A comparison of central-tendency and interconnectivity approaches to clustering multivariate data with irregular structure.

Questions: Most clustering methods assume data are structured as discrete hyperspheroidal clusters to be evaluated by measures of central tendency. If vegetation data do not conform to this model, then vegetation data may be clustered incorrectly. What are the implications for cluster stability and evaluation if clusters are of irregular shape or density? Location: Southeast Australia. Methods: We define misplacement as the placement of a sample in a cluster other than (distinct from) its nearest neighbor and hypothesize that optimizing homogeneity incurs the cost of higher rates of misplacement. Chameleon is a graph-theoretic algorithm that emphasizes interconnectivity and thus is sensitive to the shape and distribution of clusters. We contrasted its solutions with those of traditional nonhierarchical and hierarchical (agglomerative and divisive) approaches. Results: Chameleon-derived solutions had lower rates of misplacement and only marginally higher heterogeneity than those of k-means in the range of 15-60 clusters, but their metrics converged with larger numbers of clusters. Solutions derived by agglomerative clustering had the best metrics (and divisive clustering the worst) but both produced inferior high-level solutions to those of Chameleon by merging distantly-related clusters. Conclusions: Graph-theoretic algorithms, such as Chameleon, have an advantage over traditional algorithms when data exhibit discontinuities and variable structure, typically producing more stable solutions (due to lower rates of misplacement) but scoring lower on traditional metrics of central tendency. Advantages are less obvious in the partitioning of data from continuous gradients; however, graph-based partitioning protocols facilitate the hierarchical integration of solutions.

Clustering Clinical Data in R.

We are currently witnessing a paradigm shift from evidence-based medicine to precision medicine, which has been made possible by the enormous development of technology. The advances in data mining algorithms will allow us to integrate trans-omics with clinical data, contributing to our understanding of pathological mechanisms and massively impacting on the clinical sciences. Cluster analysis is one of the main data mining techniques and allows for the exploration of data patterns that the human mind cannot capture.This chapter focuses on the cluster analysis of clinical data, using the statistical software, R. We outline the cluster analysis process, underlining some clinical data characteristics. Starting with the data preprocessing step, we then discuss the advantages and disadvantages of the most commonly used clustering algorithms and point to examples of their applications in clinical work. Finally, we briefly discuss how to perform validation of clusters. Throughout the chapter we highlight R packages suitable for each computational step of cluster analysis.

A New Genetic Algorithm Approach Applied to Atomic and Molecular Cluster Studies.

A new procedure is suggested to improve genetic algorithms for the prediction of structures of nanoparticles. The strategy focuses on managing the creation of new individuals by evaluating the efficiency of operators (o 1, o 2,…,o 13) in generating well-adapted offspring. This is done by increasing the creation rate of operators with better performance and decreasing that rate for the ones which poorly fulfill the task of creating favorable new generation. Additionally, several strategies (thirteen at this level of approach) from different optimization techniques were implemented on the actual genetic algorithm. Trials were performed on the general case studies of 26 and 55-atom clusters with binding energy governed by a Lennard-Jones empirical potential with all individuals being created by each of the particular thirteen operators tested. A 18-atom carbon cluster and some polynitrogen systems were also studied within REBO potential and quantum approaches, respectively. Results show that our management strategy could avoid bad operators, keeping the overall method performance with great confidence. Moreover, amongst the operators taken from the literature and tested herein, the genetic algorithm was faster when the generation of new individuals was carried out by the twist operator, even when compared to commonly used operators such as Deaven and Ho cut-and-splice crossover. Operators typically designed for basin-hopping methodology also performed well on the proposed genetic algorithm scheme.

A graph-based short-cut to low-energy structures.

A new graph-based move class for global optimization of cluster structures is presented. Its performance and efficiency is analyzed for water clusters (H2O)n, n = 24, 61. This analysis indicates superior basin exploitation capabilities of the new move class for large clusters, compared to traditional moves.