Qualification: 
M.Tech
c_arunkumar@cb.amrita.edu

Arunkumar C. currently serves as Assistant Professor (Senior Grade) at the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore Campus. His areas of research include Artificial Intelligence, Bioinformatics and Machine Learning. In addition to the academic activities, to name some of the activities carried out under his leadership,

  • Vice Chairman - Council of Wardens, Hostels of Amrita Vishwa Vidyapeetham, Coimbatore
  • Member – Council of Wardens, Hostels of Amrita Vishwa Vidyapeetham, Coimbatore
  • Co-Convenor – ANOKHA Techfest
  • State level IETE student Forums coordinator
  • Student Branch Counsellor of IEEE, Amrita Vishwa Vidyapeetham
  • Secretary General of VIT Alumni Association which has 45000 members for 2014-2016
  • Charter President, VIT Alumni Association Coimbatore Chapter
  • Recipient of the Most Active Domestic Chapter Award of VIT Alumni Association for 2013-2014 during my tenure as President
  • Reviewer for Elsevier and Springer journals
  • Question paper setter for M.Sc degree program of Madras University
  • Question Paper setter for M.Tech program at Vivekanandha College of Engineering for Women, Tiruchengode
  • Member – Technical Program Commitee, GS Multi International Conference on Science and Technology,November 2014, Dubai,UAE
  • Member – Machine Intelligence Research Labs, USA.
  • Member of the Internal Quality and Assessment Cell(IQAC), Amrita
  • Assistant Coordinator for National Workshop on Android Development, April 2014
  • Assistant Coordinator for National Workshop on Multimedia and Video Streaming, May 2014
  • Chief Coordinator – IEEE All India Student Congress, 3-6 October 2013
  • Chief Coordinator – IEEE Face to Face Meet, April 2013
  • Program Director – Infosys Campus Connect during 2007-2008
  • Organizing Committee Member of International Collegiate Programming Contest(ICPC) since 2007
  • Organizing Secretary of International Conference on Distributed Computing and Networking(ICDCN), January 4-7,2014
  • Joint Secretary for the CSI Regional Student Convention 2011
  • Executive Secretary for the International Conference on Cloud Computing, Smart Grid and Green I.T 2009
  • Organized World Quality Day 2009
  • Has coordinated at the department level for the University’s NAAC accreditation and the university obtained the highest “A” grade in 2007.
  • Former Member of the Rotary club of Pollachi and has also received an award for offering the best of services to the club during 2007-08
  • Program Director for the Infosys Campus Connect Program of the Amrita Vishwa Vidyapeetham
  • Co-Convenor for the AICTE sponsored National seminar on Mobile and Network Security 2007

He is responsible for starting “Institution of Electronics and Telecommunication Engineers”(IETE) student forums in all engineering colleges and polytechnics in Tamilnadu under the jurisdiction of IETE Coimbatore center which expands its wings to more than 12 districts in Tamilnadu. He has also inaugurated student forums and delivered technical and non-technical lectures in more than 50 engineering colleges in Tamilnadu including some of the premier institutions like Vellore Institute of Technology, PSG college of Technology, KSR College of Engineering, Tiruchengode, Dr.Mahalingam College of Engineering and Technology, Coimbatore Institute of Technology, Kumaraguru College of Technology, Tamilnadu College of Engineering, NGP Institute of Technology, SSK College of Engineering, Easa College of Engineering, Sona College of Technology-Salem, MEPCO-Sivakasi, Oxford Engineering College, Jayaram Engineering College, Saranathan College of Engineering-Trichy to name a few. He also assisted the Amrita Vishwa Vidyapeetham in conducting a one day tutorial in the area of Network Security in association with Symantec Corporation at IIT Madras during May 2010 as a part of IFIP-Networking 2010. Under his leadership, IEEE chapter of Amrita received an Award from IEEE Madras Section for organizing maximum number of events in 2011. It is worthy to note that only 6 colleges in Tamilnadu have received this award out of 500 colleges and universities in Tamilnadu. He has also proctored and mentored the IEEE Extreme programming contest, a 24 hour online coding contest during October 2011 in which his team received the All India Ranking of 8 among 1500 teams that took part in the contest across the globe at the same time. IEEE Chapter of Amrita School of Engineering, Coimbatore won the Third prize in the IEEE Region 10(Asia Pacific Region) in the website design competition under his leadership. He is also appointed as the Organizing Secretary for the International Conference on Distributed Computing and Networking 2014 which is one of the top 10 conferences in the world to be hosted at Amrita in 2014. He is an institutional member of Computer Society of India, Coimbatore chapter and also a member of IETE and Machine Intelligence Research Labs, USA.He has published more than 20 papers in leading national and international conferences and journals.

Publications

Publication Type: Journal Article

Year of Publication Title

2019

A. Chinnaswamy and Ramakrishnan, S., “Prediction of cancer using customised fuzzy rough machine learning approaches.”, Healthc Technol Lett, vol. 6, no. 1, pp. 13-18, 2019.[Abstract]


This Letter proposes a customised approach for attribute selection applied to the fuzzy rough quick reduct algorithm. The unbalanced data is balanced using synthetic minority oversampling technique. The huge dimensionality of the cancer data is reduced using a correlation-based filter. The dimensionality reduced balanced attribute gene subset is used to compute the final minimal reduct set using a customised fuzzy triangular norm operator on the fuzzy rough quick reduct algorithm. The customised fuzzy triangular norm operator is used with a Lukasiewicz fuzzy implicator to compute the fuzzy approximation. The customised operator selects the least number of informative feature genes from the dimensionality reduced datasets. Classification accuracy using leave-one-out cross validation of 94.85, 76.54, 98.11, and 99.13% is obtained using a customised function for Lukasiewicz triangular norm operator on leukemia, central nervous system, lung, and ovarian datasets, respectively. Performance analysis of the conventional fuzzy rough quick reduct and the proposed method are performed using parameters such as classification accuracy, precision, recall, -measure, scatter plots, receiver operating characteristic area, McNemar test, chi-squared test, Matthew's correlation coefficient and false discovery rate that are used to prove that the proposed approach performs better than available methods in the literature.

More »»

2018

A. Chinnaswamy and Ramakrishnan, S., “Attribute Selection using Fuzzy Roughset based Customized Similarity Measure for Lung Cancer Microarray Gene Expression Data”, Future Computing and Informatics Journal, vol. 3, pp. 131 - 142, 2018.[Abstract]


Microarray gene expression data plays a prominent role in feature selection that helps in diagnosis and treatment of a wide variety of diseases. Microarray gene expression data contains redundant feature genes of high dimensionality and smaller training and testing samples. This paper proposes a customized similarity measure using fuzzy rough quick reduct algorithm for attribute selection. Information Gain based entropy is used to reduce the dimensionality in the first stage and the proposed fuzzy rough quick reduct method that defines a customized similarity measure for selecting the minimum number of informative genes and removing the redundant genes is employed at the second stage. The proposed method is evaluated using leukemia, lung and ovarian cancer gene expression datasets on a random forest classifier. The proposed method produces 97.22%, 99.45% and 99.6% classifier accuracy on leukemia, lung and ovarian cancer gene expression datasets respectively. The research study is carried out using the R open source software package. The proposed method shows substantial improvement in the performance with respect to various statistical parameters like classification accuracy, precision, recall, f-measure and region of characteristic compared to available methods in literature.

More »»

2018

A. Chinnaswamy, Ramakrishnan, S., and Sooraj, M. P., “Rough Set Based Variable Tolerance Attribute Selection on High Dimensional Microarray Imbalanced Data”, Data Enabled Discovery and Applications, 2018.

2018

A. Chinnaswamy, Ramakrishnan, S., and Dheeraj, S. S., “Genetic Algorithm Based Hybrid Attribute Selection using Customized Fitness Function”, Lecture Notes in Computational Vision and Biomechanics, vol. 28, pp. 1-10, 2018.[Abstract]


Attribute selection is an important step in the analysis of gene expression for cancer or illnesses in general. The huge dimensionality of gene expression data that includes many insignificant and redundant genes reduces the classification accuracy. In this study, we propose a hybrid attribute selection method to identify the small set of the most significant genes associated with the cause of cancer. The proposed method integrates the advantages of filter and a wrapper to perform attribute selection by devising a customized fitness function for the genetic algorithm. Three data sets are used that includes leukemia, CNS and colon cancer. Results of our technique are compared with the other standard techniques available in literature. The proposed hybrid approach produces comparably better accuracy than the standard implementation of the genetic algorithm.

More »»

2016

A. Chinnaswamy and Ramakrishnan, S., “Modified Fuzzy Rough Quick Reduct Algorithm for Feature Selection in Cancer Microarray Data”, Asian Journal of Information Technology, vol. 15, no. 2, pp. 199–210, 2016.[Abstract]


This study proposes a novel method that employs correlation based filter for dimensionality reduction followed by fuzzy rough quick reduct for feature selection on a particle swarm optimization search space. The first phase removed the redundant genes using correlation coefficient filter on a particle swarm optimization search space. The second phase produced a fuzzy rough quick reduct that would be used for classification. The genes obtained after feature selection are subjected to classification using traditional classifiers. It has been determined that the proposed method contributes to reduction in the total number of genes and improvement in the classifier accuracy compared to gene selection and classification using correlation coefficient and traditional fuzzy rough quick reduct algorithm. This approach also reduces the number of misclassifications that might occur in other approaches.

More »»

2016

A. Chinnaswamy and Ramakrishnan, S., “A comparative study of hybrid feature selection methods using correlation coefficient for microarray data”, Journal of Network and Innovative Computing, vol. 4, no. 1, pp. 164–174, 2016.[Abstract]


Feature selection is a key challenge before the process of classification could be performed. The classification accuracy would increase by using a good feature selection method and also at the same time reduces the cost and time involved in the computation. In this study, we applied hybrid methods by using Correlation Based Feature Selection combined with different search algorithms. The classification performance was evaluated using fuzzy rough neural network classifier on the selected gene subsets. The experimental results reveal that majority of the hybrid method selects very few gene subsets and produces much better classification accuracy. The results are validated using traditional approaches like Precision, Recall, F-Score and Region of Characteristic.

More »»

2015

A. Chinnaswamy, Natarajan, S., G, G., and V, K. Kiran P., “A Study on Automation of Blood Donor Classification and Notification Techniques”, International Journal of Applied Engineering Research, vol. 10, pp. 18503-18514, 2015.[Abstract]


The increasing demand for sophisticated, intelligent systems in the field of healthcare leads to a need for introduction of automation of processes. The area of transfusion medicine, specifically blood donation services require this implementation at the earliest. The present situation is one where most processes in blood donation services are manual and the demand for blood is constantly on the rise, augmented by declining donation rates. Hence, an intelligent system that can integrate major operations involved.

More »»

2015

A. Chinnaswamy and .Ramakrishnan, S., “A Comparative Study of different Classifiers on Microarray Cancer Gene Expression Data”, Australian Journal of Basic and Applied Sciences, no. 27, pp. 145-151, 2015.

2014

A. Chinnaswamy, Husshine, S. R., Giriprasanth, V. P., and Prasath, A. B., “Automated Classification and Segregation of Brain MRI Images into Images captured with respect to Ventricular region and Eye ball region”, ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING, vol. 4, no. 4, pp. 831-834, 2014.

2014

A. Chinnaswamy, V, P. Kumar R., and R, S. Arvind, “Age Group Estimation using Facial Features”, International Journal of Emerging Technologies in Computational and Applied Sciences(IJETCAS), vol. 2, no. 8, pp. 182-186, 2014.

2014

A. Chinnaswamy, Raghuram, T., and Sekharan, M. N., “A Hybrid Approach to Normalize the Light Illumination in Facial Images using DCT and Gamma Transformations”, International Journal of Emerging Technologies in Computational and Applied Sciences(IJETCAS), vol. 1, no. 7, pp. 106-112, 2014.

2014

A. Chinnaswamy and Ramakrishnan, S., “Two Step Feature Extraction Method for Microarray Cancer Data using Support Vector Machines”, International Journal of Computer Applications, vol. 85, no. 8, pp. 34-42, 2014.[Abstract]


Diagnosis of cancer is one of the most emerging clinical applications in microarray gene expression data. However, cancer classification on microarray gene expression data still remains a difficult problem. The main reason for this is the significantly large number of genes present relatively compared to the number of available training samples. In this paper, a novel approach to feature extraction combining the statistical t-test and absolute scoring is proposed for achieving better classification rate. Suitable classification approaches using the linear Support Vector Machines, the Proximal Support Vector Machines and the Newton Support Vector Machines is also discussed. A comparative analysis on the different techniques for feature extraction is also presented. Microarray cancer data based on Adenoma and Carcinoma with 7086 and 7457 genes of 4 and 18 patients respectively is used for this study. Increase in the classification rate of the proposed new method is clearly demonstrated in the results.

More »»

2014

A. Chinnaswamy and Raj, V., “Content Restoration of Degraded Termite Bitten Document Images”, International Journal of Engineering Research and Applications, vol. 4, no. 5, pp. 151-155, 2014.[Abstract]


Document images are often obtained by digitizing the paper documents like books or manuscripts. Due to degradation of paper quality, aging spreading of ink etc their appearance may get poor. Document may undergo termite bite due to aging and will get severely degraded .This work tries to find some solutions to increase the recognition rate of degraded characters after applying a best preprocessing technique for removing the noise due to termite bite. Main degradation for a degraded document are due to non-rectilinear camera positioning, blur, bad illumination, non-uniform backgrounds, non-flat paper surface, spreading of ink, document aging,
extraneous marks, broken characters. There are different systems which are able to deal with degradations which occur due to these type of degradations. Restoration is highly useful in a variety of fields such as document recognition, historic document analysis etc. In this paper ,we propose a method to remove the noise due to termite bite . The work has the ability to deal with larger patch sizes and allows to deal with severe degradations.

More »»

2013

A. Chinnaswamy, .M, S. K., and Aadithyan, “Image Mosaicking with Modified SURF”, International Journal of Emerging Technologies in Computational and Applied Sciences(IJETCAS), vol. 5, no. 4, pp. 452-454, 2013.

Publication Type: Conference Proceedings

Year of Publication Title

2017

A. Chinnaswamy, Sooraj, M. P., Ramakrishnan, S., and M., G., “A Comparative Performance Evaluation of Supervised Feature Selection Algorithms on Microarray Datasets”, Procedia Computer Science, vol. 115. Elsevier B.V., pp. 209-217, 2017.[Abstract]


The focus of this research paper is to compare the different filter, wrapper and fuzzy rough set based feature selection methods based on three parameters namely execution time, number of features selected in the reduced subset and classifier accuracy. The results are analyzed using the different feature selection methods on cancer microarray gene expression datasets. This research work finds KNN classifier to produce higher classifier accuracy compared to traditional classifiers available in literature. Also fuzzy rough set based feature selection approach is computationally faster and produces lesser number of genes in the reduced subset compared to correlation based filter.

More »»

2017

A. Chinnaswamy and Ramakrishna, S., “Hybrid Information Gain Based Fuzzy Roughset Feature Selection in Cancer Microarray Data”, Proceedings of IEEE International Conference on Innovations in Power and Advanced Computing Technologies. IEEE, Vellore Institute of Technology, Vellore, India, 2017.[Abstract]


The main objective of this paper is to remove the redundant genes present in the samples and thereby increase the classifier accuracy. This is accomplished by devising a hybrid approach for feature selection that selects a subset of genes from the raw dataset and then classifies the samples based on the training imparted. In this paper, a rank based information gain filter is used for dimensionality reduction. Fuzzy rough set and genetic algorithm methods were combined to form a hybrid approach that selects the prominent genes and removes the redundant ones. The process of classification is performed using extreme learning machines classifier with ten-fold cross validation strategy on three multi class cancer microarray gene expression datasets. Experimental results reveal that the proposed hybrid method produces improved higher accuracy in all the three benchmarked multi-class cancer gene expression datasets obtained from the biomedical repository compared to other techniques available in literature using extreme learning machines classifier.

More »»

2017

A. Chinnaswamy, Sooraj, M., and Ramakrishnan, S., “Finding Expressed Genes using Genetic Algorithm and Extreme Learning Machines”, 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017. Institute of Electrical and Electronics Engineers Inc., 2017.[Abstract]


Cancer diagnosis is one of the emerging applications in microarray gene expression data. Feature selection plays a crucial role because of the huge dimensionality and less training and testing samples. Finding a small subset of significant genes from a large set of gene expression data is a challenging task. This paper presents the usage of genetic algorithm as a tool to determine the informative gene subset and uses Extreme Learning Machines classifier to determine the classifier accuracy. Experiments are carried out on two microarray datasets and the results reveal that the proposed approach produces better classification rate compared to Support Vector Machines and nearest neighbor classifier.

More »»

2017

A. Chinnaswamy and Srinivasan, R., “Performance Analysis of Classifiers on Filter-Based Feature Selection Approaches on Microarray Data”, Bio-Inspired Computing for Information Retrieval Applications. IGI Global, pp. 41-70, 2017.[Abstract]


The process of Feature selection in machine learning involves the reduction in the number of features (genes) and similar activities that results in an acceptable level of classification accuracy. This paper discusses the filter based feature selection methods such as Information Gain and Correlation coefficient. After the process of feature selection is performed, the selected genes are subjected to five classification problems such as Naïve Bayes, Bagging, Random Forest, J48 and Decision Stump. The same experiment is performed on the raw data as well. Experimental results show that the filter based approaches reduce the number of gene expression levels effectively and thereby has a reduced feature subset that produces higher classification accuracy compared to the same experiment performed on the raw data. Also Correlation Based Feature Selection uses very fewer genes and produces higher accuracy compared to Information Gain based Feature Selection approach.

More »»

2016

A. Chinnaswamy and Ramakrishnan, S., “A hybrid approach to feature selection using correlation coefficient and fuzzy rough quick reduct algorithm applied to cancer microarray data”, 10th International Conference on Intelligent Systems and Control (ISCO), 2016 , vol. 15. IEEE, Karpagam College of Engineering, Coimbatore, India, pp. 414-419, 2016.[Abstract]


In this study, we applied a novel method by using correlation coefficient filter for dimensionality reduction followed by fuzzy rough quick reduct algorithm for feature selection. The classification performance was evaluated using the gene subsets obtained from correlation based filter and our proposed method. Later we compared the results with other traditional classifier techniques. After suitable experimental analysis, it has been found that our proposed method has a two-fold advantage namely selection of much lesser number of genes compared to correlation coefficient and improved classifier accuracy in majority of the cases. This approach also reduces the number of misclassifications that might occur in other approaches.

More »»

2015

A. Chinnaswamy and Srinivasan, R., “Hybrid feature selection using correlation coefficient and particle swarm optimization on microarray gene expression data”, Proceedings of the 6th International Conference in Bioinspired Computing and Applications, Advances in Intelligent Systems and Computing. Springer, ToC H Institute of Science and Technology, Kochi, India, 2015.[Abstract]


Diagnosis of cancer is one of the most emerging clinical applications in microarray gene expression data. However, cancer classification on microarray gene expression data still remains a difficult problem. The main reason for this is the significantly large number of genes present relatively compared to the number of available training samples. In this paper, we propose a hybrid feature selection approach that combines the correlation coefficient with particle swarm optimization. The process of feature selection and classification is performed on three multi-class datasets namely Lymphoma, MLL and SRBCT. After the process of feature selection is performed, the selected genes are subjected to Extreme Learning Machines Classifier. Experimental results show that the proposed hybrid approach reduces the number of effective levels of gene expression and obtains higher classification accuracy and uses fewer features compared to the same experiment performed using the traditional tree-based classifiers like J48, random forest, random trees, decision stump and genetic algorithm as well.

More »»

2014

A. Chinnaswamy and Ramakrishnan, S., “Binary Classification of cancer microarray gene expression data using extreme learning machines”, IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2014 . IEEE, 2014.[Abstract]


This paper presents the usage of Extreme Learning Machines for cancer microarray gene expression data. Extreme Learning Machines overcomes the problems of overfitting, local minima and improper training rate that are most common in traditional algorithms. We have evaluated the binary classification performance of Extreme Learning Machines on five bench marked datasets of cancer microarray gene expression data namely ALL/AML, CNS, Lung Cancer, Ovarian Cancer and Prostate Cancer. Feature Extraction has been performed using Correlation Coefficient prior to classification. The results indicate that ELM produces comparable or better results compared to the traditional classification methods like Naïve Bayes, Bagging, Random Forest and Decision Table.

More »»

2013

A. Chinnaswamy and Ramakrishna, S., “Analysis of Classification Techniques for Microarray Cancer data using Support Vector Machines”, Proceedings of International Conference on Bio-Signals, Images and Instrumentation. SSN College of Engineering, Chennai, India, 2013.

2012

R. Aarthi, Chinnaswamy, A., and Dr. Padmavathi S., “A Survey of Different Stages for Monitoring Traffic Rule Violation”, Communications in Computer and Information Science, vol. 270 CCIS. Vellore, pp. 566-573, 2012.[Abstract]


A traffic surveillance system is a controlled system that helps to monitor and regulate the traffic. In this paper, a method for extracting the license number of the vehicle that is exceeding the speed limit is proposed. A Study is conducted by covering various stages of monitoring system such as vehicle detection in the video, tracking the vehicle for speed calculation and extracting the vehicle number in the number plate that can be used in places with high public vicinity. © 2012 Springer-Verlag.

More »»

2011

R. Aarthi, Chinnaswamy, A., and K. Raghesh Krishnan, “Automatic Isolation and Classification of Vehicles in a Traffic Video”, Proceedings of the 2011 World Congress on Information and Communication Technologies (WICT 2011). Mumbai, India., pp. 357-361, 2011.[Abstract]


Among the diverse applications of computer and communication technologies, Intelligent Transport System aids in simplifying transport problems. Its aim is to gather data and provide timely feedback to traffic managers (traffic policemen) and road users. The various problems involved in processing real-time traffic data has been addressed in several areas of research that includes vehicle detection, tracking and classification. This paper proposes a technique for isolation and classification of vehicles at an abstract level. The isolation technique aims at locating regions of interest (vehicles) within the image to be classified. Classification is performed in two categories. The first category is to identify the predominant color and the second is to classify the vehicle as light or heavy. The experimental results show an accuracy of 82% even for traffic video sequences involving complicated scenes.

More »»
Faculty Research Interest: