Dr. Santhosh Kumar C. joined Amrita in 2001. He has been a visiting researcher to Faculty of Information Technology, Brno University of Technology, Czech Republic in 2007. In 2009, Dr. Santhosh served as a visiting researcher to School of Computer and Electrical Engineering, University of Auckland, New Zealand, and School of Electrical Engineering, University of New South Wales, Sydney, Australia. He is currently leading the research activities in Machine Intelligence Research Lab of Amrita School of Engineering. Dr. Santhosh's areas of research interests are Spoken Language Processing, Machine Fault Identification and Applications of Signal Processing to Biomedical Applications.




Publication Type: Journal Article
Year of Publication Publication Type Title
2016 Journal Article P. V. Sunil Nag, Silla, G. K., Gummadi, V. H. V., Harishankar, C. B., Ray, V. K., and C.Santhosh Kumar, “Model based fault diagnosis of low earth orbiting (LEO) satellite using spherical unscented kalman filter”, IFAC-PapersOnLine, vol. 49, pp. 635-638, 2016.[Abstract]

Model based fault detection and diagnosis (FDD) using a non-linear estimation technique is presented here. The non-linear estimation technique namely spherical Unscented Kalman Filter (UKF) has been applied to other kinds of estimation problems but has never been applied to the FDD problem of a Low Earth Orbiting (LEO) satellite. It has been shown in this work that compared to the standard UKF, which is a derivative free estimation technique unlike the popular Extended Kalman Filter (EKF), the spherical UKF can perform better in terms of computational savings without sacrificing accuracy. Hence it is better suited for real-time fault diagnosis. A planar model of the satellite is used to demonstrate the technique. © 2016 IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved. More »»
2015 Journal Article K. Ka George, C.Santhosh Kumar, KI Ramachandran, and Panda, Ab, “Cosine distance features for improved speaker verification”, Electronics Letters, vol. 51, pp. 939-941, 2015.[Abstract]

Similarities are used with people known already as a means to enhance speaker verification accuracy. Motivated by this, experimental work has been conducted regarding the use of cosine distance (CD) similarity with respect to a set of reference speakers, CD features, with a back-end support vector machine (CDF-SVM) classifier for speaker verification. A state-of-the-art i-vector with CD scoring (i-CDS) is used as the baseline system for the experiments and for the computation of CD similarity. Experimental results on the telephone speech of the core short2-short3 conditions of NIST 2008 speaker recognition evaluation (SRE), for female, male and both-gender trials, show that the proposed CDF-SVM outperforms the baseline i-CDS system. The CDF-SVM achieved an absolute improvement of 1.16% in equal error rate (EER) and 0.38% in minimum DCF over the baseline i-CDS for female trials. Similar performance improvements were also obtained for the male and all-gender trials of the SRE. Finally, fusing the CDF-SVM with i-CDS gave the best overall performance, an absolute improvement of 4.19% in EER and 1.99% in minimum DCF, over the individual CDF-SVM system performance for the all-gender trials. Similar performance improvements were also achieved for male and female trials. © The Institution of Engineering and Technology 2015.

More »»
2015 Journal Article D. Mohan and C.Santhosh Kumar, “An efficient IKSVM based multi-parameter patient monitoring system”, International Journal of Applied Engineering Research, vol. 10, pp. 22703-22710, 2015.[Abstract]

Multi-parameter patient monitors (MPMs) are extensively used for enhancing the quality of healthcare in both intensive care units (ICU) and in-patient wards. MPMs make use of the vital signs, respiration rate, heart rate, blood pressure and oxygen saturation (SpO<inf>2</inf>), for predicting the condition of patients. Support vector machine (SVM) is one of the most popularly used classification algorithms for developing MPMs. The kernel function, used in an SVM is a measure of similarity between any two examples, either belonging to same class or different classes. The selection of the kernel is an important aspect for the optimization of the system using SVM. If two patients have heart rates of 60 bpm and 80 bpm, intuition suggests that their heart rate similarity is 60 bpm. Extending this to n features, we may say that the total similarity is a summation of the individual similarities over n features, suggesting that intersection kernel is an ideal choice for MPM. In this paper, we explore the effectiveness of using intersection kernel SVM (IKSVM) for improving the performance of MPMs. We also compare the performance improvement of the MPM using IKSVM with the popularly used linear, polynomial and radial basis function (RBF) kernel MPMs. The results suggest that the use of intersection kernel can help enhance the performance of the MPMs significantly. Using IKSVM system, we obtained an improvement of 2.74%absolute for overall accuracy, 1.86% absolute for sensitivity and 3.00% absolute for specificity over the best baseline MPM using RBF kernel. © Research India Publications.

More »»
2013 Journal Article Va Vaijeyanthi, C.Santhosh Kumar, KI Ramachandran, Joy, J. Ka, and Kumar, A. Ab, “Application-Specific fine tuning of multi-Parameter patient monitors”, Electronics Letters, vol. 49, pp. 1432-1433, 2013.[Abstract]

Multi-parameter patient monitors (MPMs) have become increasingly important in providing quality health care to patients. A high alarm accuracy (sensitivity) will need a lower threshold for alarm detection which will lead to lower no-alarm accuracy (specificity) and viceversa. MPMs when used in an intensive care unit (ICU) need to have high sensitivity. However they need to have high specificity when used in in-patient wards for regular health check-ups. Proposed is a novel algorithm to trade-off specificity for sensitivity and viceversa depending on the application. The proposed method is referred as detection error trade-off, trade-off specificity for better sensitivity and vice-versa. The algorithm will help to extend the application of MPMs from ICUs to in-patient wards and thus enhance the quality of health care. Experiments have been conducted with an MPM using the classification and regression tree algorithm. By using the proposed algorithm, an improvement of 10.18% in sensitivity was obtained by trading-off 0.40% in specificity. Furthermore, the overall performance of the refined system is 1.15% better than the baseline system. © The Institution of Engineering and Technology 2013.

More »»
Publication Type: Conference Paper
Year of Publication Publication Type Title
2015 Conference Paper K. Ka George, C.Santhosh Kumar, Panda, Ab, R.b Ramachandran, Das, K. Aa, and Veni, S., “Minimizing the false alarm probability of speaker verification systems for mimicked speech”, in 2015 International Conference on Computing and Network Communications, CoCoNet 2015, 2015, pp. 703-709.[Abstract]

Speaker verification (SV) systems need to be robust to mimicked voices of target speakers as non-target trials to make them usable in critical applications. However, the performance of SV systems for mimicked voice test conditions has not been extensively explored. © 2015 IEEE.

More »»
Faculty Details


Faculty Email: