Mani Deepak Choudhry

Mr. Mani Deepak Choudhry

KGiSL Institute of Technology, Coimbatore, India
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 August 2024
Verified
Book Chapter
Closed access
PDF file
MCMani Deepak Choudhry
Mani Deepak Choudhry
MSM. Sundarrajan
M. Sundarrajan
SJS. Jeevanandham
S. Jeevanandham
VSV. Saravanan
V. Saravanan
As technology advances, it's becoming increasingly important to address security and privacy concerns related to AI-based biometric systems. The risks of adversarial attacks, information security breaches, and identity theft are significant threats to individuals' confidentiality. To ensure data protection, it's essential to have ongoing surveillance and robust validation measures in place. The need for user authorization, safeguarding data integrity, and the potential consequences of widespread surveillance are all critical aspects that raise privacy concerns. Balancing the benefits of these systems with the rights of individuals and societal interests requires careful consideration of ethical standards and regulations. This book chapter provides a comprehensive analysis of the privacy and security risks associated with AI-based biometric systems. It delves deeply into the security-related challenges such as data integrity breaches, identity theft risks, and adversarial attacks, underscoring the need for constant monitoring and authentication. The chapter also examines privacy concerns such as obtaining user consent, safeguarding data, and addressing the implications of widespread surveillance. Additionally, it discusses the ethical and legal considerations, highlighting the importance of striking a fair balance between the system's benefits and individual and societal rights. The chapter ultimately stresses the significance of handling these issues appropriately to deploy AI-based biometric technologies in a manner that preserves individual rights in our increasingly interconnected world. <!----> <!----> <!----> <!---->

5 October 2024 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
DPD Pavithra
D Pavithra
TPT Parameswaran
T Parameswaran
MCMani Deepak Choudhry
Mani Deepak Choudhry
SAS Amrutha
S Amrutha
TDT Deepa
T Deepa
RKR Kiruthiga
R Kiruthiga
Objectives: This paper looks into the application of LSTM networks in improving continuous patient monitoring and anomaly detection on wearable health devices by using accurate analysis of sequential physiological data. Methods: This paper presents a new use of LSTM networks, which are very powerful in the analysis of time series data, making them quite accurate in their predictions and thus adding functionality to wearable health devices. Our approach is to train an LSTM model on a huge dataset such as PhysioNet, which includes over 60,000 recordings of ECG signals from more than 50 different databases, encompassing a wide variety of physiological conditions and signal types, so the model learns across a wide range of health conditions and demographics. Findings: The proposed LSTM-based model reduces false positives by 30% and false negatives by 40%, hence improving anomaly detection accuracy by up to 30% over prior methods such as SVM, Random Forest, KNN, DBSCAN, TDL, and DQN. Novelty: This work uniquely enhances the existing literature by applying LSTM networks specifically to wearable health devices, optimizing the detection of health anomalies in real time with higher accuracy compared to traditional methods. It also introduces a novel approach to handling complex sequential physiological data, contributing to more reliable and timely medical interventions. Keywords: LSTM networks, Wearable Health Devices, Patient Monitoring, Anomaly Detection, Time-series data

16 February 2022
Verified
Conference Paper
Closed access
MCMani Deepak Choudhry
Mani Deepak Choudhry
JSJeevanandham S
Jeevanandham S
BRBiji Rose
Biji Rose
SPSruthi Mol P
Sruthi Mol P
Many industrial processes have been transformed by ict infrastructure. Artificial intelligence and machine learning algorithms have been needed by companies of all sizes, whether minor or major, to handle the terabytes of data created by sensing, actuation, production control systems, and web services. These data are large (terabytes) and diverse (picture, audio, video, graphics), necessitating the use of specific models and approaches for analysis and administration. Intelligent technologies create enormous quantities of data in massive industrial networks, hence IIoT frameworks demand clever, resilient big data analysis tools. Because of their cognitive acquisition and processing capabilities, artificial intelligence (AI) and machine learning (ML) techniques generate impressive outcomes in IIoT networks. The possibility of machine learning in IIoT applications is assessed in this research study, which also gives a comprehensive topology of IIoT and major enabling technologies. The theoretical underpinnings of numerous well-known ML algorithms, as well as several software and hardware frameworks for ML implementations, are then presented. The use of machine learning techniques in IIoT applications is briefly covered. Finally, this study identifies key problems as well as potential research directions.

2 September 2024 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
MSM Sundarrajan
M Sundarrajan
MCMani Deepak Choudhry
Mani Deepak Choudhry
JBJ Biju
J Biju
SKS Krishnakumar
S Krishnakumar
KRK Rajeshkumar
K Rajeshkumar
Background/ Objectives: Low-light medical imaging is highly challenging in clinical diagnostics due to increased noise levels that mask or obscure important anatomical details. In this respect, conventional noise reduction methods such as Gaussian filtering and median filtering usually lead to a trade-off between noise suppression and the preservation of important features in an image, thus resulting in poor-quality images. More advanced wavelet-based denoising and Non-Local Means methods exhibit superior noise reduction but remain computationally intensive and introduce artifacts. These challenges come with a need to develop more effective and efficient noise-reduction techniques. Methods: This study proposes an end-to-end deep learning framework for low-light medical image enhancement. We present a comprehensive deep-learning framework to enhance low-light medical images by integrating Convolutional Neural Networks with denoising autoencoders to build a robust noise reduction model. The CNN extracts the feature from the noisy input images, while the autoencoder does so for the reconstruction of clean images through the encoding of a noisy input in a lower-dimensional representation for the reduction of noise while retaining critical information. Findings: This study validates the proposed model through rigorous quantitative metrics such as peak signal-to-noise ratio and structural similarity index. These metrics are designed to provide a full assessment of image quality concerning noise reduction capability and preservation of details related to structure. Our model improves traditional methods in PSNR by about 5 dB on average and SSIM by 0.15, which means better noise reduction and preservation of image details. A comparative analysis of traditional techniques for noise reduction has been included, pointing out the advantages of deep learning approaches. Experimental results depict significant improvements over previous approaches. For instance, the proposed model reduces the noise level by up to 40% and facilitates clear and sharp images by up to 30%. In terms of quantification, these improvements manifest in a PSNR value of 35 dB and an SSIM score of 0.85 compared to 30 dB and 0.70 using traditional techniques. Furthermore, the study illustrates the training dynamics, feature maps, and evolution of images to present the model's incremental learning process. Novelty: This study's findings validate the proposed model's efficacy in enhancing diagnosis accuracy and improving patient outcomes in medical imaging. Keywords: Low-light medical imaging, Noise reduction, Convolutional Neural Networks, Denoising autoencoders, Medical diagnostics

23 December 2025 in Automatika
Verified
Journal Article
Open access
AAA. Amirthasaravanan
A. Amirthasaravanan
MCMani Deepak Choudhry
Mani Deepak Choudhry
SJS. Jeevanandham
S. Jeevanandham
SRS. Ramasamy
S. Ramasamy
KSK. Suvalakshmi
K. Suvalakshmi
DKD. Karthikeswaran
D. Karthikeswaran

30 June 2023
Verified
Book Chapter
Closed access
MSM. Sundarrajan
M. Sundarrajan
AJAkshya J
Akshya J
MCMani Deepak Choudhry
Mani Deepak Choudhry
BRBiji Rose
Biji Rose
TJT. Jayapratha
T. Jayapratha
VNV. Nithya
V. Nithya
The usage of cyber-physical systems is well known to play a vital role in the development of precision agriculture, which in turn raises overall output. When a network of Unmanned Aerial Vehicle (UAV) is deployed for these applications, they are considered CPS. One of the most crucial things that needs to be handled is covering the area that needs to be travelled with the least number of UAV traversals possible. UAV traversal is a crucial part of precision agriculture because it enables farmers to gather crucial information and make informed decisions that may lead to higher crop yields and cheaper costs. Thanks to improved algorithms and techniques, UAVs can traverse agricultural land more effectively and precisely. As a result, farming activities become more productive and environmentally friendly. This chapter explores the various approaches that might be used to determine the UAV's best route when it is deployed over farmland. Request access from your librarian to read this chapter's full text.