Qualification: 
Ph.D, M.E, BE
r_karthi@cb.amrita.edu

Dr. R. Karthi currently serves as Associate Professor at the Department of Computer Science and Engineering, School of Engineering, Coimbatore Campus. Her areas of research include Data Analytics, Machine Learning and application of Machine Learning Algorithms for spatiotemporal data analysis. She obtained her B. E. degree in Electronics and Communication Engineering in the year 1996 and M. E. degree in Computer Science in the year 2000. She has been awarded with Ph. D. from Anna University, Chennai in the year 2010.

Dr. Karthi was involved in the setup of Amrita CTS Innovation Lab with the funding received from Cognizant Technologies in 2013. The vision of the lab is to bring together multi-disciplinary students and provide a platform for researchers to find innovative solutions to real world problems in areas of machine learning and image processing. The lab provides facilities to M. Tech and B. Tech students who pursue their research in the areas image processing and networking and machine learning.

Awards

  • Certificate of Recognition for outstanding contribution to campus connect program – Infosys (2011). The award was conferred for introducing new industry elective course and laboratory courses titled “Business Intelligence” for students of CSE - UG and PG degree programme.
  • Best Paper Award: Received paper award for the paper: Rameshkumar, K., Rajendran, C., Karthi, R.,Modified Discrete Particle Swarm Optimization Algorithm (MDPSOA) for static permutation flow shop scheduling to minimize total flow time of jobs, Proceedings of Emerging Trends in Industrial Engineering, ETRIM 2011, NIT Calicut, 2011.

Publications

Publication Type: Journal Article

Year of Conference Publication Type Title

2018

Journal Article

B.A. Sabarish, R. Karthi, and Dr. Gireesh K. T., “Spatial Outlier Detection Algorithm for Trajectory Data”, International Journal of Pure and Applied Mathematics, vol. 118, pp. 325-330, 2018.[Abstract]


Trajectories are spatiotemporal data generated by moving objects containing the spatial position of object at various time intervals. GPS devices record this information and it is possible to construct trajectory of moving objects for analysis. Outlier analysis of trajectories is done to identify abnormal activities like intrusion detection, fraud detection, fault detection and rate event detection. In this paper, Trajectory Outlier Detection algorithm using Boundary (TODB) is proposed using a boundary construction algorithm and a binary classifier. In TODB, Convex Hull algorithm is used to construct the boundary and ray casting algorithm is used to build the binary classifier. TODB is tested for its accuracy using real world data sets. Experimental results on real world data sets demonstrate that TODB correctly classify normal and outlier trajectories

More »»

2018

Journal Article

B.A. Sabarish, R. Karthi, and Dr. Gireesh K. T., “Clustering of trajectory data using hierarchical approaches”, Lecture Notes in Computational Vision and Biomechanics, vol. 28, pp. 215-226, 2018.[Abstract]


Large volume of spatiotemporal data as trajectories are generated from GPS enabled devices such as smartphones, cars, sensors, and social media. In this paper, we present a methodology for clustering of trajectories to identify patterns in vehicle movement. The trajectories are clustered using hierarchical method and similarity between trajectories are computed using Dynamic Time Warping (DTW) measure. We study the effects on clustering by varying the linkage methods used for clustering of trajectories. The clustering method generate clusters that are spatially similar and optimal results are obtained during the clustering process. The results are validated using Cophenetic correlation coefficient, Dunn, and Davies-Bouldin Index by varying the number of clusters. The results are tested for its efficiency using real world data sets. Experimental results demonstrate that hierarchical clustering using DTW measure can cluster trajectories efficiently. © 2018, Springer International Publishing AG.

More »»

2018

Journal Article

B.A. Sabarish, R. Karthi, and Dr. Gireesh K. T., “String based Feature Representation for Trajectory Clustering (Accepted)”, International Journal of Embedded and Real-Time Communication Systems (IJERTCS), 2018.

2012

Journal Article

M. P.Gangan and R. Karthi, “Automatic Image Annotation by Classification Using Mpeg-7 Features”, International Journal of Scientific and Research Publications (IJSRP), vol. 2, no. 9, 2012.[Abstract]


Automatic image annotation (AIA) is a technique to provide semantic image retrieval. In AIA, the image contents are automatically labelled with a pre-defined set of keywords which are exploited to represent the image semantics. This paper proposes an Automatic image annotation method using MPEG-7 features. The feature vectors are provided for training the KNNclassifier. When a query image is provided by the user, the extracted features are provided to the trained KNN -classifier for annotation. The system also compares the results of different combinations of mpeg 7 descriptors. The Automatic image annotation proposed in this paper is on fruit images. This system has several applications like automatic labeling and price computing of fruits and vegetables in a grocery store, morphological analysis of fruits, for scientific studies, enhanced learning for kids and Down syndrome patients using fruits pattern recognition.

More »»

2011

Journal Article

R. Karthi, Rajendran, Cb, and Rameshkumar, K., “Neighborhood search assisted particle swarm optimization (NPSO) algorithm for partitional data clustering problems”, Communications in Computer and Information Science, vol. 192 CCIS, pp. 552-561, 2011.[Abstract]


New variant of PSO algorithm called Neighborhood search assisted Particle Swarm Optimization (NPSO) algorithm for data clustering problems has been proposed in this paper. We have proposed two neighborhood search schemes and a centroid updating scheme to improve the performance of the PSO algorithm. NPSO algorithm has been applied to solve the data clustering problems by considering three performance metrics, such as TRace Within criteria (TRW), Variance Ratio Criteria (VRC) and Marriott Criteria (MC). The results obtained by the proposed algorithm have been compared with the published results of basic PSO algorithm, Combinatorial Particle Swarm Optimization (CPSO) algorithm, Genetic Algorithm (GA) and Differential Evolution (DE) algorithm. The performance analysis demonstrates the effectiveness of the proposed algorithm in solving the partitional data clustering problems. © 2011 Springer-Verlag.

More »»

Publication Type: Book Chapter

Year of Conference Publication Type Title

2015

Book Chapter

B.A. Sabarish, R. Karthi, and Dr. Gireesh K. T., “A Survey of Location Prediction Using Trajectory Mining”, in Artificial Intelligence and Evolutionary Algorithms in Engineering Systems: Proceedings of ICAEES 2014, Volume 1, P. L. Suresh, Dash, S. Subhransu, and Panigrahi, K. Bijaya New Delhi: Springer India, 2015, pp. 119–127.[Abstract]


This paper is a research and analysis on the prediction of location of moving objects that gained popularity over the years. Trajectory specifies the path of the movement of any object. There is an increase in the number of applications using the location-based services (LBS), which needs to know the location of moving objects where trajectory mining plays a vital role. Trajectory mining techniques use the geographical location, semantics, and properties of the moving object to predict the location and behavior of the object. This paper analyses the various strategies in the process of making prediction of future location and constructing the trajectory pattern. The analyses of various mechanisms are done based on various factors including accuracy and ability to predict the distant future. Location prediction problem can be with known reference points and unknown reference points, and semantic-based prediction gives an accurate result whereas the probability-based prediction for unknown reference points.

More »»

2009

Book Chapter

R. Karthi, Arumugam, S., and Rameshkumar, K., “Discrete Particle Swarm Optimization Algorithm for Data Clustering”, in Nature Inspired Cooperative Strategies for Optimization (NICSO 2008) , Springer-Verlag, Berlin, Heidel berg, vol. 236, 2009, pp. 75 - 88.[Abstract]


In this paper, a novel Discrete Particle Swarm Optimization Algorithm (DPSOA) for data clustering has been proposed. The particle positions and velocities are defined in a discrete form. The DPSOA algorithm uses of a simple probability approach to construct the velocity of particle followed by a search scheme to constructs the clustering solution. DPSOA algorithm has been applied to solve the data clustering problems by considering two performance metrics, such as TRace Within criteria (TRW) and Variance Ratio Criteria (VRC). The results obtained by the proposed algorithm have been compared with the published results of Basic PSO (B-PSO) algorithm, Genetic Algorithm (GA), Differential Evolution (DE) algorithm and Combinatorial Particle Swarm Optimization (CPSO) algorithm. The performance analysis demonstrates the effectiveness of the proposed algorithm in solving the partitional data clustering problems.

More »»

Publication Type: Conference Proceedings

Year of Conference Publication Type Title

2011

Conference Proceedings

R. K., C., R., and R. Karthi, “Modified Discrete Particle Swarm Optimization Algorithm (MDPSOA) for static permutation flowshop scheduling to minimize total flowtime of jobs”, Proceedings of Emerging Trends in Industrial Engineering, ETRIM 2011. NIT Calicut, 2011.

2009

Conference Proceedings

R. Karthi, Arumugam, S., and Rameshkumar, K., “A Novel Discrete Particle Swarm Clustering Algorithm for Data Clustering”, COMPUTE '09 Proceedings of the 2nd Bangalore Annual Compute Conference, vol. 16. ACM, New York, NY, USA, 2009.[Abstract]


In this paper, a novel Discrete Particle Swarm Clustering algorithm (DPSC) for data clustering has been proposed. The particle positions and velocities are defined in a discrete form and an efficient approach is developed to move the particles for constructing new clustering solutions. DPSC algorithm has been applied to solve the data clustering problems by considering two performance metrics, such as TRace Within criteria (TRW) and Variance Ratio Criteria (VRC). The result obtained by the proposed algorithm has been compared with the published results of Combinatorial Particle Swarm Optimization (CPSO) algorithm and Genetic Algorithm (GA). The performance analysis demonstrates the effectiveness of the proposed algorithm in solving the partitional data clustering problems.

More »»

2008

Conference Proceedings

N. Yathindra R. Gupta, E. Rao, U., A. Baskar, and R. Karthi, “Two-step iterative algorithm to extract generative video parameters from video sequences”, Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007, vol. 3. Sivakasi, Tamil Nadu, pp. 458-463, 2008.[Abstract]


GV (Generative Video) is a framework for the analysis and synthesis of video sequences. In GV, the operational units are not the actual frames in the original sequence; it has world images which have the non redundant information about the video sequences and the ancillary data. The world images and the ancillary data form the generative video representation, the information that is needed to regenerate the original video sequence. A two-step iterative algorithm is used here to obtain the generative video parameters. The first step estimates the background texture for a fixed template. The second step estimates the object template for a fixed background-the solution is given by a simple binary test evaluated at each pixel. The algorithm converges in a few iterations, typically three to five iterations. © 2007 IEEE.

More »»
207
PROGRAMS
OFFERED
6
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
8th
RANK(INDIA):
NIRF 2018
150+
INTERNATIONAL
PARTNERS