Anitha Velu

Anitha Velu received her Bachelor degree in Electronics and Communication Engineering from Vivekanandha Educational Institutions, Tiruchengode, Tamil Nadu in 2014, Masters in VLSI Systems from Adhiyamaan College of Engineering, Hosur, Tamil Nadu in 2016 and Ph.D in Information and Communication Engineering from Anna University, Chennai in 2022. Currently she is an Assistant Professor in the Department of Electronics and Communication Engineering at Adhiyamaan College of Engineering, Hosur, India. Her research interests include Digital Image Processing, VLSI Design, Ontology and Semantic web technology.

EDUCATION

Bachelor of Engineering (Electronics and Communication Engineering)
Master of Engineering (VLSI Design)
Philosophy of Doctorate (Information and Communication Engineering)

RESEARCH INTERESTS

Digital Image Processing, VLSI Design, Ontology and Semantic Web technology

Scopus Publications

LLM pretraining methods
Anitha Velu, Raghu Ramamoorthy, S. M. Manasa, and A. Prasanth
De Gruyter



Reliable Smart Wrist Pulse Oximeter for Hypoxemia and COVID-19 Patients
Raghu Ramamoorthy, J. A. Smitha, and Anitha Velu
Springer Nature Singapore



Optimizing Vehicle-to-Vehicle (V2V) Communication Efficiency with KNN-based Dynamic Time slot Allocation
N Devakirubai, Anitha Velu, D Sumathi, and A Prasanth
IEEE
In the continually evolving field of vehicular communications, the efficient allocation of time slots for Vehicle-to-Vehicle (V2V) communication is of utmost importance. This work introduces a novel approach that employs a K-Nearest Neighbors (KNN) algorithm to allocate time slots in NR V2X sidelink communications. The allocation is specifically tailored to dynamically adjust to the current density of traffic in real-time. The efficacy of the KNN-based time slot allocation system is assessed through simulating the V2X environment, encompassing a fleet of vehicles. The efficacy of the suggested methodology is assessed in relation to a random allocation technique and it is observed that the suggested strategy notably enhances allocation efficiency, slot utilization, contention window, and communication time. The findings illustrate the capacity of a KNN-based dynamic allocation system to adapt to different levels of traffic congestion, leading to the efficient utilization of network resources and the mitigation of communication latency. Furthermore, the examination of the implementation of priority queues in the allocation process is explored, resulting in enhanced efficiency of the system in scenarios involving a substantial amount of traffic.


An Energy Efficient IoT Based Smart Street Lighting Using Low Cost SOC
Anitha Velu, Raghu Ramamoorthy, Manasa S M, and Devakirubai Navulkumar
IEEE
Internet of Things (IoT) has radically improved and modernized in every aspect of human existence. The term IoT is a recent trend that states the development a self-configurable network by connecting a variety of hardware objects, to internet without requiring human input to improve service delivery and automate processes by means of data transmission to the cloud. Streetlights are an essential component of any city, although they provide safer roadways, improved night vision, and increased visibility of public spaces it uses a significant amount of electricity and operates at maximum intensity from dusk till dawn. The wastage of electricity can be secured by having lights turn OFF on their own if it is not in use. This work presents an energy efficient IoT-based smart street lighting by using low-cost System On Chip (SOC) circuit. This work deploys an LDR sensor which acts as a decision device, to choose whether to switch ON or OFF the street light based on the level of ambient light. This simple switch has a relay at its output and is activated by either light or dark. This switching may be done using a cost-effective Wi-Fi module namely, ESP8266 for which the LDR sensed value is given as input. Any user can check the status of a street light whether it is ON/OFF from anywhere using internet in real time. It promises great dependability and remarkable stability for long-term. The proposed work is implemented using a NodeMCU board that is designed to supply the required light intensity at different times.


Impact of Ant Colony Optimization on Optimal Routing for Vehicular Ad Hoc Networks
Raghu Ramamoorthy, Anitha Velu, R China Appala Naidu, Asha Kumari A, Angel Donny F, and Harish Kumar M
IEEE
Using biologically inspired approaches has bonus advantages in offering optimal message distribution for vehicular ad hoc networks (VANETs). Bio-motivated approaches are motivated by the natural behavior of biological entities such as bees and insects. Ant colony optimization (ACO) is the optimal bio-inspired style, suitable for offering optimal routing in VANETs. The communication pattern of ACO and VANETs is similar, such as ants of ACO apply indirect communication among ants for the exchange of information, and VANETs require cooperative routing techniques for message exchange. The goal of the Bio-motivated approach is to attain proficient and accessible communication in a VANET, where vehicles turn as nodes and animatedly form a system to interchange information. In this context, the proposed work discusses the effectiveness and benefits of using a bio-inspired approach such as ACO for VANETs. To demonstrate ACO, a healthcare scenario is considered. In the healthcare system, efficient communication is required between emergency vehicles and hospitals to offer optimal treatment for patients. This work applies ACO to find the optimal path for sending an alarm to the nearest hospital from the emergency vehicle to arrange necessary things to treat patients. Using ACO increases the efficiency of the routing mechanism in all aspects such as throughput, overhead, data delivery, low latency, route discovery time, route repair time, convergence speed, and stagnation issue.


Deep Learning-Based Age and Gender Prediction through Feature Extraction from Facial Images using Convolutional Neural Networks
Manasa S M, Raghu Ramamoorthy, Anitha Velu, Angel Donny F, and Chaitrashree S
IEEE
In recent years, age estimation and gender classification have been focal points in the field of pattern recognition and computer vision. This paper introduces an automated approach for predicting age and gender by extracting features from human facial images. In contrast to conventional methods that operate on unfiltered facial images, our study demonstrates significant improvements in these tasks through the use of deep convolutional neural networks (CNNs). The employed feedforward neural network method enhances robustness for highly variable unconstrained recognition tasks, specifically targeting gender identification and age group estimation. The research methodology involves the analysis and validation of gender prediction and age estimation on two benchmark datasets: the Essex face dataset and the Adience benchmark dataset. Results indicate a substantial performance enhancement, showcasing the proposed approach's efficiency and state-of-the-art performance in both age and gender detection. The model achieves remarkable accuracy, positioning it as a notable advancement in the realm of age and gender prediction using deep learning techniques.


IoT Enabled Smart Farming: A Controlled Environment Agriculture Application
Anitha Velu, Raghu Ramamoorthy, Saravana Kumar E, and K Shruthi
IEEE
Horticulture is the science of sustainable production, advertising and marketing the intensively cultivated food and decorative plants. The major intricacy in horticulture is maintaining the temperature within the controlled environment such as polyhouse or green house which leads to plant damage like root rot, leaf spots, downy mildew. This results in IoT of human intervention in checking the temperature periodically and provide remedial measures to maintain it. In order to overcome such issues this work proposes an IoT-based Automatic Temperature Controller (ATC) system using Arduino board interfaced with the environmental data by deploying Internet of Things (IoT). The proposed work incorporates two phases: (i) Collection of data for the different floral plants and uploading it to the IoT cloud (ii) Implementing the hardware part using Arduino UNO kit for ATC system. The ATC system gets the values of temperature and humidity from DHTII sensor where, the entire system is connected to the Arduino microcontroller which compares the recorded value with the threshold value set by user in cloud. The motor will be turned on by the controller being the observed temperature is found larger than the threshold value. The proposed system has been tested on different floral plants that are of high productivity in and around Hosur, Tamil Nadu circumstances namely Gerbera daisy, Button rose, Chrysanthemum and Rose. This work can be extended for other agricultural application purposes like creepers, mushroom cultivation etc.


Ocean knowledge representation through integration of big data employing semantic web technologies
Anitha Velu and Menakadevi Thangavelu
Springer Science and Business Media LLC



Information retrieval through a knowledge base system: Semantic web based approach in South-Eastern Coastal areas of India




Ontology based ocean knowledge representation for semantic information retrieval
Anitha Velu and Menakadevi Thangavelu
Computers, Materials and Continua (Tech Science Press)



Hetero-GCD2RDF: An Interoperable Solution for Geospatial Climatic Data by Deploying Semantic Web Technologies
Anitha Velu and Menakadevi Thangavelu
Springer Science and Business Media LLC
Ocean and Land based satellite observation system comprises of various sensors and configurations. The generated Geospatial Climatic Data (GCD) by sensors is transmitted in heterogeneous file formats with heterogeneous vocabularies that lead to semantic heterogeneity of data. Government and public organizations started to publish these datasets to users through climatic web portals. The critical task in handling heterogeneous files is data interpretation and interoperability. This can be handled by facilitating the data to reach semantically structured or linked data. This paper proposes a Hetero-GCD2RDF data retrieval approach that focuses on two aspects (1) Extraction of records from satellite data and represent it as linked data namely Resource Description Framework (RDF) and (2) Implementation of SPARQL query engine to the resultant RDF for data retrieval. Data from Indian Meteorological Satellite INSAT-3D is taken as a typical example to execute the proposed approach. Where, approximately 170 files of about 650 MB in memory containing 1,278,000 records have been converted and queried. Compared to conventional methods the proposed method saves nearly 38.12% of time to represent the data in RDF. Thus, the proposed Hetero-GCD2RDF approach is recognized to be efficient, reliable and suitable for semantic web.

RECENT SCHOLAR PUBLICATIONS

Impact of Ant Colony Optimization on Optimal Routing for Vehicular Ad Hoc Networks
R Ramamoorthy, A Velu, RCA Naidu, A Kumari, H Kumar
2024 5th International Conference on Communication, Computing & Industry 6.0 2024



Deep Learning-Based Age and Gender Prediction through Feature Extraction from Facial Images using Convolutional Neural Networks
SM Manasa, R Ramamoorthy, A Velu, S Chaitrashree
2024 5th International Conference on Communication, Computing & Industry 6.0 2024



IoT-based Thermal Management System by Embedding Physical Sensors in Hybrid Vehicles
A Velu, R Ramamoorthy, A Prasanth, RK Dhanaraj
MDPI 2024



5 LLM Pretraining Methods
A Velu, R Ramamoorthy, SM Manasa, A Prasanth
Generative AI and LLMs: Natural Language Processing and Generative 2024



Reliable Smart Wrist Pulse Oximeter for Hypoxemia and COVID-19 Patients
R Ramamoorthy, JA Smitha, A Velu
International Conference on Inventive Communication and Computational 2024



An Energy Efficient IoT Based Smart Street Lighting Using Low Cost SOC
A Velu, R Ramamoorthy, SM Manasa, D Navulkumar
2024 International Conference on Electronics, Computing, Communication and 2024



Elephant Intrusion Warning System Using Low Power Wireless Personal Area Networks
RRKH Anitha Velu, Menakadevi Thangavelu
BR Patent 6,347,702 2024



Autonomous Drone Navigation Device for Obstacle Avoidance
RRPKT Prasanth Aruchamy, Jayachithra, Anitha Velu
IN Patent 425241-001 2024



Optimizing Vehicle-to-Vehicle (V2V) Communication Efficiency with KNN-based Dynamic Time slot Allocation
N Devakirubai, A Velu, D Sumathi, A Prasanth
2024 International Conference on Social and Sustainable Innovations in 2024



A Text Book of Introduction to Cyber Security
MTDN Anitha Velu, Raghu Ramamoorthy
2024



Priority Based Lightweight Cluster Rout-ing for Efficient Communication in Vehicular Ad Hoc Networks
R Ramamoorthy, SM Ma-nasa, A Velu
Central Asian Journal of Mathe-matical Theory and Computer Sci-ences 5 (2 2024



An automated moving object detection system for video surveillance applications
AP Anitha Velu
GR Patent G06V 20/52 2023



IoT enabled smart farming: a controlled environment agriculture application
A Velu, R Ramamoorthy, S Kumar, K Shruthi
2023 International Conference on Sustainable Communication Networks and 2023



An Ontological Framework for Ocean Sensor Data Interoperability Using Semantic Web Technologies for Weather Applications
AVM Thangavelu
IN Patent 202341009171 A 2023



Ocean knowledge representation through integration of big data employing semantic web technologies
A Velu, M Thangavelu
Earth Science Informatics 15 (3), 1563-1585 2022



Design and Development of Patient Monitoring in Hospitals Through AI and Data Science
RRKH Anitha Velu, Menakadevi Thangavelu
IN Patent 202241053331 A 2022



Ontology Based Ocean Knowledge Representation for Semantic Information Retrieval.
A Velu, M Thangavelu
Computers, Materials & Continua 70 (3) 2022



Information Retrieval through a Knowledge Base System: Semantic Web based Approach in South-Eastern Coastal Areas of India
A Velu, M Thangavelu
Songklanakarin Journal of Science and Technology 44 (1), 272-280 2022



An Efficient Method for Segmentation of Cerebrospinal Fluid in Hydrocephalus affected T2 weighted MRI images
A Velu
Central Asian Journal of Theoretical and Applied Sciences 3 (5), 493-511 2022



Hetero-GCD2RDF: An interoperable solution for geospatial climatic data by deploying semantic web technologies
A Velu, M Thangavelu
Wireless Personal Communications 117 (4), 3527-3551 2021

MOST CITED SCHOLAR PUBLICATIONS

Hetero-GCD2RDF: An interoperable solution for geospatial climatic data by deploying semantic web technologies
A Velu, M Thangavelu
Wireless Personal Communications 117 (4), 3527-3551 2021
Citations: 8



IoT enabled smart farming: a controlled environment agriculture application
A Velu, R Ramamoorthy, S Kumar, K Shruthi
2023 International Conference on Sustainable Communication Networks and 2023
Citations: 6



Ontology Based Ocean Knowledge Representation for Semantic Information Retrieval.
A Velu, M Thangavelu
Computers, Materials & Continua 70 (3) 2022
Citations: 4



Ocean knowledge representation through integration of big data employing semantic web technologies
A Velu, M Thangavelu
Earth Science Informatics 15 (3), 1563-1585 2022
Citations: 3



IoT-based Thermal Management System by Embedding Physical Sensors in Hybrid Vehicles
A Velu, R Ramamoorthy, A Prasanth, RK Dhanaraj
MDPI 2024
Citations: 1



An Energy Efficient IoT Based Smart Street Lighting Using Low Cost SOC
A Velu, R Ramamoorthy, SM Manasa, D Navulkumar
2024 International Conference on Electronics, Computing, Communication and 2024
Citations: 1



Information Retrieval through a Knowledge Base System: Semantic Web based Approach in South-Eastern Coastal Areas of India
A Velu, M Thangavelu
Songklanakarin Journal of Science and Technology 44 (1), 272-280 2022
Citations: 1

GRANT DETAILS

1. “An Efficient Parallel Turbo Decoder Architecture for Wireless Network Applications,” funded by Institution of Engineers, India under Grant-in-aid scheme with ID: RDPG2016017.
2. “A Novel Approach Of Designing Ontology Based Semantic Web Architecture Addressing Satellite Data Interoperability For Ocean Applications,” funded by Institution of Engineers, India under Grant-in-aid scheme with ID: DR2019006.

INDUSTRY EXPERIENCE

Over 1 year of experience as R&D Trainee in Trilok Laboratories Pvt Ltd, Bangalore