Browsing by Author "Balasaravanan T"

Now showing 1 - 4 of 4

A COMPARATIVE ANALYSIS OF WEB BASED MULTIPLE SEQUENCE ALIGNMENT TOOLS USING CERTAIN METABOLICALLY IMPORTANT PROTEIN CODING GENE SEQUENCES
(Dr.NGP Arts and Science College, Coimbatore, 2018-09-02) Boobashini S; Arunpriya C; Balasaravanan T
Multiple sequence alignment is an alignment of three or more biological sequences, generally protein, DNA, or RNA. The input set of query sequences are assumed to have an evolutionary relationship i.e., they are descended from a common ancestor. The resulting MSA, sequence homology can be inferred and phylogenetic analysis can be conducted to assess the sequences' shared evolutionary origins. In this paper, six different mammalian species gene sequence were compared with human gene sequences. Metabolically important genes such as Amylase, ATPase, Cytochrome-B, Haemoglobin, and Insulin where chosen for comparison. The DNA sequences of FASTA format was retrieved from NCBI databank and used as input sequences for Multiple sequence analysis using ClustalW, MUSCLE, and T-Coffee. Multiple sequence alignment score and phylogenetic trees where obtained from all the three tools and discussed with the snapshots and findings.
AN EFFICIENT CANCER CLASSIFICATION USING EXPRESSIONS OF VERY FEW GENES USING SUPPORT VECTOR MACHINE
(Sun College of Engineering and Technology, Nagercoil, 2011-03-24) Arunpriya C; Balasaravanan T; Antony Selvadoss Thanamani
Gene expression profiling by microarray technique has been effectively utilized for classification and diagnostic guessing of cancer nodules. Several machine learning and data mining techniques are presently applied for identifying cancer using gene expression data. Though, these techniques have not been proposed to deal with the particular needs of gene microarray examination. Initially, microarray data is featured by a high-dimensional feature space repeatedly surpassing the sample space dimensionality by a factor of 100 or higher. Additionally, microarray data contains a high degree of noise. The majority of the existing techniques do not sufficiently deal with the drawbacks like dimensionality and noise. Gene ranking method is later introduced to overcome those problems. Some of the widely used Gene ranking techniques are T-Score, ANOVA, etc. But those techniques will sometimes wrongly predict the rank when large database is used. To overcome these issues, this paper proposes a technique called Enrichment Score for ranking purpose. The classifier used in the proposed technique is Support Vector Machine (SVM). The experiment is performed on lymphoma data set and the result shows the better accuracy of classification when compared to the conventional method.
AN EFFICIENT HIERARCHICAL CLUSTERING ALGORITHM FOR PROTEIN SEQUENCING
(Government College of Technology, Coimbatore, 2009-02-22) Arunpriya C; Meera S; Balasaravanan T
Clustering is the division of data into groups of similar objects. The main objective of this unsupervised leaming technique is to find a meaningful partition by using a distance or similarity function. This paper discusses about the incremental clustering algorithm-Leaders and Sub leaders- an extension of leader algorithm, suitable for protein sequences of bioinformatics is proposed for effective clustering and prototype selection for pattern classification .It is a simple and efficient technique to generate a hierarchical structure for finding the sub clusters within each cluster. The experimental results of the proposed algorithm are compared with that of the Nearest Neighbour Classifier (NNC) methods. It is found to be computationally efficient when compared to NNC. Classification accuracy obtained using the representatives generated by Leader - Sub leader method is found to be better than that of using the Leaders method and NNC method. Even if more number of prototypes is generated classification time is less when compared to NNC methods
AN EFFICIENT LEAF RECOGNITION ALGORITHM FOR PLANT CLASSIFICATION USING SUPPORT VECTOR MACHINE
(Periyar University, Salem., 2012-03-21) Arunpriya C; Balasaravanan T; Antony Selvadoss Thanamani
Recognition of plants has become an active area of research as most of the plant species are at the risk of extinction. This paper uses an efficient machine learning approach for the classification purpose. This proposed approach consists of three phases such as preprocessing, feature extraction and classification. The preprocessing phase involves a typical image processing steps such as transforming to gray scale and boundary enhancement. The feature extraction phase derives the common DMF from five fundamental features. The main contribution of this approach is the Support Vector Machine (SVM) classification for efficient leaf recognition. 12 leaf features which are extracted and orthogonalized into 5 principal variables are given as input vector to the SVM. Classifier tested with flavia dataset and a real dataset and compared with k-NN approach, the proposed approach produces very high accuracy and takes very less execution time.