Arun V

@sairam.edu.in

Assistant Professor / Department of Artificial Intelligence and Data Science
Sri Sairam Engineering College

Arun V


               Download Compact PDF  
https://researchid.co/arunprof3284

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Engineering, Computer Science, Computer Science Applications
9

Scopus Publications

24

Scholar Citations

2

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Explainable Traffic Image Classification: A Hybrid Grad-CAM and LIME Approach with Superpixel-aware Refinement
    P Badharudheen, V. Arun
    2026 2nd International Conference on Advances in Intelligent Computing and Applications Aicaps 2026, 2026
    Intelligent transportation system requires accurate and interpretable vehicle classification mechanism, where trust and transparency in its decision-making process are very important. Existing deep learning models like ResNet18 offers high accuracy in its classification process, but they operate like a Blackbox which lacks transparency and explainability in the decision-making process. This paper presents an innovative explainable AI (XAI) framework for traffic image classification by combining the two most popular interpretation techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME), to produce visual, tabular and textual explanations for vehicle classification methods. To further enhance the visual fidelity of explanations, we introduce a superpixel-aware refinement strategy which can be used to improve the localization of important regions in the output generated from the Grad-CAM heatmaps. Using a ResNet18 pre-trained model on the ImageNet dataset, we first applied the Grad-CAM method to generate a classdiscriminative heatmaps and then utilized the LIME technique to identify the important pixels that contributed more to the prediction of the particular vehicle class. To provide humanreadable justifications for the prediction, the output generated from this framework are then mapped into textual and tabular formats. The result obtained from this hybrid approach maintains classification accuracy as well as it provides human readable explanations on its prediction there by increasing the trust and understanding of AI outputs.
  • Dynamic Multilevel User Allocation in MEC Using CESO for Resource Efficiency and QoE
    V Arun, M Azhagiri
    International Journal of Advanced Computer Science and Applications, 2026
    Mobile Edge Computing (MEC) has become one of the key paradigms to enable next-generation networks in supporting applications that are latency sensitive and computation-intensive. Nevertheless, the resourceful placement of heterogeneous and dynamically incoming user tasks with distributed edge servers is a problematic issue to be achieved because of network fluctuation, non-uniform resource availability, and variance in Quality of Experience (QoE) demand. To overcome these constraints, this study suggests the Dynamic Multilevel User Allocation Algorithm (DMUAA) that incorporates a new Cognitive Evolutionary Synergy Optimization (CESO) framework in order to reach stable, adaptive, and resource-optimizing allocation in real-time. DMUAA means a hierarchical optimization pipeline that consists of heuristic initialization, stochastic refinement, and strategic game-theoretic equilibrium assisted by a coordination and feedback mechanism that guarantees the constant adaptation to variations in user mobility and load. The system model collaboratively optimizes the latency, energy, resource, and QoE under the multi-constraint edge-server conditions. Extensive simulations over a wide range of resource capabilities, user rates, and mobility patterns indicate that DMUAA can be greatly superior to five state-of-the-art baselines, which are the MGGO, GTA, EUA, HAILP, and LGP. Findings indicate that DMUAA decreases average end-to-end latency by 18-34%, increases Resource Utilization Efficiency (RUE) by 12–27%, and increases Service Continuity Rate (SCR) by 15–30% over the current practices. The solved approach also produces 20-35% greater QoE, better load balancing (with up to 25% reduced LBI), and up to 22 per cent greater energy-QoE efficiency (EQR). Moreover, CESO allows for more rapid and stable convergence, and DMUAA comes to optimal allocation states 40-55% quicker than competing algorithms.
  • Hybrid deep reinforcement learning and genetic algorithm-based resource allocation framework for edge computing
    V. Arun, M. Azhagiri
    Peer to Peer Networking and Applications, 2025
  • Context Anomaly Identification Algorithm Using Dirichlet
    A. Priyadharshini, V. Arun, R. D. Sathiya, M. Priyadharsini
    Cognitive Fairness Aware Techniques for Humanmachine Interface, 2025
    Upon arrival of the data from the source, they are mapped to the graph model based on their context. The contexts of the node (events) are identified by using the Context Identification Algorithm (CAI). If an instance appears to be anomalous only in a specific context, it is called a Contextual anomaly. Anomaly (or outlier) detection is the task of identifying data points that are “very strange” compared to the majority of observations. Contextual anomaly detection algorithms evaluate individual data points for data analysis with an anomaly score, which serves as the basis for subsequent decision-making. Anomaly score is based on contextual threshold and feedback-based dynamic relationships between entities. Machine learning provides successful prediction of non-parametric identification, named as conformal prediction.
  • Design of Long-Term Evolution Based Mobile Edge Computing Systems to Improve 5G Systems
    V. Arun, M. Azhagiri
    Proceedings of the 2nd International Conference on Edge Computing and Applications Icecaa 2023, 2023
    Mobile edge computing is an emerging technology that enables mobile devices to access cloud services with reduced latency by moving computing, storage, and network control closer to the network edge. This advancement allows mobile devices to operate for longer periods on a single charge. With the advent of 5G communications, there is increasing interest in exploring the integration of mobile edge computing within existing mobile networks. The proposed work aims to develop a portable 5G computing system that offloads computational tasks to edge servers, thereby reducing latency and improving energy efficiency. The work focuses on designing efficient workload allocation algorithms to optimize the distribution of tasks to the supported servers. By implementing and evaluating a practical mobile-based computing system based on Long-Term Evolution (LTE), this research aims to demonstrate the real-world effectiveness of such mobile edge computing programs, with particular emphasis on reducing delays and enhancing energy efficiency.
  • Water pollution monitoring using IOT
    Arun. V, , Bhooveshwaran. B, Rakkesh M.P, , and
    International Journal of Innovative Technology and Exploring Engineering, 2019
    Activities performed by humans is one of the major reasons for the increase in pollution. This increase in the pollution of earth unfairly influenced the water bodies that is a need for eternity. Asia has the most number of contaminated water bodies which is mainly composed of Bacteria through Human waste. Even if we side with treating water instead of prevention of pollution, identifying the extent to which the water body is contaminated is an essential problem that needs to be addressed. Factoring BOD and dissolved oxygen which are the prime causes of biological contamination of a water body is essential for a system monitoring water pollution. This paper addresses the issue of contamination magnitude through the use of IOT components. Monitoring and presenting data is the main scope of this system.
  • Deep learning hyper parameter optimization for video analytic in centralized system
    Arun V., , Shuvam Bhattacharjee, Ritik Khandelwal, Kanishk Malik, , , and
    International Journal of Engineering and Advanced Technology, 2019
    A framework to perform video examination is proposed utilizing a powerfully tuned convolutional arrange. Recordings are gotten from distributed storage, preprocessed, and a model for supporting order is created on these video streams utilizing cloud-based framework. A key spotlight in this paper is on tuning hyper-parameters related with the profound learning calculation used to build the model. We further propose a programmed video object order pipeline to approve the framework. The scientific model used to help hyper-parameter tuning improves execution of the proposed pipeline, and results of different parameters on framework's presentation is analyzed. Along these lines, the parameters that contribute toward the most ideal presentation are chosen for the video object order pipeline. Our examination based approval uncovers an exactness and accuracy of 97% and 96%, separately. The framework demonstrated to be adaptable, strong, and adjustable for a wide range of utilizations.
  • E-voting using a decentralized ethereum application
    International Journal of Engineering and Advanced Technology, 2019
  • Emotion prediction using semantic analysis neural network
    Journal of Advanced Research in Dynamical and Control Systems, 2019

RECENT SCHOLAR PUBLICATIONS

  • Hybrid deep reinforcement learning and genetic algorithm-based resource allocation framework for edge computing
    V Arun, M Azhagiri
    Peer-to-Peer Networking and Applications 18 (6), 320 , 2025
    2025.0
    Citations: 2
  • Techno slot sleeker
    Arun V , Ashwathi , E,Sujithaa , S, Mothiesh , Maharika CJ
    International Journal Of Creative Research Thoughts (IJCRT) 12 (8), 169-173 , 2024
    2024.0
  • SWEEPEASE - A CUSTOMIZED ROBOT VACUUM FOR INDIVIDUALS WITH MOBILITY CHALLENGES
    AV Madhumitha G, Saktheeswari P, Keerthana Sathish
    International Journal Of Novel Research And Development 9 (3) , 2024
    2024.0
  • CROP RECOMMENDATION AND YIELD PREDICTION USING BEST MACHINE LEARNING PRACTICES
    AV Sneha M S , S N Vedhika , Guru Prasath N , Srivasthan V A
    INTERNATIONAL JOURNAL OF PROGRESSIVE RESEARCH IN ENGINEERING MANAGEMENT AND … , 2024
    2024.0
  • ENHANCING QUALITY OF LIFE: DESIGN AND IMPLEMENTATION OF AN INTEGRATED ASSISTIVE ROBOT FOR ELDERLY CARE
    AV Nivetha E , Shrinithi G R , Madhu Vadhini M
    International Journal Of Creative Research Thoughts 12 (4) , 2024
    2024.0
  • Design of long-term evolution based mobile edge computing systems to improve 5G systems
    V Arun, M Azhagiri
    2023 2nd International Conference on Edge Computing and Applications (ICECAA … , 2023
    2023.0
    Citations: 15
  • Review on Smart Shopping Carts using RFIDs, AI and IoT
    VASNVBM Shreemadhi B
    International Journal for Modern Trends in Science and Technology,, 49-51 , 2022
    2022.0
  • Deep learning hyper parameter optimization for video analytic in centralized system
    K Arun, V. , Bhattacharjee, S. , Khandelwal, R. , Malik
    International Journal of Engineering and Advanced Technology , 2019
    2019.0
  • E-voting using a decentralized ethereum application
    RV Arun, V. , Dutta, A. , Rajeev, S. , Mathew
    International Journal of Engineering and Advanced Technology , 2019
    2019.0
    Citations: 7
  • Emotion prediction using semantic analysis neural network
    PC Arun V, Vineeth R
    Journal of Advanced Research in Dynamical and Control Systems 11 (04) , 2019
    2019.0
  • Optimal Road Trip Planning with Hybrid Genetic Algorithm
    V Arun, H Pandey, H Badlani, RPS Sisodiya, A Sethi

MOST CITED SCHOLAR PUBLICATIONS

  • Design of long-term evolution based mobile edge computing systems to improve 5G systems
    V Arun, M Azhagiri
    2023 2nd International Conference on Edge Computing and Applications (ICECAA … , 2023
    2023.0
    Citations: 15
  • E-voting using a decentralized ethereum application
    RV Arun, V. , Dutta, A. , Rajeev, S. , Mathew
    International Journal of Engineering and Advanced Technology , 2019
    2019.0
    Citations: 7
  • Hybrid deep reinforcement learning and genetic algorithm-based resource allocation framework for edge computing
    V Arun, M Azhagiri
    Peer-to-Peer Networking and Applications 18 (6), 320 , 2025
    2025.0
    Citations: 2
  • Techno slot sleeker
    Arun V , Ashwathi , E,Sujithaa , S, Mothiesh , Maharika CJ
    International Journal Of Creative Research Thoughts (IJCRT) 12 (8), 169-173 , 2024
    2024.0
  • SWEEPEASE - A CUSTOMIZED ROBOT VACUUM FOR INDIVIDUALS WITH MOBILITY CHALLENGES
    AV Madhumitha G, Saktheeswari P, Keerthana Sathish
    International Journal Of Novel Research And Development 9 (3) , 2024
    2024.0
  • CROP RECOMMENDATION AND YIELD PREDICTION USING BEST MACHINE LEARNING PRACTICES
    AV Sneha M S , S N Vedhika , Guru Prasath N , Srivasthan V A
    INTERNATIONAL JOURNAL OF PROGRESSIVE RESEARCH IN ENGINEERING MANAGEMENT AND … , 2024
    2024.0
  • ENHANCING QUALITY OF LIFE: DESIGN AND IMPLEMENTATION OF AN INTEGRATED ASSISTIVE ROBOT FOR ELDERLY CARE
    AV Nivetha E , Shrinithi G R , Madhu Vadhini M
    International Journal Of Creative Research Thoughts 12 (4) , 2024
    2024.0
  • Review on Smart Shopping Carts using RFIDs, AI and IoT
    VASNVBM Shreemadhi B
    International Journal for Modern Trends in Science and Technology,, 49-51 , 2022
    2022.0
  • Deep learning hyper parameter optimization for video analytic in centralized system
    K Arun, V. , Bhattacharjee, S. , Khandelwal, R. , Malik
    International Journal of Engineering and Advanced Technology , 2019
    2019.0
  • Emotion prediction using semantic analysis neural network
    PC Arun V, Vineeth R
    Journal of Advanced Research in Dynamical and Control Systems 11 (04) , 2019
    2019.0
  • Optimal Road Trip Planning with Hybrid Genetic Algorithm
    V Arun, H Pandey, H Badlani, RPS Sisodiya, A Sethi