Ruchika Malhotra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ruchika Malhotra has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
- Megha Khanna
Department of Computer Science, Sri Guru Gobind Singh College of Commerce, University of Delhi, Delhi, India
10 shared publications - Anjali Bansal
Delhi Technological University
5 shared publications - Marouane Kessentini
Grand Valley State University, Allendale, USA
5 shared publications - Anjali Sharma
Department of Planning Monitoring and Evaluation, CSIR-National Physical Laboratory, Pusa, India
4 shared publications - Kusum Lata
University School of Management and Entrepreneurship, Delhi Technological University, Delhi, India
4 shared publications Ankita Bansal
Netaji Subhas Institute of Technology
3 shared publications
Latest Publications
- 3 November 2026
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
Generation of software test cases using hybridization of grey wolf optimizer and artificial bee colony algorithm
Automated test case generation (ATCG) is a crucial task in the process of software testing. It aims to reduce the overall time required for manual testing and minimize total overhead. Evolutionary algorithms (EAs) in software testing are problem-specific applications explored by a few researchers but remain underutilized. This paper designs a local search strategy by hybridizing two search-based algorithms (SBAs): the Artificial Bee Colony (ABC) algorithm and the Grey Wolf Optimizer (GWO) algorithm; inspired by domain-specific knowledge. The proposed algorithm is constructed by integrating the duty-based phases of these two algorithms and merging them to form subsequent levels of the hybrid algorithm. The proposed algorithm is evaluated using three specific performance metrics: percentage coverage, test suite size, and time taken. Experimental results demonstrate enhanced performance compared to both its constituent algorithms and the conventional baseline algorithms, including Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).
- 3 November 2026
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
Generation of software test cases using hybridization of grey wolf optimizer and artificial bee colony algorithm
Automated test case generation (ATCG) is a crucial task in the process of software testing. It aims to reduce the overall time required for manual testing and minimize total overhead. Evolutionary algorithms (EAs) in software testing are problem-specific applications explored by a few researchers but remain underutilized. This paper designs a local search strategy by hybridizing two search-based algorithms (SBAs): the Artificial Bee Colony (ABC) algorithm and the Grey Wolf Optimizer (GWO) algorithm; inspired by domain-specific knowledge. The proposed algorithm is constructed by integrating the duty-based phases of these two algorithms and merging them to form subsequent levels of the hybrid algorithm. The proposed algorithm is evaluated using three specific performance metrics: percentage coverage, test suite size, and time taken. Experimental results demonstrate enhanced performance compared to both its constituent algorithms and the conventional baseline algorithms, including Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).
- 2 August 2026
- Published by Springer Nature
- p. 352-362
A Hybrid Model of Grey Wolf and Whale Optimization for Software Defect Prediction
- 2 August 2026
- Published by Springer Nature
- p. 352-362
A Hybrid Model of Grey Wolf and Whale Optimization for Software Defect Prediction
- 2 July 2026
- Published by Springer Nature
- p. 68-82
A Robust Federated Learning Approach for Software Defect Prediction Under Class Imbalance
- 2 July 2026
- Published by Springer Nature
- p. 68-82
A Robust Federated Learning Approach for Software Defect Prediction Under Class Imbalance
- 2 July 2026
- Published by Springer Nature
- p. 227-238
Use of Ensemble Learners to Predict Number of Defects in a Software
- 2 July 2026
- Published by Springer Nature
- p. 227-238
Use of Ensemble Learners to Predict Number of Defects in a Software
- Open Access
- 5 May 2026
- Published by MDPI AG in Preprints.org
Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation
We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.
- 5 May 2026
- Published by MDPI AG in Preprints.org
Open AccessTopology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation
We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.
- Open Access
- 28 April 2026
- Published by MDPI AG in Preprints.org
SparseContrast: Dynamic Sparse Attention for Efficient and Accurate Contrastive Learning in Medical Imaging
We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-ray disease detection in low-data settings. Traditional contrastive learning methods rely on dense attention mechanisms, which are computationally expensive and often process redundant regions in medical images. To resolve this, SparseContrast introduces a sparse attention mechanism that selectively concentrates on diagnostically pertinent areas, markedly decreasing computational burden without compromising accuracy. The framework adaptively trims attention maps in the training phase, directed by a compact saliency predictor which concurrently optimizes sparsity and feature quality. This method not only speeds up training and inference by as much as 40% relative to dense attention benchmarks but also boosts diagnostic accuracy by focusing on areas of clinical importance. Moreover, the approach remains indifferent to the selection of backbone architecture, which permits its application to both convolutional and transformer-based models. Experiments show SparseContrast attains comparable or better performance in disease identification tasks with greater efficiency relative to current approaches. The proposed framework delivers a practical approach for implementing contrastive learning in medical imaging settings with limited resources, where computational efficiency and diagnostic accuracy are paramount.
- 28 April 2026
- Published by MDPI AG in Preprints.org
Open AccessSparseContrast: Dynamic Sparse Attention for Efficient and Accurate Contrastive Learning in Medical Imaging
We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-ray disease detection in low-data settings. Traditional contrastive learning methods rely on dense attention mechanisms, which are computationally expensive and often process redundant regions in medical images. To resolve this, SparseContrast introduces a sparse attention mechanism that selectively concentrates on diagnostically pertinent areas, markedly decreasing computational burden without compromising accuracy. The framework adaptively trims attention maps in the training phase, directed by a compact saliency predictor which concurrently optimizes sparsity and feature quality. This method not only speeds up training and inference by as much as 40% relative to dense attention benchmarks but also boosts diagnostic accuracy by focusing on areas of clinical importance. Moreover, the approach remains indifferent to the selection of backbone architecture, which permits its application to both convolutional and transformer-based models. Experiments show SparseContrast attains comparable or better performance in disease identification tasks with greater efficiency relative to current approaches. The proposed framework delivers a practical approach for implementing contrastive learning in medical imaging settings with limited resources, where computational efficiency and diagnostic accuracy are paramount.
- Open Access
- 4 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 520
SBMEV: A Stacking-Based Meta-Ensemble Vehicle Classification Framework for Real-World Traffic Surveillance
Developing vehicle classification remains a fundamental challenge for intelligent traffic management in the Indian urban environment, where traffic exhibits high heterogeneity, density and unpredictability. In the Indian subcontinent, vehicle movement is erratic, congestion is high, and vehicle types vary significantly. Conventional global benchmarks often fail to capture these complexities, highlighting the need for a region-specific dataset. To address this gap, the present study introduced the EAHVSD dataset, a novel real-world image collection comprising 10,864 vehicle images from four distinct classes, acquired from roadside surveillance cameras at multiple viewpoints and under varying conditions. This dataset is designed to support the development of an automatic traffic counter and classifier (ATCC) system. A comprehensive evaluation of eleven state-of-the-art deep learning models, namely VGG16, VGG19, MobileNetV2, Xception, AlexNet, ResNet50, ResNet152, DenseNet121, DenseNet201, InceptionV3, and NASNetMobile, was carried out. Among these, the highest accuracy result has been achieved by VGG-16, MobileNetV2, InceptionV3, DenseNet-121, and DenseNet-201. We developed a stacking-based meta-ensemble framework to leverage the complementary strengths of its components and overcome their individual limitations. In this approach, a meta-learner classifier integrates the predictions of the best-performing models, thereby improving robustness, scalability, and real-world adaptability. The proposed ensemble model achieved an overall classification accuracy of 96.04%, a Cohen’s Kappa of 0.93, and an AUC of 0.99, consistently outperforming the individual models and existing baselines. A comparative analysis with prior studies further validates the efficacy and reliability of the stacking-based meta-ensemble method. These findings position the proposed frameworks as a robust and scalable solution for efficient vehicle classification under practical surveillance constraints, with potential applications in intelligent transportation systems and traffic management.
- 4 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 520
Open AccessSBMEV: A Stacking-Based Meta-Ensemble Vehicle Classification Framework for Real-World Traffic Surveillance
Developing vehicle classification remains a fundamental challenge for intelligent traffic management in the Indian urban environment, where traffic exhibits high heterogeneity, density and unpredictability. In the Indian subcontinent, vehicle movement is erratic, congestion is high, and vehicle types vary significantly. Conventional global benchmarks often fail to capture these complexities, highlighting the need for a region-specific dataset. To address this gap, the present study introduced the EAHVSD dataset, a novel real-world image collection comprising 10,864 vehicle images from four distinct classes, acquired from roadside surveillance cameras at multiple viewpoints and under varying conditions. This dataset is designed to support the development of an automatic traffic counter and classifier (ATCC) system. A comprehensive evaluation of eleven state-of-the-art deep learning models, namely VGG16, VGG19, MobileNetV2, Xception, AlexNet, ResNet50, ResNet152, DenseNet121, DenseNet201, InceptionV3, and NASNetMobile, was carried out. Among these, the highest accuracy result has been achieved by VGG-16, MobileNetV2, InceptionV3, DenseNet-121, and DenseNet-201. We developed a stacking-based meta-ensemble framework to leverage the complementary strengths of its components and overcome their individual limitations. In this approach, a meta-learner classifier integrates the predictions of the best-performing models, thereby improving robustness, scalability, and real-world adaptability. The proposed ensemble model achieved an overall classification accuracy of 96.04%, a Cohen’s Kappa of 0.93, and an AUC of 0.99, consistently outperforming the individual models and existing baselines. A comparative analysis with prior studies further validates the efficacy and reliability of the stacking-based meta-ensemble method. These findings position the proposed frameworks as a robust and scalable solution for efficient vehicle classification under practical surveillance constraints, with potential applications in intelligent transportation systems and traffic management.
- 24 November 2025
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 30 (5) , 1392-1410
Automatic test suite generation using bat algorithm
The Bat Algorithm (BA), inspired by the echolocation behavior of bats, has gained prominence as a promising search-based technique for global optimization. This paper explores its application in automatic test suite generation (TSG) through a creative methodology that inserts mutants in the original data and verifies correctness using mathematical constraints. It further provides a comparative analysis against three established search-based algorithms (SBAs): Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC) algorithm. The analysis focuses on test suite size as a primary metric of the algorithm's effectiveness. Through rigorous experimentation, the performance of the Bat Algorithm has been validated in producing better results compared to the baseline algorithms. It outperformed the performance in terms of reduction in test suite size, achieving a 71.8%, 55.82%, and 18.99% reduction compared to GA, PSO, and ABC, respectively. These results highlight its potential for enhancing TSG in various domains of computer science.
- 24 November 2025
- Published by SAGE Publications in Intelligent Data Analysis: An International Journal
- Vol. 30 (5) , 1392-1410
Automatic test suite generation using bat algorithm
The Bat Algorithm (BA), inspired by the echolocation behavior of bats, has gained prominence as a promising search-based technique for global optimization. This paper explores its application in automatic test suite generation (TSG) through a creative methodology that inserts mutants in the original data and verifies correctness using mathematical constraints. It further provides a comparative analysis against three established search-based algorithms (SBAs): Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC) algorithm. The analysis focuses on test suite size as a primary metric of the algorithm's effectiveness. Through rigorous experimentation, the performance of the Bat Algorithm has been validated in producing better results compared to the baseline algorithms. It outperformed the performance in terms of reduction in test suite size, achieving a 71.8%, 55.82%, and 18.99% reduction compared to GA, PSO, and ABC, respectively. These results highlight its potential for enhancing TSG in various domains of computer science.