Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Journal of Applied Data Sciences
Harprith Kaur R S
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

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

Found 3 Documents
Search

 1 
An Optimized U-Net and MobileNetV2 Framework for Accurate and Efficient Brain Tumour Classification from MRI Images R Elavarasi; S Murugesan; S Ramalingam; P Kanimozhi; Harprith Kaur R S
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1468

Abstract

Accurate brain tumour identification from magnetic resonance imaging (MRI) requires models that can effectively localize tumour regions while maintaining high classification performance and computational efficiency. This study presents an integrated U-Net–MobileNetV2 framework for automated brain tumour analysis using MRI images. The proposed pipeline incorporates image thresholding, morphological processing, contour-based cropping, bicubic resizing, normalization, and data augmentation prior to model training. U-Net is employed to segment tumour regions and preserve diagnostically relevant spatial information, while MobileNetV2 performs lightweight classification using segmentation-guided representations. The dataset consists of 512 × 512-pixel brain MRI images divided into 80% training, 10% validation, and 10% testing subsets. Model performance is evaluated using accuracy, precision, recall, and F1-score and compared with CNN, Random Forest, Naïve Bayes, and Support Vector Machine classifiers. The proposed framework achieves 99.52% accuracy, 97.57% precision, 98.05% recall, and 97.81% F1-score, outperforming all evaluated baseline models. Compared with the strongest baseline, SVM, the proposed method improves accuracy by 1.43 percentage points. These results demonstrate that combining segmentation-driven tumour localization with lightweight deep feature learning provides an effective framework for accurate and computationally efficient MRI-based brain tumour classification.
An Optimized U-Net and MobileNetV2 Framework for Accurate and Efficient Brain Tumour Classification from MRI Images R Elavarasi; S Murugesan; S Ramalingam; P Kanimozhi; Harprith Kaur R S
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1468

Abstract

Accurate brain tumour identification from magnetic resonance imaging (MRI) requires models that can effectively localize tumour regions while maintaining high classification performance and computational efficiency. This study presents an integrated U-Net–MobileNetV2 framework for automated brain tumour analysis using MRI images. The proposed pipeline incorporates image thresholding, morphological processing, contour-based cropping, bicubic resizing, normalization, and data augmentation prior to model training. U-Net is employed to segment tumour regions and preserve diagnostically relevant spatial information, while MobileNetV2 performs lightweight classification using segmentation-guided representations. The dataset consists of 512 × 512-pixel brain MRI images divided into 80% training, 10% validation, and 10% testing subsets. Model performance is evaluated using accuracy, precision, recall, and F1-score and compared with CNN, Random Forest, Naïve Bayes, and Support Vector Machine classifiers. The proposed framework achieves 99.52% accuracy, 97.57% precision, 98.05% recall, and 97.81% F1-score, outperforming all evaluated baseline models. Compared with the strongest baseline, SVM, the proposed method improves accuracy by 1.43 percentage points. These results demonstrate that combining segmentation-driven tumour localization with lightweight deep feature learning provides an effective framework for accurate and computationally efficient MRI-based brain tumour classification.
Enhancing Network Security and Content Control in Academic Environments Using Pi-hole R Elavarasi; P Gajalakshmi; D Kadhiravan; M Naresh; Harprith Kaur R S
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1472

Abstract

Academic institutions require reliable internet access to support teaching, research, communication, and digital learning activities. However, unrestricted connectivity may expose institutional networks to non-academic content, malicious domains, excessive bandwidth consumption, and unauthorized access attempts. This study develops and evaluates a lightweight DNS-based internet filtering architecture using Pi-hole for centralized content control in academic environments. The system was deployed on a Raspberry Pi 3B+ as the primary DNS resolver, enabling domain requests to be processed through configurable blocklists, whitelists, scheduled policies, and centralized query logging. Its performance was compared with firewall-based filtering, proxy-server filtering, and browser-extension filtering using five evaluation dimensions: blocking effectiveness, CPU efficiency, cost-effectiveness, scalability, and bypass resistance. The results show that Pi-hole achieved the highest overall score of 9.0, with scores of 9 for blocking effectiveness, CPU efficiency, and bypass resistance, 10 for cost-effectiveness, and 8 for scalability. The enterprise firewall provided greater client capacity but required substantially higher infrastructure and operational costs. Proxy servers offered application-level control but imposed higher computational overhead, while browser extensions were inexpensive but limited in scalability and resistance to circumvention. The findings demonstrate that Pi-hole provides a balanced, centralized, and resource-efficient filtering solution for small- and medium-sized academic networks. Its effectiveness can be further strengthened through forced DNS redirection, firewall integration, role-based policies, and automated domain classification.
Co-Authors D Kadhiravan M Naresh P Gajalakshmi P Kanimozhi R Elavarasi S Murugesan S Ramalingam