Dr. Balamurugan Mani

@acharya.ac.in

Associate Professor, Department of MCA
Acharya Institute of Graduate Studies, Bengaluru

Dr. Balamurugan Mani


                              Download Compact PDF  
https://researchid.co/balamuruganmani
Dr. Balamurugan Mani is working as an associate professor in the Department of MCA, Acharya Institute of Graduate Studies, Bengaluru, Karnataka, India. He had more than 14 years of teaching, research, and administrative experience in various reputed colleges, universities, and institutions. He has published a number of international journal papers and books related to computer science, engineering, and IT with indexes of Scopus and Web of Science. He has published research papers in academic and scientific journals as well as in different professional conference proceedings and workshops. He has involved the academic professional membership bodies of ISTE, ACM, IAENG, CSTA, and many more. He received the best award for various disciplines of teaching and research activities.

EDUCATION

Ph. D in Computer Science (2022)

Postdoctoral researcher (2025-2026)

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition
14

Scopus Publications

207

Scholar Citations

6

Scholar h-index

5

Scholar i10-index

Scopus Publications

  • Optimized Cloud Security Using Time-Oriented Latency Approximation-Based Data Encryption with Levy-Flight Whale Optimization
    M. Balamurugan, G. Gunasekaran, T. Margaret Mary, R. Kalaiarasi
    SN Computer Science, 2026
  • Enhanced Video Surveillance Framework Using Improved Faster R-CNN ResNet101 and LP-SIFT for Robust Object Detection and Tracking
    Balamurugan M, Vibinchandar S, Rajesh Rao K, Narasimha Murthy G K
    2026 Innovations in Machine Engineering and Digital Conference Imed 2026, 2026
    Video surveillance systems are security tools designed to observe, capture, and evaluate unauthorized visual data activities. The methodology in video surveillance systems involves real-time video capture, processing, and analysis using AI, whereas the research gap lies in improving accuracy, privacy preservation, and adaptability to complex environments. This study proposed a new lightweight filtering method called L-Filter, which offers accurate predictions of video frames without objects of interest through hybrid time- series analysis. Subsequently, traditional segmentation methods in video surveillance lack contextual understanding and temporal consistency, which Modulated Memory Networks (MMN) aim to address using adaptive memory-driven feature modulation. Faster R-CNN is the regional popular model for object detection, which is used for the classification and segmentation. The objective of this work is to discover objects in images or videos. To optimize the accuracy and efficiency of video classification by fine-tuning the model parameters, the Gradient Sine Linear (GSL) optimizer has greatly improved the performance over a range of effectiveness and practicality of neural network architectures, and datasets in deep learning are well demonstrated.
  • Trailblazing Strategy: Implementing IoT-Powered Machine Learning to Identify Harmful Potatoes
    D. Gopinath, M. B. Yashoda, P. Ananthi, M. Balamurugan
    Lecture Notes in Networks and Systems, 2025
  • Hybrid Video Enhancement Framework Using Generative Convolutional Vision Transformer
    Balamurugan M, Narasimha Murthy G K, Rajesh Rao K, C. Balaji
    Proceedings 2025 International Conference on Transformative Computing Technologies Ictct 2025, 2025
    Enhancing video content is more challenging than improving still images because of greater computational demands and larger data volumes, along with the complexity of maintaining spatiotemporal consistency. These challenges are often exacerbated by the scarcity of sample pairs for the supervised methods. Therefore, we introduced a robust adversarial framework for video enhancement that learns from unpaired video samples. In this study, we investigated a classification method for detecting false positives in video enhancements using Computer Vision. Video enhancement with Gabor filters captures texture and edge features by emulating the sensitivity system in different orientations. PixStabNet is a deep learning model designed for feature extraction to stabilize video frames at the pixel level and ensure temporal consistency for reliable surveillance analysis. This model improves feature extraction by preserving crucial motion and appearance features in dynamic scenes. RVM + builds on the RVM design concept and offers a novel approach for advanced video segmentation. GenConViT combines convolutional and transformer techniques, where convolutional feature extraction is enhanced using attention-based transformers. Data training was extended until October 2023.This approach captures both local and global spatiotemporal patterns, resulting in an improved video quality. The Beluga Whale Optimization Algorithm (BWO) further enhances video quality by adjusting the enhancement parameters for optimal visual clarity, inspired by the echolocation and cooperative behavior of beluga whales. A highresolution multimodal dataset is ideal for developing and benchmarking video enhancement techniques for autonomous driving and deep learning research because it includes synchronized cameras and LiDAR streams across various geographical locations under different lighting conditions. In terms of F1-score, recall, accuracy, and precision, the experimental developments showed values of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$99.81 \%, 98.84 \%, 98.88 \%, 98.85 \%$</tex>, and 99.02 % respectively.
  • Dynamic Mimic-based Moving Target Defense Mechanisms for Enhancing Security and Resilience in Mobile Ad Hoc Networks
    Gopinath D, Balamurugan M, Margaret Mary T, A. Kanagaraj, S. Sharmila
    Proceedings of the 4th International Conference on Intelligent Computing Information and Control Systems Icoiics 2025, 2025
    Mobile Ad Hoc Networks (MANETs) become increasingly essential for applications requiring flexible, infrastructure-free communication, like military missions, disaster relief, and IoT installations. They are vulnerable to a wide variety of security threats, including routing attacks, node impersonation, and eavesdropping, due to their dynamic topology, decentralized nature, and limited resources. Current security paradigms tend to find it difficult to cope with the dynamic and unpredictable nature of MANETs, presenting a large research gap in designing viable proactive defense approaches suitable for such networks. This research focuses on filling the above gap through designing a new security framework that incorporates mimic defense and moving target defense (MTD) approaches to make MANETs more resilient. Precisely, the goal is to provide dynamic changes-such as routing heterogeneity, node identification randomization, and resource distribution diversification-that repeatedly reshape the attack surface of the network, making it more complex for any possible adversaries and less impactful from attacks. Toward this aim, we introduced attack modeling and attack chain analysis specifically for MANET settings in order to simulate various types of attacks and measure the proposed framework's robustness. Dynamic security measures were deployed in a simulation setting, and performance indicators like attack success rate, network throughput, and latency were quantified. The outcomes indicated that the proposed methods significantly lowered the success rate of typical attacks, such as black hole and Sybil attacks, while keeping network performance at acceptable levels. In addition, the simulations indicated enhancements in overall network resilience and responsiveness in adversarial settings. These results suggest that the use of mimicry and MTD strategies in MANETs represents a promising direction for the design of proactive, adaptive security systems. This work adds to the general task of securing infrastructure-less networks and is of significant import to their deployment in critical sectors where secure, fault-tolerant communication is critical.
  • Investigation of deep learning image fusion techniques for medical imaging
    Songklanakarin Journal of Science and Technology, 2024
  • Soil Aggregate Stability Prediction Using a Hybrid Machine Learning Algorithm
    M. Balamurugan
    Metaheuristics for Machine Learning Algorithms and Applications, 2024
    The concept of soil aggregate stability (SAS) is utilized as a criterion for soil composition because several soil ecosystem functions depend on the presence of stable aggregates. Predictive models have gained increased attention as a replacement for direct measurements because aggregate stability is rarely recorded in soil surveys. In order to anticipate soil aggregate stability, this work aims to develop a novel machine learning (ML) technique called the hybrid tree-based twin-bounded support vector machine (HT-TBSVM). Unexpected discoveries were made by examining soil records that provided information on soil properties such as structure, soil nutrient concentration, alkalinity, and moisture aggregates. This collection includes 109 soil samples from Chile's hyperarid, arid, and semiarid regions, as well as humid areas, including cultivated fields, grasslands, and tree plantations. The most prevalent soil types in this dataset were clay loam, sandal loam, and loam, and the values for each soil attribute ranged widely. The mean absolute error (MAE), R 2 , normalized root mean square error (nRMSE), and root mean square error (RMSE) are used as different indicators to determine the effectiveness of the given prediction. We evaluated these measurements in comparison to conventional approaches to predicting SA stability. The experimental results show that the proposed approach outperforms conventional approaches in terms of outcomes.
  • Exploring Single Frame Deraining Techniques: A Comprehensive Investigation
    Muthukumar Balamurugan, Varun P. Gopi
    2024 3rd International Conference on Electrical Electronics Information and Communication Technologies Iceeict 2024, 2024
    Single-frame deraining is an essential task in the modelling vision based challenges, plays a pivotal role in enhancing the visual quality of images captured under adverse weather conditions. There have been substantial advancements in the development of deraining techniques leveraging various deep learning architectures. This paper presents an in-depth survey of the existing literature on Single-frame deraining, directing towards methodologies, challenges, and advancements in this domain. The survey covers a wide range of deraining techniques, including traditional methods based on handcrafted features, as well as state-of-the-art deep learning approaches utilizing convolutional neural networks (CNNs) and transformers. The existing methodologies are categorized based on their underlying principles, such as image decomposition, physical modelling, and deep learning-based approaches. Additionally, the paper discusses the datasets commonly used for evaluating deraining algorithms and highlights the key performance metrics employed for benchmarking. Furthermore, the strengths and limitations of different deraining approaches are analysed, and promising directions for future research are identified. Through this survey, the objective is to furnish research scientists and specialists with an in-depth grasp of the available methods in Single frame deraining, thereby facilitating further advancements in this critical area of computer vision
  • Development of a Grey Wolf Optimized-Gradient Boosted Decision Tree Metamodel for Heart Disease Prediction
    International Journal of Intelligent Systems and Applications in Engineering, 2024
  • Revolutionizing Magnetic Resonance Imaging Image Reconstruction: A Unified Approach Integrating Deep Residual Networks and Generative Adversarial Networks
    M Nagalakshmi, M. Balamurugan, B. Hemantha Kumar, Lakshmana Phaneendra Maguluri, Abdul Rahman Mohammed ALAnsari, Yousef A.Baker El-Ebiary
    International Journal of Advanced Computer Science and Applications, 2024
    — Advancements in data capture techniques in the field of Magnetic Resonance Imaging (MRI) offer faster retrieval of critical medical imagery. Even with these advances, reconstruction techniques are generally slow and visually poor, making it difficult to include compression sensors. To address these issues, this work proposes a novel hybrid GAN-DRN architecture-based method for MRI reconstruction. This approach greatly improves texture, boundary characteristics, and picture fidelity over previous methods by combining Generative Adversarial Networks (GANs) with Deep Residual Networks (DRNs). One important innovation is the GAN's all-encompassing learning mechanism, which modifies the generator's behaviour to protect the network against corrupted input. In addition, the discriminator assesses forecast validity thoroughly at the same time. With this special technique, intrinsic features in the original photo are skillfully extracted and managed, producing excellent results that adhere to predetermined quality criteria. The
  • Selection of Routing Protocol-Based QoS Improvement for Mobile Ad Hoc Network
    V. Vinoth Kumar, R. Deepa, D. Ranjith, M. Balamurugan, J. M. Balajee
    Eai Springer Innovations in Communication and Computing, 2022
  • Dimensionally improved residual neural network to detect driver distraction in real time
    M Balamurugan, R Kalaiarasi
    Journal of Physics Conference Series, 2021
  • Prediction and Analysis of Plant-Leaf Disease in Agricultural by using Image Processing and Machine Learning Techniques
    T. R. Ganesh Babu, S. Priya, J. Gopi Chandru, M. Balamurugan, J. Gopika, R. Praveena
    2021 International Conference on Computational Performance Evaluation Compe 2021, 2021
  • Tiny object detection: Comparative study using single stage CNN object detectors
    Rakshitha Gopal, Sandeep Kuinthodu, Muthukumar Balamurugan, Mallabadkar Atique
    2019 5th IEEE International Wie Conference on Electrical and Computer Engineering Wiecon Ece 2019 Proceedings, 2019

RECENT SCHOLAR PUBLICATIONS

  • Optimized Cloud Security Using Time-Oriented Latency Approximation-Based Data Encryption with Levy-Flight Whale Optimization
    M Balamurugan, G Gunasekaran, T Margaret Mary, R Kalaiarasi
    SN Computer Science 7 (5), 445 , 2026
    2026
  • Enhanced Video Surveillance Framework Using Improved Faster R-CNN ResNet101 and LP-SIFT for Robust Object Detection and Tracking
    M Balamurugan, S Vibinchandar, K Rajesh Rao, GK Narasimha Murthy
    2026 Innovations in Machine, Engineering, and Digital Conference (IMED), 1-4 , 2026
    2026
  • An Intellectual Framework for Heart Disease Detection Using Multi‐Scale Convolutional Autoencoder With Adaptive Gated Recurrent Unit
    M Balamurugan, S Meera
    International Journal of Adaptive Control and Signal Processing , 2026
    2026
  • Dynamic Mimic-based Moving Target Defense Mechanisms for Enhancing Security and Resilience in Mobile Ad Hoc Networks
    D Gopinath, M Balamurugan, T Margaret Mary
    2025 International Conference on Intelligent Computing, Information and … , 2025
    2025
  • Hybrid Video Enhancement Framework Using Generative Convolutional Vision Transformer
    M Balamurugan, NM GK, R Rao, C Balaji
    2025 International Conference on Transformative Computing Technologies … , 2025
    2025
  • Dysgraphia Disorder Detection And Classification Using Enhanced Adaptive Butterfly Optimization Algorithm
    CNB Balamurugan M, Gopinath D, Kalaiarasi R
    International Journal of Environmental Sciences 11 (5), 1471-1483 , 2025
    2025
  • Early Detection of Dementia using AI-Powered Analysis of MRI/CT Scans: A Deep learning Approach
    VH Balamurugan M, Rajesh Rao K, Narasimha Murthy G K
    Journal of Emerging Technologies and Innovative Research 12 (7), 767-770 , 2025
    2025
  • Integrating Deep Learning Models and Facial Recognition for Advanced Intelligent Surveillance Systems
    M Balamurugan, R Kalaiarasi, D Gopinath, HJ Shanthi
    International Conference on Sustainability Innovation in Computing and … , 2025
    2025
    Citations: 1
  • Hybrid optimized temporal convolutional networks with long short-term memory for heart disease prediction with deep features
    M Balamurugan, DS Meera
    Computer Methods in Biomechanics and Biomedical Engineering 28 (7), 996-1020 , 2025
    2025
    Citations: 6
  • Enhancing Meal Recommendation Algorithms: A Contextual Approach to Machine Learning Calibration
    M Balamurugan, A Keshav, S Viswanathan, R Dinesh
    2025 International Conference on Computing and Communication Technologies … , 2025
    2025
  • Real-Time Bidirectional Sign Language Translation Using MobileNet and Tensorflow Lite
    M Balamurugan, G Nivedha, R Devi, G Jeevika
    2025 International Conference on Computing and Communication Technologies … , 2025
    2025
  • HERA-A PCOD Tracker and Stablizer
    M Balamurugan, S Raman
    2025 International Conference on Computing and Communication Technologies … , 2025
    2025
    Citations: 1
  • Trailblazing Strategy: Implementing IoT-Powered Machine Learning
    D Gopinath, MB Yashoda, P Ananthi, M Balamurugan
    Proceedings of International Conference on Recent Trends in Computing: ICRTC … , 2025
    2025
  • Lung Cancer Classification using DenseNet Multi Model Optimization Techniques
    VK Balamurugan M, Narasimha Murthy G K, Nagaraju M L, Rajesh Rao K
    Computer Science & Engineering: An International Journal (CSEIJ) 15 (1), 255-269 , 2025
    2025
  • Design and control of a grid-connected solar-wind hybrid sustainable energy generation systems using DFIG
    GBA Kumar, M Balamurugan, KNS Kumar, R Gatti
    International Journal of Applied Power Engineering (IJAPE) 14, 188 , 2025
    2025
    Citations: 3
  • An intelligent method for predicting cardiac disease based on PSO-convolutional neural network
    M Balamurugan, PB Prince
    International Journal of Medical Engineering and Informatics 17 (5), 463-475 , 2025
    2025
    Citations: 1
  • Enhancing Agricultural Decision-Making Using Machine Learning: Variety Selection and Yield Prediction for Agriculture Culture Improvement
    S Upadhyay, N Indumathi, M Balamurugan, B Kumar, S Mandal, ...
    International Conference on Recent Trends in Artificial Intelligence and IoT … , 2024
    2024
  • SDKL Hybrid ML Model to Predict Heart Disease Detection
    M Balamurugan, S Meera
    Next-Gen Technologies in Computational Intelligence, 71-75 , 2024
    2024
  • Soil Aggregate Stability Prediction Using a Hybrid Machine Learning Algorithm
    M Balamurugan
    Metaheuristics for Machine Learning: Algorithms and Applications, 301-314 , 2024
    2024
  • Revolutionizing Magnetic Resonance Imaging Image Reconstruction: A Unified Approach Integrating Deep Residual Networks and Generative Adversarial Networks
    PTDYABEE Dr M Nagalakshmi, Dr. M. Balamurugan, Dr. B. Hemantha Kumar ...
    International Journal of Advanced Computer Science and Applications 15 (1 … , 2024
    2024
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • Protective and curative effects of polyphenolic extracts from Ichnocarpus frutescense leaves on experimental hepatotoxicity by carbon tretrachloride and tamoxifen
    C Kumarappan, M Vijayakumar, E Thilagam, M Balamurugan, ...
    Annals of hepatology 10 (1), 63-72 , 2016
    2016
    Citations: 44
  • Comparative computational impact analysis of multi-layer composite materials
    S Bhagavathiyappan, M Balamurugan, M Rajamanickam, R Vijayanandh, ...
    AIP Conference Proceedings 2270 (1), 040007 , 2020
    2020
    Citations: 42
  • Development and in-vitro evaluation of mucoadhesive buccal tablets of domperidone
    M Balamurugan, VS Saravanan, P Ganesh, SP Senthil, PV Hemalatha, ...
    Research Journal of Pharmacy and Technology 1 (4), 377-380 , 2008
    2008
    Citations: 39
  • Prediction of chronic disease in kidneys using machine learning classifiers
    CP Kashyap, GSD Reddy, M Balamurugan
    2022 1st International Conference on Computational Science and Technology … , 2022
    2022
    Citations: 28
  • Development of a Grey Wolf Optimized-Gradient Boosted Decision Tree Metamodel for Heart Disease Prediction
    N Ganesh, M Balamurugan, JS Chohan, K Kalita
    International Journal of Intelligent Systems and Applications in Engineering … , 2023
    2023
    Citations: 11
  • Hybrid optimized temporal convolutional networks with long short-term memory for heart disease prediction with deep features
    M Balamurugan, DS Meera
    Computer Methods in Biomechanics and Biomedical Engineering 28 (7), 996-1020 , 2025
    2025
    Citations: 6
  • An efficient mechanism to detect skin disease using svm
    M Balamurugan, J Periasamy, M Akash, P Sricharan, A Poon-godi
    Journal of Green Engineering 10 (10), 9506-9516 , 2020
    2020
    Citations: 5
  • Selection of Routing Protocol - Based QoS Improvement for Mobile Adhoc Network
    JMB V Vinoth Kumar, R Deepa, D Ranjith, M Balamurugan
    International Conference on Computing, Communication, Electrical and … , 2022
    2022
    Citations: 4
  • Dimentionally Improvised Residual Neural Networks to Detect Driver Distraction in real time
    RK M Balamurugan
    Journal of Physics: Conference Series (First International Conference on … , 2021
    2021
    Citations: 4
  • Formulation, Characterization and In-vitro Evaluation of Abacavir Sulphate Loaded Microspheres
    N Chandarsekaran, M Balamurugan
    Research Journal of Pharmacy and Technology 6 (7), 731 , 2013
    2013
    Citations: 4
  • Design and control of a grid-connected solar-wind hybrid sustainable energy generation systems using DFIG
    GBA Kumar, M Balamurugan, KNS Kumar, R Gatti
    International Journal of Applied Power Engineering (IJAPE) 14, 188 , 2025
    2025
    Citations: 3
  • Revolutionizing Magnetic Resonance Imaging Image Reconstruction: A Unified Approach Integrating Deep Residual Networks and Generative Adversarial Networks
    PTDYABEE Dr M Nagalakshmi, Dr. M. Balamurugan, Dr. B. Hemantha Kumar ...
    International Journal of Advanced Computer Science and Applications 15 (1 … , 2024
    2024
    Citations: 2
  • Smart Dine-in: A Personalized Food Recommendation System
    A Keshav, S Viswanathan, R Dinesh
    2023 Intelligent Computing and Control for Engineering and Business Systems … , 2023
    2023
    Citations: 2
  • Blockchain technology empirical studies on the demand of distributed network
    MK Mishra, M Balamurugan, R Reena Roy, M Amanullah, ...
    Journal of Physics: Conference Series 1964 (4), 042012 , 2021
    2021
    Citations: 2
  • Efficient Healthcare Framework for Senior Benefaction
    M Balamurugan, JK Periasamy, C Gnanapriya, K Vijiyalakshmi, E Vanitha
    International Journal of Innovative Technology and Exploring Engineering … , 2019
    2019
    Citations: 2
  • Integrating Deep Learning Models and Facial Recognition for Advanced Intelligent Surveillance Systems
    M Balamurugan, R Kalaiarasi, D Gopinath, HJ Shanthi
    International Conference on Sustainability Innovation in Computing and … , 2025
    2025
    Citations: 1
  • HERA-A PCOD Tracker and Stablizer
    M Balamurugan, S Raman
    2025 International Conference on Computing and Communication Technologies … , 2025
    2025
    Citations: 1
  • An intelligent method for predicting cardiac disease based on PSO-convolutional neural network
    M Balamurugan, PB Prince
    International Journal of Medical Engineering and Informatics 17 (5), 463-475 , 2025
    2025
    Citations: 1
  • An intelligent tool to predict and analyze students' stress for their academic growth
    M Balamurugan, M SG
    2023 Intelligent Computing and Control for Engineering and Business Systems … , 2023
    2023
    Citations: 1
  • Sniffing detection using machine learning
    M Balamurugan, P Vasanth, S Grihith, G Youkesh
    2023 Intelligent Computing and Control for Engineering and Business Systems … , 2023
    2023
    Citations: 1