V Santhi

Dr. V Santhi

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
13 February 2018 in Composite Interfaces
Verified
Journal Article
Closed access
MRM.T. Ramesan
M.T. Ramesan
VSV Santhi
V Santhi
Conducting polymer composites of polypyrrole (PPy) and silver doped nickel oxide (Ag-NiO) nanocomposites were synthesised by in situ polymerisation of pyrrole with different contents of Ag-NiO nanoparticles. The formation of nanocomposites were studied by Fourier transform infrared (FTIR) and UV–vis spectroscopy, field emission scanning electron microscopy (FE-SEM), X-ray diffraction (XRD), thermogravimetric analysis (TGA), differential scanning calorimetry (DSC) and AC and DC conductivity measurements. The sensitivity of ammonia gas through the nanocomposite was analysed with respect to different contents of nanoparticles. Spectroscopic studies showed the shift in the absorption bands of polymer nanocomposite than that of pure PPy indicating the strong interaction between the nanoparticles and polymer chain. FESEM revealed the uniform dispersion of nanoparticles with spherically shaped metal oxide particles in PPy matrix. The XRD pattern indicated a decrease in amorphous domain of PPy with increase in loading of nanoparticles. The higher thermal stability and glass transition temperature of polymer nanocomposites than that of pure PPy were revealed from the TGA and DSC respectively. The dielectric properties, DC and AC conductivity of nanocomposites were much higher than PPy and these electrical properties increases with the loading of nanoparticles. The nanocomposites showed an enhancement in sensitivity towards ammonia gas detection than PPy.

23 July 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SSSambhaji Marutirao Shedole
Sambhaji Marutirao Shedole
VSV Santhi
V Santhi

18 March 2025 in IEEE Access
Verified
Journal Article
Open access
PRPadmaja Ramachandra
Padmaja Ramachandra
VSV Santhi
V Santhi
Lenders typically conduct thorough credit checks to mitigate credit default risk before lending money. Proactively predicting loan defaulters has become increasingly important. However, creating robust deep-learning algorithms that classify loan defaulters requires abundant data, potentially compromising individuals’ privacy. We investigate the potential of replacing the original data with statistically similar synthetic data to be used as training data to predict loan defaulters. Generative adversarial networks stand out with the best privacy utility trade-off among the many approaches that can generate synthetic data. However, limited data and membership inference attacks still significantly affect the privacy of the synthetic data generated. This paper uses federated learning to create synthetic data to improve loan defaulter prediction. By allowing multiple institutions to collaboratively train a shared model without directly exchanging sensitive loan data, this privacy-preserving approach allows for the utilization of more extensive and diverse datasets, potentially leading to significant improvements in prediction accuracy compared to traditional, siloed approaches. This method also builds a layer of privacy to safeguard against membership inference attacks using a differentially private optimizer layer in the WGAN architechture. The proposed framework utilizes a Min-Max Module and Autoencoders for global representation of distributed loan data, followed by a Federated WGAN, enhanced with a Gaussian noise-added Adagrad optimizer, to generate high-fidelity, privacy-preserved synthetic credit risk data. Furthermore, we use CTGAN to mitigate class imbalance in the synthetic dataset. Finally, we test the generated synthetic dataset using a model trained on the real dataset to check its utility. With this novel framework, we could attain a privacy-utility tradeoff in a federated environment. Our extensive experimentation, which includes a variety of communication rounds, client populations, and privacy budgets, demonstrates that the proposed framework achieves an impressive 95% accuracy. The proposed model marks a significant improvement over both a non-federated setup, which achieves 82% accuracy, and FLIGAN with 73% accuracy, which possesses the same functionalities with different techniques.

23 March 2025 in International Journal of Data Informatics and Intelligent Computing
Verified
Journal Article
Open access
PDF file
SSSambhaji Marutirao Shedole
Sambhaji Marutirao Shedole
VSV Santhi
V Santhi
With the growing popularity of the Internet of Things (IoT) and the proliferation of AI-powered smart devices, a vast amount of digital data is being stored and shared on public platforms such as LinkedIn, Facebook, Twitter, Flickr, and other social media websites. Among these, digital images are the most commonly used medium for data sharing. Recent reports indicate that Google Photos stores over a billion images per week. Additionally, digital images play a crucial role in various applications, including social media, smart healthcare, intelligent transportation systems, industrial automation, robotics, the film industry, legal systems, news and insurance industries, and business sectors. However, the misuse of these images raises significant concerns regarding privacy and security. Identity theft, a growing issue in the 21st century, is a primary contributor to fraud in India and other countries. Thus, ensuring the security of digital images is a critical challenge that needs to be addressed. Currently, watermarking algorithms offer the most cost-effective solution for securing digital images. Watermarking involves embedding hidden marks within digital content to enhance its security. The key benefits of watermarking include: 1. Reducing bandwidth and storage demands, 2. Preventing copyright infringement and ownership disputes, 3. Protecting against tampering, and 4. Serving as an authentication keyword. Watermarking has gained significant traction in various fields, including cybersecurity and e-governance; given the growing importance of digital watermarking from a security perspective, this study aims to provide a comprehensive analysis of watermarking techniques and their evaluation methods across different applications. The findings of this extensive study are presented in this paper. Social media and healthcare. The primary objective of watermarking research is to enhance robustness, watermark capacity, and invisibility—an intricate trade-off among these factors. However, many existing watermarking techniques lack adequate security measures. Various approaches are available for both implementing and evaluating digital watermarking algorithms.

29 August 2022 in International Journal of System Assurance Engineering and Management
Verified
Journal Article
Closed access
PDF file
TRT. Ramesh
T. Ramesh
VSV Santhi
V Santhi

23 February 2024
Verified
Book Chapter
Closed access
VSV Santhi
V Santhi
YSYamala N. V. Sai Sabareesh
Yamala N. V. Sai Sabareesh
PSPonnada Prem Sudheer
Ponnada Prem Sudheer
VKVilluri Poorna Sai Krishna
Villuri Poorna Sai Krishna
Smart homes, smart buildings, and smart cities increase the quality of living by creating a world that is better and more secure, reducing dependency on human needs and efforts. This chapter investigates the complex landscape of security threats resulting from the integration of AIoT (artificial intelligence of things) and cloud platforms within the domains of smart homes, smart buildings, and smart cities. It examines the distinctive challenges and vulnerabilities that arise when these technologies converge. These technologies hold the potential to significantly enhance the quality of life, reinforce home security, and facilitate elderly care. However, their effectiveness hinges on access to extensive data about users' homes and private lives. This chapter underscores the critical need to address the ensuing security and privacy concerns, which present substantial barriers to the widespread adoption of these promising technologies.