Qualification: 
Ph.D, M.Tech, BE
m_neethu@cb.amrita.edu

Dr. Neethu Mohan currently serves as Assistant Professor at the Center for Computational Engineering and Networking (CEN), Amrita Vishwa Vidyapeetham, Coimbatore, India.

Education

  • December 2013 - December 2019: Ph. D. Signal Processing
    Amrita Vishwa Vidyapeetham, Tamilnadu, India.
    Ph. D. Thesis: Parameter Estimation and Forecasting Methods for Emerging Power Grids Using Data-Adaptive Techniques 
  • August 2011 -  July 2013: Master of Technology, Remote Sensing and Wireless Sensor Networks
    Amrita Vishwa Vidyapeetham, Tamilnadu, India
  • June 2007 - May 2011: Bachelor of Engineering, Electronics and Communication Engineering,
    Anna University, Tamilnadu, India

Professional Experience

Year Affiliation
March 2020- Till Date Assistant Professor, Center for Computational Engineering and Networking (CEN), Amrita Vishwa Vidyapeetham, Coimbatore, India
July 2019 - December 2019 Faculty Associate, Department of Electronics and Communication Engineering, Amrita School of Engineering, Amritapuri, Kollam, India
August 2013 - June2019 Research Scholar, Center for Computational Engineering and Networking (CEN), Amrita Vishwa Vidyapeetham, Coimbatore, India

 

 

Publications

Publication Type: Book Chapter

Year of Publication Title

2021

S. Akshay, Dr. Soman K. P., Dr. Neethu Mohan, and Sachin Kumar S., “Dynamic Mode Decomposition and Its Application in Various Domains: An Overview”, in Applications in Ubiquitous Computing, R. Kumar and Paiva, S., Eds. Cham: Springer International Publishing, 2021, pp. 121–132.[Abstract]


The unprecedented availability of high-fidelity data measurements in various disciplines of engineering and physical and medical sciences reinforces the development of more sophisticated algorithms for data processing and analysis. More advanced algorithms are required to extract the spatiotemporal features concealed in the data that represent the system dynamics. Usage of advanced data-driven algorithms paves the way to understand the associated dominant dynamical behavior and, thus, improves the capacity for various tasks, such as forecasting, control, and modal analysis. One such emerging method for data-driven analysis is dynamic mode decomposition (DMD). The algorithm for DMD is introduced by Peter J. Schmid in 2010 based on the foundation of Koopman operator (Schmid. J Fluid Mech 656:5–28, 2010). It is basically a decomposition algorithm with intelligence to identify the spatial patterns and temporal features of the data measurements. DMD has recently gained improved interest due to its dominant ability to mine meaningful information from available measurements. It has revolutionized the analysis and modeling of physical systems like fluid dynamics, neuroscience, financial trading markets, multimedia, smart grid, etc. The ability to recognize the spatiotemporal patterns makes DMD as prominent among other similar algorithms. DMD algorithm merges the characteristics of proper orthogonal decomposition (POD) and Fourier transform.

More »»

Publication Type: Conference Paper

Year of Publication Title

2020

Dr. Neethu Mohan, S. S., K., and Dr. Soman K. P., “Group Sparsity Assisted Synchrosqueezing Approach for Phonocardiogram Signal Denoising”, in 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2020.[Abstract]


Computer aided diagnosis (CAD) framework gains huge importance in today's medical world for the automatic cardiac disease monitoring. The CAD framework requires preprocessing of acquired phonocardiogram (PCG) signals to extract informative features from it. Denoising is an important preprocessing step for cardiac disease diagnosis. This paper proposes a novel, group sparsity assisted synchrosqueezing approach for improved PCG signal denoising. In the proposed approach, the PCG signals are initially denoised by exploiting the group sparse (GS) property of the heart sound signals. In the second step, the denoised result is improved by utilizing the synchrosqueezing wavelet transform (SSWT) by eliminating the unwanted higher order frequency components using the extracted intrinsic mode type functions. The robustness of the proposed approach is evaluated by using several PCG signal databases. The superior performance compared to other existing models confirms that the proposed approach can be useful for improved PCG denoising tasks in automatic cardiac monitoring systems.

More »»

2020

M. T. Vyshnav, Sachin Kumar S., Dr. Neethu Mohan, and Dr. Soman K. P., “Random fourier feature based music-speech classification”, in Journal of Intelligent & Fuzzy Systems, 2020, vol. 38, pp. 6353 - 6363.[Abstract]


The present paper proposes Random Kitchen Sink based music/speech classification. The temporal and spectral features such as spectral centroid, Spectral roll-off, spectral flux, Mel-frequency cepstral coefficients, entropy, and Zero-crossing rate are extracted from the signals. In order to show the competence of the proposed approach, experimental evaluations and comparisons are performed. Even though both speech and music signals differ in their production mechanisms, those share many common characteristics such as a common spectrum of frequency and are comparatively non-stationary which makes the classification difficult. The proposed approach explicitly maps the data to a feature space where it is linearly separable. The evaluation results shows that the proposed approach provides competing scores with the methods in the available literature.

More »»

2019

A. R. Nair, Dr. Soman K. P., and Dr. Neethu Mohan, “A Novel Method for Multiple Power Quality Disturbance Classification using Dynamic Mode Decomposition”, in 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 2019.[Abstract]


The quality supply of power plays a major role in power systems. Ensuring the quality supply of power has become a prominent issue in modern days due to the introduction of microgrids (MG) with distributed generation systems (DGS) and renewable energy sources (RES) such as solar, wind etc. A novel method based on dynamic mode decomposition (DMD) features are used for multiple power quality disturbance classification. The algorithms's intelligence to extract elemental dynamic patterns over time of the power quality data is used for accurate classification. The different features such as eigenvalues, eigen-vectors and dynamic mode frequencies extracted through DMD are classified using multi-class classifiers such as random forest, support vector machines and decision tree. The advantage of the proposed method is evaluated under different noise and noiseless power quality events and variations. The promising results obtained using the proposed method highlight the potential usage of DMD based features for time-series identification of power quality disturbances (PQD) in power systems.

More »»

2019

K. Sreelakshmi, Sasidhar, T. T., Dr. Neethu Mohan, and Dr. Soman K. P., “A Methodology for Spikes and Transients Detection and Removal in Power Signals Using Chebyshev Approximation”, in 2019 9th International Conference on Advances in Computing and Communication (ICACC), 2019.[Abstract]


The smart grid is an important empowering agent for a prosperous society. However, due to the involvement of various renewable energy sources, power electronic devices and loads, the grid is prone to distortions which reduce the power quality. It is very important to improve the quality of the power signal as it can damage the equipment that consumes it. In this paper, a novel and robust method is developed to improve the power quality by using Chebyshev approximation. The proposed methodology detects the spike and transient distortions in power signals and removes them effectively. The efficacy of the proposed method is tested over different noise intensities and also compared with a VMD based signal smoothing system. The promising results evince that the system can be used for power quality improvement in smart grid environment. This method is useful for predicting the exact locations and magnitudes of disturbances in future time so that control/corrective actions can be taken to rectify the distortions.

More »»

2019

V. T. Priyanga, Chandni, M., Dr. Neethu Mohan, and Dr. Soman K. P., “Data-driven Analysis for Low Frequency Oscillation Identification in Smart Grid using FB-DMD and T-DMD Methods”, in 2019 9th International Conference on Advances in Computing and Communication (ICACC), 2019.[Abstract]


The major challenges faced by the modern interconnected grids are the disturbances caused due to the presence of the low frequency oscillations (LFO). These inter-area modes can cause a huge disturbances and may also lead to the failure of the entire electric grid system. Hence, monitoring of these low frequency oscillations and mitigating its effects are very much important to maintain stability of the power system. To employ a better control over the grid and to bring up the stability of the system, the damped modes of the power signal generated must be known even under a noisy condition. Based on the past literature, dynamic mode decomposition (DMD) method has proven to be the best to identify the damped modes of a signal. However, it fails to give satisfying results in the presence of noises. Hence, two variants of DMD namely forward-backward DMD (FB-DMD) and total-DMD (T-DMD) are adapted in this paper to find the dynamic modes of the system which helps to identify the low frequency modes even under a noisy condition. Based on the experimental results and analysis, T-DMD is found to be suitable to predict the low frequency modes with higher accuracy and lower complexity.

More »»

2019

S. Saj T. K, Dr. Neethu Mohan, S, S. Kumar, and Dr. Soman K. P., “Significance of Incorporating Chebfunction Coefficients for Improved Machine Fault Diagnosis”, in IOP Conference Series: Materials Science and Engineering, 2019, vol. 561, p. 012090.[Abstract]


For any industry the efficiency and performance of rotating machinery/mechanical systems is a major concern. Bearings and gears are two essential parts in a rotating machinery and any defects in these components can lead to a major breakdown of the system thus causing large economical loss for the company. An appropriate machine condition monitoring system is essential in such scenarios for identifying the health of the machines. Therefore in this paper fault diagnosis of rotating mechanical systems is performed as a feature dependent-pattern classification problem. The machine is made to run in different good as well faulty conditions and the vibration signals are collected. Then chebfunction coefficients are extracted from the vibration signals as part of the feature extraction process. Finally, the extracted features are classified using regularized least squares (RLS) for identifying the good and faulty bearing as well as gear conditions of the machine. The evaluations are performed using different kernel functions and the average accuracy reported is 98% for bearing and gear data. The various experiments performed claims that the proposed system can be used for real-time fault diagnosis in rotating mechanical systems with sufficient accuracy.

More »»

2019

R. - V. Krishnamohan, S, S., Dr. Neethu Mohan, and Dr. Soman K. P., “Dynamic Mode Decomposition based feature for Image Classification”, 2019.[Abstract]


Irrespective of the fact that Machine learning has produced groundbreaking results, it demands an enormous amount of data in order to perform so. Even though data production has been in its all-time high, almost all the data is unlabelled, hence making them unsuitable for training the algorithms. This paper proposes a novel method of extracting the features using Dynamic Mode Decomposition (DMD). The experiment is performed using data samples from Imagenet. The learning is done using SVM-linear, SVM-RBF, Random Kitchen Sink approach (RKS). The results have shown that DMD features with RKS give competing results.

More »»

2019

Dr. Neethu Mohan, Dr. Soman K. P., and S. Kumar, S., “A Data-driven Approach for Estimating Power System Frequency and Amplitude Using Dynamic Mode Decomposition”, in Proceedings of the Conference on the Industrial and Commercial Use of Energy, ICUE, 2019, vol. 2018-October.[Abstract]


To ensure power system stability, control and quality supply of power, it is essential to monitor power system parameters such as frequency and amplitude. This paper proposes a data-driven approach based on dynamic mode decomposition (DMD) algorithm for the accurate estimation of frequency and amplitude in smart grid. In the proposed approach, to extract the multiple frequency components, including harmonics, inter-harmonics and subharmonics, a stacked measurement matrix is created by appending multiple time-shifted versions of power signals. An optimal hard-thresholding is performed on the singular values of the measurement matrix to deal with the uncertainties and high-level noises. Further, the frequency and amplitude are computed based on the extracted dynamic modes. The performance of the proposed approach is confirmed through various experiments conducted on different power system scenarios under noisy and noiseless conditions. The effectiveness of the DMD based method is verified by comparing the results with several state-of-the-art methods. The promising results suggest that the proposed approach can be used as an efficient candidate for estimating the power system frequency and amplitude. © 2018 Asian Institute of Technology.

More »»

2018

Dr. Neethu Mohan, S. Kumar, S., and Dr. Soman K. P., “An L1 -Norm Based Optimization Approach for Power Line Interference Removal in ECG Signals”, in Progress in Intelligent Computing Techniques: Theory, Practice, and Applications, Singapore, 2018.[Abstract]


Accurate analysis and proper interpretation of electrophysical recordings like ECG is a real necessity in medical diagnosis. Presence of artifacts and other noises can corrupt the ECG signals and can lead to an improper disease diagnosis. Power line interferences (PLI) occurring at 50/60 Hz is a major source of noises which could corrupt the ECG signals. This motivates the removal of PLI from ECG signals and is a foremost preprocessing task in ECG signal analysis. In this paper, we deal an \$\${\backslashell _1}\$\$ℓ1norm based optimization approach for PLI removal in ECG signals. The sparsity inducing property of \$\${\backslashell _1}\$\$ℓ1norm is used for efficient removal of power noises. The effectiveness of this approach is evaluated on ECG signals corrupted with power line interferences and random noises.

More »»

2018

A. Ravikumar, Dr. Neethu Mohan, and Dr. Soman K. P., “Performance Enhancement of a Series Active Power Filter using Kalman Filter based Neural Network Control Strategy”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018.[Abstract]


Increased use of power electronic converters at various stages of power system is the main cause of harmonics and reactive power. Presence of harmonics adds pollution to the power system or degrades the quality of power. A series active power filter is used to reduce the harmonics and also compensate reactive power. This paper explores the use of a Kalman filter based neural network controller for enhancing the operation of a three phase series active power filter which is connected at the input of a non-linear load. The entire experiment has been conducted in MATLAB/Simulink environment. It is observed that there is substantial reduction in harmonics with this proposed control scheme. The three phase total harmonic distortion in the non-linear load circuit has been reduced from 33.63% to 2.61%.

More »»

2018

A. Chandran, Anjali, T., Dr. Neethu Mohan, and Dr. Soman K. P., “Overlapping Group Sparsity Induced Condition Monitoring in Rotating Machineries”, in Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016), Cham, 2018.[Abstract]


Maintenance of rotating parts in machines is not easy. Prediction of faults in advance reduces the frequency of breakdown and improves the life time of machines. This paper proposes a machine condition monitoring system, which formulates the fault diagnosis problem as a machine learning based pattern classification problem. The vibration signals acquired from rotating machines are initially processed by a group-sparse denoising algorithm namely Overlapping Group Shrinkage (OGS). In OGS, the group sparse signal denoising problem is casted as a convex optimization problem with a group sparsity promoting penalty function. The denoised signals are then processed by Variational Mode Decomposition (VMD), which decomposes the signal into specific frequency modes. For representing the signal in the feature space, energy of each mode is extracted and is classified by LS-SVM classifier. The performance of the proposed condition monitoring system is evaluated in terms of classification accuracies and is compared with statistical features.

More »»

2018

V. G. Sujadevi, Dr. Soman K. P., S. Kumar, S., and Dr. Neethu Mohan, “A Novel Cyclic Convolution Based Regularization Method for Power-Line Interference Removal in ECG Signal”, in Advances in Signal Processing and Intelligent Recognition Systems, Cham, 2018.[Abstract]


Applying signal processing to bio-signal record such as electrocardiogram or ECG signals provide vital insights to the details in diagnosis. The diagnosis will be exact when the extracted information about the ECG is accurate. However, these records usually gets corrupted/contaminated with several artifacts and power-line interferences (PLI) thereby affects the quality of diagnosis. Power-line interferences occurs in the range close to 50 Hz/60 Hz. The challenge is to remove the interferences without altering the original characteristics of ECG signal. Since the ECG signals frequency range is close to PLI, several articles discuss PLI removal methods which are mathematically complex and computationally intense. The present paper proposes a novel PLI removal method that uses a simple optimization method involving a circular convolution based \$\${\backslashell _2}\$\$-norm regularization. The solution is obtained in closed form and hence computationally simple and fast. The effectiveness of the proposed method is evaluated using output signal-to-noise-ratio (SNR) measure, and is found to be state-of-the-art.

More »»

2018

Dr. Neethu Mohan and Dr. Soman K. P., “Power System Frequency and Amplitude Estimation Using Variational Mode Decomposition and Chebfun Approximation System”, in 2018 Twenty Fourth National Conference on Communications (NCC), Hyderabad, India, 2018.[Abstract]


The accurate estimation of power system frequency and amplitude is essential for power system monitoring, stability, control, and protection. This work proposes a novel approach for power system frequency and amplitude estimation based on variational mode decomposition (VMD) algorithm and Cheb-function (Chebfun) approximation system. In this work, the spectral information of power signals is extracted using VMD as sub-signals or modes. Each mode is further interpolated by Chebyshev polynomials in continuous domain using Chebfun system. The instantaneous frequency and amplitude are estimated based on zero crossings and local extrema locations of the continuous function. The robustness of the approach is evaluated on various power system scenarios and the results are compared with other existing methods. The promising results suggest that the proposed approach can be used as an efficient candidate for power system frequency and amplitude estimation.

More »»

2017

V. G. Sujadevi, Dr. Soman K. P., Kumar, S. S., Dr. Neethu Mohan, and Arunjith, A. S., “Denoising of phonocardiogram signals using variational mode decomposition”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Udupi, India, 2017.[Abstract]


Recent advances in signal processing and the revolution by the mobile technologies have spurred several innovations in all the areas and albeit more so in home based tele-medicine. We used variational mode decomposition (VMD) based denoising on large-scale phonocardiogram (PCG) data sets and achieved better accuracy. We have also implemented a reliable, external hardware and mobile based phonocardiography system that uses VMD signal processing technique to denoise the PCG signal that visually displays the waveform and inform the end-user and send the data to cloud based analytics system.

More »»

2017

Dr. Neethu Mohan, Dr. Soman K. P., and Vinayakumar, R., “Deep power: Deep learning architectures for power quality disturbances classification”, in 2017 International Conference on Technological Advancements in Power and Energy ( TAP Energy), Kollam, India, 2017.[Abstract]


The transformation of the conventional electric power grid to modern smart grid are subjected to power system quality and reliability problems. In order to ensure reliable, secure and quality supply of power, it is important to characterize and classify the power quality disturbances. Power quality (PQ) disturbance classification schemes implicitly relies o n feature engineering to extract unique and accurate features such as statistical information, spatio-temporal characteristics, stationary and non-stationary behavior of PQ signals. This paper explores the potentiality of deep learning algorithms to characterize and classify various PQ disturbances in smart grid. Deep learning algorithms have the inherent capability to automatically learn optimal features from raw input data and thus to avoid time-consuming feature engineering. To understand the effectiveness of various deep learning mechanisms, different architectures namely convolution neural network (CNN), recurrent neural network (RNN), identity-recurrent neural network (I-RNN), long short-term memory (LSTM), gated recurrent units (GRU) and convolutional neural network-long short-term memory (CNN-LSTM) are studied in this paper. Several experiments are conducted to propose an optimal deep learning architecture with specific network parameters and topologies. The performance of the proposed deep learning architecture is evaluated on a set of synthetic single and combined PQ disturbances and real-time PQ events. The proposed architecture is found to be accurate for real-time characterization and classification of power quality disturbances in smart grid.

More »»

2017

S. Jose, Dr. Neethu Mohan, Sowmya, and Dr. Soman K. P., “Least square based image deblurring”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, Manipal, Mangalore, India, 2017.[Abstract]


An image can be basically defined as an object that represents visual observation, which can be created and stored in the electronic form, produced from an optical device. When we take a photograph, there can be many problems associated with that particular image. Among them, one of the main issue is the blur of the image. Blur can be defined as something which will become vague or less distinct. A blurred image looks sharper or more detailed, if we are able to perceive all the objects and their shapes correctly in it. The main cause for blur is the out of focus issue of the camera/sensor. An image which is in out of focus will appear in a blurred state. Even if, at the present time, with an auto focus facility, sometimes we will not get the image in the correct focus. Most probably, a part of the image will be crisp and clear, however rest will be ill-defined. Image deblurring is a common and important process in fields like digital photography, medical imaging and astronomy. Hence, removing or dropping the total amount of blur is the most important task before being applying to the image analysis techniques. In this paper, a colour image deblurring algorithm based on the concept of least squares is proposed. The 1D least square based deconvolution technique is extended to colour image deblurring. The proposed approach is experimented on standard test images and the results are compared with classical total variation image deblurring algorithm. The effectiveness of the proposed approach is evaluated in terms of standard quality metrics such as PSNR and SSIM. © 2017 IEEE.

More »»

2016

S. Sa Kumar, Dr. Neethu Mohan, Prabaharan, Pb, Dr. Soman K. P., J., M., and J., J., “Total Variation Denoising Based Approach for R-peak Detection in ECG Signals”, in Procedia Computer Science, 2016, vol. 93, pp. 697-705.[Abstract]


Detecting R-peak signal from electrocardiogram or ECG signal plays a vital role in cardiac monitoring system and ECG applications. In this paper, Total Variation Denoising (TVD) based approach is proposed to find the locations of R-peaks in the ECG signal. One advantage of using TVD method is that it preserves the sharp slopes or the peaks in the signal. This motivated to use TVD method for R-peak detection problem. The proposed approach is evaluated using the first channel, 48 ECG records from MIT-BIH Arrhythmia database. The accuracy of TVD based approach is calculated on all the 48 records. The proposed method gives 9 false-negative or FN beats, 126 false-positive or FP beats, positive-predictivity of 99.885%, sensitivity of 99.914%, with an overall accuracy of 99.79%. © 2016 The Authors. Published by Elsevier B.V.

More »»

2016

D. Pankaj, S, S. Kumar, Dr. Neethu Mohan, and Dr. Soman K. P., “Image Fusion Using Variational Mode Decomposition”, in International Conference on Innovation in Information Embedded and Communication Systems (ICIIECS’16), 2016.

2016

G. B. Gowri, S. Kumar, S., Dr. Neethu Mohan, and Soman, K. P., “A VMD Based Approach for Speech Enhancement”, in Advances in Signal Processing and Intelligent Recognition Systems, Cham, 2016, vol. 425, pp. 309-321.[Abstract]


This paper proposes a Variational Mode Decomposition (VMD) based approach for enhancement of speech signals distorted by white Gaussian noise. VMD is a data adaptive method which decomposes the signal into intrinsic mode functions (IMFs) by using the Alternating Direction Method of Multipliers (ADMM). Each IMF or mode will contain a center frequency and its harmonics. This paper tries to explore VMD as a Speech enhancement technique. In the proposed method, the noisy speech signal is decomposed into IMFs using VMD. The noisy IMFs are enhanced using two methods; VMD based wavelet shrinkage (VMD-WS) and VMD based MMSE log STSA (VMD-MMSE). The speech signal distorted with different noise levels are enhanced using the VMD based methods. The level of noise reduction and speech signal quality are measured using the objective quality measures.

More »»

2015

Dr. Maneesha V. Ramesh, Dr. Neethu Mohan, and Arya Devi R. D., “Micro grid architecture for line fault detection and isolation”, in Smart Cities and Green ICT Systems (SMARTGREENS), 2015 International Conference on, 2015.[Abstract]


One of the major problems power grids system face today is the inability to continuously deliver power at the consumer side. The main reason for this is the occurrence of faults and its long term persistence within the system. This persistence of faults causes the cascading failure of the system, thereby adversely affecting the connected loads. Traditional methods of fault isolation cause the shutdown of power to a large area to maintain the system stability. Today, localization of faults and its isolation is doing manually. Therefore, a localized fault recovery mechanism is very essential to maintain the system’s stability after the occurrence of a fault. In this paper, we have developed fast fault detection and isolation mechanism for single phase to neutral line fault in a three phase islanded micro grid scenario. The fault detection and isolation during the islanded operation mode of a micro grid is very critical, since bidirectional power flow is present. The fault detection mechanism we developed can detect and isolate the fault within a few milliseconds and localize the fault within a two second delay for both in single and bi-directional power flow scenarios. The proposed system is capable of locating the exact faulted segment with the aid of the communication network integrated into the power grid. The implemented system was tested with different ranges of fault current and the analysis showed that the proposed system could localize the fault with less than a two second delay.

More »»
PDF iconMicro-Grid-Architecture-for-Line-Fault-Detection-and-Isolation.pdf

Publication Type: Journal Article

Year of Publication Title

2020

Dr. Neethu Mohan and Dr. Soman K. P., “A Data-driven Technique for Harmonics Monitoring in Emerging Power Grids using Noise-aware Dynamic Mode Decomposition”, Measurement Science and Technology, vol. 31, p. 015016, 2020.[Abstract]


A future power grid should be more robust, efficient, renewable, stable, reconfigurable, resilient, and distributed with more advanced control, protection and security schemes. It will combine a myriad of technologies such as information, communication, and power system engineering with computational intelligence. Because of the high proliferation of renewable energy sources, distributed generation systems and non-linear loads, grids are affected by several distortions and issues related to quality, stability, and control. Harmonics monitoring is a primary task in power grids for their safe and stable operation. It is essential for the protection and control of microgrid systems. Detection of harmonics, inter-harmonics and sub-harmonics improves the quality supply of power and protects the consumer equipments from failures. This paper investigates the effectiveness of a noise-aware dynamic mode decomposition algorithm, namely total-dynamic mode decomposition (TDMD), for harmonics monitoring in power grids. The ability of the TDMD algorithm to extract the hidden dynamic characteristics of time-series data is exploited for harmonics identification and its analysis. In the proposed method, multiple time-shifted copies of measured power signals are appended to create the initial data matrices. A singular value decomposition-based hard-thresholding is performed to avoid the ambiguities in the measured signal. Further, the eigendecomposition is performed using the TDMD algorithm and the corresponding frequencies and amplitudes are estimated. The performance advantage of the proposed method is verified by conducting several experiments using simulated and field measurements. The satisfactory performance certifies the practical applications of the proposed method for harmonics monitoring in emerging power grids

More »»

2019

R. - V. K, Dr. Neethu Mohan, and Dr. Soman K. P., “Data-driven Computing in Elasticity via Chebyshev Approximation”, arXiv preprint arXiv:1904.10434, 2019.[Abstract]


This paper proposes a data-driven approach for computing elasticity by means of a non-parametric regression approach rather than an optimization approach. The Chebyshev approximation is utilized for tackling the material data-sets non-linearity of the elasticity. Also, additional efforts have been taken to compare the results with several other state-of-the-art methodologies. More »»

2019

V. G. Sujadevi, Dr. Neethu Mohan, S. Kumar, S., Akshay, S., and Dr. Soman K. P., “A hybrid method for fundamental heart sound segmentation using group-sparsity denoising and variational mode decomposition”, vol. 9, no. 4, pp. 413 - 424, 2019.[Abstract]


Segmentation of fundamental heart sounds–S1 and S2 is important for automated monitoring of cardiac activity including diagnosis of the heart diseases. This pa-per proposes a novel hybrid method for S1 and S2 heart sound segmentation using group sparsity denoising and variation mode decomposition (VMD) technique. In the proposed method, the measured phonocardiogram (PCG) signals are denoised using group sparsity algorithm by exploiting the group sparse (GS) property of PCG signals. The denoised GS-PCG signals are then decomposed into subsequent modes with specific spectral characteristics using VMD algorithm. The appropriate mode for further processing is selected based on mode central frequencies and mode energy. It is then followed by the extraction of Hilbert envelope (HEnv) and a thresholding on the selected mode to segment S1 and S2 heart sounds. The performance advantage of the proposed method is verified using PCG signals from benchmark databases namely eGeneralMedical, Littmann, Washington, and Michigan. The proposed hybrid algorithm has achieved a sensitivity of 100%, positive predictivity of 98%, accuracy of 98% and detection error rate of 1.5%. The promising results obtained suggest that proposed approach can be considered for automated heart sound segmentation.

More »»

2018

Dr. Neethu Mohan, Dr. Soman K. P., and S. Sachin Kumar, “A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model”, Applied Energy, vol. 232, pp. 229-244, 2018.[Abstract]


The electric load forecasting is extremely important for energy demand management, stability and security of power systems. A sufficiently accurate, robust and fast short-term load forecasting (STLF) model is necessary for the day-to-day reliable operation of the grid. The characteristics of load series such as non-stationarity, non-linearity, and multiple-seasonality make such prediction a troublesome task. This difficulty is conventionally tackled with model-driven methodologies that demand domain-specific knowledge. However, the ideal choice is a data-driven methodology that extracts relevant and meaningful information from available data even when the physical model of the system is unknown. The present work is focused on developing a data-driven strategy for short-term load forecasting (STLF) that employs dynamic mode decomposition (DMD). The dynamic mode decomposition is a matrix decomposition methodology that captures the spatio-temporal dynamics of the underlying system. The proposed data-driven model efficiently identifies the characteristics of load data that are affected by multiple exogenous factors including time, day, weather, seasons, social activities, and economic aspects. The effectiveness of the proposed DMD based strategy is confirmed by conducting experiments on energy market data from different smart grid regions. The performance advantage is verified using output quality measures such as RMSE, MAPE, MAE, and running time. The forecasting results are observed to be competing with the benchmark methods. The satisfactory performance suggests that the proposed data-driven model can be used as an effective tool for the real-time STLF task.

More »»

2016

A. Chandran, Dr. Neethu Mohan, and Dr. Soman K. P., “Non-convex group sparsity denoising for bearing fault diagnosis using SVM”, International Journal of Control Theory and Applications, vol. 9, pp. 4433-4443, 2016.[Abstract]


Bearings are the pivotal components in rotating machines whose failure can result in unpredicted loss in productivity. Hence the faults on bearing need to be rectified as early as possible. In this paper four conditions of a DC motor namely good condition, defect on inner of race, defect on outer of race and defect on both inner and outer of race are obtained and subjected to classification using statistical features after a preprocessing operation for denoising. The denoising algorithm employed for preprocessing is Overlapping Group Shrinkage (OGS) and SVM is the classifier used. The accuracy in classification is found to be more when statistical features of denoised signal are fed as inputs to the classifier. Later, a vibration signal modeling system and its denoising is studied. © International Science Press.

More »»

2016

K. R. Rithu Vadhana, Dr. Neethu Mohan, and Dr. Soman K. P., “Convex denoising of hyperspectral images using non-convex tight frame regularization for improved sparsity based classification”, International Journal of Control Theory and Applications, vol. 9, pp. 4445-4451, 2016.[Abstract]


Hyperspectral images contain large spectral and spatial information's and hence it is widely used in the field of remote sensing for various application such as urban planning, disaster management and land use land cover classification. However, these images are usually corrupted by various kind of noises and which adversely affect the quality of images. In order to resolve thisissue, various preprocessing technique are exploited while dealing with hyperspectral images. convexdenoising using non-convex tight frame regularization technique is proposed as a preprocessing technique. After preprocessing, the images are classified using Orthogonal Matching Pursuit (OMP) algorithm. The classification results are evaluated interms of accuracy assessment measures. Also, the impact of the proposed preprocessing stageis compared with classification results of existing denoising techniques such as Total Variation(TV)denoising and wavelet based denoising. © International Science Press.

More »»

2016

L. Prakash, Dr. Neethu Mohan, S. Kumar, S., and Dr. Soman K. P., “Accurate frequency estimation method based on basis approach and empirical wavelet transform”, Advances in Intelligent Systems and Computing, vol. 380, pp. 801-809, 2016.[Abstract]


Due to proliferating harmonic pollution in the power system, analysis and monitoring of harmonic variation in real-time have become important. In this paper, a novel approach for estimation of fundamental frequency in power system is discussed. In this method, the fundamental frequency component of the signal is extracted using Empirical Wavelet Transform. The extracted component is then projected onto fourier basis, where the frequency is estimated to a resolution of 0.001 Hz. The proposed approach gives an accurate frequency estimate compared with some existing methods. © Springer India 2016. More »»

2016

Dr. Neethu Mohan, S. Kumar, S., Poornachandran, P., and Dr. Soman K. P., “Modified variational mode decomposition for power line interference removal in ECG signals”, International Journal of Electrical and Computer Engineering, vol. 6, pp. 151-159, 2016.[Abstract]


Power line interferences (PLI) occurring at 50/60 Hz can corrupt the biomedical recordings like ECG signals and which leads to an improper diagnosis of disease conditions. Proper interference cancellation techniques are therefore required for the removal of these power line disturbances from biomedical recordings. The non-linear time varying characteristics of biomedical signals make the interference removal a difficult task without compromising the actual signal characteristics. In this paper, a modified variational mode decomposition based approach is proposed for PLI removal from the ECG signals. In this approach, the central frequency of an intrinsic mode function is fixed corresponding to the normalized power line disturbance frequency. The experimental results show that the PLI interference is exactly captured both in magnitude and phase and are removed. The proposed approach is experimented with ECG signal records from MIT-BIH Arrhythmia database and compared with traditional notch filtering. Copyright © 2016 Institute of Advanced Engineering and Science. All rights reserved.

More »»

2015

B. Premjith, Dr. Neethu Mohan, Prabaharan Poornachandran, and Dr. Soman K. P., “Audio Data Authentication with PMU Data and EWT”, Procedia Technology, vol. 21, pp. 596 - 603, 2015.[Abstract]


Digital forensics has become a flourishing research area. Electrical Network Frequency (ENF) plays an important role in assessing the authenticity of a digital recording such as audio. ENF criterion is a tool for extracting the embedded power line frequency from the recording. A cross correlation between a reference PMU data and extracted ENF signal can be done in order to determine the authenticity of an audio signal. In this paper, Empirical Wavelet Transform (EWT) is used for extracting the ENF from an audio signal. EWT decomposes signal into N modes. Hilbert Transform is used to compute the instantaneous frequency and amplitude of the extracted mode corresponding to ENF. EWT method is not able to capture the weak harmonics in a signal. This problem is resolved by fixing the frequency domain boundaries of each mode.

More »»

2015

S. Vishvanathan, Dr. Neethu Mohan, and Dr. Soman K. P., “Sparse banded matrix filter for image denoising”, vol. 8, 2015.[Abstract]


Noise is one of the prime factors which degrade the quality of an image. Hence, image denoising is an essential image enhancement technique in the image processing domain. In this paper, we use low-pass sparse banded filter matrices for image denoising. Sparsity is the key concept in this filter design. We applied the designed low-pass filter both row-wise and column-wise to denoise the image. The proposed method is experimented on standard test images corrupted with different types of noises namely Gaussian, White Gaussian, Salt & Pepper and Speckle with noise level equals to 0.01, 0.05 and 0.1. The effectiveness of the proposed method of denoising is evaluated by the computation of standard quality metric known as Peak Signal-to-Noise Ratio (PSNR). The experimental result analysis shows that the proposed image denoising technique based on sparse banded filter matrices results in significant improvement in PSNR around 2dB to 8dB for different type of noises with noise level equal to 0.1 and is also aided by the visual analysis.

More »»

2015

Dr. Neethu Mohan, Ambika, P. S., S. Kumar, S., Dr. Saimurugan M., and Soman, K. P., “Multicomponent fault diagnosis using statistical features and regularized least squares”, International Journal of Applied Engineering Research, vol. 10, no. 20, pp. 19074-19080, 2015.[Abstract]


The efficiency and performance of rotating machinery is of major concern in any industrial system. Proper machine condition monitoring is really crucial for identifying the health of machines. The detection and diagnosis of faults in the machinery is important in proper machine condition monitoring. In this paper the multicomponent fault diagnosis in mechanical systems is formulated as machine learning based pattern classification problem. A machine fault simulator setup with different fault conditions induced in its shaft-bearing assembly is utilised for the purpose. The machine is made to run in various good and faulty environments and the vibration signals are extracted from them using an accelerometer. The statistical features extracted from the vibration signals were used for representing the signal in the feature space. The decision tree algorithm is used for selecting the major features that contribute towards classification. Later those features are classified using regularized least squares algorithm for identifying the good and faulty shaft-bearing conditions of the machine. The results were obtained with different kernel functions and accuracies are compared. © Research India Publications. More »»

2012

G. Abraham, Dr. Soman K. P., Prasannan, N., S, S., and Dr. Neethu Mohan, “Two Stage Wavelet based Image Denoising”, International Journal of Computer Applications, vol. 56, no. 14, 2012.

Publication Type: Conference Proceedings

Year of Publication Title

2017

Sowmya, Ashwini B, Dr. Neethu Mohan, Shriya se, and Dr. Soman K. P., “Performance Evaluation of Edge Feature Extracted using Sparse Banded Matrix Filter Applied for Face Recognition”, IEEE International Conference on Circuit, Power and Computing, ICCPCT-2017. Baselious Mathews II College of Engineering, Kerala, pp. 19-20, 2017.[Abstract]


This paper deals with the performance evaluation of sparse banded matrix filter applied for Face recognition. Edges extracted using the sparse banded matrix filter (ABFilter) is used as a feature descriptor for face recognition. The classification is done using Random Kitchen Sink which is accessed through GURLS library and also classified using Support Vector Machines (SVM). The experimental evaluation of sparse banded matrix filter is done on a standard face database (Yale). Edge detection is the process of locating the sharp discontinuity in an image. It is a basic tool which is used in many image processing applications such as face recognition. In this paper, we have compared the performance of sparse banded matrix filter with existing edge detecting filters such as Sobel, Prewitt, Canny and Robert. Though many filters exist for edge detection, sparse banded matrix filter is known for the edge detection with minimal discontinuity. The experimental evaluation shows that the edge feature descriptors of Yale face database obtained using sparse banded matrix filter provides 88 % accuracy using GURLS and 81% using SVM.

More »»

2015

Sowmya, Dr. Neethu Mohan, and Dr. Soman K. P., “Edge Detection Using Sparse Banded Filter Matrices”, Second International Symposium on Computer Vision and the Internet (VisionNet’15). Elsevier Procedia Computer Science Journal, SCMS School of Engineering, Aluva, Kochi , pp. 10–17, 2015.[Abstract]


Edges are intensity change, which occur on the boundary between two regions in an image. Edges can be used as feature descriptors of an object. Hence, edge detection plays an important role in computer vision applications. This paper presents the application of sparse banded filter matrices in edge detection. The filter design is formulated in terms of banded matrices. The sparsity property of the designed filter leads to efficient computation. In our proposed method, we applied sparse banded high-pass filter row-wise and column-wise to extract the vertical and the horizontal edges of the image respectively. The proposed technique is experimented on standard images and the results are compared with the state-of-the-art methods. The visual comparison of the experimental results shows that the proposed approach for edge extraction based on sparse banded filter matrices produces result comparable to the existing methods. The advantage of the proposed approach is that the continuous edges are attained without any parameter tuning.

More »»