Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal International Journal of Reconfigurable and Embedded Systems (IJRES) Bulletin of Electrical Engineering and Informatics Indonesian Journal of Electrical Engineering and Computer Science
Mehta, Shilpa
Unknown Affiliation
Economics, Econometrics & Finance Electrical & Electronics Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
A novel ensemble deep network framework for scene text recognition Dasari, Sunil Kumar; Mehta, Shilpa; Steffi, Diana
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 13, No 2: July 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v13.i2.pp403-413

Abstract

In recent years, scene text recognition (STR) has always been considered a sequence-to-sequence problem. Attention-based techniques have a greater potential for context-semantic modelling, but they tend to overfit inadequate training data. STR is one of the most important and difficult challenges in image-based sequence recognition. A novel framework ensemble deep network (EDN) is proposed, EDN comprises customized convolutional neural network (CNN), and deep autoencoder. Customized CNN is designed by introducing the optimal spatial transformation module for optimizing the input of irregular text to read for same size. Further, deep autoencoder is introduced with effective attention mechanism utilizing the inherent features. The proposed ensemble deep network-proposed system (EDN-PS) approach outperforms the existing state-of-art techniques for both irregular and regular scene-texts and upon further simulations, the proposed model generates better results for IIIT5K, ICDAR-13, ICDAR-15, and CUTE dataset in comparison with the existing system hence our proposed EDN-PS model outperforms the existing state-of-art methods.
Bayesian probabilistic modeling in robosoccer environment for robot path planning Steffi, Diana; Mehta, Shilpa; Venkatesh, Kanyakumari Ayyadurai
Bulletin of Electrical Engineering and Informatics Vol 13, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i1.6080

Abstract

The main goal of a route planning approach is to find a trajectory that safely transports the robot from one site to the next. Furthermore, it should provide an energy-efficient path so the computer can calculate it rapidly. This study develops a path-planning system for robots to approach the ball without collision. The Bayesian optimization algorithm (BOA) is used to identify the shortest path between the robot and the ball. BOA employs a probabilistic model to seek the optimum of an uncertain objective function efficiently. The performance of the BOA-based path planning system is compared to other optimization algorithms such as genetic algorithm, ant colony optimization, and firefly algorithm. BOA’s acquisition functions such as expected improvement, probability of improvement (PI), and upper confidence bound, are investigated. The exact locations of the robots and the ball are fed into optimization problems to discover the optimum path. The results reveal that the BOA system outperforms other systems in terms of computational time for planning the optimum path in dynamic situations and BOA-PI is the fastest algorithm.
Object detection on robosoccer environment using convolution neural network Steffi, Diana; Mehta, Shilpa; Venkatesh, Venkatesh
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 1: January 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v29.i1.pp286-294

Abstract

Robots with autonomous capabilities depend on vision capabilities to detect and interact with objects and their environment. In the field of robotic research, one of the focus areas is the robosoccer platform that is being used to implement and test new ideas and findings on computer vision and decision making. In this article, an efficient real-time object detection algorithm is employed in a robosoccer simulation environment by deploying a convolution neural network and Kalman filter based tracking algorithms. This study's objective is to classify nao, ball, and the goalpost as well as to validate nao and ball tracking without human intervention from initial frame to last frame. In comparison with the existing methods, the proposed method is robust and fast in identifying three classes namely nao, ball, and goalpost with a speed of 1.67 FPS and a mAP of 95.18%. By implementing this approach, soccer playing robots can make appropriate decisions during game play.
Co-Authors Dasari, Sunil Kumar Steffi, Diana Venkatesh, Kanyakumari Ayyadurai Venkatesh, Venkatesh