Sofia Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sofia Singh has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Garima Shukla
Amity University
6 shared publications - Dolly Sharma
Hill University Haldwani
4 shared publications - Vanshaj Awasthi
Amity University Mumbai
4 shared publications - Arju Malik
IIMT Engineering College
2 shared publications - Dipti Theng
Department of CSE, Symbiosis International University
2 shared publications - Sachin Kumar
Department of CSE‐College of Engineering Chandigarh Group of Colleges Landran, Sahibzada Ajit Singh Nagar Punjab India
2 shared publications
Latest Publications
- 8 August 2026
- Published by Springer Nature
- p. 263-274
Beyond the Lyrics: Comparative Analysis of Deep Learning Approaches for Sentiment Classification in Song Lyrics
- 8 August 2026
- Published by Springer Nature
- p. 263-274
Beyond the Lyrics: Comparative Analysis of Deep Learning Approaches for Sentiment Classification in Song Lyrics
- Open Access
- 8 December 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (6) , 30154-30160
CamoVision: A Dual-Mode Deep Learning Framework for Camouflaged Object Detection in Images and Videos
Camouflaged Object Detection (COD), is a technology with applications in military surveillance, protection of animals, and intelligent security systems. Traditional computer vision COD methods, such as edge detection and color-based segmentation, frequently fail to function well in real-world scenarios that undergo rapid transformations over time. CamoVision is a Deep Learning (DL)-based dual-mode framework that has the ability to locate camouflaged objects in photos (CamoVision 1.0) and video streams (CamoVision 2.0). To improve the design, which is based on the U-Net and a ResNet-50 encoder, a hybrid loss function that consisted of Dice and BCE was utilized. In addition, the model was trained using strategies that involved mixed precision to maximize its efficiency and speed up the convergence process. The acquired Intersection-over-Union (IoU) score of 0.82 and Dice coefficient of 0.85 showcase the robustness of the proposed system. In addition, the video pipeline operates in real time at a rate of 30 fps, which makes it versatile enough to be utilized in settings where time is of particular significance.
- 8 December 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (6) , 30154-30160
Open AccessCamoVision: A Dual-Mode Deep Learning Framework for Camouflaged Object Detection in Images and Videos
Camouflaged Object Detection (COD), is a technology with applications in military surveillance, protection of animals, and intelligent security systems. Traditional computer vision COD methods, such as edge detection and color-based segmentation, frequently fail to function well in real-world scenarios that undergo rapid transformations over time. CamoVision is a Deep Learning (DL)-based dual-mode framework that has the ability to locate camouflaged objects in photos (CamoVision 1.0) and video streams (CamoVision 2.0). To improve the design, which is based on the U-Net and a ResNet-50 encoder, a hybrid loss function that consisted of Dice and BCE was utilized. In addition, the model was trained using strategies that involved mixed precision to maximize its efficiency and speed up the convergence process. The acquired Intersection-over-Union (IoU) score of 0.82 and Dice coefficient of 0.85 showcase the robustness of the proposed system. In addition, the video pipeline operates in real time at a rate of 30 fps, which makes it versatile enough to be utilized in settings where time is of particular significance.
- 21 November 2025
- Published by Springer Nature
- p. 251-262
Analysing Lightweight Language Models for Real-Time Mental Health Counselling: A Data-Driven Approach
- 21 November 2025
- Published by Springer Nature
- p. 251-262
Analysing Lightweight Language Models for Real-Time Mental Health Counselling: A Data-Driven Approach
- 26 October 2025
- Published by Springer Nature
- p. 515-527
A Virtual Whiteboard with Hand Gesture Recognition Using OpenCV Module
- 26 October 2025
- Published by Springer Nature
- p. 515-527
A Virtual Whiteboard with Hand Gesture Recognition Using OpenCV Module
- 26 October 2025
- Published by Springer Nature
- p. 565-574
Priority-Driven MAC Protocol Design for IoT-Enabled Wireless Body Area Networks
- 26 October 2025
- Published by Springer Nature
- p. 565-574
Priority-Driven MAC Protocol Design for IoT-Enabled Wireless Body Area Networks
- 26 October 2025
- Published by Springer Nature
- p. 293-308
Intelligent Image Enhancement Using AI Techniques in Health Care
- 26 October 2025
- Published by Springer Nature
- p. 293-308
Intelligent Image Enhancement Using AI Techniques in Health Care
- 22 October 2025
- Published by Springer Nature
- p. 513-527
Synergizing Generative Adversarial Network-Driven Synthetic Data Pipelines with Deep Neural Networks for Enhanced Breast Cancer Diagnosis
- 22 October 2025
- Published by Springer Nature
- p. 513-527
Synergizing Generative Adversarial Network-Driven Synthetic Data Pipelines with Deep Neural Networks for Enhanced Breast Cancer Diagnosis
- 22 October 2025
- Published by Springer Nature
- p. 127-141
Attention-Augmented MobileNetV2 for MRI-Based Brain Tumor Classification: Cosine Annealing and Advanced Metrics
- 22 October 2025
- Published by Springer Nature
- p. 127-141
Attention-Augmented MobileNetV2 for MRI-Based Brain Tumor Classification: Cosine Annealing and Advanced Metrics
- Open Access
- 2 August 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (4) , 26047-26053
Hybrid 3D CNN and ResNet Deep Transfer Learning for High-Resolution Hippocampal Atrophy Mapping and Automated Alzheimer’s MRI Diagnosis
Early and accurate detection of Alzheimer's disease (AD) is crucial for a timely clinical intervention. Atrophy of the hippocampus has been established as a key neurodegenerative biomarker. This study presents a Hybrid 3D CNN–ResNet model for automated hippocampal segmentation and dementia classification using high-resolution MRI scans. The proposed framework integrates 3D U-Net-based hippocampal segmentation with multi-scale feature extraction and deep residual learning, enabling a precise atrophy quantification and robust classification across the AD stages. A standardized preprocessing pipeline, incorporating NIfTI conversion, spatial normalization, denoising, and contrast enhancement, ensures consistency across multi-site datasets. The model was optimized using AdamW, Cyclical Learning Rate (CLR), and early stopping, achieving 97.31% classification accuracy and a 92.84% Dice Similarity Coefficient (DSC) for hippocampal segmentation. Grad-CAM and SHAP-based interpretability confirm the biologically meaningful feature representations, aligning with established hippocampal atrophy patterns in AD progression. The external validation on the OASIS dataset demonstrated strong generalization, with only a 2.3% accuracy reduction, underscoring the model’s robustness and clinical applicability. These findings establish the proposed approach as an effective and interpretable deep learning framework for early AD diagnosis and longitudinal disease monitoring.
- 2 August 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (4) , 26047-26053
Open AccessHybrid 3D CNN and ResNet Deep Transfer Learning for High-Resolution Hippocampal Atrophy Mapping and Automated Alzheimer’s MRI Diagnosis
Early and accurate detection of Alzheimer's disease (AD) is crucial for a timely clinical intervention. Atrophy of the hippocampus has been established as a key neurodegenerative biomarker. This study presents a Hybrid 3D CNN–ResNet model for automated hippocampal segmentation and dementia classification using high-resolution MRI scans. The proposed framework integrates 3D U-Net-based hippocampal segmentation with multi-scale feature extraction and deep residual learning, enabling a precise atrophy quantification and robust classification across the AD stages. A standardized preprocessing pipeline, incorporating NIfTI conversion, spatial normalization, denoising, and contrast enhancement, ensures consistency across multi-site datasets. The model was optimized using AdamW, Cyclical Learning Rate (CLR), and early stopping, achieving 97.31% classification accuracy and a 92.84% Dice Similarity Coefficient (DSC) for hippocampal segmentation. Grad-CAM and SHAP-based interpretability confirm the biologically meaningful feature representations, aligning with established hippocampal atrophy patterns in AD progression. The external validation on the OASIS dataset demonstrated strong generalization, with only a 2.3% accuracy reduction, underscoring the model’s robustness and clinical applicability. These findings establish the proposed approach as an effective and interpretable deep learning framework for early AD diagnosis and longitudinal disease monitoring.
- 16 February 2024
- Published by Springer Nature
- p. 263-274
Identification of Height and Gender Using Deep Learning Application
- 16 February 2024
- Published by Springer Nature
- p. 263-274
Identification of Height and Gender Using Deep Learning Application