Dr S A Kalaiselvan

@stpetershyd.com

Professor & Department of Computer Science and Engineering
St Peters Engineering College

Dr S A Kalaiselvan


                  Download Compact PDF  
https://researchid.co/kalaiselvanresearch
Sivalingam Ambigapthi Kalaiselvan currently works at the Department of Computer Science and Engineering, Engineering College (NAAC A & UGC-Autonomous), Hyderabad. Kalaiselvan does research in Computer Communications (Networks) and Fine Automata Theory(WSN). Their current project is 'Under Water

EDUCATION

B.E(CSE), M.E(CSE), PhD(CSE)

RESEARCH INTERESTS

Network Communication, Wireless Sensor Networks, Optimization Algorithms, Sensor Networks, Routing Protocols, ACO, UWSN
36

Scopus Publications

Scopus Publications

  • Project OG: A Framework for Personalized 3D Organ Generation with Biomaterial Formulation for Bioprinting
    A M D Arun Balaji, A Sowmiyan, S A Kalaiselvan
    Proceedings of 2nd International Conference on Multi Agent Systems for Collaborative Intelligence Icmsci 2026, 2026
    This document describes a method for optimizing patient-specific bioinks for 3D bioprinting of organs using Machine Learning techniques (Random Forests) and Marching Cubes for Reconstruction of Patient-Specific Data (CT/MRI) to achieve optimal bioink formulations for each organ based on a patient's CT/MRI scan. The process consists of four steps: Collecting patient data, Converting to CAD Models (With volumetric and vascularity density fidelity of DRC and VDC respectively), Optimizing bioink formulations, Printing the organ using Controlled Maturation and Vascularization. Marching Cubes is able to create models with significantly greater accuracy and Speed than threshold-based approaches, allowing for sub-millimeter CAD models that are necessary for making organs with vascularity. The Random Forest models bioink formulations for an organ by mapping bioink formulation variables and rheological properties against the VIT and BI product characteristics and performance metrics of the bioprinted organ. The constructs currently made with this technology have been shown to replicate 90-93% of the unique anatomical characteristics of the organ, making them useful for surgical planning, research and drug testing. The main challenge to a successful transplant using this technology is the retention of cell viability after 3D Printing. Future research should emphasize creating the desired Vascular Patterns to achieve Aged / Matured cells and understanding Regulatory pathways.
  • Region Based Cluster Aided Routing Protocol for Environment Monitoring in Heterogeneous Wireless Sensor Networks
    Saritha Mahankali, R. Kesavan, S. A. Kalaiselvan
    Journal of Advanced Research in Applied Sciences and Engineering Technology, 2025
    Heterogeneous wireless sensing networks (HWSNs) that are limited by their batteries' power consumption might benefit greatly from more efficient routing algorithms. It is essential that routing accounts for the diversity of network nodes to achieve optimal performance. This letter considers sensor nodes with random initial energies and random disparities in data output rate (traffic) to build a realistic clustering-based WSN suitable for heterogeneous sensing applications. The protocol divides the space into numerous zones with different distance thresholds to deal with the hotspot problem that the multi-hop method creates. The advantages of region-divided routing ensure that only qualified nodes compete for the role of cluster's head during the choice phase and that the cluster heads with the greatest remaining energy in the extremely energetic area are selected as the relay node throughout the inter-cluster routing that includes several hops phase. The simulation findings demonstrate that the protocol may efficiently equalize energy consumption throughout the network, eliminate the issue of "hot spots," be used in an energy-diverse system, and lengthen the service life of the network.
  • Node Position Estimation and Coverage Hole Detection in Wireless Sensor Networks Using Clustering-Guided Twin Contrastive Learning with Meerkat Optimization Algorithm
    Saritha Mahankali, R. Kesavan, S.A. Kalaiselvan
    2025 International Conference on Networks and Cryptology Netcrypt 2025, 2025
    Multiple deployment scenarios exist where Wireless Sensor Networks (WSNs) serve as important elements for environmental surveillance and emergency response and medical infrastructure monitoring. Traditional node position estimating approaches along with coverage hole detection instruments make networks unreliable in performance terms. GPS-based localization methods demonstrate shortcomings due to high resource allocation and limited benefits for battery-constrained sensor nodes. Traditional coverage hole detection methods that use static models show poor performance during network dynamics because node failures alongside mobility result in reduced monitoring accuracy. The investigation leads to the development of a novel framework that unites optimization approaches with machine learning algorithms to handle present challenges. With the Crayfish Optimization Algorithm the exact positioning of nodes enables the precise detection of edge nodes throughout the network. Through a Clustering-Guided Twin Contrastive Learning (CG-TCL) protocol network voids become detectable through the discovery process which processes network spatial and contextual behavior patterns. After MOA optimization of CG-TCL models practitioners experience both enhanced calculation speed along with improved predictive accuracy. The framework achieves superior detection of node positions along with coverage holes while maintaining 99.9% precise performance to enhance both WSN reliability and scalability and environmental adaptability.
  • Data Classification Using Sardine Optimized Adversarial Generative Quaternion Network with Fibonacci Q-Matrix Hyperchaotic Encryption Schemes in Cloud
    Kooragayala Sukeerthi, R. Kesavan, S.A. Kalaiselvan
    2025 International Conference on Networks and Cryptology Netcrypt 2025, 2025
    In the era of cloud computing sensitive information management requires data classification to function securely across all industries. A protected framework for cloud-based data analytics with privacy preservation emerges through integrating sophisticated encryption techniques with neural networks. The need to protect data grows increasingly critical because organizations must specify precise performance measures as well as classification accuracy metrics. The developing thrilling cybersecurity and cloud data disclosure world continues to inspire many trailblazing privacy protection solutions that leap forward unimpeded. The research proposes and builds a new framework called AS-FiQ-AgQN, which fuses adaptive optimization with advanced encryption and secure classification. The framework secures data confidentiality by employing Fibonacci Q-Matrix Hyperchaotic Encryption. Data classification on the encrypted data is performed using Adversarial generative Quaternion Network which is further optimized using Adaptive Sardine Optimization for better performance of the network. Performances have proven to yield astonishing results, with accuracy above 99.5 %, precision of 99.3 %, and recall above 99.7 %, which affirms the efficiency with which the system operates. Through these evaluations researchers confirm the framework's success in both precise data categorization while ensuring encryption safety at the cloud level. Data classification based on AS-FiQ-AgQN produces a robust secure system to protect privacy that enables accurate predictive cloud analytics with reliable data protection.
  • Energy-Aware Routing and Data Transmission in Underwater Wireless Sensor Networks via Optimized Progressive Feedback Cascaded Visual Cosine CNN
    Aruna Gayatri Kodukulla, M. Amanullah, S A Kalaiselvan
    Proceedings of 5th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2025, 2025
    Underwater Wireless Sensor Networks (UWSNs) facilitate communication between deep-sea sensor nodes and surface sinks, which is essential for marine research, environmental monitoring, and surveillance. However, efficient and reliable communication is challenged by harsh underwater environments and limited resources. UWSNs suffer from high energy consumption, unstable links, and reduced transmission accuracy due to limited bandwidth, node mobility, and acoustic channel impairments. Traditional routing and transmission techniques often fail to strike a balance between energy efficiency and reliability, creating a strong need for intelligent, adaptive, and robust optimization methods. This paper proposes a novel energy-efficient framework that integrates the Fishier Mantis Optimization Algorithm (FMOA) for routing, the Progressive Feedback Cascaded Visual Cosine Convolutional Neural Network (PFCVCCNN) for data transmission, and the Sharpbelly Fish Optimization (SFO) for parameter fine-tuning. Simulation results show that the proposed framework achieves lower EC (2.5 J), higher PDR (94%), reduced PLR (6%), and superior TA (99.12%) compared to existing protocols. The integration of FMOA, PFCVCCNN, and SFO provides a scalable, adaptive, and reliable solution for energy-efficient communication in UWSNs, significantly enhancing network lifetime and data delivery performance under challenging underwater conditions.
  • QoS-Aware Resilient Routing Protocols Leveraging Cosine Similarity-Centric Convolutional Neural Network for WSN-Assisted IoT Using Clustering Techniques
    B. Swathi, M. Amanullah, S.A. Kalaiselvan
    2025 International Conference on Networks and Cryptology Netcrypt 2025, 2025
    The Wireless Sensor Networks integrated with Internet of Things (WSN-IoT) serve as the backbones of such applications as smart cities, health monitoring, and environmental monitoring requiring high efficiency and secure communication for Quality of Service (QoS). However, an important challenge has been in routing in dynamic WSN-IoT systems ensuring energy-efficient resilient and QoS-aware operations. This research addresses the issues of hotspot formation, energy depletion, and secure data transmission in clustered WSN-IoT networks. The requirement for robust scalable routing protocols able to maintain QoS requirements even in dynamic environments drives the motivation to develop new protocols. The proposed “QoS-Aware Resilient Routing Protocols leveraging Cosine Similarity-Centric Convolutional Neural Network for WSN-assisted IoT Using Clustering Techniques” (Ski-CSC2-A2O), leverages a Bi-Concentric Hexagonal network structure with mobile sink assistance for energy-efficient data collection. The Skill Optimization Algorithm optimizes clustering which results in balanced power consumption while identifying optimal Cluster Heads. Secure and QoS-aware routing is achieved through a Cosine SimilarityCentric Convolutional Neural Network, while network parameters are fine-tuned using Aphid Ant Optimization. Simulation results demonstrate the effectiveness of the proposed protocol, achieving a Packet Delivery of 99.3%, throughput of 99.6%, and an extended network lifetime surpassing 99.4% of baseline approaches, even with large packet sizes and increased transmission rounds. The Ski-CSC2-A2O protocol provides WSN-IoT systems with highly efficient secure solutions through its capabilities to ensure energy efficiency robust performance QoS while functioning ideally in real-time IoT applications.
  • Predictive Analytics and Recommendation Systems in Banking
    Sowmiya Lakshmee L, Kalaiselvan Sivalingam Ambigapathi, Jagadish M, Abishek A
    Proceedings of the 2025 11th International Conference on Communication and Signal Processing Iccsp 2025, 2025
    The banking industry has undergone a paradigm shift with the rise of artificial intelligence (AI) predictive analytics and recommendation systems. Artificial intelligence, machine learning, and natural language processing are revolutionizing financial services — they allow for real-time fraud detection, tailored financial product recommendations, and consumer segmentation. Banking Sector: The Impact of Machine Learning Algorithms on Customer Engagement, Risk Management and Decision Making. The study aligns with a hybrid recommendation model and a supervised fraud detection system to optimize banking operations. Customer segmentation using clustering-based methods increases personalization, and predictive analytics have shown improved fraud detection accuracy at 92% using random forest classifiers. These developments enhance customer experience, mitigate financial risks, and increase profitability.
  • Secure and Efficient Urban Parking Solution: A Blockchain-Integrated Smart Parking Management System
    S A Kalaiselvan, R. Kesavan, V.Sivaraman, K.T.Anand, C.Jehan, S.Sangeetha
    Proceedings of 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things Icoici 2025, 2025
    In increasing limited space and congestion, the parking vehicle management is important in the smart cities. The existing method often fails in smart parking solutions such as security, and energy efficiency. The suggested Smart Parking Management System enhances user experience, security, and parking efficiency in order to address this issue. This proposed system begins with registering and authenticating the user via mobile app and user accounts are secured. To analyse the real-time availability of spaces, the sensors in the parking zone employed to found the whether the spaces or occupied or available. Before sending the collected sensor data to the cloud for safe blockchain storage, it first pre-processed to remove irrelevant information. Afterthought, booking the parking area the smart contracts is taken care of payments for ensuring the smooth transaction process. Flowingly, parking assignments using dynamic space allocation algorithms using Reinforcement methods based on the past data and user behavior. The user data protection and unauthorised used activity is detected using federated learning method and multi-factor security methods. Users get notifications when spots become available, and the system continuously learns to enhance the upcoming parking experiences. The advanced smart parking management system gradually improves the user satisfaction. Overall this innovative method surpasses the existing methods in the light of effectiveness, security, and a sustainable urban environment.
  • Energy-efficient and fault-tolerant routing mechanism for WSN using optimizer based deep learning model
    B. Swathi, Dr. M. Amanullah, S.A. Kalaiselvan
    Sustainable Computing Informatics and Systems, 2024
  • PACKET SIZE AND MOBILITY AWARE CLUSTER BASED ROUTING MECHANISM FOR WIRELESS SENSOR NETWORKS
    Journal of Environmental Protection and Ecology, 2024
  • Node Coverage and Connectivity Optimization in Heterogeneous Wireless Sensor Networks Using Improved Flower Pollination Algorithm
    Saritha Mahankali, R. Kesavan, S.A. Kalaiselvan
    Proceedings of the 4th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2024, 2024
  • HOP COUNT BASED EKF ALGORITHM AND AUV BASED ROUTING IN UNDERWATER WIRELESS SENSOR NETWORKS
    Journal of Environmental Protection and Ecology, 2024
  • Multi-Keywords Based Fully Homomorphic Encryption and Data Classification for Cloud Security and Privacy
    Kooragayala Sukeerthi, R. Kesavan, S.A. Kalaiselvan
    2024 IEEE 2nd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2024, 2024
  • KNN-BASED SENSITIVITY CLASSIFICATION AND HOMOMORPHIC ENCRYPTION FOR CLOUD SECURITY AND PRIVACY
    Journal of Environmental Protection and Ecology, 2024
  • Virtual Zone Construction for Clustering Process in Mobile Wireless Sensor Networks
    B. Swathi, M. Amanullah, S.A. Kalaiselvan
    2024 IEEE 2nd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2024, 2024
  • Optimizing AUV Positioning and Data Transmission with Actor Critic (A3C) Algorithm in Underwater Wireless Sensor Networks
    Aruna Gayatri Kodukulla, M. Amanullah, S A Kalaiselvan
    Proceedings of the 4th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2024, 2024
  • Blockchain Powered Carbon Credit Marketplace
    S.A Kalaiselvan, J.S Prasanna Venkatesh, A.M Vasanth Kumar, K Raghul Karthik
    Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024
  • AFHO-DL: Enhancing Energy Efficiency through Resource Allocation AI-enabled WSNs and IoT Integration
    S A Kalaiselvan, J. Manoranjini, S. Hemalatha, M. Lenin Kumar
    2024 3rd International Conference on Electrical Electronics Information and Communication Technologies Iceeict 2024, 2024
  • Advancing Underwater Communication with NBO-MFO Hybrid Routing in UWSNs
    S.A. Kalaiselvan, M.Lenin Kumar, M. Amanullah, T.R. Mani Chigurupati
    Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024
  • Trajectory-Driven Efficiency: An Energy-Efficient Opportunistic Routing Protocol for Industrial IoT Wireless Sensor Networks
    G. Govinda Rajulu, M. Murugesan, S.K. Mahaboog Basha, S.A. Kalaiselvan, M. Lenin Kumar
    Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024
  • Revolutionizing Financial Cloud Services: AI and Blockchain-driven Resource Allocation for Maximized Transaction Speed and Security
    M. Lenin Kumar, M. Amanullah, Revatthy Krishnamurthy, N. Mohana Suganthi, S.A. Kalaiselvan
    2024 3rd International Conference on Electrical Electronics Information and Communication Technologies Iceeict 2024, 2024
  • Congestion Control Routing Scheme for WSN using AI Technologies
    SK Mahaboob Basha, E. Gurumoorthi, E. Mercy Beulah, R. Kesavan, S.A. Kalaiselvan, Lenin Kumar
    2024 3rd International Conference on Electrical Electronics Information and Communication Technologies Iceeict 2024, 2024
  • RETRACTION:Enhancing QoE predictions with complex neural networks and diverse datasets
    S.K. Mahaboob Basha, S.A. Kalaiselvan
    Journal of Intelligent and Fuzzy Systems, 2023
  • AN EXPERIMENTAL INVESTIGATION BASED ON SERVICES OF VIDEO STREAMING USING DEEP NEURAL NETWORK FOR CONTINUOUS QOE PREDICTION
    Journal of Theoretical and Applied Information Technology, 2023
  • PREDICTION OF AUTO-DETECTION FOR TRACKING OF SUB-NANO SCALE PARTICLE IN 2D AND 3D USING SVM-BASED DEEP LEARNING
    Journal of Theoretical and Applied Information Technology, 2023
  • A Detailed Study on Security and Privacy Analysis and Mechanisms in Cloud Computing
    Kooragayala Sukeerthi, R. Kesavan, S. A. Kalaiselvan
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • A Study and Analysis of Energy Efficient Parameters and Protocols in Energy Efficiency in Wireless Sensor Networks
    B. Swathi, M. Amanullah, S. A. Kalaiselvan
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • A Review of Cluster based Routing Protocols in Heterogeneous Wireless Sensor Networks
    Saritha Mahankali, R. Kesavan, S. A. Kalaiselvan
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • COMPARISON ON VIDEO STREAMING INTERVENTION ON NEURAL NETWORK QOE PROBLEM STATEMENT TECHNIQUE
    SK. Mahaboob Basha, C. Parthasarathy, S. A. Kalaiselvan, J. Senthil Murugan
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • Hybrid Optimized Energy Efficient Routing Protocol for Underwater Acoustic Sensor Networks Based on Grey Wolf and Bat Algorithms
    S.A. Kalaiselvan, R. Kesavan, Somasundaram, E. Gurumoorthi
    2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
  • An intricate spectrogram processing in speech enhancement using machine learning with cloud computing
    Yenna Geetha Reddy, G Mahendran, Ameer Al-Khaykan, Omar A. Alkawak, S. A. Kalaiselvan, A. Priya
    Proceedings of the IEEE International Conference Image Information Processing, 2023
  • A multimodal biometric authentication scheme based on feature fusion for improving security in cloud environment
    Teena Joseph, S. A. Kalaiselvan, S. U. Aswathy, R. Radhakrishnan, A. R. Shamna
    Journal of Ambient Intelligence and Humanized Computing, 2021
  • An efficient technique in bio engineering for FMMS with effective data communication in UWSN
    International Journal of Control Theory and Applications, 2016
  • Location verification based neighbor discovery for shortest routing in underwater acoustic sensor network
    Advances in Environmental Biology, 2015
  • UDRPG: Dynamic key management based node authentication for secret communication in MANET
    G. Venkata Swaroop, G. Murugaboopathi, S. A. Kalaiselvan
    2014 International Conference on Science Engineering and Management Research Icsemr 2014, 2014
  • An energy-efficient routing protocol for UASN by AFISHS optimization algorithm
    International Journal of Applied Engineering Research, 2014