S
Sudha Radhika
Researcher at Birla Institute of Technology and Science
Publications - 29
Citations - 289
Sudha Radhika is an academic researcher from Birla Institute of Technology and Science. The author has contributed to research in topics: Fault (power engineering) & Fault detection and isolation. The author has an hindex of 7, co-authored 25 publications receiving 130 citations. Previous affiliations of Sudha Radhika include Geethanjali College of Engineering and Technology & Tokyo Polytechnic University.
Papers
More filters
Proceedings ArticleDOI
K-Nearest Neighbors and Grid Search CV Based Real Time Fault Monitoring System for Industries
TL;DR: K-Nearest Neighbors (KNN) and grid search cross validation (CV) have been used to train and optimize the model to give the best results and the accuracy in prediction has been seen to be 80%.
Journal ArticleDOI
Cyclone damage detection on building structures from pre- and post-satellite images using wavelet based pattern recognition
TL;DR: In this article, the authors used wavelet-extracted statistical features and by edge detection, and classification using Artificial Neural Network (ANN) and Support Vector Machine (SVM) to identify cyclone-prone building roof structures.
Journal ArticleDOI
Evaluation of surface roughness in incremental forming using image processing based methods
TL;DR: In this paper, the authors focused on evaluation of surface roughness (Ra) in incrementally formed parts by different image processing based methods, twenty-seven parts are formed as per full factorial design in incremental forming by varying three important process parameters over three levels each.
Journal ArticleDOI
Use of post-storm images for automated tornado-borne debris path identification using texture-wavelet analysis
TL;DR: In this paper, an efficient automatic tracking method, texture wavelet analysis, from wind-borne debris deposits distributed around damaged building structures is introduced. But the method is limited to post-storm aerial imagery only, rather than the conventional pre-storm and poststorm images together.
Journal ArticleDOI
Automatic Detection of Buildings from Aerial Images Using Color Invariant Features and Canny Edge Detection
Shraddha Singhal,Sudha Radhika +1 more
TL;DR: The aim is to extract the buildings from high resolution color aerial images using color invariance property and canny edge detection technique, which is able to detect 85-90% buildings from color aerial image.