Dr.P.Venkatakrishnan Perumalsamy
@cmrtc.ac.in
Associate Professor ECE Department
CMR Technical Campus
Indian
EDUCATION
BE ME PhD
RESEARCH INTERESTS
Signal Processing and Wavelets
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
N. Nagarani, Sivasankari Jothiraj, P. Venkatakrishnan, and R. Senthil Kumar
IGI Global
The period of life during pregnancy for young parents is pleasant, especially for the mother. Many factors are taken into account during pregnancy, including the fetal heart, head position, cervical dilation, thickness, position, and length. The cervical length should be routinely assessed by ultrasound if it is less than 25 mm. The authors hope to use this participatory framework to generate new ideas for defining normal and abnormal cervical function during pregnancy. Recently, deep learning techniques have revolutionized artificial intelligence (AI) research in pregnancy. Cervical image data obtained by ultrasound are often compared using computer vision pattern analysis, which promises to be a major revolution. In further research and development in AI-based ultrasonography, the clinical application of AI in medical ultrasonography faces unique obstacles. This chapter focuses on the utilization of machine learning approaches in prenatal medicine, with a particular emphasis on interpretable ML applications that produce objective results and assist doctors in identifying key parameters
Krishnan Jeyakanth, Perumalsamy Venkatakrishnan, and Chinnasamy Chitra
Wiley
Jeyakanth Krishnan, Venkatakrishnan Perumalsamy, Chitra Chinnasamy, and Dhivya Udhayasuriyan
IEEE
In this research work, an evolutionary development approach is introduced for channel assignment in CRNs. These approaches are divine by some kind of adoptive development approach. In this proposed methodology, we utilized PSO with DE technique. It effectively maximize the throughput of CN while gratifying interference constraints of both primary and secondary users in network. It also solves the joint spectrum and power allocation problem in CRNs. In addition, a repair process is involved to ignore conflicts with secondary users to enhance spectrum in CRNs. The resulting algorithm is known as Hybridization of Differential Evolution based Particle Swarm optimization with repair process (HoDEPSO-RP). The performance analysis of this proposed HoDEPSO-RP is estimated by simulation techniques. This proposed work provides better performance result when compared with other existing algorithms.
Senthilkumar Ramachandraarjunan, Venkatakrishnan Perumalsamy, and Balaji Narayanan
IOS Press
Monitoring indoor air quality stays needed for human health because people use more than 95% of air in their indoor rooms. An Intelligent Internal Air Quality Monitoring (IIAQM) system built on the Internet of Things (IoT) devices has been developed and tested in Quantanics Techserv Private Limited, Tamilnadu, India. To monitor the levels of CO2, PM2.5 (Particle Matters 2.5), and moisture measurement, the IIAQM model has been used to monitor the present level of air quality. The gateway collects IIAQM sensor data in a few seconds and transfers data to cloud server. Approved users can incorporate the cloud systems through mobile applications or web servers. Installation of sensor networks, instrument transformers, and IoT-powered microcontrollers will provide air quality monitoring for buildings. The proposed window controller configuration is designed with the help of a Recurrent Neural Network (RNN) to predict the air quality level in advance. If the air quality level is above the normal level, the window controller automatically will open with the help of sensor activity control system. After the AQI (Air Quality Index) becomes normal, hence the window controller is closed automatically. The air quality index, CO2, and humidity data are visualized on the Grafana dashboard.
G. Dinesh, P. Venkatakrishnan, and K. Meena Alias Jeyanthi
Wiley
P. Arunachalam, P. Venkatakrishnan, and N. Janakiraman
IEEE
Clinical imaging techniques have been widely used in the classification of cancer biopsy specimen histopathology images of limb soft tissue sarcoma (STS). Here, by automatically differentiating cell patterns in malignant and non-malignant tumors, an efficient classifier based on both accuracy and time requirements is significantly improved, which further reduces intra-inter-observer variations. Color normalization is carried out using a linear transformation into a grayscale image and the region of interest (ROI) of the image is selected by the pathologist. The wavelet transform has been used to extract statistical texture features (SFT) from the grayscale image of this ROI, and neural correlates with extracted features networks were trained For the purpose test, the features of a new limb STS tissue sample image are extracted and these extracted values are presented to the already trained networks for classification. In this case, the proposed research uses an artificial neural network (ANN), which leads to prominence by improving the classification methods based on accuracy, sensitivity and specificity. Here, two different types of ANN classifiers are discussed with back propagation neural network (BPNN) and radial basis function network (RBFN) classifiers. Furthermore, here the most significant difference between BPNN and RBFN is analyzed using the receiver operating characteristics (ROC) area under the curve. The performance accuracy of these two classification methods reaches 96.36% and 90.91 % for RBFN and BPNN, respectively. Based on these accuracy values, RBFN is found to be more efficient than BPNN classifiers. Finally the cancer cell classification accuracy is increased, decision- making time is reduced, and the initial treatment plan for chronic disease of the limbs tumor has been achieved
P. Arunachalam, P. Venkatakrishnan, and N. Janakiraman
IEEE
Pathological examination is important for an accurate diagnosis of Synovial Sarcoma (SS). It is the most common cancer of the soft tissues of the limb in adolescents and adults. In this work, SS was used to determine the discriminant singularity characteristics using Wavelet Leaders (WL). The most popular technique for measuring the discriminant singularity characteristics of an image signal is the Lipschitz Exponent (LE). The singularity measurement was based on LE function by taking a slope of logarithmic scale versus logarithmic Wavelet Transform Modulus Maxima (WTMM). Here, the presence of the singularity was measured using WTMM and WL by summing each color component of an image signal. The performance characteristics of the statistical discrimination are evaluated and compared with the non-parametric hypothesis using the Wilcoxon rank-sum test. The most important difference between WTMM and WL was analyzed using the Receiver Operating Characteristics (ROC) curve. From the experimental analysis that the WL method provides excellent discriminant singularities or discontinuities performance characteristics such as area, standard error, z-statistics, and p-values. Finally, the results of experiments have proven that a WL can express practical, precise, robust, and satisfactory performance in practice.
G. Dinesh, P. Venkatakrishnan, and K. Meena Alias Jeyanthi
Wiley
R. Senthilkumar, P. Venkatakrishnan, and N. Balaji
Elsevier BV
Abstract The rapid growth of industry and transport within this contemporary progress, there was sufficient consideration given to air quality monitoring; but conventional air quality monitoring methods are inefficient to produce adequate spatial and temporal resolutions of the air quality information by cost-effective also the period time clarifications. During the paper, we propose a distinct methodology to achieve the air quality monitoring system, using this fog computing-based Internet of Things (IoT). In this paper proposed an embedded system, where sensors collect the air quality information within period time and send it over the fog nodes. Every fog node may be an extraordinarily virtualized program hosted at a committed computing node implemented with a connection interface. Data gathered by Microprocessor based IoT sensing things do not seem to be causing on into the cloud server to the process. Preferably, they do send through the adjacent fog node to get quick, including high-rise rate service. Though, fog node will refine non-actionable data (e.g., regular device measurement) also forward them to the Cloud for lengthy run storage and batch analytics. The Cloud may be a convenient location to run world analytics at information gathered from commonly shared devices over sustained periods (months, years). General purpose processor (microprocessor) and IoT cloud platforms were involved in developing this whole infrastructure and model for analysis. Empirical outcomes reveal that this advanced method is responsible for sensing air quality, which serves to expose the modification patterns regarding air quality through a certain level.
N. Nagarani, P. Venkatakrishnan, and N. Balaji
Elsevier BV
Abstract In the surveillance of military system Unmanned Ariel vehicles (UAV’s) offers a remarkable service. Software Defined Network (SDN) is one of approach for UAV for improving target localization with surveillance for many applications . One of the critical issues for an Unmanned Ariel vehicles (UAV’s) landing is the detection of runway in a low visibility conditions with computer vision. Also, the key problem is the accurate and robust detection of runway. A method of runway detection for fixed wing UAVs with a forward-looking camera is uses sensor based communication in network framework between source (UAV’S) and destination (runway sensor). Yet, this depends on the technical experience for landing an UAV’s safely. Nowadays, highly advanced equipments are being developed for improving safety and transportation system to handle the problem of landing under low visibility conditions. However, natural or habitual vision could be reduced during low visibility situations. This may be due to many meteorological factors like haze, darkness, fog etc. From the discussion made in this paper, the authors mainly concentrate on managing an aircraft system under low luminosity condition during the landing. In this research, effective Morphological fusion method is employed for the prediction of virtual runway imagery to avoid accident landing process. For this, fusion of sensor data for DEM (Digital Elevation Map) Data, infrared image (IR) and navigation parameter are used. The performance of this research using Morphological fusion method gives a fused image of the runway prediction for UAV’s under poor visibility condition. After obtaining the fused image, it is involved in ROI (Region of Interest) contour tracing process to get the clear location of landing of an UAV’s without harm. The virtual imaginary model can be produced through contour tracing to predict runway. By this method, a less prediction time or setting time is achieved and maximum accuracy is obtained through simulation using MATLAB tool. Finally, the proposed experimental outcomes are compared with the existing technology. The proposed approach will be use in aircraft sensor based communication between the network (source to destination) to detect the target and to provide a better surveillance for military applications.
Harmonic analysis of the power system signal is a proliferating research in the field of electronics technology. Whenever, we analyze odd and ever harmonics are present in the signal, imperative operation is needed to transform from the time domain to the frequency domain. Hence, all the researchers are utilizing the Fourier Transform technique is very effective for the analysis of odd and even harmonics in the frequency domain. In the past two decades, Wavelet Transform is a wonderful technique to analyze the harmonics both frequency and time domain as well. The analysis of harmonic and its probability distribution are most important for the purpose to predict the harmonic effects in the present situation. We treated all the harmonics and its corresponding frequency distribution are considered as a zero mean unit variance. The overlapping these distributions (small, medium, large) are analyzed with help of statistical data processing technique. It is one of the most important basic plots in the decision theory and it provides the constructive decision about the overlapping of a frequency distribution in power system signal. The curvature as a plot of sensitivity and specificity underlying the harmonics are present and not present distributive (Gaussian). The above determined values are lying in the interval probability [0, 1] and it is depends only the nature of the dataset. In this paper, we explained with help of MATLAB and level of understand the basic concept of ROC is demonstrated. The dataset is drawn from the example of odd and even harmonics are generated and the probability distribution as input to our MATLAB program.
V. Prithivirajan, P. Venkatakrishnan, and A. Punitha
Indian Society for Education and Environment
Objectives: The objective of this paper is to design a 2-bit DMTL phase shifter with low insertion loss, improved phase shift per dB loss with minimum number of switches. Methods/Analysis: In order to reduce the insertion loss tapered impedance section proposed previous researchers introduces impedance discontinuity at the end of the taper that introduces a fringing capacitance at the transition region which cannot be neglected while calculating the loaded line capacitance. The proposed chamfered transmission line design for phase shifter overcomes this shortcoming with a uniform high impedance line that does not have any discontinuities and causes variations of propagation constant along the length of the transmission line. The proposed design also reduces the discontinuity effects associated with step width junction and reflection is much reduced. Findings: Chamfering the corners at the contact area of switch with the transmission line reduces the discontinuity effects associated with step width junction. The achieved phase shift is 178.87o at 17GHz with an insertion loss of -0.87dB and return loss in both up, down states less than -15dB. Design and simulation results of the phase shifter with respect to pull-in voltage of the switch, RF characterization is done using Coventorware and HFSS.
P. Venkatakrishnan and S. Sangeetha
Elsevier BV
Abstract A proliferation of signal processing community, the dynamic behavior and the singularity detection are key steps, because dynamics and singularities carry most of signal information. Wavelet zoom is very good at localization of singularities. The Lipschitz Exponent (LE) is the most popular measure of the singularity characteristics of a signal. The singularity, by mean of an LE of a function, is measured by taking a slope of a log-log plot of scale s versus wavelet transform modulus maxima (WTMM). In this paper, we measured the singularity using WTMM, Inter Scale Wavelet Maximum (ISWM) and Wavelet Leaders (WL) by adding white Gaussian noises to the human EEG signal. The statistical performances are assessed (Mean, Standard Deviation (SD), Skewness, SD/Mean, Number of singular points (NSP)) and compared by means of non-parametric hypothesis test (Mann–Whitney U -test). Highly significant differences have been found between WTMM, ISWM and WL using Receiver Operating Characteristics (ROC) curve. WL method provides good performance of singularity measure when the more prominent noise influenced the EEG signal. The result of experiments demonstrated that a Wavelet leader is more precise and robust.
P. Venkatakrishnan, S. Sangeetha, J.S. Gnanasekaran, M.G. Vishnukumar, and A.S. Padmanaban
Elsevier BV
Abstract Machinery health monitoring is a key step in the implementation of maintenance in industry. A remarkable property of the wavelet transform is its ability to characterize the local regularity of machines. The Lipschitz exponent (LE) is the most popular measure of the regularity behavior of a signal. In this paper we adopt a new area-based objective function used to determine the Lipschitz exponent value. We analyzed four different set of gear box data such as normal, slight ward, medium warm and one tooth broken condition. We applied statistical features are commonly used to provide a measure of the vibration level that can be compared to a threshold value indicative of a failed condition. Through the analysis and diagnosis of measuring vibration signal using LE based objective function, the algorithm is verified to be reliable and effective.
P. Venkatakrishnan, R. Sukanesh, and S. Sangeetha
Springer Science and Business Media LLC
Interactions among neural signals in different frequency components have become a focus of strong interest in biomedical signal processing. The bispectrum is a method to detect the presence of quadratic phase coupling (QPC) between different frequency bands in a signal. The traditional way to quantify phase coupling is by means of the bicoherence index (BCI), which is essentially a normalized bispectrum. The main disadvantage of the BCI is that the determination of significant QPC becomes compromised with noise. To mitigate this problem, a statistical approach that combines the bispectrum with an improved surrogate data method to determine the statistical significance of the phase coupling is introduced. The method was first tested on two simulation examples. It was then applied to the human EEG signal that has been recorded from the scalp using international 10–20 electrodes system. The frequency domain method, based on normalized spectrum and bispectrum, describes frequency interactions associated with nonlinearities occurring in the observed EEG.
P. Venkatakrishnan, S. Sangeetha, and R. Sukanesh
IEEE
Detection of sleep spindles in EEG was commonly performed inefficiently by doctorpsilas eye inspection. In this paper, a new approach is presented for analysis of EEG signals and detection and localization of sleep spindles. By estimating auto recursive (AR) models on short segments the EEG is described as a superposition of harmonic oscillators with damping and frequencies varying in time. Most of the oscillatory events are detected, whenever the damping coefficients of one or more frequencies fall below a predefined threshold. The algorithm works well for the detection of sleep spindles and in addition identifies delta and alpha waves.