Computer Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition, Economics and Econometrics
24
Scopus Publications
Scopus Publications
JPEG-compression agnostic identification of generative art using explainable spatial domain features Vrinda Kohli, Janmey Shukla, Harish Sharma, Narendra Khatri Array, 2026 In recent years, the art landscape has undergone a considerable transformation with the emergence of AI-powered generative art tools, challenging traditional notions of artistic authenticity and ownership. The exponential growth of generative artwork sharing on social media platforms has created an urgent need to protect artists' intellectual properties from impersonation, forgery, and style appropriation. This study introduces an innovative, lightweight detection framework that efficiently distinguishes AI-generated art from human-created artwork by analyzing spatial domain features using tree-based ensembles. The study focuses on two prominent generative image architectures, StyleGAN2-ADA and Stable Diffusion, to explore the method's effectiveness across various classes of probabilistic deep generative models while incorporating JPEG compression considerations to reflect real-world social media conditions. The framework was evaluated across a diverse dataset of 10,000 images, achieving a detection accuracy of 94.43 % for StyleGAN2-ADA and 97.97 % for Stable Diffusion outputs on average across varying quality factors (QF). A key limitation observed is the lack of cross-architecture generalization-classifiers trained on one generative model do not reliably detect outputs from others, highlighting the need for architecture-agnostic detection strategies for real-world deployment. These results demonstrate comparable or better performance to existing deep learning solutions, requiring significantly less computational resources and training data. The proposed approach represents a significant step towards digital art authentication, offering a practical solution for real-time detection of AI-generated artwork in social media environments. Future work will focus on expanding the framework's capabilities to address emerging generative models and developing and integrating tools for automatic art authentication across various social media platforms.
Green Goals, Gray Areas: Understanding the Complexities of Electric Vehicle Adoption in India Review of Integrative Business and Economics Research, 2026
Advanced Battery Management System Design and Validation Using Simulink for Enhanced Efficiency and Longevity Kushagra Singh Lodha, Narendra Khatri, Harish Sharma Sist 2025 2025 IEEE 5th International Conference on Smart Information Systems and Technologies Conference Proceedings, 2025 An effective Battery Management System (BMS) is a key to guaranteeing safe operation, maximum efficiency, and prolonged lifespan of batteries in varied charge-discharge cycles and environmental conditions. A proper BMS is always tracking voltage and temperature in cells, analyzing the state-of-charge (SoC) and state-of-health (SoH), synchronizing power supply for minimizing overcharge and thermal runaway risks, enhancing the charging process, balancing the SoC quantity among individual cells, and disconnecting the battery pack from the load when needed to avoid possible failures. BMSs are widely employed in industrial and commercial applications, maximizing battery efficiency while keeping the battery state within safe limits to ensure maximum lifespan. Simulink is a suitable tool to simulate BMS, since it is full of modeling and simulation capabilities. It allows for the generation of single-cell-equivalent circuits, parameter estimation, electronic circuit design, generation of control logic, code generation, and verification processes. Electrical networks that simulate real system topologies can be used to model battery packs, parameterize circuit components from test data to accurately model cell chemistry, and power electronics circuits interconnecting the pack to control systems. With Simulink, it is possible to simulate closed-loop control algorithms dedicated to fault detection and supervisory logic, as well as state observers for online SoC and SoH estimation. By simulating a BMS in various operating and fault conditions, Simulink allows for exhaustive pre-hardware testing. Its real-time simulation capabilities also allow for hardware-in-the-loop (HIL) testing, thus ensuring a validated BMS design before hardware implementation.
Hybrid PSO-ACO Optimized CNN: A Novel Approach for Pneumonia Detection Harshit Sharma, Simran Kaur, Harish Sharma, Harshada Chandel 2025 2nd Asia Pacific Conference on Innovation in Technology Apcit 2025, 2025 Pneumonia detection is a critical task in medical imaging that involves accurately classifying chest X-ray images to diagnose the presence of pneumonia. Deep Convolutional Neural Networks (CNNs) have demonstrated remarkable success in this domain by automatically extracting and learning relevant features from X-ray images, making them highly effective for medical diagnosis. However, optimizing CNN architectures and identifying ideal hyperparameters remains a complex and challenging process that requires extensive tuning and evaluation. This study proposes a novel approach that integrates Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) with CNNs to enhance image classification performance. By leveraging PSO’s global exploration capabilities and ACO’s local exploitation strengths, the proposed PSO-ACO framework effectively balances the search process within the hyperparameter space. The seamless integration of these metaheuristic algorithms into CNN architecture optimization results in significant improvements in classification accuracy and a reduction in training time. Beyond enhancing CNN efficiency, this hybrid strategy contributes to improved diagnostic accuracy while mitigating time constraints in clinical settings.
Deep Learning-Based Automated Diagnosis and Classification of Rice Leaf Diseases Using CNN Architectures for Sustainable Agriculture C S Santhosh, Sharath Kumar R, Nisha P, Narendra Khatri, Harish Sharma, et al. Proceeding 12th International Conference on Information Technology Innovation Technologies Icit 2025, 2025 A staple crop, rice feeds a substantial chunk of the world's population. However, several diseases adversely affect productivity and quality; therefore, timely diagnosis and management are required to prevent significant crop losses. Nowadays, agronomists' identification of rice leaf diseases is laborious, time-consuming, and prone to human error. Several automated and accurate disease detection and classification solutions have recently emerged with the advancements of artificial intelligence (AI) and deep learning. In this work, the results were analyzed using deep learning algorithms such as CNN, VGG19, EfficientNetB0, ResNet50, and DenseNet121 to diagnose and classify the type of rice leaf disease, including its severity and the location in which it is found. With the help of a dataset containing rice leaf images infected with bacterial leaf blight, brown spot, leaf blast, and other similar types of infection, DenseNet121 outdid all the different models and scored with an accuracy of 94, precision of 0.93, recall of 0.94 and F1-score of 0.93. The results indicate the feasibility of deep learning-based approaches to improve rice disease management practices for sustainable agricultural productivity.
ANALYZING THE EFFECT OF CLIMATE CHANGE ON CROP YIELD OVER TIME USING MACHINE LEARNING TECHNIQUES Heta Patel, Harish Sharma, Varuni Sharma Precision Agriculture for Sustainability Use of Smart Sensors Actuators and Decision Support Systems, 2024 Climate change has affected our planet adversely over the years, and situations are getting worse day by day. Agriculture being primarily affected by climatic parameters; climate change has its adverse effect on the field of agriculture too. Various methods have also been adopted to organically produce crop yield. But, such methods along with modern agricultural practices, such as greenhouse farming, etc., are not yet widely spread across the globe. Especially the developing countries are not yet able to fully adapt to the modern farming techniques and include the state-of-the-art technologies in their farming system. This becomes a major issue as developing countries are the ones that mostly have tropical weather, which in turn is very fruitful for producing crops. Hence, there is a need to deeply analyze and understand the climatic effect on the agricultural yield due to global warming. Understanding and predicting the yield while keeping in mind the climatic parameters help farmers to prepare well for the adversities and minimize 306loss or even adapt to modern technologies and maximize profits. A lot of research and analysis has already been done toward yield forecasting as well as the effect of climate on crops. But, there is no existing amalgamation of all parameters and techniques to study the process of yield forecasting. So now, there is a need to put all the research previously performed under a common umbrella and understand the most important factors affecting crop yield. In this chapter, the authors have presented a detailed comparative study and analysis of all factors affecting the crop yield as well as understanding the climatic effect on the produce. In this chapter, along with parameter analysis, the authors have also presented a study of machine learning algorithms that has been previously proven to present exceptional results in terms of yield forecasting. Not only does the data studied in this chapter help us to analyze the global agricultural scenario, but also the time frame of a few decades for the crop yield data is considered to examine deeply the climatic factor affecting the yield.
Understanding the Factors behind Consumers’ Purchase Intention toward Electric Cars in India Review of Integrative Business and Economics Research, 2024
Impact and Challenges for the Indian Education System Due to the COVID-19 Pandemic Encyclopedia of Covid Volumes 1 18, 2024
Impact and challenges for the indian education system due to the COVID-19 pandemic Impacts and Implications of Covid 19 an Analytical and Empirical Study, 2021
Region based undetectable multiple image watermarking Shalu Singh, Ranjan Kumar Arya, Harish Sharma 2016 International Conference on Computational Techniques in Information and Communication Technologies Icctict 2016 Proceedings, 2016
