Search results for "cluster analysis"
showing 10 items of 848 documents
2021
Strength training exercises are essential for rehabilitation, improving our health as well as in sports. For optimal and safe training, educators and trainers in the industry should comprehend exercise form or technique. Currently, there is a lack of tools measuring in-depth skills of strength training experts. In this study, we investigate how data mining methods can be used to identify novel and useful skill patterns from a binary multiple choice questionnaire test designed to measure the knowledge level of strength training experts. A skill test assessing exercise technique expertise and comprehension was answered by 507 fitness professionals with varying backgrounds. A triangulated appr…
Cluster Aggregation for Analyzing Event-Related Potentials
2017
Topographic analysis are references independent for Event-Related Potentials (ERPs), and thus render statistically unambiguous results. This drives us to develop an effective clustering approach to finding temporal samples possessing similar topographies for analysing the temporal-spatial ERPs data. The previous study called CARTOOL used single clustering method to cluster ERP data. Indeed, given a clustering method, the quality of clustering varies with data and the number of clusters, motivating us to implement and compare multiple clustering algorithms via using multiple similarity measurements. By finding the minimum distance among the various clustering methods and selecting the most s…
Sectors on sectors (SonS): A new hierarchical clustering visualization tool
2011
Clustering techniques have been widely applied to extract information from high-dimensional data structures in the last few years. Graphs are especially relevant for clustering, but many graphs associated with hierarchical clustering do not give any information about the values of the centroids' attributes and the relationships among them. In this paper, we propose a new visualization approach for hierarchical cluster analysis in which the above-mentioned information is available. The method is based on pie charts. The pie charts are divided into several pie segments or sectors corresponding to each cluster. The radius of each pie segment is proportional to the number of patterns included i…
Clustering categorical data: A stability analysis framework
2011
Clustering to identify inherent structure is an important first step in data exploration. The k-means algorithm is a popular choice, but K-means is not generally appropriate for categorical data. A specific extension of k-means for categorical data is the k-modes algorithm. Both of these partition clustering methods are sensitive to the initialization of prototypes, which creates the difficulty of selecting the best solution for a given problem. In addition, selecting the number of clusters can be an issue. Further, the k-modes method is especially prone to instability when presented with ‘noisy’ data, since the calculation of the mode lacks the smoothing effect inherent in the calculation …
A practical solution to the problem of automatic word sense induction
2004
Recent studies in word sense induction are based on clustering global co-occurrence vectors, i.e. vectors that reflect the overall behavior of a word in a corpus. If a word is semantically ambiguous, this means that these vectors are mixtures of all its senses. Inducing a word's senses therefore involves the difficult problem of recovering the sense vectors from the mixtures. In this paper we argue that the demixing problem can be avoided since the contextual behavior of the senses is directly observable in the form of the local contexts of a word. From human disambiguation performance we know that the context of a word is usually sufficient to determine its sense. Based on this observation…
A methodology to assess the intrinsic discriminative ability of a distance function and its interplay with clustering algorithms for microarray data …
2013
Abstract Background Clustering is one of the most well known activities in scientific investigation and the object of research in many disciplines, ranging from statistics to computer science. Following Handl et al., it can be summarized as a three step process: (1) choice of a distance function; (2) choice of a clustering algorithm; (3) choice of a validation method. Although such a purist approach to clustering is hardly seen in many areas of science, genomic data require that level of attention, if inferences made from cluster analysis have to be of some relevance to biomedical research. Results A procedure is proposed for the assessment of the discriminative ability of a distance functi…
A Microcalcification Detection System in Mammograms based on ANN Clustering
2018
Breast cancer is one of the leading causes to women mortality in the world. Clustered microcalcifications (MCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this work, we present a novel method for the detection of MCs in mammograms which consists of regions of Interest (ROIs) segmentation, based on a spatial filter that allows the detection of small and large microcalcifications, clustering and classification of MCs by Artificial Neural Network. The system has been tested on a public dataset of digital images and compared with previous approaches. The results demonstrate that the proposed approach could achie…
Organization and evolution of synthetic idiotypic networks
2012
We introduce a class of weighted graphs whose properties are meant to mimic the topological features of idiotypic networks, namely the interaction networks involving the B-core of the immune system. Each node is endowed with a bit-string representing the idiotypic specificity of the corresponding B cell and a proper distance between any couple of bit-strings provides the coupling strength between the two nodes. We show that a biased distribution of the entries in bit-strings can yield fringes in the (weighted) degree distribution, small-worlds features, and scaling laws, in agreement with experimental findings. We also investigate the role of ageing, thought of as a progressive increase in …
Empirically Determined, Psychopathological Subtypes in Children With ADHD
2013
OBJECTIVE: The aim of this study was to empirically determine subgroups of ADHD defined by specific patterns of psychopathology. METHOD: A clinical sample of 223 children with ADHD, aged 5 to 14 years, was examined with the Child Behavior Checklist (CBCL). In addition, comorbid psychiatric disorders, psychosocial risk factors, and socioeconomic status were assessed. RESULTS: Cluster analysis of CBCL subscales yielded a solution with four distinct subgroups. While "externalizers" showed a high rate of comorbid oppositional defiant disorder (ODD) and conduct disorder (CD), "obsessive-compulsives" exhibited thought problems, low rates of comorbid CD, and high symptoms of inattention. "High psy…
The SISCone jet algorithm optimised for low particle multiplicities
2011
The SISCone jet algorithm is a seedless infrared-safe cone jet algorithm. There exists an implementation which is highly optimised for a large number of final state particles. However, in fixed-order perturbative calculations with a small number of final state particles, it turns out that the computer time needed for the jet clustering of this implementation is comparable to the computer time of the matrix elements. This article reports on an implementation of the SISCone algorithm optimised for low particle multiplicities.