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 Informatics and Communication Technology (IJ-ICT) Vokasi UNESA Bulletin of Engineering, Technology and Applied Science
Suddul, Geerish
Unknown Affiliation
Computer Science & IT Engineering Mechanical Engineering Transportation

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

Found 3 Documents
Search

 1 
A custom-built deep learning approach for text extraction from identity card images Suddul, Geerish; Seguin, Jean Fabrice Laurent
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 13, No 1: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v13i1.pp34-41

Abstract

Information found on an identity card is needed for different essential tasks and manually extracting this information is time consuming, resource exhaustive and may be prone to human error. In this study, an optical character recognition (OCR) approach using deep learning techniques is proposed to automatically extract text related information from the image of an identity card in view of developing an automated client onboarding system. The OCR problem is divided into two main parts. Firstly, a custom-built image segmentation model, based on the U-net architecture, is used to detect the location of the text to be extracted. Secondly, using the location of the identified text fields, a (CRNN) based on long short-term memory (LSTM) cells is trained to recognise the characters and build words. Experimental results, based on the national identity card of the Republic of Mauritius, demonstrate that our approach achieves higher accuracy compared to other studies. Our text detection module has an intersection over union (IOU) measure of 0.70 with a pixel accuracy of 98% for text detection and the text recognition module achieved a mean word recognition accuracy of around 97% on main fields of the identity card.
Enhancing biodegradable waste management in Mauritius through real-time computer vision-based sorting Suddul, Geerish; Babajee, Avitah; Rambarun, Nundjeet; Armoogum, Sandhya
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 14, No 3: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v14i3.pp1119-1125

Abstract

Mauritius faces a significant waste management challenge due to the indiscriminate mixing of biodegradable and non-biodegradable waste. This practice hinders proper recycling and composting efforts, contributing to environmental pollution and resource depletion. This research proposes a computer vision-based system for real-time classification of waste into biodegradable and non-biodegradable categories. Transfer learning approach based on deep learning models, specifically DenseNet121, MobileNet, InceptionV3, VGG16 and VGG19 were evaluated with two different classifiers, the K-nearest neighbors (KNN) and support vector machine (SVM). Our experiments demonstrate that the MobileNet paired with SVM achieves a classification accuracy of 97% for detection in realtime. Compared to other studies, our results demonstrate better performance and realtime classification capabilities through the implementation of a prototype, facilitating automatic sorting of waste.
A Deep Learning Approach to Fake News Classification Using LSTM Andrianarisoa, Sitraka Herinambinina; Ravelonjara, Henri Michaël; Suddul, Geerish; Foogooa, Ravi; Armoogum, Sandhya; Sookarah, Doorgesh
Vokasi Unesa Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.39360

Abstract

The rapid spread of misinformation on digital platforms poses a major challenge today. The ability to detect false information is essential to mitigate the associated harmful consequences. This research presents a deep learning approach for detecting fake news using Long Short-Term Memory (LSTM) model, which captures linguistic patterns and long-term dependencies in text. Our approach consists of optimizing the model through different experiments based on hyperparameter tuning, on a pre-processed dataset. The evaluation is performed using different metrics such as accuracy, precision, recall, and F1-score. Experimental results show that the LSTM model achieves high accuracy of 0.9974, with embedding dimension of 128 using 100 LSTM units, batch size of 64 and drop-out rate of 0.48. It is a substantial improvement over previous studies. The application of cross-validation further confirms the model’s reliability. This research demonstrates that the application of a fine-tuned LSTM network with robust data preprocessing can provide a powerful tool to combat online misinformation.
Co-Authors Andrianarisoa, Sitraka Herinambinina Armoogum, Sandhya Babajee, Avitah Foogooa, Ravi Rambarun, Nundjeet Ravelonjara, Henri Michaël Seguin, Jean Fabrice Laurent Sookarah, Doorgesh