LOGESHWARAN R

@srmist.edu.in

Assistant Professor and Department of Data Science and Business Systems
SRM Institute of Technology

LOGESHWARAN R


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

EDUCATION

Currently Pursuing PhD in Underwater Communications and networks, Completed M.E in 2009 and B.E in 2007

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Networks and Communications, Ocean Engineering, Information Systems, Artificial Intelligence
11

Scopus Publications

67

Scholar Citations

4

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Empowering Communities Through Democratic Crowdfunding Decisions
    Arnav Shukla, Subhashree Choudhury, R. Logeshwaran
    Lecture Notes in Networks and Systems, 2026
  • Web-Based Real-Time Slouch Detection Using PoseNet and TensorFlow.js7
    Logeshwaran R, Gokulakrishnan M, M. Sindhuja
    2025 6th International Conference on Data Intelligence and Cognitive Informatics Icdici 2025, 2025
    Prolonged desk work and inadequate ergonomics in remote workspaces have produced substantial health problems linked to posture among students, software developers as well as digital workers and students. Slouching which people perform frequently leads to chronic back pain in addition to spinal misalignment and severe musculoskeletal disorders. Posture monitoring systems based on wearable devices and physical postureadjustment equipment tend to be too expensive while also posing discomfort and being difficult to use outside laboratory settings. The research develops an unobtrusive and instant slouch detection system through browser execution which utilizes PoseNet from TensorFlow.js. The system evaluates slouching posture through webcam body landmark analysis which compares nose position relative to shoulder and ear positions. Users can set how sensitive the system should be for determining slouching through calculation of the normalized vertical distance factor. The system alerts users through desktop notification after recognizing slouching postures. The system differs from conventional AI posture models because it performs its analyses within web browsers on clients' computers with no need for backend operations and no requirements for high-end hardware and app installations.
  • Hybrid Golden Eagle Optimization and Simulated Annealing (H-GEO-SA) for Efficient Resource Allocation in Edge Computing
    N. Jagadish Kumar, K. Rajkumar, G. Elangovan, M. Anand, R. Logeshwaran
    Advanced Metaheuristics for Scheduling in Distributed Manufacturing Systems, 2025
    The Hybrid Golden Eagle Optimization and Simulated Annealing (H-GEO-SA) algorithm provides an efficient method for resource allocation in edge computing. By combining the global exploration of Golden Eagle Optimization (GEO) with the local optimization of Simulated Annealing (SA), H-GEO-SA ensures comprehensive exploration and precise optimization. This hybrid approach facilitates dynamic resource allocation, enhances load balancing, and decreases energy consumption amidst variable workloads. In comparison to conventional optimization methods like Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Ant Colony Optimization (ACO), H-GEO-SA exhibits superior convergence speeds, improved system agility, and effective task allocation. Empirical evidence supports the algorithm's adaptability to real-time scenarios and its capability in minimizing latency and energy expenditure. In summary, H-GEO-SA emerges as a scalable and resilient optimization strategy for augmenting performance in contemporary edge computing systems.
  • FPGA Based AI Inference Accelerator for Low-End Embedded Systems
    S. Premalatha, R. NandhaKumar, T. Marthandan, R. Logeshwaran, P. Dharmasastha, K. Sivaperumal
    Proceedings 3rd International Conference on Artificial Intelligence and Machine Learning Applications Healthcare and Internet of Things Aimla 2025, 2025
    Aim: This research aims to develop a hardware accelerator to inference AI models for low-end embedded platforms using FPGAs as they are reconfigurable, have parallel and real-time processing capabilities and most importantly they consume very low power makes it best suited for low-end power constrained embedded platforms. In this paper we have implemented Handwritten Digit Classification based on MNIST dataset. Materials and Methods: In this research there are two groups. Group 1 refers to implementation in Raspberry Pi 4B and the power consumption, inference time and accuracy is compared with FPGA implementation. Group 2 refers to FPGA implementation of CNN based handwritten digit classification, where development is done using Xilinx ISE Design Suite and Vivado-HLS software and other softwares for training and quantizing the model. Result: The analysis of the performance comparison between raspberry pi and FPGA based implementation of the same model shows that FPGA based implementation is 14x times faster and 1.8x times power efficient than raspberry pi with negligible effect on accuracy. The FPGA took only 12.9% of total LUTs. Significance less than 0.001 Conclusion: The FPGA based neural network accelerator shows promising results in power efficiency and inference time makes it applicable for use with low-end embedded platforms and makes AI inference possible for them in real-time.
  • Analysis of Precoder Decomposition Algorithms for MIMO System Design
    S. Markkandan, R. Logeshwaran, N. Venkateswaran
    IETE Journal of Research, 2023
    Wireless communication over Multiple Input and Multiple Output (MIMO) channel achieve increased transmission rate by dividing the input stream into a multitude of parallel data streams which are transmitted in parallel. Precoding at the transmitter aims to decompose the channel into an uncorrelated multiple subchannels using the channel decomposition technique so that data streams will be sent in parallel independent subchannels. The proposed analysis is to analyze the performances of the MIMO precoder using various channel decomposition algorithms are compared and its computational complexity is analyzed. The channel decomposition schemes considered are Singular Value Decomposition, Geometric Mean Decomposition, LDLH, LU, Schur, QR and Jordan decomposition. The simulation and analytical results confirm that precoding for the MIMO channel decomposed by the QR scheme outperforms all the other precoding methods based on channel decomposition in the light of Bit Error Rate performance and involves a relatively lesser number of Floating Point Operations.
  • Optimum frequency selection for localization of underwater AUV using dynamic positioning parameters
    Logeshwaran Rajasekaran, Sakthivel Murugan Santhanam
    Microsystem Technologies, 2021
  • Experimental study and analysis of low frequency signal characteristics for UWA communication in bay of bengal
    R. Logeshwaran, S.Sakthivel Murugan
    4th IEEE Conference on Information and Communication Technology Cict 2020, 2020
    Underwater communication is a prominent research for undersea navigation, ocean investigation, and localize the automated underwater vehicles (AUVs). Acoustic communication is broadly utilized in underwater environments due to low attenuation (signal reduction) of sound in water. The implementation of underwater acoustic communication (UWAC) system design is challenging by major factors such as time-varying channel conditions, limited available bandwidth, diverse pressure conditions, huge Doppler spread, long propagation delay, and salinity. This work analyzes the frequency for signal transmission to enhance the coverage and connectivity between the sensor AUVs which are in observation under secluded ocean contour. Experimental studies have been conducted in the Bay of Bengal, India. The results are presented for different frequencies and the region of optimal frequencies with respect to depth is formulated which can be much suitable for AUVs and Submarine communications.
  • Performance analysis of cluster head selection routing protocol in underwater acoustic wireless sensor network
    P. Rajalakshmi, R. Logeshwaran
    2nd International Conference on Electronics and Communication Systems Icecs 2015, 2015
    Underwater communication has become a popular research area because of many applications such as oceanography data collection, ocean exploration, undersea navigation, and control of autonomous underwater vehicles (AUVs). Since electromagnetic wave communication does not propagate well in underwater, long communication ranges are only possible through the use of acoustic waves. Acoustic communication is the most versatile and widely used technique in underwater environments due to the low attenuation (signal reduction) of sound in water. Underwater acoustic communication is a technique of sending and receiving message below water. The implementation of underwater acoustic communication (UWAC) system is rendered challenging by factors such as limited available bandwidth, throughput, long propagation delay, large Doppler spread, and time-varying channel conditions. From this limitation in underwater wireless networks, throughput is one of the main parameter will be affected. Based on network structure, routing protocols in Underwater Communication Networks can be divided into two categories: flat routing and hierarchical or clustering routing. Due to a variety of advantages, clustering is suitable an active branch of routing technology in underwater communication Networks. Based on these findings, to developing cluster based routing protocol is designed to improve the throughput of the network by considering connectivity and coverage.
  • Performance analysis of cdma technique in underwater acoustic wireless communication
    International Journal of Applied Engineering Research, 2015
  • Development of cluster based routing protocol in slow moving autonomous underwater vehicles
    International Journal of Applied Engineering Research, 2015
  • Performance study on the suitability of reed solomon codes in WiMAX
    R. Logeshwaran, I.Joe Louis Paul
    2010 International Conference on Wireless Communication and Sensor Computing Icwcsc 2010, 2010

RECENT SCHOLAR PUBLICATIONS

  • Hybrid Golden Eagle Optimization and Simulated Annealing (H-GEO-SA) for Efficient Resource Allocation in Edge Computing
    NJ Kumar, K Rajkumar, G Elangovan, M Anand, R Logeshwaran
    Advanced Metaheuristics for Scheduling in Distributed Manufacturing Systems … , 2026
    2026.0
  • Empowering Communities Through Democratic Crowdfunding Decisions
    A Shukla, S Choudhury, R Logeshwaran
    International Conference on ICT for Sustainable Development, 339-348 , 2025
    2025.0
  • Analysis of precoder decomposition algorithms for MIMO system design
    S Markkandan, R Logeshwaran, N Venkateswaran
    IETE Journal of Research 69 (6), 3398-3405 , 2023
    2023.0
    Citations: 34
  • Underwater Cognitive Acoustic Networks Architecture, Development and Deployment
    SMS Logeshwaran R, Balaji K
    International Journal of Next-Generation Computing 13 (2), 1-17 , 2022
    2022.0
  • Optimum frequency selection for localization of underwater AUV using dynamic positioning parameters
    L Rajasekaran, SM Santhanam
    Microsystem Technologies 27 (12), 4291-4303 , 2021
    2021.0
    Citations: 7
  • Experimental Study and Analysis of Low Frequency Signal Characteristics for UWA Communication in Bay of Bengal
    R Logeshwaran, SS Murugan
    2020 IEEE 4th Conference on Information & Communication Technology (CICT), 1-10 , 2020
    2020.0
    Citations: 1
  • Performance analysis of cluster head selection routing protocol in underwater acoustic wireless sensor network
    P Rajalakshmi, R Logeshwaran
    2015 2nd International Conference on Electronics and Communication Systems … , 2015
    2015.0
    Citations: 8
  • Robust Cross Layer Design for Cognitive MIMO Ad Hoc Network for Optimal Resource Allocation
    S Mugunthan, R Logeshwaran
    International Journal of Engineering Innovations and Research 2 (2), 144 , 2013
    2013.0
  • Performance study on the suitability of Reed Solomon Codes in WiMAX
    R Logeshwaran, IJL Paul
    2010 International Conference on Wireless Communication and Sensor Computing … , 2010
    2010.0
    Citations: 17
  • Development of Cluster Based Routing Protocol in Underwater Acoustic Wireless Network
    P Rajalakshmi, R Logeshwaran

MOST CITED SCHOLAR PUBLICATIONS

  • Analysis of precoder decomposition algorithms for MIMO system design
    S Markkandan, R Logeshwaran, N Venkateswaran
    IETE Journal of Research 69 (6), 3398-3405 , 2023
    2023.0
    Citations: 34
  • Performance study on the suitability of Reed Solomon Codes in WiMAX
    R Logeshwaran, IJL Paul
    2010 International Conference on Wireless Communication and Sensor Computing … , 2010
    2010.0
    Citations: 17
  • Performance analysis of cluster head selection routing protocol in underwater acoustic wireless sensor network
    P Rajalakshmi, R Logeshwaran
    2015 2nd International Conference on Electronics and Communication Systems … , 2015
    2015.0
    Citations: 8
  • Optimum frequency selection for localization of underwater AUV using dynamic positioning parameters
    L Rajasekaran, SM Santhanam
    Microsystem Technologies 27 (12), 4291-4303 , 2021
    2021.0
    Citations: 7
  • Experimental Study and Analysis of Low Frequency Signal Characteristics for UWA Communication in Bay of Bengal
    R Logeshwaran, SS Murugan
    2020 IEEE 4th Conference on Information & Communication Technology (CICT), 1-10 , 2020
    2020.0
    Citations: 1
  • Hybrid Golden Eagle Optimization and Simulated Annealing (H-GEO-SA) for Efficient Resource Allocation in Edge Computing
    NJ Kumar, K Rajkumar, G Elangovan, M Anand, R Logeshwaran
    Advanced Metaheuristics for Scheduling in Distributed Manufacturing Systems … , 2026
    2026.0
  • Empowering Communities Through Democratic Crowdfunding Decisions
    A Shukla, S Choudhury, R Logeshwaran
    International Conference on ICT for Sustainable Development, 339-348 , 2025
    2025.0
  • Underwater Cognitive Acoustic Networks Architecture, Development and Deployment
    SMS Logeshwaran R, Balaji K
    International Journal of Next-Generation Computing 13 (2), 1-17 , 2022
    2022.0
  • Robust Cross Layer Design for Cognitive MIMO Ad Hoc Network for Optimal Resource Allocation
    S Mugunthan, R Logeshwaran
    International Journal of Engineering Innovations and Research 2 (2), 144 , 2013
    2013.0
  • Development of Cluster Based Routing Protocol in Underwater Acoustic Wireless Network
    P Rajalakshmi, R Logeshwaran