K. Balamurugan
Research Subjects
K. Balamurugan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Karthikeyan Velayuthapandian
Department of ECE, Mepco Schlenk Engineering College, Sivakasi, India
2 shared publications - Lakshmana Rao Namamula
information technology, Institute of Public Administration and Management, tower hill, Freetown, SIERRA LEONE
2 shared publications - M. Vijayaraj
Department of ECE, Government College of Engineering Tirunelveli, Tirunelveli District, India
2 shared publications Manickam Ramasamy
Department of EEE, FETBE, UCSI University, Kuala Lumpur, Malaysia
2 shared publicationsS. Suja Priyadharsini
Department of ECE, Anna University Regional Campus-Tirunelveli, Tirunelveli, Palayamkottai, India
2 shared publicationsV. Karthikeyan
Department of ECE, Kalasalingam Institute of Technology, Virudhunagar, Krishnankoil, India
2 shared publications
Latest Publications
- Open Access
- 5 October 2025
- Published by Anapub Publications in Journal of Machine and Computing
- p. 2513-2529
Bio Inspired Adaptive Control Mechanisms in Mechatronic Systems Using Multi Objective Evolutionary Deep Learning Optimization Techniques
The use of robotic arms in mechatronic systems is quite common because of their precision and adaptability uses, but the control of such nonlinear and dynamic systems has been an uphill task because of the presence of uncertainties and external disturbances. In this regard, the proposed study will solve the mentioned problems by designing an effective adaptive control approach to improve the accuracy of trajectory tracking, the system energy consumption, and stability. The novelty of this study is to incorporate Echo State Network (ESN) with a hybrid met heuristic algorithm, which consists of Harris Hawks Optimisation (HHO) and Reptile Search Algorithm (RSA) to tune the important parameters of ESN, such as spectral radius, leakage rate and scaling of input. The described ESN-RSA-HHO framework will have a closed-loop architecture that will produce optimised torque commands to provide robust control of a 2-DOF robotic arm that operates under different operation conditions. Simulation has revealed that the ESN-RSA-HHO controller produces a root mean square tracking error of 0.012 rad, an energy saving of 28 per cent and an overshoot of 2.8 per cent, which is entirely better than the traditional PID control and LSTM-based control, as well as the non-optimised ESN models. The convergence behaviour and phase plane plot prove that the system can continue to be stable in even disturbed cases. The results confirm the efficiency of the suggested adaptive robot control framework and allow noting its future use in the mechatronic sphere.
- 5 October 2025
- Published by Anapub Publications in Journal of Machine and Computing
- p. 2513-2529
Open AccessBio Inspired Adaptive Control Mechanisms in Mechatronic Systems Using Multi Objective Evolutionary Deep Learning Optimization Techniques
The use of robotic arms in mechatronic systems is quite common because of their precision and adaptability uses, but the control of such nonlinear and dynamic systems has been an uphill task because of the presence of uncertainties and external disturbances. In this regard, the proposed study will solve the mentioned problems by designing an effective adaptive control approach to improve the accuracy of trajectory tracking, the system energy consumption, and stability. The novelty of this study is to incorporate Echo State Network (ESN) with a hybrid met heuristic algorithm, which consists of Harris Hawks Optimisation (HHO) and Reptile Search Algorithm (RSA) to tune the important parameters of ESN, such as spectral radius, leakage rate and scaling of input. The described ESN-RSA-HHO framework will have a closed-loop architecture that will produce optimised torque commands to provide robust control of a 2-DOF robotic arm that operates under different operation conditions. Simulation has revealed that the ESN-RSA-HHO controller produces a root mean square tracking error of 0.012 rad, an energy saving of 28 per cent and an overshoot of 2.8 per cent, which is entirely better than the traditional PID control and LSTM-based control, as well as the non-optimised ESN models. The convergence behaviour and phase plane plot prove that the system can continue to be stable in even disturbed cases. The results confirm the efficiency of the suggested adaptive robot control framework and allow noting its future use in the mechatronic sphere.
- 13 March 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (31) , 38927-38957
Attention-based multi dimension fused-feature convolutional neural network framework for speaker recognition
- 13 March 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (31) , 38927-38957
Attention-based multi dimension fused-feature convolutional neural network framework for speaker recognition
- RetractionOpen Access
- 21 May 2024
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 27 (2) , 307
Retraction Note: Speaker identification using hybrid neural network support vector machine classifier
- 21 May 2024
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 27 (2) , 307
RetractionOpen AccessRetraction Note: Speaker identification using hybrid neural network support vector machine classifier
- Open Access
- 1 May 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (5)
Optical response and temperature shielding coatings using tri-layer structure composed of titania/silica/titania
The fabrication of metamaterials with inspiration from nature paved the door for the creation of revolutionary passive and active devices. Butterfly wings are one of them, and their multilayered structure motivated nanotechnologists, physicists, and other optoelectronic and photonic engineers to develop photonic crystals, dielectric reflectors, and Bragg reflectors for use in visible light communication, solar cells, and other photonic and optoelectronic applications. We report the sol–gel spin coating of a dielectric reflector on the glass substrate, an optical passive component consisting of titania and silica thin films for infrared radiation reflection. Individual thin films of titania and silica on glass substrates were studied using an x-ray diffractometer, which indicated anatase of titania and the amorphous nature of silica at a Bragg angle of 25° with a sharp and wide peak, respectively. The multilayer structure of titania/silica/titania was further investigated using Fourier transform infrared spectroscopy, which revealed the presence of Ti–O–Ti and Si–O–Si vibrational bonds at wavenumbers 546 and 973 cm−1, respectively, as well as the presence of Ti–O–Si vibrational bond at 1100 cm−1. The thickness of the multilayer titania/silica/titania was measured using a cross-sectional field emission scanning electron microscope (FESEM) and found to be 160/240/160 nm, respectively. Finally, reflection investigation on the multilayer structure using ultraviolet–visible–near-infrared spectroscopy validated the reflection of the infrared spectrum area by around 70% and showed to be beneficial for temperature shielding applications on glass furnishings.
- 1 May 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (5)
Open AccessOptical response and temperature shielding coatings using tri-layer structure composed of titania/silica/titania
The fabrication of metamaterials with inspiration from nature paved the door for the creation of revolutionary passive and active devices. Butterfly wings are one of them, and their multilayered structure motivated nanotechnologists, physicists, and other optoelectronic and photonic engineers to develop photonic crystals, dielectric reflectors, and Bragg reflectors for use in visible light communication, solar cells, and other photonic and optoelectronic applications. We report the sol–gel spin coating of a dielectric reflector on the glass substrate, an optical passive component consisting of titania and silica thin films for infrared radiation reflection. Individual thin films of titania and silica on glass substrates were studied using an x-ray diffractometer, which indicated anatase of titania and the amorphous nature of silica at a Bragg angle of 25° with a sharp and wide peak, respectively. The multilayer structure of titania/silica/titania was further investigated using Fourier transform infrared spectroscopy, which revealed the presence of Ti–O–Ti and Si–O–Si vibrational bonds at wavenumbers 546 and 973 cm−1, respectively, as well as the presence of Ti–O–Si vibrational bond at 1100 cm−1. The thickness of the multilayer titania/silica/titania was measured using a cross-sectional field emission scanning electron microscope (FESEM) and found to be 160/240/160 nm, respectively. Finally, reflection investigation on the multilayer structure using ultraviolet–visible–near-infrared spectroscopy validated the reflection of the infrared spectrum area by around 70% and showed to be beneficial for temperature shielding applications on glass furnishings.
- Open Access
- 13 October 2023
- Published by IOP Publishing in Engineering Research Express
- Vol. 5 (4) , 045017
Development of SRAM-APB protocol interface and verification
The purpose of this mechanism is to enhance the chip’s internal connections and read/write memory capabilities. The Advanced Microcontroller Bus Architecture (AMBA) is one such shared bus that uses static random-access memory to achieve this goal. As a result, it’s important to weigh a variety of design options before diving into the Verilog description. It’s also important to remember that the system must be designed to accommodate a large number of interoperable modules and memories. The design, on the other hand, starts with fewer modules and a less complicated description and realisation that relies on memory access. ModelSim is used to simulate after the delay has been modelled in Verilog. Since the interface’s static random-access memory uses an APB protocol, its performance may be tested at this stage. In addition, Questasim employs verification modules and System Verilog technologies to guarantee the system’s operation. From the obtained results, the Direct Memory Access (DMA) with SRAM-APB outperforms the alternatives, particularly in frame transmission schemes, with a wire efficiency that is 1.4 times higher and a dynamic energy efficiency that is nearly twice as high as those of conventional configurations.
- 13 October 2023
- Published by IOP Publishing in Engineering Research Express
- Vol. 5 (4) , 045017
Open AccessDevelopment of SRAM-APB protocol interface and verification
The purpose of this mechanism is to enhance the chip’s internal connections and read/write memory capabilities. The Advanced Microcontroller Bus Architecture (AMBA) is one such shared bus that uses static random-access memory to achieve this goal. As a result, it’s important to weigh a variety of design options before diving into the Verilog description. It’s also important to remember that the system must be designed to accommodate a large number of interoperable modules and memories. The design, on the other hand, starts with fewer modules and a less complicated description and realisation that relies on memory access. ModelSim is used to simulate after the delay has been modelled in Verilog. Since the interface’s static random-access memory uses an APB protocol, its performance may be tested at this stage. In addition, Questasim employs verification modules and System Verilog technologies to guarantee the system’s operation. From the obtained results, the Direct Memory Access (DMA) with SRAM-APB outperforms the alternatives, particularly in frame transmission schemes, with a wire efficiency that is 1.4 times higher and a dynamic energy efficiency that is nearly twice as high as those of conventional configurations.
- Retracted
- 30 November 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (4) , 1041-1053
RETRACTED ARTICLE: Speaker identification using hybrid neural network support vector machine classifier
- 30 November 2022
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 25 (4) , 1041-1053
RetractedRETRACTED ARTICLE: Speaker identification using hybrid neural network support vector machine classifier
- Open Access
- 1 February 2022
- Published by IOP Publishing in Journal of Physics Communications
- Vol. 6 (2) , 022001
Roadmap for machine learning based network-on-chip (M/L NoC) technology and its analysis for researchers
A few decades ago, communication inside the chip is done by transferring signals between the cores. This conventional method is not worthy because of the increase in latency and power consumption. To rectify this issue Network-on-Chip (NoC) technology has emerged. NoC technology is invented to transfer data packets instead of signals. Machine Learning NoC (M/LNoC) is a very fast-growing technology in today’s Integrated Circuit world for the communication between Intellectual property (IP) cores. The machine learning algorithms are used in the existing and emerging novel NoCs. In this paper, various evolving NoC technologies to decrease the transfer latency, power consumption of the IC is addressed for the implementation of the machine learning algorithm. The NoCs working with machine learning algorithms are called M/L NoC. We also provided the security issues to be focused- on in the M/L NoC. Also, we have provided the available NoC tools for the NoC researchers.
- 1 February 2022
- Published by IOP Publishing in Journal of Physics Communications
- Vol. 6 (2) , 022001
Open AccessRoadmap for machine learning based network-on-chip (M/L NoC) technology and its analysis for researchers
A few decades ago, communication inside the chip is done by transferring signals between the cores. This conventional method is not worthy because of the increase in latency and power consumption. To rectify this issue Network-on-Chip (NoC) technology has emerged. NoC technology is invented to transfer data packets instead of signals. Machine Learning NoC (M/LNoC) is a very fast-growing technology in today’s Integrated Circuit world for the communication between Intellectual property (IP) cores. The machine learning algorithms are used in the existing and emerging novel NoCs. In this paper, various evolving NoC technologies to decrease the transfer latency, power consumption of the IC is addressed for the implementation of the machine learning algorithm. The NoCs working with machine learning algorithms are called M/L NoC. We also provided the security issues to be focused- on in the M/L NoC. Also, we have provided the available NoC tools for the NoC researchers.
- 24 August 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 121 (4) , 2511-2528
Performance Analysis of Optad-NoC: A Novel Optimized Routing Algorithm and Intelligent Router for 3D Network-on-Chip
- 24 August 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 121 (4) , 2511-2528
Performance Analysis of Optad-NoC: A Novel Optimized Routing Algorithm and Intelligent Router for 3D Network-on-Chip
- 30 June 2016
- Published by The Institute of Electronics Engineers of Korea in JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
- Vol. 16 (3) , 359-366
Performance Oriented Docket-NoC (Dt-NoC) Scheme for Fast Communication in NoC
- 30 June 2016
- Published by The Institute of Electronics Engineers of Korea in JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
- Vol. 16 (3) , 359-366
Performance Oriented Docket-NoC (Dt-NoC) Scheme for Fast Communication in NoC