Prasanna Bharathi - Academia.edu (original) (raw)

Papers by Prasanna Bharathi

Computer Systems Science and Engineering

Due to the advanced developments in communication technologies, Internet of vehicles and vehicula... more Due to the advanced developments in communication technologies, Internet of vehicles and vehicular adhoc networks (VANET) offers numerous opportunities for effectively managing transportation problems. On the other, the cloud environment needs to disseminate the emergency message to the vehicles which are consistently distributed on the roadway so that every vehicle gets the messages from closer vehicles in a straightforward way. To resolve this issue, clustering and routing techniques can be designed using computational intelligence approaches. With this motivation, this paper presents a new type-2 fuzzy sets based clustering with metaheuristic optimization based routing (T2FSC-MOR) technique for secure communication in VANET. The T2FSC-MOR technique aims to elect CHs and optimal routes for secure intercluster data transmission in VANET. The proposed model involves T2FSC technique for the selection of CHs and construction of clusters. The T2FSC technique uses different parameters namely traveling speed (TS), link quality (LQ), trust factor (TF), inter-vehicle distance (IVD), and neighboring node count (NCC). The inclusion of trust factor helps to select the proper cluster heads (CHs) for secure data dissemination process. Moreover, trust aware seagull optimization based routing (TASGOR) approach was derived for the optimal selection of routes in VANET. In order to validate the enhanced performance of proposed technique, the set of simulations take place and the outcomes are examined interms of different measures. The experimental outcomes highlighted the improved performance of the proposed model over the other state of art techniques with a higher throughput of 98%.

The Journal of Supercomputing, 2022

Intelligent Computing and Applications, 2020

Inorganic Chemistry Communications, 2022

Intelligent Automation & Soft Computing, 2022

Remote sensing (RS) is a very reliable and effective way to monitor the environment and landscape... more Remote sensing (RS) is a very reliable and effective way to monitor the environment and landscape changes. In today's world topographic maps are very important in science, research, planning and management. It is quite possible to detect the changes based on RS data which is obtained at two different times. In this paper, we propose an optimal technique that handles problems like urban green space destruction and detection of crop stress assessment. Firstly, the optimal preprocessing is performed on the given RS dataset, for image enhancement using geometric correction and image registration. Secondly, we propose the improved cat swarm optimization algorithm to optimize the greenery region with the help of vegetation index parameters like Normalized Difference Built-up Index (NDBI) & Normalized Difference Vegetation Index (NDVI). Thirdly, we use Conditional Principal Component Analysis (PCA) to reduce dimension of a response matrix & retain the dominant information to identify key vegetation indices and the classification of crops. Then, an optimal decision maker-based post classification method is introduced to differentiate area changes based on the overlay of two or more classified images. From the simulation results we observed and conclude that the performance of proposed crop classification, crop stress and yield assessments performed very effective compared to existing methods in terms of F-Measure, recall, precision & accuracy.

Intelligent Data Communication Technologies and Internet of Things, 2021

In recent years, SMS spam messages are increasing exponentially due to the increase in mobile pho... more In recent years, SMS spam messages are increasing exponentially due to the increase in mobile phone users. Also, there is a yearly increment in the volume of mobile phone spam. Filtering the spam message has become a key aspect. On the other side, machine learning has become an attractive research area and shown the capacity in data analysis. So, in this paper, two popular algorithms named Naive Bayes and support vector machine are applied to SMS data. The SMS dataset is considered from Kaggle resource. The detailed result analysis is presented. Accuracy of 96.19% and 98.79% is noticed for the chosen algorithms, respectively, for spam SMS detection.

Lecture Notes in Networks and Systems, 2021

Previous works have shown that convolutional neural networks can achieve good performance in imag... more Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network structure could alleviate these problems, but at the cost of additional computational overhead. In this paper, we propose a novel spatial-adaptive denoising network (SAD-Net) for efficient single image blind noise removal. To adapt to changes in spatial textures and edges, we design a residual spatial-adaptive block. Deformable convolution is introduced to sample the spatially related features for weighting. An encoder-decoder structure with a context block is introduced to capture multiscale information. By conducting noise removal from coarse to fine, a high-quality noise-free image is obtained. We apply our method to both synthetic and real noisy image datasets. The experimental results demonstrate that our method outperforms the state-of-the-art denoising methods both quantitatively and visually.

In this paper presents Improve Power Quality of Grid Connected Unbalance loads Employing Dual Vol... more In this paper presents Improve Power Quality of Grid Connected Unbalance loads Employing Dual Voltage Source Converters. The proposed scheme is comprised of two inverters back to back connection, which enables the microgrid to exchange power generated by the distributed energy resources and also to compensate the local unbalanced and nonlinear load. The control algorithms are developed based on fuzzy logic control theory to operate dual voltage source converters in grid sharing and grid injecting modes. The proposed scheme has increased reliability, lower cost due to reduction in filter size, and better utilization of microgrid power while using reduced dc-link voltage rating for the main inverter. These features make the DVSI scheme a promising option for microgrid supplying nonlinear and unbalance loads. The Simulation results are discussed adopting MATLAB software.

Monitoring, collecting data and analyzing dynamic environmental changes plays a key role in a man... more Monitoring, collecting data and analyzing dynamic environmental changes plays a key role in a manufacturing or any industry. The main objective of this paper is to design fabricate and implement an autonomous robot, which would travel autonomously in a pre-planned environment, measure and analyze parameters like temperature, humidity, carbon-di-oxide, nitrogen , dust, noise and radio frequency levels. The measured values are then uploaded to a cloud, perhaps if the measured values are more than a threshold, it will show an alert (or send a notification to the admin). The robot’s movement is controlled using gyroscope and distance sensors. The robot also has a manual control mode which is enabled with high technology cameras for surveillance. The robot is controlled through a Raspberry Pi and the inbuilt Wi-Fi module helps to upload the measured data to the cloud. The Raspberry Pi controls the motor driver circuit, which in-turn drives the motor. Raspberry Pi is enabled with image pr...

AIM: To study and evaluate the different organisms that are responsible for congenital nasolacrim... more AIM: To study and evaluate the different organisms that are responsible for congenital nasolacrimal duct obstruction .To initiate appropriate antimicrobials based on the sensitivity patterns of the isolated organisms. Methods: It is a prospective study conducted in Sarojini Devi Eye hospital during September 2016 to February 2018. 112 samples from 100 cases were collected from clinically diagnosed congenital nasolacrimal duct obstruction with epiphora below 1 year without any ocular and systemic diseases .Swabs taken were analysed for causative microorganisms of congenital nasolacrimal duct obstruction. Results: In our study out of 112 samples[88 unilateral cases+12 bilateral cases ]82 cases [73.21%] were culture positive, of which80 [71.42%]were bacterial,2 cases [1.78%]were mixed [ bacterial +fungal].Gram positive bacteria were predominant, staphylococcus epidermidis 56[68.29%] followed by Staphylococcus aureus 13[15.85%].Among gram negative bacteria Escherichia coli 1 [1.21%], kl...

Mathematical and Computational Applications, 2021

A method recently advanced as the conformable Euler method (CEM) for the finite difference discre... more A method recently advanced as the conformable Euler method (CEM) for the finite difference discretization of fractional initial value problem Dtαyt = ft;yt, yt0 = y0, a≤t≤b, and used to describe hyperchaos in a financial market model, is shown to be valid only for α=1. The property of the conformable fractional derivative (CFD) used to show this limitation of the method is used, together with the integer definition of the derivative, to derive a modified conformable Euler method for the initial value problem considered. A method of constructing generalized derivatives from the solution of the non-integer relaxation equation is used to motivate an alternate definition of the CFD and justify alternative generalizations of the Euler method to the CFD. The conformable relaxation equation is used in numerical experiments to assess the performance of the CEM in comparison to that of the alternative methods.

Infectious Disorders - Drug Targets, 2021

Foot infections being one of the major complications, accounts for nearly 15% of people with diab... more Foot infections being one of the major complications, accounts for nearly 15% of people with diabetes and in-crease their risk for amputation in lower extremities. Though various factors contribute to the development of diabetic foot infection, poor glycemic control poses a greater risk paving way for a number of micro-organisms to colonize the wound. In order to restore the lost granulation tissue at the ulcer site, the prime aim should not only be attaining a glycemic control but also must focus on performing culture by clinically differentiating the stage of infection as well as to manage or control the infection by selecting a rational empiric antibiotic regimen, amidst the uncertainty that exists in choosing best antimicro-bial therapy in emerging multi-drug resistance worldwide. This review mainly analyzes that although among the existence of various undefined microbiome being prevalent in causing diabetic foot infections, how the current trend of antibiotics in use, aid in tr...

International Journal of Recent Technology and Engineering, 2019

Patient monitoring is the heart of the health care domain in day to day life either at home or at... more Patient monitoring is the heart of the health care domain in day to day life either at home or at hospital. This paper focuses an Intelligent ECG Monitoring System to monitor the heart patients residing at distant places at low cost and complexity using Internet of Things. The proposed system automatically screens the health condition of the patient and records their Electrocardiogram through heart rate sensor and ATtiny Board. ATtiny is a low cost IoT device used along with heart rate sensor and ESP8266 to record the electrocardiogram of the patients. The ECG is sent to the doctors, nurses or the patient’s relatives residing in the remote places through the internet to help them in remote monitoring of the patients with ease.

Procedia Computer Science, 2018

In recent days, suspicious action recognition is a significant topic in intelligent video surveil... more In recent days, suspicious action recognition is a significant topic in intelligent video surveillance and computer vision research. Action recognition methodologies are specially needed for surveillance systems which are required to prevent crimes and treacherous actions before occurring. In this paper, we present 3D-Convolutional Neural Networks (3D-CNN) with 3D motion cuboid for action detection and recognizing in videos. The experiments are conducted on benchmark KTH and Weizmann dataset. The proposed method is compared with the existing methods in terms of accuracy. The results show that this approach is outperforms previously published results.