Dr.Pradeep .J
@smvec.ac.in
Associate Professor, Department of Electronics and Communication Engineering,
Sri Manakula Vinayagar Engineering College
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Madurakavi Karthikeyan, J Pradeep, M Harikrishnan, R Sitharthan, Naveen Mishra, M Rajesh, and Thamizharasan Sivanesan
IOP Publishing
R. Kurinjimalar, J. Pradeep, K. Jayapreethi, M. Madhumitha, and S. Narmadha
IEEE
Heavy vehicles for public transportation and goods carriers are playing a vital role in the national economy. Heavy motor vehicles, such as buses and trucks, have an inadvertently higher ground clearance, which is a disadvantage during road accidents when people fall and get trapped under the vehicle's wheels. To save people's lives, in this paper an actuator shield based life-saving system is proposed and developed. The system consists of LiDAR ranging system, a thermal camera, and a Raspberry Pi-based fast computing system interfaced to control a dynamic servo-actuated angular shield for wheels. The LiDAR range-sensing sensor detects the road surface to vary the ground clearance of the wheel's shield, which maintained the ground clearance of some height to avoid hitting obstacles. To find the human falling near the wheels, the thermal camera plays a vital role. When the human is detected, it actuates the servo motors and shield to zero ground clearance, and thus people are saved by keeping them from getting under the wheels. The entire system consumes less power and is simple to install, so it can be retrofitted to existing vehicles, resulting in no deaths from vehicle collisions. As a result, the proposed system is used to save lives from the heavy vehicle accidents at low initial cost and low maintenance cost.
Arunagiri P, Pradeep Jayabala, Harikrishnan M, and Martin L
Bentham Science Publishers Ltd.
Aim:: Wind energy, being a non-conventional and sustainable renewable resource, provides electrical energy through the rotation of the blades of a wind turbine caused by wind impact. To ensure the sustainability of this resource, maintenance of the wind turbines is essential. Methods:: The incorporation of emerging technologies into the tedious processes has enabled quality improvement in the performance of systems. Augmented reality, which enhances the 3D digital content over the real world, may be used to leverage the tedious process of wind turbine maintenance by providing a user-friendly environment. Results/Discussion: AR utilization provides great insights into the problems occurring in specific parts of a wind turbine, thereby easing out the complexity of field workers. The objective is to create an augmented reality environment to monitor the proper functioning and detect the faultiness in a wind turbine with accuracy. Conclusion:: AR utilization can help facilitate better maintenance service, thereby increasing the life of a wind turbine.
Madurakavi Karthikeyan, Pradeep Jayabala, Sitharthan Ramachandran, Shanmuga Dhanabalan, Thamizharasan Sivanesan, and Manimaran Ponnusamy
MDPI AG
We present a simple dual band absorber design and investigate it in the terahertz (THz) region. The proposed absorber works in dual operating bands at 5.1 THz and 11.7 THz. By adjusting the graphene chemical potential, the proposed absorber has the controllability of the resonance frequency to have perfect absorption at various frequencies. The graphene surface plasmon resonance results in sharp and narrow resonance absorption peaks. For incident angles up to 8°, the structure possesses near-unity absorption. The proposed sensor absorber’s functionality is evaluated using sensing medium with various refractive indices. The proposed sensor is simulated for glucose detection and a maximum sensitivity of 4.72 THz/RIU is observed. It has a maximum figure of merit (FOM) and Quality factor (Q) value of 14 and 32.49, respectively. The proposed optimal absorber can be used to identify malaria virus and cancer cells in blood. Hence, the proposed plasmonic sensor is a serious contender for biomedical uses in the diagnosis of bacterial infections, cancer, malaria, and other diseases.
J. Pradeep, M. Harikrishnan, and K. Vijayakumar
Springer Singapore
P. Mahes Kumar, G. R. Anantha Raman, S Balachandran, J Pradeep, and A Suresh
American Scientific Publishers
R. Radhiga and J. Pradeep
IEEE
In recent years modern automobiles integrates numerous number of Electronic components are increased rapidly. These automotive embedded systems have great demand for dependability, on designing the FlexRay protocol. FlexRay (FR) protocol is mainly for scalable, flexible, high speed deterministic, error tolerant communication in order to meet growing safety related challenges in the automobile industry. This paper explores the general issues of functional coverage pertaining to the FlexRay specification. The presented work demonstrated as designed of communication controller of FlexRay node with Finite State Machine (FSM). The simulation and Synthesis result are presented in this paper using Xilinx software as tool.
J. Pradeep, E. Srinivasan, and S. Himavathi
IEEE
In this paper, an off-line handwritten English character recognition system using hybrid feature extraction technique and neural network classifiers are proposed. A hybrid feature extraction method combines the diagonal and directional based features. The proposed system suitably combines the salient features of the handwritten characters to enhance the recognition accuracy. Neural Network (NN) topologies, namely, back propagation neural network and radial basis function network are built to classify the characters. The k-nearest neighbour network is also built for comparison. The Feed forward NN topology exhibits the highest recognition accuracy and is identified to be the most suitable classifier. The proposed system will aid applications for postal/parcel address recognition and conversion of any hand written document into structural text form. The performance of the recognition systems is compared extensively using test data to draw the major conclusions of this paper.
J. Pradeep
International Digital Organization for Scientific Information (IDOSI)
Handwriting recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications that includes, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. Neural Network (NN) with its inherent learning ability offers promising solutions for handwritten character recognition. This paper identifies the most suitable NN for the design of hand written English character recognition system. Different Neural Network (NN) topologies namely, back propagation neural network, nearest neighbour network and radial basis function network are built to classify the characters. All the NN based Recognition systems use the same training data set and are trained for the same target mean square error. Two hundred different character data sets for each of the 26 English characters are used to train the networks. The performance of the recognition systems is compared extensively using test data to draw the major conclusions of this paper
J. Pradeep, E. Srinivasan, and S. Himavathi
IEEE
An off-line handwritten alphabetical character recognition system using multilayer feed forward neural network is described in the paper. A new method, called, diagonal based feature extraction is introduced for extracting the features of the handwritten alphabets. Fifty data sets, each containing 26 alphabets written by various people, are used for training the neural network and twenty different handwritten alphabets characters are used for testing. The proposed recognition system performs quite well yielding higher levels of recognition accuracy compared to the systems employing the conventional horizontal and vertical methods of feature extraction. This system will be suitable for converting handwritten documents into structural text form and recognizing handwritten names.
J. Pradeep, E. Srinivasan, and S. Himavathi
IEEE
Handwriting recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. In this paper an attempt is made to recognize handwritten characters for English alphabets without feature extraction using multilayer Feed Forward neural network. Each character data set contains 26 alphabets. Fifty different character data sets are used for training the neural network. The trained network is used for classification and recognition. In the proposed system, each character is resized into 30×20 pixels, which is directly subjected to training. That is, each resized character has 600 pixels and these pixels are taken as features for training the neural network. The results show that the proposed system yields good recognition rates which are comparable to that of feature extraction based schemes for handwritten character recognition.