Guguloth Rajender Naik
@kitsw.ac.in
Associate Professor, Department of Electrical & Electronics Engineering
Kakatiya Institute of Technology & Science
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
G. Rajender Naik and K. Ashoka Reddy
IEEE
Classification of ECGs is an important task for proper identification of the signal which helps in suitable diagnosis of the patient. This paper proposes a new algorithm for ECG basic classification as normal or abnormal. As there are many existing methods for classification like support vector machine, neural networks, neuro-fuzzy algorithms and so on, the main objective of this work is to compare performance analysis of two selected methods, one with adaptive neuro-fuzzy algorithm as the existing method and the other with the proposed method i.e., multimodal decision learning algorithm. The comparative analysis deals with the parameters like true positive (TP), true negative (TN), False positive (FP), False negative (FN), False rejection ratio (FRR), false acceptance ratio (FAR), global acceptance ratio (GAR), confusion matrix (CM), Kappa coefficient (KC), Sensitivity, Specificity and Accuracy. Pre-recorded ECG signals of MIT-BIH database are used for processing, filtering, classification and performance evaluation. Simulation results indicate the ECG signal as normal or abnormal with respect to the above defined parameters.
G. Rajender Naik, P. Mahesh, B. Mohan, and V. Raghuram Mahathi
IEEE
Though the wireless sensor networks offer new possibilities and capabilities, there are a number of issues that hinder their development in practice. It can be argued that robotics can solve or greatly reduce the impact of many of these issues. This work reviews a new way of sensing the temperature of remote locations particularly where a human-being cannot reach by using the navigation system. The developed navigation system is a temperature sensing robot that can function autonomously or can be controlled by a human operator. It is equipped with on-board processor, Two RF communication channels and a best platform for mobility. It is preprogrammed using AT89S52 Microcontroller. The system is under the direct control of the user. In the autonomous mode, the robot will travel to some distance in the prescribed direction as per the predefined commands. The navigation system has a temperature sensor on its board which can be operated either using the base station or whenever the collision occurs. The system is embedded with a CCD Camera to capture the images of the locations traversed by the moving system. The images can be captured with the help of a TV Tuner dongle.
G. Rajender Naik and K. Ashoka Reddy
IEEE
This paper proposes a method of feature reduction process i.e., selection of the best features for accurately identifying an electrocardiogram (ECG) signal as basically normal or abnormal. This is done by Intensity Weighted Fire-Fly Optimization (IWFFO) Algorithm. After extracting the best features, a kernel model for machine learning is proposed to classify the category of the signal as normal or abnormal. This is done by Multimodal Decision Learning (MDL) classification method. The proposed work is compared with traditional ECG signal classification method i.e., support vector machine (SVM) by considering the parameters like true positive (TP), true negative (TN), False positive (FP), False negative (FN), False rejection ratio (FRR), false acceptance ratio (FAR), global acceptance ratio (GAR), confusion matrix (CM), Kappa coefficient (KC), Sensitivity, Specificity and Accuracy. Records for MIT-BIH database are used for performance evaluation. Simulation results indicate the ECG signal as normal or abnormal with respect to the above defined parameters.
G. Rajender Naik and K. Ashoka Reddy
IEEE
This work proposes a simplified approach for filtering electrocardiogram (ECG) signal by means of Gaussian Mean Variant Filtering technique and feature extraction procedure using Integrated Peak Analyzer method. The preprocessing stage is confined to signal filtering and smoothening the waveform with the conventional filters like low pass filter, Butterworth filter, Finite impulse (FIR) filter, least mean squares (LMS) filter and the proposed filter. The next stage includes feature extraction procedure using peak estimations of QRS complexes and their pulse transit time (PTT) estimations. For this purpose, a novel model, Integrated Peak Analyzer is used. Finally the obtained results from the proposed methods are compared with the adaptive filters.
Namani Rakesh, T. Venkata Madhavaram, K. Ajith, G. Rajendra Naik, and P. Nagarjun Reddy
IEEE
The performance of the Solar PV array is dependent on solar irradiation, temperature, power mismatch and shading. Solar PV arrays are losing its efficiency by the effect of shading. Solar PV array applications around the globe are reported with the problems of shading. Passing clouds, shade of a big tree, the neighbours building completely reduce the output power yield even though the size of Solar Power Plant is large. So, in order to solve this issue, a New Technique (Magic Square) is proposed in this paper to increase the generated power by configuring the modules of a shaded photovoltaic array. In this approach, the physical location of the modules in Total Cross Tied (TCT) connected in the solar PV array is arranged based on Magic Square arrangement pattern. The arrangement is done in such a way that, only the physical locations of the modules are changed and the electrical connections remained unaltered. In this work, the Global Peaks are achieved by plotting PV characteristics. For different types of shading patterns, the performance is calculated. The theoretical calculations are compared with MATLAB simulations to validate the results.
A. Vamshi Kumar, K. Ajith, P. Nagarjuna Reddy, G. Rajender Naik, and N. Rakesh
IEEE
Distribution Generation aims at integrating different power plants to increase the reliability and provide additional power quality benefits. Coming to the grid-connected mode, almost all the commercial single-phase inverters for DG systems inject only active power to the grid, i.e., the reference current is computed from the reference active power p* that must be generated. This paper deals with a single-phase inverter acquiring power quality features, i.e., active and reactive power generation along with current harmonics compensation. This is achieved by integrating the functions of shunt Active Power Filter (APF) to the control scheme. The control scheme employs a current reference generator with a dedicated repetitive current controller. Two phase conversion of single phase system is used in this paper for the extraction of harmonic components and also for supplying required reactive power by load. The simulation results are presented for the grid connected inverter that generates active power and compensates the reactive power and current harmonics of local loads, thus achieving complete power quality features.