Search

Your search keyword '"Shankar, M."' showing total 249 results
Start Over Author "Shankar, M." Publisher ieee
249 results on '"Shankar, M."'

28. Integrated Trajectory Optimization and Cubature Kalman Filter for UAV-Based Target Tracking with Unknown Initial Position

Author

Sheng Xu, Linlong Wu, Bhavani Shankar M. R., and Prabhu Babu

Subjects
Electrical & electronics engineering [C06] [Engineering, computing & technology], Ingénierie électrique & électronique [C06] [Ingénierie, informatique & technologie]
Abstract

This paper investigates the target localization/tracking by angle-of-arrival (AOA) sensors carried on an unmanned aerial vehicle (UAV). In many practical applications, the UAV's own position is not available, since the global position system (GPS) can hardly work in the indoor environment or interference region. Therefore, considering the unknown initial position of the UAV, a modified cubature Kalman filter (CKF) is developed to estimate both the target states and UAV's initial position jointly by leveraging a benchmark anchor. To further improve the estimation efficiency, we propose an algorithm to optimize the UAV flying trajectory by minimizing the the trace of the estimation covariance matrix in the CKF. According to the simulation results, an observation is found that the UAV will keeping flying alternatively between the anchor and target to guarantee the estimation performance.

Published
2022
Full Text
View/download PDF

48. Analysis and Classification of ECG Signal based on Whale Optimization with Compact Multiclass Support Vector Machine

Author

Dharun D, Bhavani K, Priyanka G S, Gowri Shankar M, and Ganesh Babu C

Subjects
Support vector machine, business.industry, Computer science, Dimensionality reduction, Waveform, General pattern, Pattern recognition, Artificial intelligence, Sensitivity (control systems), Ecg signal, business, Isomap, Signal
Abstract

A Non-stationary signal called an electrocardiogram (ECG) is utilized to evaluate the rate of cardiac beats. Doctors can identify potential illnesses by comparing the general pattern and shape of the ECG waveform. Electrocardiogram (ECG) signals are the most often utilized technology in the diagnosis and analysis of arrhythmias. Dimensionality reduction technique like Isomap has been used to minimize the dimensions of the ECG data in this study. Whale Optimization Algorithm (WOA) and Compact Multiclass Support Vector Machine (CMSVM) were being used to classify the dimensionally reduced data. Isomap are classified using WOA+CMSVM, the analysis reveals that a specificity of 96.64%, sensitivity of 92.51% and overall accuracy of 97.69 % are achieved.

Published
2021
Full Text
View/download PDF

49. Coordinated Factor Analysis and Water Wave Optimization (WWO) Classifier for Classification of Arrhythmias from ECG Signal

Author

Gowri Shankar M, Priyanka G S, Madhumitha S, Rakshaa Shree M, and Ganesh Babu C

Subjects
Computer science, business.industry, Multifunction cardiogram, Low-pass filter, Pattern recognition, Classifier (linguistics), Preprocessor, cardiovascular diseases, Artificial intelligence, Sensitivity (control systems), High-pass filter, business, Linear filter, Active noise control
Abstract

The Electrocardiogram (ECG) is a bioelectric record of heart activity. ECG signal classification is crucial for heart disease diagnosis. It is difficult to make an appropriate ECG classification. In this study, MIT-BIH Arrhythmia ECG data base from physionet has been used to classify Cardiogram Signals. The very first, raw ECG signal is preprocessed by using noise cancellation (filtering) methods are Adaptive noise cancellation techniques, low pass linear noise cancellation techniques and high pass linear filter. After preprocessing reduces the dimensionality of data by using Coordinated Factor Analysis (CFA) and finally, dimensionally reduced signals are classified by using Water Wave Optimization (WWO) classifier. The Performance metrics like Performance Index, Accuracy, Sensitivity, and Specificity are evaluated using WWO to analyze the classification of arrhythmias from ECG signals.

Published
2021
Full Text
View/download PDF

50. Performance Analysis for Arrhythmia Classification using PSO, GWO and SVM

Author

Haris Mita J, Gowri Shankar M, and Ganesh Babu C

Subjects
0303 health sciences, Heartbeat, Computer science, business.industry, Wavelet transform, Particle swarm optimization, Cardiac arrhythmia, Pattern recognition, 02 engineering and technology, Reduction (complexity), Support vector machine, 03 medical and health sciences, ComputingMethodologies_PATTERNRECOGNITION, 0202 electrical engineering, electronic engineering, information engineering, Feature (machine learning), 020201 artificial intelligence & image processing, Sensitivity (control systems), Artificial intelligence, business, 030304 developmental biology
Abstract

Proper heart rate or heart rhythm leads to healthy lifestyle. Improper heart rhythm means heartbeat will be sometimes too fast or too slow. Such preternatural condition of heart is named as Cardiac arrhythmia. Arrhythmia occurs when there is no proper working of electrical impulses present in the heart. An earlier detection of irregular heart rhythm is necessary in order to rescue ones survival. Classification of arrhythmia is needed for diagnosis. This paper confers the Principle component analysis as feature reduction process to reduce high dimensional input without influencing classification methods and two classification techniques such as Particle swarm optimization (PSO), Grey wolf optimizer (GWO) and Support Vector Machine (SVM). Performance Analysis for these three techniques is compared where it is used to classify various arrhythmias. The result explores the performance metrics for PSO, GWO, SVM and also integration of two methods such as PSO with SVM, GWO with SVO and shows that GWO integrated with SVM has 99.89% accuracy and performance better than other algorithms.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results