the elimination of noise clusters using an information theoretic method. The new clustering algorithm and the CVI are then assembled within the common model selection procedure to determine the number of clusters in categorical sequence sets. A case study on commonly used protein sequences and the experimental results on some real-world sequence sets from different domains are given to demonstrate the performance of the proposed method.

SLMBC: spiral life cycle model-based Bayesian classification technique for efficient software fault prediction and classification

Software fault prediction and classification plays a vital role in the software development process for assuring high quality and reliability of the software product. Earlier prediction of the fault-prone software modules enables timely correction of the faults and delivery of reliable product. Generally, the fuzzy logic, decision tree and neural networks are deployed for fault prediction. But these techniques suffer due to low accuracy and inconsistency. To overcome these issues, this paper proposes a spiral life cycle model-based Bayesian classification technique for efficient software fault prediction and classification. In this process, initially the dependent and independent software modules are identified. The spiral life cycle model is used for testing the software modules in each life cycle of the software development process. Bayesian classification is applied to classify the software modules as faulty module and non-faulty module, by using the probability distribution models. Robust similarity-aware clustering algorithm performs clustering of the faulty and non-faulty software modules based on the similarity measure of the features in the dataset. From the experimental results, it is observed that the proposed method enables accurate prediction and classification of the faulty modules. The proposed technique achieves higher accuracy, precision, recall, probability of detection, F-measure and lower error rate than the existing techniques. The misclassification rate of the proposed technique is found to be lower than the existing techniques. Hence, the reliability of the software development process can be improved.

AVLINK: Robust Clustering Algorithm based on Average Link Applied to Protein Sequence Analysis

AVLINK: Robust Clustering Algorithm based on Average Link Applied to Protein Sequence Analysis

Evaluation of the Quality of Robust Clustering Algorithm TCLUST on the Example of Dataset of Air Pollutants Emission in Krakow

Acquisition and data collection is currently a very dynamic processes. In order to obtain from data useful information, when huge quantities of data, the processing of the data is not a trivial task. Cluster analysis is very helpful in this and the result of grouping the result of grouping allows us to comprehend the available information and look at it from a different perspective. In any case, we are not able to show the entire spectrum of issues related to data analysis. Therefore we limit our discussion to the analysis of clusters, then we describe the TCLUST algorithm. The authors of the algorithm are H. Fritz, L. A. García-Escudero, A. Mayo-Iscar (see Fritz et al. 2011, 2012). In the paper we present the pros and cons robust clustering algorithm, and we discuss the available functions in the package tclust. Then on the example of dataset of air pollutants emission in Krakow we try to evaluate the quality of robust clustering algorithm.

Novel Approach to Unsupervised Change Detection Based on a Robust Semi-Supervised FCM Clustering Algorithm

This study presents a novel approach for unsupervised change detection in multitemporal remotely sensed images. This method addresses the problem of the analysis of the difference image by proposing a novel and robust semi-supervised fuzzy C-means (RSFCM) clustering algorithm. The advantage of the RSFCM is to further introduce the pseudolabels from the difference image compared with the existing change detection methods; these methods, mainly use difference intensity levels and spatial context. First, the patterns with a high probability of belonging to the changed or unchanged class are identified by selectively thresholding the difference image histogram. Second, the pseudolabels of these nearly certain pixel-patterns are jointly exploited with the intensity levels and spatial information in the properly defined RSFCM classifier in order to discriminate the changed pixels from the unchanged pixels. Specifically, labeling knowledge is used to guide the RSFCM clustering process to enhance the change information and obtain a more accurate membership; information on spatial context helps to lower the effect of noise and outliers by modifying the membership. RSFCM can detect more changes and provide noise immunity by the synergistic exploitation of pseudolabels and spatial context. The two main contributions of this study are as follows: (1) it proposes the idea of combining the three information types from the difference image, namely, (a) intensity levels, (b) labels, and (c) spatial context; and (2) it develops the novel RSFCM algorithm for image segmentation and forms the proposed change detection framework. The proposed method is effective and efficient for change detection as confirmed by six experimental results of this study.

Robust clustering by detecting density peaks and assigning points based on fuzzy weighted K-nearest neighbors

Clustering by fast search and find of Density Peaks (referred to as DPC) was introduced by Alex Rodríguez and Alessandro Laio. The DPC algorithm is based on the idea that cluster centers are characterized by having a higher density than their neighbors and by being at a relatively large distance from points with higher densities. The power of DPC was demonstrated on several test cases. It can intuitively find the number of clusters and can detect and exclude the outliers automatically, while recognizing the clusters regardless of their shape and the dimensions of the space containing them. However, DPC does have some drawbacks to be addressed before it may be widely applied. First, the local density ρi of point i is affected by the cutoff distance dc, and is computed in different ways depending on the size of datasets, which can influence the clustering, especially for small real-world cases. Second, the assignment strategy for the remaining points, after the density peaks (that is the cluster centers) have been found, can create a “Domino Effect”, whereby once one point is assigned erroneously, then there may be many more points subsequently mis-assigned. This is especially the case in real-word datasets where there could exist several clusters of arbitrary shape overlapping each other. To overcome these deficiencies, a robust clustering algorithm is proposed in this paper. To find the density peaks, this algorithm computes the local density ρi of point i relative to its K-nearest neighbors for any size dataset independent of the cutoff distance dc, and assigns the remaining points to the most probable clusters using two new point assignment strategies. The first strategy assigns non-outliers by undertaking a breadth first search of the K-nearest neighbors of a point starting from cluster centers. The second strategy assigns outliers and the points unassigned by the first assignment procedure using the technique of fuzzy weighted K-nearest neighbors. The proposed clustering algorithm is benchmarked on publicly available synthetic and real-world datasets which are commonly used for testing the performance of clustering algorithms. The clustering results of the proposed algorithm are compared not only with that of DPC but also with that of several well known clustering algorithms including Affinity Propagation (AP), Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and K-means. The benchmarks used are: clustering accuracy (Acc), Adjusted Mutual Information (AMI) and Adjusted Rand Index (ARI). The experimental results demonstrate that our proposed clustering algorithm can find cluster centers, recognize clusters regardless of their shape and dimension of the space in which they are embedded, be unaffected by outliers, and can often outperform DPC, AP, DBSCAN and K-means.