Background: The first distinct differentiation event in mammals occurs at the blastocyst stage when totipotent blastomeres differentiate into either pluripotent inner cell mass (ICM) or multipotent trophectoderm (TE). Here we determined, for the first time, global gene expression patterns in the ICM and TE isolated from bovine blastocysts. The ICM and TE were isolated from blastocysts harvested at day 8 after insemination by magnetic activated cell sorting, and cDNA sequenced using the SOLiD 4.0 system. Results: A total of 870 genes were differentially expressed between ICM and TE. Several genes characteristic of ICM (for example, NANOG, SOX2, and STAT3) and TE (ELF5, GATA3, and KRT18) in mouse and human showed similar patterns in bovine. Other genes, however, showed differences in expression between ICM and TE that deviates from the expected based on mouse and human. Conclusion: Analysis of gene expression indicated that differentiation of blastomeres of the morula-stage embryo into the ICM and TE of the blastocyst is accompanied by differences between the two cell lineages in expression of genes controlling metabolic processes, endocytosis, hatching from the zona pellucida, paracrine and endocrine signaling with the mother, and genes supporting the changes in cellular architecture, stemness, and hematopoiesis necessary for development of the trophoblast.

/pdf/global-gene-expression-of-the-inner-cell-mass-and-17tst4b4zk.pdf

Global gene expression of the inner cell mass and trophectoderm of the bovine blastocyst

Clustering has been used in various disciplines like software engineering, statistics, data mining, image analysis, machine learning, web cluster engines, and text mining in order to deduce the groups in large volume of data. The notion behind clustering is to ascribe the objects to clusters in such a way that objects in one cluster are more homogeneous to other clusters. There are variegated clustering algorithms available viz k-means clustering, cobweb clustering, db-scan clustering, fartherstfirst clustering, and x-means clustering algorithm but K-means on the whole comprehensively used algorithm for unsupervised clustering dilemma. In this paper k-means clustering is being optimised using genetic algorithm so that the problems of k-means can be overridden. The outcomes of k-means clustering and genetic k-means clustering are evaluated and compared; obtained result shows K-means with GA algorithm suggest new improvements in this research domain.

On K-means data clustering algorithm with genetic algorithm

This paper is written based on the need for Computerized Maintenance Management System's (CMMS) decision analysis capability to achieve world class status in maintenance management. Investigations indicate that decision analysis capability is often missing in existing CMMSs and collected data in the systems are not completely utilized. How to utilize the gathered data to provide guidelines for maintenance engineers and managers to make proper maintenance decisions has always been a crucial question. In order to provide decision support capability, the aim of this paper is to provide and examine three different decision making techniques which can be linked to CMMS and add value to collected data. This research has been conducted within a global project in a large manufacturing site in Sweden to provide a new maintenance management system for the company. The data from the main studies were collected through document analysis complemented by discussions with maintenance engineers and managers at the case company to verify the data. Methods including a Multiple Criteria Decision Making (MCDM) technique called TOPSIS, k-means clustering technique, and one decision making model borrowed from the literature were used. The results indicate the most appropriate maintenance decision for each of the selected machines/parts according to factors such as frequency of breakdowns, downtime, and cost of repairing. The paper concludes with a comparison of results obtained from the different decision making techniques and also a discussion on possible improvements needed to increase the capability of the maintenance decision making models.

Maintenance decision making, supported by computerized maintenance management system

The high of student success and the low of student failure can reflect the quality of a college. One of the factors of fail students was drop out. To solve the problem, so mining data with K-means Clustering was applied. K-Means Clustering method would be implemented to clustering the drop out students potentially. Firstly the the result data would be clustering to get the information of all students condition. Based on the model taken was found that students who potentially drop out because of the unexciting students in learning, unsupported parents, diffident students and less of students behavior time. The result of process of K-Means Clustering could known that students who more potentially drop out were in Cluster 1 caused Credit Total System, Quality Total, and the lowest Grade Point Average (GPA) compared between cluster 2 and 3.

https://iopscience.iop.org/article/10.1088/1742-6596/1007/1/012049/pdf

The effect of mining data k-means clustering toward students profile model drop out potential

Developing effective clustering method for high dimensional dataset is a challenging problem due to the curse of dimensionality. Among all the partition based clustering algorithms, k-means is one of the most well known methods to partition a dataset into groups of patterns. However, the k-means method converges to one of many local minima. And it is known that, the final result depends on the initial starting points (means). Many methods have been proposed to improve the performance of k-means algorithm. In this paper, we have analyzed the performance of our proposed method with the existing works. In our proposed method, we have used Principal Component Analysis (PCA) for dimension reduction and to find the initial centroid for k-means. Next we have used heuristics approach to reduce the number of distance calculation to assign the data point to cluster. By comparing the results on iris data set, it was found that the results obtained by the proposed method are more effective than the existing method.

Performance analysis of k-means with different initialization methods for high dimensional data

Due to incredible growth of high dimensional dataset, conventional data base querying methods are inadequate to extract useful information, so researchers nowadays is forced to develop new techniques to meet the raised requirements. Such large expression data gives rise to a number of new computational challenges not only due to the increase in number of data objects but also due to the increase in number of features/attributes. Hence, to improve the efficiency and accuracy of mining task on high dimensional data, the data must be preprocessed by an efficient dimensionality reduction method. Recently cluster analysis is a popularly used data analysis method in number of areas. K-means is a well known partitioning based clustering technique that attempts to find a user specified number of clusters represented by their centroids. But its output is quite sensitive to initial positions of cluster centers. Again, the number of distance calculations increases exponentially with the increase of the dimensionality of the data. Hence, in this paper we proposed to use the Principal Component Analysis (PCA) method as a first phase for K-means clustering which will simplify the analysis and visualization of multi dimensional data set. Here also, we have proposed a new method to find the initial centroids to make the algorithm more effective and efficient. By comparing the result of original and new approach, it was found that the results obtained are more accurate, easy to understand and above all
the time taken to process the data was substantially reduced. Keywords: Cluster analysis, K-means Algorithm, Dimensionality Reduction, Principal Component Analysis, Hybridized K-means algorithm

/pdf/a-hybridized-k-means-clustering-approach-for-high-3h2qydx28e.pdf

B Dash

Papers

A hybridized K-means clustering approach for high dimensional dataset