Sandhya Bansal

Bio-Sketch: Dr. Sandhya Bansal
Dr. Sandhya Bansal is a Professor in the Department of Computer Science & Engineering at Maharishi Markandeshwar Engineering College, MMDU, Mullana, with 19 years of teaching experience in B.Tech and M.Tech programs. She earned her Ph.D. in Computer Science and Engineering in 2017 and has qualified UGC-NET in Computer Science Applications. Her academic interests include Design & Analysis of Algorithms, Data Structures, Computer Architecture, Soft Computing, Metaheuristics, Vehicle Routing Problems, and Computer Vision.
Dr. Bansal has published extensively in high-impact SCI and Scopus-indexed journals and conferences, with over 50 publications covering areas like sign language recognition, facial expression recognition, deep learning, and optimization algorithms. She has also authored and co-authored several book chapters, including works published by Springer, Elsevier, and CRC Press.

EDUCATION

UGC Net (CSE), P.hD (CSE), M.Tech, B.tech

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition, Human-Computer Interaction

Scopus Publications

Enhanced Dark and Light Channel Priors for Single-Image De-hazing
Parmeet Kaur, Sandhya Bansal
Lecture Notes in Networks and Systems, 2026
Improved feature reduction framework for sign language recognition using autoencoders and adaptive Grey Wolf Optimization
Rajeev Goel, Sandhya Bansal, Kavita Gupta
Scientific Reports, 2025
Automatic Sign Language Recognition Systems (ASLR) offers smooth communication between hearing-impaired and normal-hearing individuals, enhancing educational opportunities for impaired. However, it struggles with "curse of dimensionality" due to excessive features resulting in prolonged training time and exhaustive computational demand. This paper proposes technique that integrates machine learning and swarm intelligence to effectively address this issue. The proposed technique, initially, extracts features using histrogram of gradient (HOG) approach and then reduces dimensions of extracted features using unsupervised autoencoder and subsequently refining the feature set with an improved GWO algorithm. A handcrafted artificial neural network serves as the classifier within this integrated framework, denoted as AEGWO-Net. Exhaustive experimentations were conducted on six different datasets namely ASL, ASL MNIST, ISL, ArSL, MNIST Digits, and IEEE-ISL containing gestures of different languages to demonstrate the performance of AEGWO-Net. The AEGWO-Net demonstrates superior performance improving accuracy and F1 score by 6% and 4% respectively compared to PCA-IGWO and KPCA-IGWO algorithms. Achieving high accuracy (98.40%), F1-score (96.59%), MCC (97.14%), and AUC (96.21%) indicates the robustness and generalizability of the AEGWO-Net method even with reduced dimensionality. Furthermore, a comparison between AEGWO-Net with other existing swarm intelligence techniques is also made to demonstrate its superiority.
Optimizing Facial Expression Recognition in Challenging Environment: A Streamlined CNN with Pre-processing Techniques
Richa Grover, Sandhya Bansal
Journal of the Institution of Engineers India Series B, 2025
SILK-SVM: An Effective Machine Learning Based Key-Frame Extraction Approach for Dynamic Hand Gesture Recognition
Arpneek Kaur, Sandhya Bansal
Arabian Journal for Science and Engineering, 2025
Enhancing facial expression recognition in uncontrolled environment: a lightweight CNN approach with pre-processing
Richa Grover, Sandhya Bansal
Neural Computing and Applications, 2025
Exploring Sign Language in Complex Background: Techniques, Datasets and Challenges
Nishi Midha, Sandhya Bansal
Proceedings of the 2025 12th International Conference on Computing for Sustainable Global Development Indiacom 2025, 2025
The Deaf community plays an important and vibrant role in society with sign language is used as primary means of communication. Sign language often remains confined within their community due to a lack of understanding among those without hearing impairments. SLR (Sign Language Recognition) solves this problem by enabling better communication and understanding of sign language among common people. This paper represents critical and systematic review of 71 articles for Sign recognition. In this paper we review how SLR makes significant strides, particularly through the development of innovative algorithm-driven techniques in both traditional and deep learning approaches. This review provides an overview of these advancements, focusing on main methodologies, including traditional methods and deep learning. It also examines available sign language datasets, identifies the challenges facing SLR with respect to different complexity by analysing and comparing the fundamental principles of various SLR techniques corresponding to complex patterns.
Enhancing Emotion Recognition from Facial Images: A Two-Stage Model Using Deep Learning and Traditional Classifiers
Richa Grover, Sandhya Bansal
Lecture Notes in Networks and Systems, 2025
Efficient Facial Expression Recognition Through Lightweight CNN Technique on Public Datasets
Richa Grover, Sandhya Bansal
SN Computer Science, 2025
Precision Classification of Tomato Leaf Diseases Using Genetic Algorithm and KNN-Based Feature Optimization
Bibek Joshi, Sandhya Bansal, Kavita Gupta
Lecture Notes in Networks and Systems, 2025
Comparative Analysis of Artifact Based Deepfake Detection Techniques Using Convergence, EER, and Accuracy Metrics
Preeti Rana, Sandhya Bansal, Sonika Nagar, Ashish Malik
2025 International Conference on Sustainability Innovation and Technology Icsit 2025, 2025
As of now, there is huge upthrust to the fake media. It's a complete mayhem. Intent was to boost this industry, give some breathing space, rejuvenate the lungs of this industry, instead we have ended up creating a monster which is becoming bigger than the creator. We have some really state of art techniques which are really lagging in providing security to all of us. Performance of this almost obsolete defence system is so questionable. Focus here is to show the mirror to defence system & provide major inputs which can end up giving strong fire wall. These methods were assessed using key performance indicators: Convergence rate, Estimated Error Rate (EER), and Accuracy (ACC) to determine the most robust method for detecting manipulated facial content. Among them, EfficientFake demonstrated superior performance, achieving the highest accuracy (94.5 %), lowest EER (3.98 %), and fastest convergence <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(98.3 \%)$</tex>, establishing it as the most effective technique in the study. Furthermore, this paper explores various artifact-based indicators that can reveal deepfake manipulation techniques which is a biggest threat in emerging digital technology. Each artifact's origin, detection approach, effectiveness, and limitations are systematically analysed. Based on these insights, future work will aim to create a novel deep learning-based detection framework that integrates multiple artifact cues to enhance accuracy, generalization, and robustness against sophisticated face forgeries.
Optimizing Vehicle Routes for Waste Collection Using Soft Computing Techniques
Sandhya Bansal, Vishal Dattana, Charu Sharma, Kavita Gupta, Rajeev Goel
Computational Techniques in Environmental Engineering, 2025
Enhanced Triple Layered Approach for Mitigating Security Risks in Cloud
Tajinder Kumar, Purushottam Sharma, Xiaochun Cheng, Sachin Lalar, Shubham Kumar, Sandhya Bansal
Computers Materials and Continua, 2025
Exploring Deepfake Detection: Techniques, Datasets and Challenges
Preeti Rana, Sandhya Bansal
International Journal of Computing and Digital Systems, 2024
Image Enhancement and Restoration: Deep Learning for Image Dehazing
Parmeet Kaur, Sandhya Bansal
Lecture Notes in Networks and Systems, 2024
HOG Landmarks and Illumination Artifacts for Deep Fake Detection
Preeti Rana, Sandhya Bansal
Proceedings 2024 2nd International Conference on Advanced Computing and Communication Technologies Icacctech 2024, 2024
Hand Anatomy and Neural Network-Based Recognition for Sign Language
Akansha Tyagi, Sandhya Bansal
IETE Journal of Research, 2024
A Machine Learning Based Approach for Dynamic Hand Gesture Recognition in Human-Robot Interaction
Arpneek Kaur, Sandhya Bansal
2024 12th International Conference on Intelligent Systems and Embedded Design Ised 2024, 2024
Facial Expression Recognition: Deep Survey, Progression and Future Perspective
Richa Grover, Sandhya Bansal
2023 International Conference on Advancement in Computation and Computer Technologies Incacct 2023, 2023
Artifact Based Deepfake Detection Methods
Preeti, Sandhya Bansal
Proceedings of 2023 2nd International Conference on Informatics Ici 2023, 2023
An Adaptive Frame Selection and Deep Learning-Based Dynamic Hand Gesture Recognition System for Sterile Environments
Arpneek Kaur, Sandhya Bansal
2023 International Conference on Computational Intelligence Networks and Security Iccins 2023, 2023
CNN-based Human Emotion Recognition from Facial Images in Controlled-Uncontrolled Environment
Richa Grover, Sandhya Bansal
Proceedings of 2023 2nd International Conference on Informatics Ici 2023, 2023
Estimating Factors of Agile Software Development Using Fuzzy Logic: A Survey
Jahidul Hasan Antor, Sandhya Bansal, Jamal
Lecture Notes in Electrical Engineering, 2023
Classification of Tomato Leaf Disease using Feature Extraction with KNN Classifier
Bibek Joshi, Sandhya Bansal, Charu Sharma
Proceedings of the IEEE International Conference Image Information Processing, 2023
Scope of Machine Learning in Mobile Wireless Sensor Networks
Kavita Gupta, Sandhya Bansal, Ajay Khurana
Lecture Notes in Networks and Systems, 2023
Improved Speech Recognition using Vector Quantization, Genetic Algorithm and Neural Networks
Meenu Bala, Sandhya Bansal, Charu Sharma
2023 International Conference on Computer Electronics and Electrical Engineering and their Applications Ic2e3 2023, 2023
Blockchain in healthcare: A systematic review and future perspectives
Deep Learning for Healthcare Decision Making, 2022
mRMR-PSO: A Hybrid Feature Selection Technique with a Multiobjective Approach for Sign Language Recognition
Sandhya Rani Bansal, Savita Wadhawan, Rajeev Goel
Arabian Journal for Science and Engineering, 2022
Ground Vehicle and UAV Collaborative Routing and Scheduling for Humanitarian logistics using Random Walk Based Ant Colony Optimization
Scientia Iranica, 2022
Hybrid FiST_CNN Approach for Feature Extraction for Vision-Based Indian Sign Language Recognition
Akansha Tyagi, Sandhya Bansal
International Arab Journal of Information Technology, 2022
Sign Language Recognition Using Hand Mark Analysis for Vision-Based System (HMASL)
Akansha Tyagi, Sandhya Bansal
Lecture Notes in Electrical Engineering, 2022
Recognition of Indian Sign Language using Hand geometry and Neural Network
Akansha Tyagi, Sandhya Bansal
3rd IEEE 2022 International Conference on Computing Communication and Intelligent Systems Icccis 2022, 2022
Hybrid FAST-SIFT-CNN (HFSC) Approach for Vision-Based Indian Sign Language Recognition
Akansha Tyagi, Sandhya Bansal
International Journal of Computing and Digital Systems, 2022
Deep Learning for Dynamic Hand Gesture Recognition: Applications, Challenges and Future Scope
Arpneek Kaur, Sandhya Bansal
2022 5th International Conference on Multimedia Signal Processing and Communication Technologies Impact 2022, 2022
A Hybrid of Sine Cosine and Particle Swarm Optimization (HSPS) for solving heterogeneous fixed fleet vehicle routing problem
Sandhya Bansal, Savita Wadhawan
International Journal of Applied Metaheuristic Computing, 2021
Feature extraction technique for vision-based indian sign language recognition system: A review
Akansha Tyagi, Sandhya Bansal
Advances in Intelligent Systems and Computing, 2021
Uses of Drones in Fighting COVID-19 Pandemic
Kavita Gupta, Sandhya Bansal, Rajiv Goel
Proceedings of the 2021 10th International Conference on System Modeling and Advancement in Research Trends Smart 2021, 2021
Comparative analysis of feature detection and extraction techniques for vision-based ISLR system
Akansha Tyagi, Sandhya Bansal, Arjun Kashyap
Pdgc 2020 2020 6th International Conference on Parallel Distributed and Grid Computing, 2020
An improved ant colony algorithm based on levy flight distribution
S. Bansal, R. Goel, R. Maini
Advances in Mathematics Scientific Journal, 2020
Corrigendum to “Vehicle routing problem with time windows having stochastic customers demands and stochastic service times: Modelling and solution” (Journal of Computational Science (2019) 34 (1–10), (S1877750318308810), (10.1016/j.jocs.2019.04.003))
Rajeev Goel, Raman Maini, Sandhya Rani Bansal
Journal of Computational Science, 2019
Vehicle routing problem with time windows having stochastic customers demands and stochastic service times: Modelling and solution
Rajeev Goel, Raman Maini, Sandhya Bansal
Journal of Computational Science, 2019
Hybrid algorithms for rich vehicle routing problems: A survey
Rajeev Kr. Goel, Sandhya Rani Bansal
Smart Delivery Systems Solving Complex Vehicle Routing Problems, 2019
Fuzzy Based Parameter Adaptation in ACO for Solving VRP
Sandhya, Rajiv Goel
International Journal of Operations Research and Information Systems, 2019
A novel method to handle route failure in fuzzy vehicle routing problem with hard time windows and uncertain demand
Sandhya Bansal, Rajeev Kumar Goel, Vijay Katiyar
International Journal of Advanced Operations Management, 2017
Vehicle routing problem with time windows having uncertain demand using fuzzy ant system
International Journal of Applied Engineering Research, 2015
Use of ant colony system in solving vehicle routing problem with time window constraints
Sandhya Bansal, Rajeev Goel, C. Mohan
Advances in Intelligent Systems and Computing, 2014

GRANT DETAILS

Co-Principal Investigator for a funded project on automating sign language recognition for the speech- and hearing-impaired community, supported by DST Haryana.

RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)

Software : She is the Co-Principal Investigator for a funded project on automating sign language recognition for the speech- and hearing-impaired community, supported by DST Haryana.

Industry, Institute, or Organisation Collaboration

Punjabi University Patiala