@kce.ac.in
Principal
Karpagam College of Engineering
PhD in Low Power VLAI Design, ME in Applied Electronics, BE in Electrical and Electronics Engineering
VLSI Design, Automation, Electric Drives and Instrumentation
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
K. Sukanya and P. Vijayakumar
Computers, Materials and Continua (Tech Science Press)
Vasuki Andiappan and Vijayakumar Ponnusamy
Springer Science and Business Media LLC
M. Jayamohan, S. Yuvaraj, and P. Vijayakumar
IEEE
To alleviate increase rate of crime, security personnel, IP camera, CCTV (Closed-Circuit Television) is traditionally employed. But human vigilance leads to errors. Hence, automated video surveillance and analytics are implemented to minimize these errors. Human behaviour recognition algorithms can be used reactively to prevent issues or proactively for post-incident inquiry. There is increasing demand in automated video surveillance, which involves face detection, object detection, license plate detection. This study provides the most recent state-of-the-art image processing algorithms for automatic behaviour detection approaches, with an emphasis on human activity monitoring.
A. Vasuki and Vijayakumar Ponnusamy
Computers, Materials and Continua (Tech Science Press)
V. Padmajothi, J L Mazher Iqbal, and Vijayakumar Ponnusamy
Elsevier BV
D. Malathi, Vijayakumar Ponnusamy, S. Saravanan, D. Deepa, and Tariq Ahamed Ahanger
Computers, Materials and Continua (Tech Science Press)
Aman Kumar Mishra and Vijayakumar Ponnusamy
Computers, Materials and Continua (Tech Science Press)
Cell-Free massive MIMO (mMIMO) offers promising features such as higher spectral efficiency, higher energy efficiency and superior spatial diversity, which makes it suitable to be adopted in beyond 5G (B5G) networks. However, the original form of Cell-Free massive MIMO requires each AP to be connected to CPU via front haul (front-haul constraints) resulting in huge economic costs and network synchronization issues. Radio Stripe architecture of cell-free mMIMO is one such architecture of cell-free mMIMO which is suitable for practical deployment. In this paper, we propose DNN Based Parallel Decoding in Radio Stripe (DNNBPDRS) to decode the symbols of User Equipments (UEs) in the uplink in a parallel fashion to reduce computational complexity by reducing delay in processing. Moreover, to solve the issue of Access Point (AP) selection in radio stripe networks, we propose a Channel link-based AP selection (CLBAPS) algorithm to choose the best APs in terms of channel link quality. The proposed DNNBPDRS framework not only improves Symbol Error Rate (SER) performance when compared to counterparts but is also proved to be comparatively far lesser computational complex. Moreover, the numerical result indicates the proposed AP selection algorithm CLBAPS performs better than random selection of AP in radio stripe networks.
Malathi Devendran, Indumathi Rajendran, Vijayakumar Ponnusamy, and Diwakar R. Marur
International Information and Engineering Technology Association
In recent years, machine learning algorithms related to images have been widely utilized by Convolution Neural Networks (CNN), and it has a high accuracy for recognition of an image. As CNN contains large number of computations, hardware accelerator like Field Programmable Gate Array is employed. Quite 90 % of operations during a CNN involves convolution. The objective of this work is to scale back the computation time to increase the peak, width and the pixel intensity levels in the input image. The execution time of a image processing program is mostly spent on loops. Loop optimization is a process of accelerating speed and reducing the overheads related to loops. It plays a crucial role in improving performance and making effective use of multiprocessing capabilities. Loop unrolling is one of the loop optimization techniques. In our work CNN with four levels of loop unrolling is used. Due to this delay is reduced compared with conventional Xilinix. With the assistance of strides and padding the 40 % of computation time has been reduced and is verified in MATLAB.
V.K.R. Rajeswari Satuluri and Vijayakumar Ponnusamy
IEEE
Quantum Computing (QC) has come into view as an emerging technology. Machine Learning(ML) and QC have become ubiquitous in recent years. This study has focused on surveying the enhancement of ML with QC. Applications of QC in different fields are thoroughly discussed. The Biomedical/Healthcare field of research has potential with QC-enhanced ML (QML). Advancements in an amalgamation of ML with QC are further elaborated. QML concepts are introduced with current research advances. The survey ends with challenges in the new technology and future work considerations.
Aman Kumar Mishra and Vijayakumar Ponnusamy
IEEE
Cell-Free massive MIMO(CFmM) requires every AP to be connected to CPU via front haul (front-haul constraints) resulting in huge economic costs and network synchronization issues. Radio Stripe architecture of cell-free mMIMO is one such architecture of CFmM which is suitable for practical deployment and is slated to be deployed in 6th generation (6G) network according to industry experts. Moreover, millimeter wave (mmW) band, which largely remains underutilized due to its propagation issues (owing to large propagation distances) can offer data rate up to 5Gbps in wireless networks. Owing the deployment nature of radio stripe(RS) (inside train, metro, stadium, common places, etc.) make it possible for mmW spectrum to be utilized in RS network. In this article we explore the possibility of mmW CFmM based on radio stripe to be adopted in 6th generation (6G) and beyond wireless networks.
Vijayakumar Ponnusamy, Diwakar R. Marur, Deepa Dhanaskodi, and Thangavel Palaniappan
International Information and Engineering Technology Association
This work proposes deep learning neural network-based X-ray image classification. The X-ray baggage scanning machinery plays an essential role in the safeguard of customs, airports, and other systematically very important landmarks and infrastructures. The technology at present of baggage scanning machines is designed on X-ray attenuation. The detection of threatful objects is built on how different objects attenuate the X-ray beams going through them. In this paper, the deep convolutional neural network of YOLO is utilized in classifying baggage images. Real-time performance of the baggage image classification is an essential one for security scanning. There are many computationally intensive operations in the You Only Look Once (YOLO) architecture. The computational intensive operations are implemented in the Field Programmable Gate Array (FPGA) platform to optimize process delays. The critical issues involved in those implementations include data representation, inner products computation and implementation of activation function and resolving these issues will also be a significant task. The FPGA implementation results show that with less resource occupancy, the YOLO implementation provides maximum accuracy of 98.9% in classifying X-ray baggage images and identifying hazardous materials. This result proves that the proposed implementation is best suited for practical system deployments for real-time Baggage scanning.
A. Vasuki and Vijayakumar Ponnusamy
IEEE
Intelligent Reflecting Surfaces (IRS) are wave propagation controlling structures, which provide considerable phase shift on the incident wave in wireless communication system. Depending on the phase shift, constructive and destructive energy focusing is achieved towards the concerned and irrelevant users. Therefore, it is necessary to design such structures for evaluating the wave propagation in real time environment. In this article, we use periodic sub-wavelength design that couple to the wave components of the incident electromagnetic wave, showing features that are not available in the environment. We design a meta-surfaces based unit cell with different placements on the substrate and evaluate the performance of it over a different range of frequencies.
Nagaraj Balakrishnan, Arunkumar Rajendran, Danilo Pelusi, and Vijayakumar Ponnusamy
Elsevier BV
A. Athiraja and P. Vijayakumar
Springer Science and Business Media LLC
A P Manjari, S Sanchana, P Vijayakumar, and Bala Naga Jyothi V
IEEE
True north seeking system is one of the essential components of marine navigation. These systems will be installed on ships and underwater vehicles, to guide Pilot in the defined path by measuring true north. Gyroscope, one of the sensors used for this application works based on the principle of Coriolis Effect. Thus, these sensors are rendered independent of external sources for location information such as GNSS and magnetic disturbances. However, these are typically realized using expensive and bulky gyroscopes such as ring laser gyroscopes and fibre optic gyroscopes. This work presents a method to seek the true north using cost-effective, compact MEMS gyroscope as part of inertial navigation system. A precise and feasible rotation modulation method to account for the errors arising due to the inherent features and properties of the gyroscope and external factors is proposed for static mode where an LSM based algorithm is used for estimating the heading angle with respect to the true north.
Vijayakumar Ponnusamy, J. Christopher Clement, K. C. Sriharipriya, and Sowmya Natarajan
Springer International Publishing
Balakrishnan Nagaraj, Rajendran Arunkumar, K. Nisi, and Ponnusamy Vijayakumar
Springer Science and Business Media LLC
Kumaravel Sureshkumar and Vijayakumar Ponnusamy
SAGE Publications
Efficient approach for power flow management of hybrid renewable energy system connected smart grid system is proposed in this paper. Here, the proposed approach is the combination of both the modified elephant herding optimization algorithm with tabu search algorithm named as MEHOTSA. In the proposed technique, the modified elephant herding optimization algorithm plays out the assessment procedure to establish the exact control signals for the system and builds up the control signals database for the offline way in light of the power variety between source side and the load side. The multi-objective function is shaped by the grid required active power and reactive power varieties generated based on the accessible source power. The accomplished dataset is used to work the Tabu search algorithm on the online way and it leads the control procedure in less execution time. The proposed technique-based control model enhances the control parameters of the power controller in light of the power flow varieties. By utilizing the proposed methodology, the power flow management of the smart grid system is controlled dependent on the source side and load side parameters varieties. Additionally, the proposed methodology is in charge of controlling the energy sources so as to produce the power demanded by the grid, utilizing optimally both renewable energy sources and energy storage devices. Finally, the proposed model be actualized in MATLAB/Simulink platform and the performance are compared with other techniques.
Sureshkumar Kumaravel and Vijayakumar Ponnusamy
Informa UK Limited
In this paper, an optimal power flow management of a hybrid renewable energy source (HRES) with a hybrid approach is proposed. Here, the proposed method is the consolidation of Improved Bear Smell ...
K. Sureshkumar and Vijayakumar Ponnusamy
Elsevier BV
G. Sophia Jasmine and P. Vijayakumar
Springer Science and Business Media LLC
P. Santhosh and P. Vijayakumar
Springer Science and Business Media LLC
A. Stanly Paul, P. Vijayakumar, and R. Shijitha
Springer Science and Business Media LLC
Aruchamy Sakthivel, P. Vijayakumar, A. Senthilkumar, L. Lakshminarasimman, and S. Paramasivam
Elsevier BV