Qualification: 
M.Tech, B-Tech
anurajk@am.amrita.edu

Anuraj K. currently serves as an Assistant Professor at the Department of Electronics and Communication Engineering, Amrita School of Engineering, Amritapuri. She pursued her M. Tech. in Optoelectronics and Optical Communication from Kerala University in 2012.

Publications

Publication Type: Book Chapter

Year of Publication Title

2020

Poorna S. S., M. Reddy, R. Kiran, Akhil, N., Kamath, S., Mohan, L., Anuraj K., and Pradeep, H. S., “Computer Vision Aided Study for Melanoma Detection: A Deep Learning Versus Conventional Supervised Learning Approach”, in Advanced Computing and Intelligent Engineering, Advances in Intelligent Systems and Computing, vol. 1082, 2020, pp. 75 - 83.[Abstract]


Melanoma is one of the most fatal type of skin cancer. Among the 2–3 million skin cancer diagnosed around the world each year, around 5% is affected with melanoma. Early detection of melanoma can save a life. A computer vision aided system with reasonable accuracy was developed for the early diagnosis of melanoma. The analysis was done using dermoscopic images downloaded from publically available database. After preprocessing, the features capable of melanoma identification, viz., ABCD parameters: Asymmetry, Border, Color, and Diameter are extracted. The analysis includes a comparative study between conventional machine learning techniques and deep learning. The learning techniques: Total Dermoscopic Score, K-Nearest Neighbor, Support Vector Machine and Convolutional Neural Networks were used for classification. The results of the study showed that deep learning-based method gives more accurate and precise detection of melanoma compared to conventional supervised learning techniques.

More »»

2020

Anuraj K. and Poorna S. S., “Performance Analysis of Optimization Algorithms Using Chirp Signal”, in Inventive Computation Technologies. ICICIT 2019. Lecture Notes in Networks and Systems, vol. 98, 2020, pp. 132 - 137.[Abstract]


In order to evaluate the material charateristics and defects, different input signals are allowed to pass through the material. These signals are able to capture the hidden information regarding the material while traversing througnh it. These material signatures can be obtained by analyzing the reflected signals. This enables us to study the material properties and defects non-invasively. The different input signals can be modelled as Chirp signal, Gaussian echo, combination of echoes, etc. In this paper, analysis is done using chirp as the input signal. The parameter estimation is done using Maximum Likelihood and different optimization techniques are adopted for minimizing the error. Eventhough the results obtained for all optimization algorithms are comparable with the actual parameters, Levenberg-Marquardt algorithm gave the best fit, with minimum average absolute relative error.

More »»

Publication Type: Conference Paper

Year of Publication Title

2018

R. N. Aditya, K. Abhijeeth, S., Anuraj K., and Poorna S. S., “Error Analysis of Optimization Algorithms in Ultrasonic Parameter Estimation”, in 2018 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)2018 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2018.[Abstract]


The back scattered ultrasonic echo carries several valuable information in its amplitude, bandwidth, delay in time, phase and time of flight. This information is capable of characterizing properties of the material from which it is reflected. In order to model the reverberations, white Gaussian noise is added to Gaussian echo. The required set of parameters are estimated from the noise altered echo using Maximum Likelihood Estimation. This reduces to least square curve fitting, due to additive white gaussian noise. For optimizing the estimated parameters from the back-scattered signal, different algorithms such as Levenberg-Marquardt, Trust-Region Reflective, Active Set, Quasi Newton and Sequential quadratic programming are used. The proposed work aims at the error analysis of estimated signals using the above-mentioned optimization algorithms for different SNR values viz. 0-20dB. Further the noise added signals are subjected to wavelet denoising, prior to parameter estimation. The experimental result shows that the lowest mean square error is obtained for the echo parameters optimized using Levenberg-Marquardt algorithm, for both noisy and de-noised cases. More »»

2013

Anuraj K., “Detection of Cervical lesions in vivo by Multi-spectral Diffused Reflectance Imaging”, in 4th International conference of stem cells and cancer, 2013.

Publication Type: Conference Proceedings

Year of Publication Title

2018

Poorna S. S., Anuraj K., and Saikumar C., “Ultrasonic Signal Modelling and Parameter Estimation : A Comparative Study Using Optimization Algorithms”, In: Zelinka I., Senkerik R., Panda G., Lekshmi Kanthan P. (eds) Soft Computing Systems. ICSCS 2018. Communications in Computer and Information Science, , vol. 837. Springer, Singapore, 2018.[Abstract]


The parameter estimation from ultrasonic reverberations is used in applications such as non-destructive evaluation, characterization and defect detection of materials. The parameters of back scattered Gaussian ultrasonic echo altered by noise: Received time, Amplitude, Phase, bandwidth and centre-frequency should be estimated. Due to the assumption of the nature of noise as additive white Gaussian, the estimation can be approximated to a least square method. Hence different least square cure-fitting optimization algorithms can be used for estimating the parameters. Optimization techniques: Levenberg-Marquardt(LM), Trust-region-reflective, Quasi-Newton, Active Set and Sequential Quadratic Programming are used to estimate the parameters of noisy echo. Wavelet denoising with Principal Component Analysis is also applied to check if it can make some improvement in estimation. The goodness of fit for noisy and denoised estimated signals are compared in terms of Mean Square Error (MSE). The results of the study shows that LM algorithm gives the minimum MSE for estimating echo parameters from both noisy and denoised signal, with minimum number of iterations.

More »»

2018

Poorna S. S., Anuraj K., and Nair, G. J., “A Weight Based Approach for Emotion Recognition from Speech: An Analysis Using South Indian Languages”, In: Zelinka I., Senkerik R., Panda G., Lekshmi Kanthan P. (eds) Soft Computing Systems. ICSCS 2018. Communications in Computer and Information Science, vol. 837. Springer Singapore, Singapore, 2018.[Abstract]


A weight based emotion recognition system is presented to classify emotions using audio signals recorded in three south Indian languages. An audio database with containing five emotional states namely anger, surprise, disgust, happiness, and sadness is created. For subjective validation, the database is subjected to human listening test. Relevant features for recognizing emotions from speech are extracted after suitably pre-processing the samples. The classification methods, K-Nearest Neighbor, Support Vector Machine and Neural Networks are used for detection of respective emotions. For classification purpose the features are weighted so as to maximize the inter cluster separation in feature space. An inter performance comparison of the above classification methods using normal, weighted features as well as feature combinations are analyzed.

More »»

2018

Poorna S. S., Anuraj K., Renjith, S., Vipul, P., and Nair, G. J., “EEG Based Control using Spectral Features”, 2nd International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud). Palladam, India, pp. 788-794, 2018.[Abstract]


In the present days, Brain Computer Interfaces (BCI) are used in applications pertaining to diagnostics and prosthetics for neurological disorders, navigation of unmanned aerial vehicles and gaming. Detailed analysis of spectral features and classifiers using eye blink control from Electroencephalogram (EEG) will be described in this paper. In this study, the signals were acquired using an EEG headset, where the ocular pulses dominated the data. Principal Component Analysis was used to extract the ocular components. From the resultant signal, the features: sum of spectral peaks, bandwidth, power spectral entropy, and Cepstral coefficients of the blinks were extracted for supervised learning. The classification methods Multiclass Support Vector Machine (SVM), Quadratic Discriminant Analysis (QDA) and Artificial Neural Networks (ANN) were evaluated using these features independently as well as together. The results showed that among the three features, spectral peaks and bandwidth gave more classification accuracy. Also while features were taken together, QDA gave superior classification results in terms of accuracy, sensitivity and specificity compared to Multi class SVM and ANN.

More »»

Publication Type: Journal Article

Year of Publication Title

2016

V. Gopala Prabitha, Suchetha, S., Jayanthi, J. Lalitha, Baiju, K. Vijayakuma, Rema, P., Anuraj K., Mathews, A., Sebastian, P., and Subhash, N., “Detection of cervical lesions by multivariate analysis of diffuse reflectance spectra: a clinical study”, Lasers in Medical Science, vol. 31, pp. 67–75, 2016.[Abstract]


Diffuse reflectance (DR) spectroscopy is a non-invasive, real-time, and cost-effective tool for early detection of malignant changes in squamous epithelial tissues. The present study aims to evaluate the diagnostic power of diffuse reflectance spectroscopy for non-invasive discrimination of cervical lesions in vivo. A clinical trial was carried out on 48 sites in 34 patients by recording DR spectra using a point-monitoring device with white light illumination. The acquired data were analyzed and classified using multivariate statistical analysis based on principal component analysis (PCA) and linear discriminant analysis (LDA). Diagnostic accuracies were validated using random number generators. The receiver operating characteristic (ROC) curves were plotted for evaluating the discriminating power of the proposed statistical technique. An algorithm was developed and used to classify non-diseased (normal) from diseased sites (abnormal) with a sensitivity of 72 {%} and specificity of 87 {%}. While low-grade squamous intraepithelial lesion (LSIL) could be discriminated from normal with a sensitivity of 56 {%} and specificity of 80 {%}, and high-grade squamous intraepithelial lesion (HSIL) from normal with a sensitivity of 89 {%} and specificity of 97 {%}, LSIL could be discriminated from HSIL with 100 {%} sensitivity and specificity. The areas under the ROC curves were 0.993 (95 {%} confidence interval (CI) 0.0 to 1) and 1 (95 {%} CI 1) for the discrimination of HSIL from normal and HSIL from LSIL, respectively. The results of the study show that DR spectroscopy could be used along with multivariate analytical techniques as a non-invasive technique to monitor cervical disease status in real time. More »»

Faculty Research Interest: