Girirajan B
@sru.edu.in
Assistant Professor and Department of Electronics and Communication Engineering
SR University
RESEARCH, TEACHING, or OTHER INTERESTS
Control and Systems Engineering, Biomedical Engineering, Electrical and Electronic Engineering, Hardware and Architecture
Scopus Publications
Scopus Publications
K K, , , , , , Anitha D, S S.Prabu, B B.Girirajan, and Arun M
ASPG Publishing LLC
The agricultural industry faces significant challenges in improving efficiency and productivity, particularly in monitoring crop health and environmental conditions. Traditional methods are often labor-intensive, time-consuming, and lack real-time data, leading to suboptimal decision-making. Recent advancements in Internet of Things (IoT) and Artificial Intelligence (AI) technologies offer promising solutions. Long Range (LoRa) communication, a type of low-power wide-area network (LPWAN), enables long-distance data transmission with minimal power consumption, making it ideal for rural and expansive agricultural areas. When combined with deep learning, which can analyze large volumes of data to generate predictive insights, these technologies have the potential to revolutionize agricultural practices by providing farmers with timely and accurate information to optimize crop management and resource utilization. This study introduces an intelligent mote for agricultural applications, leveraging Long Range (LoRa) communication and deep learning techniques to improve precision farming. Traditional agricultural monitoring methods are labor-intensive and lack real-time insights. To address this, the mote is equipped with sensors to monitor temperature, humidity, soil moisture, and light intensity, transmitting real-time data over long distances with minimal power consumption using LoRaWAN. The collected data is processed by deep learning models to predict crop yield and identify potential issues. Field tests demonstrated a 15% improvement in yield prediction accuracy and a 20% reduction in water usage compared to traditional methods. These results highlight the effectiveness of integrating LoRa and deep learning in enhancing agricultural resource management and productivity.
B Girirajan, B. Raveendra Naick, Hassan M. Al-Jawahry, Revanasiddappa, and Rana Veer Samara Sihman Bharattej R
IEEE
Nowadays, the urban cities are facing increasing strain due to the swift increase in population inside metropolitan areas. It is anticipated that the centered strategy for smart cities will address both the ecological environment and urban life. The food business is one of major IoT application areas in smart cities. In smart cities, IoT technology aid in the real-time monitoring, analysis, and management of the food business. In this study, an Internet of Things (IoT) based Dynamical Food Chain of Supply for Smart Cities using Dynamic Vehicle Routing (IFSCDVR) using Fire Hawk Optimization (FHO) technique is suggested, which guarantees food quality while also offering intelligent vehicle routing and the ability to identify the reasons for contamination of food. This strategy would increase the effectiveness and precision of the supply chain network with the smallest possible dataset size. The findings demonstrate that the suggested system works better than the current methodologies. The proposed IFSCDVR-FHO achieved overall performance of 91.34% of accuracy, 89.56% of precision, 89.68% of recall and 90.21% of f1. score.
B. Girirajan, Nijaguna G S, Pramodhini R, Myasar Mundher Adnan, and Gandla Shivakanth
IEEE
In recent years, an efficiency of task scheduling is evolved as a major challenge in cloud platforms. Especially, identifying the optimal resources for input tasks is the major challenges faced by the task scheduler. So, in this research, a Modified Whale Optimization Algorithm (MWOA) is proposed to improve the behaviour in task scheduling by applying the parameters such as resource allocation and load balancing. Capacity criteria based MWOA algorithm determines the effective Virtual Machine (VM) for execution of tasks in queue. An effectiveness of proposed WOA algorithm is analysed by the utilization of performance measures such as memory storage, execution time, cost and makespan. The attained results from the proposed WOA algorithm are outperformed in various predictable optimization algorithms such as Storm, Spark, Flink and Kafka. The results of proposed WOA algorithms demonstrates the better performances in minimum execution time of 612ms, and memory storage of 309Kb on Kafka platform.
B Girirajan, Hemalatha K. L, B. N. Manjunath, Suma S, and M. Pushpavalli
IEEE
Mobile Ad-Hoc Network (MANET) is self-configuring WSN which doesn't need any specific infrastructure due to their pure dynamic network. The efficient clustering and routing are growing attention in the background of limit energy resources and environment friendly transmitting behaviors. In this paper, Ant Bee Colony and Whale Optimization Algorithm (ABCWOA) algorithm is proposed for effective clustering and routing in MANET. The optimal cluster head and route paths are selected by utilizing the proposed optimization algorithm. The developed ABCWOA algorithm minimizes the nodes' energy utilization while increasing the data transmission in MANET. The performance of developed algorithm is estimated by utilizing performance measure of throughput, network lifetime, delay and energy consumption. The proposed algorithm attained the high throughput of 0.97 Mbps, 0.99 Mbps, 0.99 Mbps and 0.99 Mbps for 50, 100, 150 and 200 nodes which is superior than other existing algorithms like Particle Swarm Optimization (PSO), Cuckoo Search Optimization (CSO), Ant Bee Colony (ABC) optimization and Whale Optimization Algorithm (WOA).
Sureka N, B. Girirajan, Komuravelly Sudheer Kumar, B. S. Deepa Priya, and Sowmya M
IEEE
Intrusion Detection System (IDS) is one of the common deep learning (DL) techniques that are used to find and identify outliers to prevent adversarial attacks, fraud, and network intrusions. This paper proposed a hybrid Particle Swarm Optimization and Grey Wolf Optimization (HPSOGWO) based Convolutional Neural Network (CNN) model for intrusion detection systems. The proposed HPSOGWO is evaluated on the NSL-KDD dataset which contains 5 different classes and 41 features. The PSO is good for global exploration and GWO is for local exploitation. The hybrid PSO and GWO algorithm achieves a better balance between exploration and exploitation and enhances convergence speed. The CNN is utilized to enhance the system's capability to identify and classify intrusion accurately and effectively. The proposed HPSOGWO-based CNN model attains better results by utilizing evaluation metrics like accuracy, precision, recall, specificity, and f1-score values about 0.9918, 0.9852, 0.9908, 0.9879 and 0.9767 correspondingly which is comparatively higher than existing techniques like Chicken Swarm Optimization based Deep Long Short-Term Memory (ChCSO based Deep LSTM), Deep Neural Network (DNN) and LSTM.
G. Neelima, Dhanunjaya Rao Chigurukota, Balajee Maram, and B. Girirajan
Elsevier BV
Balasubramanian Girirajan, Himanshu Shekhar, Wen-Cheng Lai, Hariraj Kumar Jagannathan, and Parameshachari Bidare Divakarachar
MDPI AG
In a recent trend, electric vehicles (EV) have been facing various power quality issues, so fuel cells (FC) are considered the best choice for integrating EV technology to enhance performance. A fuel cell electric vehicle (FCEV) is a type of EV that uses a fuel cell combined with a small battery or super-capacitor to power its on-board electric motor. However, the power obtained from the FC system is much less and is not enough to drive the EV. So, another energy source is required to deliver the demanded power, which should contain high voltage gain with high conversion efficiency. The traditional converter produces a high output voltage at a high duty cycle, which generates various problems, such as reverse recovery issues, voltage spikes, and less lifespan. High switching frequency and voltage gain are essential for the propulsion of FC-based EV. Therefore, this paper presents an improved radial basis function (RBF)-based high-gain converter (HGC) to enhance the voltage gain and conversion efficiency of the entire system. The RBF neural model was constructed using the fast recursive algorithm (FRA) strategy to prune redundant hidden-layer neurons. The improved RBF technique reduces the input current ripple and voltage stress on the power semiconductor devices to increase the conversion ratio of the HGC without changing the duty cycle value. In the end, the improved RBF with HGC achieved an efficiency of 98.272%, vehicle speed of 91 km/h, and total harmonic distortion (THD) of 3.12%, which was simulated using MATLAB, and its waveforms for steady-state operation were analyzed and compared with existing methods.
N Anil Kumar, Gopathoti Kiran Kumar, B. Girirajan, Anandbabu Gopatoti, S Kiran, and Partha Sarkar
IEEE
A significant part of our daily lives is influenced by images. It is common for people to capture and edit a lot of photos. In this paper, dark images are enhanced and the quality of the images is assessed. Image quality was checked using a CNN algorithm. Dark images will be noisy and low in quantity. The purpose of this paper is to describe a novel method for improving dark images captured at nighttime through dehazing, image replication, denoising, exposure fusion, band ratioing, and weight map creation. Initially, the paper focuses on the quality of the input image. As a second step, they propose an efficient dehazing model using weight map creation to remove haziness and improve image quality. It is crucial and necessary to remove night time haze to keep human eyes from suffering from poor vision. Band ratioing methods can be helpful for analyzing brightness and darkness levels. Based on the results, the proposed methodology is able to improve the image and reduce noise in the dark low light image and produce a good HDR quality tone image.
A. Balamurugan, B. Girirajan, Kattupalli Sudhakar, Pandarinath Potluri, K. Ravikumar, and Amruta Ramdas Sane
IEEE
To organize and make sense of huge amount of data is one of the most essential problems in corporate company and our day - today life. “Data Science,” an emerging field of study, aims to address it. The basis of the field of data science is found in the principles of data management and machine learning. Researchers from both of these subfields engage in a significant amount of conversation and collaboration with one another. The entirety of the value of data is investigated, beginning with its inception and continuing all the way through its final application in forecasting, decision-making, and various other fields of study. In addition to this, it is able to understand and precisely analyze visual input, as well as store this information in visual memory and retrieve it when it is required. A few examples include Visual Graphs, the Statistics Report, Market Growth and other similar tools.
Prabu Subramani, Khalid Sattar, Rocío de Prado, Balasubramanian Girirajan, and Marcin Wozniak
MDPI AG
Connected autonomous vehicles (CAVs) currently promise cooperation between vehicles, providing abundant and real-time information through wireless communication technologies. In this paper, a two-level fusion of classifiers (TLFC) approach is proposed by using deep learning classifiers to perform accurate road detection (RD). The proposed TLFC-RD approach improves the classification by considering four key strategies such as cross fold operation at input and pre-processing using superpixel generation, adequate features, multi-classifier feature fusion and a deep learning classifier. Specifically, the road is classified as drivable and non-drivable areas by designing the TLFC using the deep learning classifiers, and the detected information using the TLFC-RD is exchanged between the autonomous vehicles for the ease of driving on the road. The TLFC-RD is analyzed in terms of its accuracy, sensitivity or recall, specificity, precision, F1-measure and max F measure. The TLFC- RD method is also evaluated compared to three existing methods: U-Net with the Domain Adaptation Model (DAM), Two-Scale Fully Convolutional Network (TFCN) and a cooperative machine learning approach (i.e., TAAUWN). Experimental results show that the accuracy of the TLFC-RD method for the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset is 99.12% higher than its competitors.
Ch. Rajendra Prasad, Polaiah Bojja, Pamula Raja Kumari, and B. Girirajan
IOP Publishing
Abstract The wireless body area networks are an integral part of the Internet of Things for eHealthcare applications. These networks suffer from two major problems such as energy consumption and lifetime of the overall network. To address these problems, a temperature aware priority-based routing algorithm for WBANs is proposed. This algorithm employs temperature aware routing, priority-based routing, and variable time-slot assignment. The temperature-aware routing enhances the stability of the overall network by providing an alternate route. The priority-based routing facilitates reliable data transmission among the sink and the sensor nodes which will enhance the lifetime of the overall network. The variable time-slot assignment in the scheduling phase prevents the collisions by employing a new synchronization schem e which will minimize overall network energy consumption. The performance proposed algorithm was analyzed with three network parameters and the results showed improved performance as compared with the traditional routing protocols.
B. Aparna and Mr. B. Girirajan
IOP Publishing
Abstract In approximating, the requirement for accurate results is ignored because of some other applications with better performance in terms of area or delay. Multipliers are key arithmetic circuits in many of these applications including digital signal processing (DSP). Here in this paper we propose an approximate multiplier circuit with two various architectures where one is designed by modifying the design of the circuit by adding AND-OR logic approximation in the partial product generation stage and a dual quality adder at the final stage of the multiplication for error recovery. The other one is by adding the same AND-OR logic approximation in the partial product reduction stage where it is applied tow only least significant part and accurate adders are used in the remaining for final outcome. In addition, many errors make little noticeable variations in practice, for instance image processing owing to human perceptual restrictions. Error-tolerant algorithms and their utilization inspired the progress of inexact multipliers which trade-off between power efficiency, area and speed. The proposed approximate multipliers have been shown that both have a lower area and one with better accuracy and error recovery other with delay than an exact Wallace multiplier and existing approximate designs. Functional analysis has shown that on a statistical basis, the proposed multipliers have considerable error distances and thus, they achieve a high accuracy and better area. To show the effectiveness of the work we had implemented and image processing application with the help of Xilinx System generator. The total designs are done and implemented in Xilinx ISE 14.7 with Verilog HDL coding.
P. Ganesan, L. M. I. Leo Joseph, V. Kalist, and B. Girirajan
Springer Singapore