T. Deepa

ORCID: 0000-0003-4398-3679
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • PAPR reduction in OFDM
  • Optical Wireless Communication Technologies
  • Multilevel Inverters and Converters
  • Advanced Wireless Communication Technologies
  • Advanced Wireless Communication Techniques
  • Wireless Communication Networks Research
  • Advanced DC-DC Converters
  • Optical Network Technologies
  • Silicon Carbide Semiconductor Technologies
  • Microgrid Control and Optimization
  • Low-power high-performance VLSI design
  • IoT-based Smart Home Systems
  • Anomaly Detection Techniques and Applications
  • Analog and Mixed-Signal Circuit Design
  • Induction Heating and Inverter Technology
  • Semiconductor Lasers and Optical Devices
  • Sparse and Compressive Sensing Techniques
  • Network Security and Intrusion Detection
  • Advanced Photonic Communication Systems
  • Impact of Light on Environment and Health
  • Advanced Battery Technologies Research
  • Wireless Body Area Networks
  • Numerical Methods and Algorithms
  • Energy Harvesting in Wireless Networks
  • Advanced Power Amplifier Design

Sri Venkateswara University
2024-2025

Saveetha University
2024

SRM Institute of Science and Technology
2013-2024

Vellore Institute of Technology University
2016-2024

General Motors (India)
2024

Feng Chia University
2024

Horizon College and Seminary
2024

ASA College
2024

SRM University
2013-2018

Anna University, Chennai
2011

Classification of brain tumor plays a vital role in medical imaging for accurate diagnosis, treatment, and monitoring. Deep learning approaches have gained significant traction this industry because their ability to extract relevant features from images. The research suggests employing an ensemble classifier with weighted voting mechanism categorize glial cell malignancies such as Astrocytoma, Glioblastoma multiforme, Oligodendroglioma, Ependymoma. proposed technique employs three main...

10.22399/ijcesen.803 article EN International Journal of Computational and Experimental Science and Engineering 2025-01-05

Recently, the number of Internet Things (IoT) networks has been grown exponentially, which results in more data sharing between devices without appropriate security mechanisms. Since huge management is involved, maintaining time constraints IoT another significant issue. To address these issues, an intelligent intrusion detection system adapted to recognize or predict a cyber-attack using Elite Machine Learning algorithms (EML), and lightweight protocol used manage time-constrained The...

10.1109/access.2022.3161566 article EN cc-by IEEE Access 2022-01-01

The Internet of Things (IoT) is a global information and communication technology which aims to connect any type device the internet at time in location. Nowadays billions IoT devices are connected world, this leads easily cause vulnerability devices. increasing users different IoT-related applications more data attacks happening networks after fog layer. To detect reduce deep learning model used. In article, hybrid sample selected recurrent neural network-extreme machine (hybrid SSRNN-ELM)...

10.32604/iasc.2022.022856 article EN cc-by Intelligent Automation & Soft Computing 2022-01-01

Calculation of firing angles for the efficient operation multilevel inverter is very important. This paper gives a simple guide to calculate inverter. The are calculated Nearest Level Modulation and Selective Harmonics Elimination which two popular low switching frequency modulation schemes. schemes implemented on Multilevel DC-link generate nine level output. simulation carried out using Matlab/Simulink software. Matlab code THD also presented. Hardware result shown validate results....

10.1109/i-pact44901.2019.8960205 article EN 2019 Innovations in Power and Advanced Computing Technologies (i-PACT) 2019-03-01

Abstract Face recognition is one of the most active areas research from past two decades. Attempts are being made to understand how a human recognizes another face. It widely accepted that facial can be based on structural information and nonstructural / spatial details. In present study, he applying differential observations using Eigen docking characteristics many built-in features artificial neural networks. The proposed method aims obtain feature by reducing such as eyes, nose, mouth,...

10.1088/1742-6596/1964/6/062023 article EN Journal of Physics Conference Series 2021-07-01

Summary With the convergence of Internet Things (IoT), 5G, and artificial intelligence, number security violations disturbances on IoT devices networks has increased. Traditional intrusion detection systems (IDS) are inadequate to handle detect attacks. This article proposes an improved critical feature selection (ICFS) algorithm with ensemble learning (EL) for IDS in IoT‐Message queuing telemetry transport (MQTT) network. The proposed framework includes four major parts: (i) RPIMQTTSET...

10.1002/cpe.7445 article EN Concurrency and Computation Practice and Experience 2022-11-01

This paper proposes a solar shot noise suppression algorithm using the complex empirical mode decomposition (CEMD) for orthogonal frequency division multiplexing (OFDM) based visible light vehicular communication. The primary can be used only real-valued signals. In this work, it is extended to use in realm After desired signal broken down into its intrinsic functions (IMF), noisy frequencies are easily eliminated. performance results show that CEMD - good alternative mitigating intense...

10.1109/iceeict56924.2023.10157347 article EN 2023-04-05

Abstract System based on orthogonal frequency division multiplexing with non-orthogonal multiple access represents one of the most promising technology for next generation broadcasting and communication systems. One main challenges in OFDM-based systems is achieving a high peak-to-average power ratio (PAPR). This paper proposes novel precoding method, namely Zadoff-Chu matrix transform, PAPR reduction OFDM NOMA On top that, continuous-magnitude signals require an expensive mixed-signal DAC,...

10.21203/rs.3.rs-1449629/v1 preprint EN cc-by Research Square (Research Square) 2023-03-01

In recent years, many research solutions offered to recognize human emotional states automatically. As per the report of world healthcare organization, people fell unfortunately on road and could not provide first aid time, resulting in death. The proposed design overcomes emergency emotion management system with help physiological sensors. sensors, such as Galvanic Skin Response (GSR) Blood Volume Pressure (BVP) are used identify signals. Initially, ESP32 controller captures signal from GSR...

10.1109/icoei56765.2023.10125696 article EN 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI) 2023-04-11

<span lang="EN-US">Visible Light Communication (VLC) has become an accolade to its radio frequency counterpart. In VLC system, orthogonal division multiplexing (OFDM) drawn much attention, because of simple equalization, high spectral efficiency, data rate and robustness intersymbol interference (ISI). Besides, there are emerging applications that ought be gotten with low latency reliability. To diminish power requirements no transmission capacity extension, Trellis coded modulation...

10.11591/ijece.v9i2.pp1184-1190 article EN International Journal of Electrical and Computer Engineering (IJECE) 2019-04-01

In recent years imprecise multiplier has been widely studied for image processing applications; this is done through compressors. For multiplication when the width large then higher compressor adders are used to reduce reduction stage. The challenging task in approximation via truth table, K-map impossible. paper, 8:2 designed and a novel comparison technique developed approximation. proposed 16x16 compared with existing multiplier. new efficient area, power, delay. Another performance...

10.1109/conecct50063.2020.9198611 article EN 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) 2020-07-01

Orthogonal Frequency Division Multiplexing (OFDM) is an efficient transmission technique for high data rate communication systems. The major problem of OFDM system Peak to Average Power Ratio (PAPR) which reduces the efficiency and increases complexity. In this paper, logarithmic based companding (i.e, mu law) Square rooting (SQRT) have been suggested as simple effective PAPR reduction techniques OFDM. This paper analyzes law SQRT signal on M ary QAM modulation technique. Simulation results...

10.1109/ice-ccn.2013.6528513 article EN 2013-03-01

Objectives: To study and implement various spatial domain denoising filters on Pap Smear microscopic images. Methods/Statistical Analysis: In this paper, we calculated the performance metrics to estimate best fit filtering technique among considered for study. Study of around 300 images with low high color densities are which includes from two different standard slide preparation techniques i.e. Conventional Based Cytology (CBC) Liquid (LBC). Performance is analyses based like PSNR, MSE, NAE...

10.17485/ijst/2016/v9i45/96623 article EN Indian Journal of Science and Technology 2016-12-09

A grid tied photovoltaic system using modular multilevel inverter topology is proposed in this paper. Basic unit structure of used capable converting DC power from PV array to AC for feeding the household loads or utility grid. The has lesser electronic devices compared existing topologies. generates a nearly sinusoidal signal and achieves better output profile with low total harmonic distortion. Simulation carried out MATLAB/Simulink software results are presented.

10.11591/ijpeds.v10.i4.pp2013-2020 article EN International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering 2019-12-01

Many of the Internet Things (IoT) profit significantly from long-range connectivity with low power. Low power wide area network (LPWAN) technologies are designed to extend coverage by minimizing energy efficiency and less expense data throughput. Long range WAN (LoRaWAN) is a media access control (MAC) protocol operated LoRa Alliance using unlicensed radio modulation technology. LoRaWAN provides successful innovation meet long–range low-power demands. offers three distinct device classes (A,...

10.1016/j.procs.2020.04.253 article EN Procedia Computer Science 2020-01-01
Coming Soon ...