Institution
Maharaja Institute of Technology, Coimbatore
About: Maharaja Institute of Technology, Coimbatore is a based out in . It is known for research contribution in the topics: Deep learning & Support vector machine. The organization has 183 authors who have published 187 publications receiving 869 citations.
Topics: Deep learning, Support vector machine, Wireless sensor network, Computer science, Ferromagnetism
Papers
More filters
••
TL;DR: In this article, a planar flow of an electrically conducting incompressible viscous fluid on a vertical plate with variable wall temperature and concentration in a doubly stratified micropolar fluid in the presence of a transverse magnetic field was studied.
Abstract: An attempt has been made to study a steady planar flow of an electrically conducting incompressible viscous fluid on a vertical plate with variable wall temperature and concentration in a doubly stratified micropolar fluid in the presence of a transverse magnetic field. The novelty of the present study is to account for the effect of a spanwise variable volumetric heat source in a thermal and solutal stratified medium. The coupled non-linear governing equations are solved numerically by using Runge–Kutta fourth order with shooting technique. The flow characteristics in boundary layers along with bounding surface are presented and analyzed with the help of graphs.
84 citations
••
TL;DR: In this article, mass and heat transfer analysis over an electrically conducting viscoelastic (Walters B′) fluid over a stretching surface in presence of transverse magnetic field is addressed.
Abstract: This article addresses the mass and heat transfer analysis over an electrically conducting viscoelastic (Walters B′) fluid over a stretching surface in presence of transverse magnetic field. The impact of chemical reaction, as well as non-uniform heat source, are also taken into account. Similarity transformations are employed to model the equations. The governing equations comprises of momentum, energy, and concentration which are modified to a set of non-linear differential equations and then solved by applying confluent hypergeometric function known as “Kummer’s function”. The exact solution for heat equation is obtained for two cases i.e. (1) Prescribed surface temperature, (2) Prescribed wall heat flux. Physical behavior of all the sundry parameters are against concentration, temperature, and velocity profile are presented through graphs. The inclusion of magnetic field is counterproductive in diminishing the velocity distribution whereas reverse effect is encountered for concentration and temperature profiles.
63 citations
••
01 Nov 2021TL;DR: A comparative study was done using pre- trained models such as VGG-19 and ResNet-50 as against training from scratch, showing that the pre-trained models with proper finetuning was comparable with Iyke-Net, a CNN trained from scratch.
Abstract: In medical imaging, segmentation plays a vital role towards the interpretation of X-ray images where salient features are extracted with the help of image segmentation. Without undergoing surgery, clinicians employ various modalities ranging from X-rays and CT-Scans to ultrasonography, and other imaging techniques to visualise and examine interior human body organ and structures. To ensure appropriate convergence, training a deep convolutional neural network (CNN) from scratch is tough since it requires more computational time, a big amount of labelled training data and a considerable degree of experience. Fine-tuning a CNN that has been pre-trained using, for instance, a huge set of labelled medical datasets, is a viable alternative. In this paper, a comparative study was done using pre-trained models such as VGG-19 and ResNet-50 as against training from scratch. To reduce overfitting, data augmentation and dropout regularization was used. With a recall of 92.03%, our analysis showed that the pre-trained models with proper finetuning was comparable with Iyke-Net, a CNN trained from scratch.
45 citations
••
TL;DR: Two methods for identification and classification of healthy and unhealthy tomato leaves are proposed and it is revealed that the fusion approach with PNN classifier outperforms than other methods.
Abstract: Plant diseases are a major threat to the productivity of crops, which affects food security and reduces the profit of farmers. Identifying the diseases in plants is the key to avoiding losses by proper feeding measures to cure the diseases early and avoiding the reduction in productivity/profit. In this article, the authors proposed two methods for identification and classification of healthy and unhealthy tomato leaves. In the first stage, the tomato leaf is classified as healthy or unhealthy using the KNN approach. Later, in the second stage, they classify the unhealthy tomato leaf using PNN and the KNN approach. The features are like GLCM, Gabor, and color are used for classification purposes. Experimentation is conducted on the authors own dataset of 600 healthy and unhealthy leaves. The experimentation reveals that the fusion approach with PNN classifier outperforms than other methods.
43 citations
••
TL;DR: An improved PSO technique with a constraint treatment mechanism called dynamic search space squeezing strategy is devised to accelerate the optimization process in the PSO algorithm to improve the dynamics of power system.
Abstract: This paper presents the automatic generation control of two unequal areas with diverse power generation sources like thermal, hydro, wind and diesel power plants. Three evolutionary optimization te...
41 citations
Authors
Showing all 183 results
Name | H-index | Papers | Citations |
---|---|---|---|
Shanthi Murali | 23 | 49 | 20070 |
Prakash Periasamy | 13 | 50 | 665 |
Vijaylakshmi Dayal | 10 | 31 | 226 |
H.K. Chethan | 7 | 14 | 89 |
P. K. Pattnaik | 7 | 19 | 186 |
V. Kumar Chinnaiyan | 7 | 21 | 143 |
N. Shobha Rani | 6 | 25 | 91 |
Smitha Joyce Pinto | 5 | 12 | 147 |
S. Murali | 4 | 5 | 62 |
Y. H. Sharath Kumar | 4 | 14 | 63 |
V Punith Kumar | 4 | 5 | 53 |
V. Punith Kumar | 4 | 5 | 53 |
Y. H. Sharath Kumar | 4 | 8 | 85 |
Mahesh Rao | 3 | 9 | 44 |
Ajay Kumar Saw | 3 | 12 | 22 |