Computer-aided Cluster Research Articles

RETRACTED: Computer-aided cluster formation in wireless sensor networks using machine learning

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

Computer-Aided Clustering Analysis of Short-Term Interactive Data of Industry Microblog Marketing Effect and Number of Fans Based on Quantum Evolutionary Game Algorithm

Computer-Aided Clustering Analysis of Short-Term Interactive Data of Industry Microblog Marketing Effect and Number of Fans Based on Quantum Evolutionary Game Algorithm

Interpretation of cluster structures in pain-related phenotype data using explainable artificial intelligence (XAI).

In pain research and clinics, it is common practice to subgroup subjects according to shared pain characteristics. This is often achieved by computer-aided clustering. In response to a recent EU recommendation that computer-aided decision making should be transparent, we propose an approach that uses machine learning to provide (1) an understandable interpretation of a cluster structure to (2) enable a transparent decision process about why a person concerned is placed in a particular cluster. Comprehensibility was achieved by transforming the interpretation problem into a classification problem: A sub-symbolic algorithm was used to estimate the importance of each pain measure for cluster assignment, followed by an item categorization technique to select the relevant variables. Subsequently, a symbolic algorithm as explainable artificial intelligence (XAI) provided understandable rules of cluster assignment. The approach was tested using 100-fold cross-validation. The importance of the variables of the data set (6 pain-related characteristics of 82 healthy subjects) changed with the clustering scenarios. The highest median accuracy was achieved by sub-symbolic classifiers. A generalized post-hoc interpretation of clustering strategies of the model led to a loss of median accuracy. XAI models were able to interpret the cluster structure almost as correctly, but with a slight loss of accuracy. Assessing the variables importance in clustering is important for understanding any cluster structure. XAI models are able to provide a human-understandable interpretation of the cluster structure. Model selection must be adapted individually to the clustering problem. The advantage of comprehensibility comes at an expense of accuracy.

“Ficedula”: an open-source MATLAB toolbox for cutting, segmenting and computer-aided clustering of bird song

Qualitative and quantitative assessments of bird song repertoires are important in studies related to song learning, sexual selection and cultural evolution. Despite methods for automatic analysis, it is still necessary to engage in manual cutting, segmenting and clustering of bird song elements in many cases. Here, we describe a program, the Ficedula Toolbox, which has been made available for free to the bird song research community and has recently come into extensive use. The main advantages of this package are the opportunity to conduct all processing steps in one framework and the option of carrying out computer-aided manual clustering. Output files are ready for further analyses, such as estimation of repertoire size, sequential analysis and repertoire overlap calculation. With this program, findings based on empirical data from the Collared Flycatcher (Ficedula albicollis) song show high inter-observer similarity, and thus, reproducible results. The toolbox may be especially applicable to the analysis of song in species with moderately high repertoires.

Computer-aided cluster expansion: An efficient algebraic approach for open quantum many-particle systems

We introduce an equation of motion approach that allows for an approximate evaluation of the time evolution of a quantum system, where the algebraic work to derive the equations of motion is done by the computer. The introduced procedures offer a variety of different types of approximations applicable for finite systems with strong coupling as well as for arbitrary large systems where augmented mean-field theories like the cluster expansion can be applied. Program summaryProgram Title: EoM_main.frmProgram Files doi:http://dx.doi.org/10.17632/fjwxr28j3d.1Licensing provisions: CC By 4.0Programming language:FORMNature of problem: Quantum many-particle systems are an important subject in fundamental and applied research. The calculation of the time evolution of such systems is a key aspect to investigate and understand their properties. In most cases the Hilbert space that represents the quantum mechanical system is too big to be processed by numerically exact methods and approximation methods have to be used.Solution method: The program automates an equation-of-motion technique that uses the generalized Ehrenfest equation to derive the time evolution for expectation values of physical observables. The cluster expansion is used to close the hierarchy of the equations of motion. The offered method allows for a variety of different types of approximations to solve such problems with small numerical effort [1]. [1] Leymann, H.A.M., Foerster, A., Wiersig, J., 2014. Expectation value based equation-of-motion approach for open quantum systems: A general formalism. Phys. Rev. B 89 (8), 085308.

Genotypic Characterization ofPseudomonas aeruginosaIsolated from Human and Animal Sources in Egypt

Two different techniques for the molecular typing of Pseudomonas aeruginosa were used to study the epidemiology of P. aeruginosa strains. Colonization with P. aeruginosa was studied by taking samples of human origin collected from urine, sputum samples of patients suffering from lung manifestations and patients exposed to third-degree burns. In addition, samples of animal origin were collected from mastitic milk and lung tissues of slaughtered calves and from the internal organs of diseased chickens. Typing of 18 isolates was performed by random amplified polymorphic DNA analysis and amplified fragment length polymorphism analysis. Computer-aided cluster analysis indicated that similar groups of related isolates were obtained by each method.

Supervised cluster classification using the originaln-dimensional space without transformation into lower dimension

A novel supervised classification algorithm, direct clustering in n-dimensional space (DCNS), was developed for difficult data sets where conventional methods of supervised clustering are expected to fail. The method is based, when applied on >3-dimensional spaces, on an algorithm that performs special treatment on the measurement space, so that the treated space can allow a computer-aided clustering methodology similar to that used by human vision. However, unlike other techniques that reduce the dimensionality of the space, the proposed method preserves the original dimensions while performing a computer-simulated human vision clustering in the original n-dimensional space. Thus the overlap between clusters that results from the dimensionality reduction is eliminated. The proposed method was applied to two real data sets. The results are compared with those obtained using principal component analysis (PCA), an artificial neural network (ANN), and the k-nearest-neighbor (KNN) technique. On one data set containing only two clusters, the DCNS algorithm gives better cluster separation than the other three methods. However, when all four methods were applied on the second data set, containing eight different clusters, PCA, ANN and KNN were unable to give useful cluster separation, while the DCNS method was able to separate all clusters and classify the unknown points successfully with their corresponding clusters. The DCNS technique is able to perform other important cluster analysis tasks, such as testing the discriminatory power of a variable, selecting one variable from many, and conducting preliminary unsupervised clustering. Copyright © 2000 John Wiley & Sons, Ltd.

Diversity of uncultured microorganisms associated with the seagrass Halophila stipulacea estimated by restriction fragment length polymorphism analysis of PCR-amplified 16S rRNA genes.

The diversity of microorganisms associated with the leaves of the seagrass Halophila stipulacea in the northern Gulf of Elat was examined by culture-independent analysis. Microorganisms were harvested by a sonication treatment for total-community genomic DNA isolation. Oligonucleotides complementary to conserved regions in the 16S rRNA-encoding DNA (rDNA) of bacteria were used for PCR amplification. The 16S rDNA PCR products were subcloned and further characterized by a restriction fragment length analysis termed ARDRA (amplified rDNA restriction analysis). These analyses were carried out after reamplifying the cloned fragments with two primers binding symmetrically to the plasmid immediately on both sides of the cloned insert. Computer-aided clustering was performed after separate restriction analysis with enzymes HinfI and HpaII. By this method, 103 cloned 16S rDNA fragments were clustered into a total of 58 different groups. Sequence analysis of clones with an identical ARDRA pattern confirmed that members of an ARDRA group were closely related to each other. The sequenced clones were found to be affiliated with a marine snow-associated plastid-like rRNA clone and with a marine Hyphomonas strain, respectively. The method applied in this study could be useful for the routine study of other microbial communities of interest.

Computer-aided clustering of citation networks as a tool of mapping of research trends in biomedicine

The use of the cluster analysis in scientometrics is dealt with. The ways of developing citation networks and mapping research field with the help of this method are also presented. The methodology of computer-aided cluster analysis of citation is described, which allows to map the structure of a research field and to identify main tendencies of its development.

Computer-Aided Cluster Analysis as a Rapid Method Assisting Mineral Identification: ABSTRACT

Cluster analysis is one of the multivariate statistical methods that measure the similarity between objects. Aided by a microcomputer, cluster analysis offers rapid results that can lead to mineral identification based on the chemical composition of the minerals. In the process of cluster analysis, the chemical composition of the unknown minerals is either stored into a data file during an on-line quantitative analysis (e.g., electron microprobe analysis), or manually input to the data file. The data of the unknown minerals are respectively compared with an existing identification data matrix that consists of the chemical composition of related reference minerals. The unknown minerals can then be identified with the reference minerals by the closest similarity (e.g., highest correlation coefficient or lowest distance coefficient) in the dendrogram. By using the concentrations of major and minor elements as the variables, quantitative data obtained from some electron microprobe analyses have been tested and approximately 80% of unknown minerals are accurately identified.

An investigation of protistan phylogeny using a numerical taxonomy (cluster) analysis of mitotic systems

Fourteen mitotic characteristics of 83 species, or groups of species, representing 134 species spread among the “fungi”, “algae”, “protozoa” and “related” organisms are analyzed by computer-aided cluster analysis techniques. The resultant clusters are represented as phenograms that indicate the degree of similarity among the mitotic systems considered. When compared with other criteria, some clusters correlate well with established taxa but others contain a heterogeneous array of species. Some established taxa are widely dispersed. Some of these “deviant” clusters are probably artefacts of the methodology but others are considered to indicate novel but true common ancestry. It is concluded that this type of analysis and data have phylogenetic value but must be used with considerable care.