Leveraging Advanced Deep Learning Algorithms for Corn Leaf Disease Detection Tejas Chauhan, Madhu Shukla, Vijay Katkar, Biswaranjan Acharya, Vassilis C. Gerogiannis, Andreas Kanavos International Journal on Artificial Intelligence Tools, 2025 Effective detection of corn leaf diseases is vital for preventing significant agricultural losses. This paper presents a novel methodology that integrates Transfer Learning, Kernel Principal Component Analysis (Kernel PCA)-based feature enhancement, and bio-inspired optimization to improve disease classification on corn leaves. Several pretrained models, including MobileNet, VGG16, and various DenseNet and ResNet architectures, were employed to extract deep features from corn leaf images. Kernel PCA was used to capture nonlinear patterns, enhancing the models’ discriminative power. Classification was performed using the XGBoost algorithm, optimized through the Slime Mould Algorithm (SMA) for feature selection and hyperparameter tuning. Experimental results demonstrate that MobileNet achieved the highest performance with an accuracy of 99.08% and specificity of 99.39%, while DenseNet169 showed comparable effectiveness. The interpretability of the proposed framework was validated using Local Interpretable Model-Agnostic Explanations (LIME), which visually highlighted the critical regions of leaf images influencing disease classification decisions. This integrated approach provides a robust, accurate, and interpretable system for corn leaf disease detection.
Harnessing AI for climate solutions: Tools and techniques Kumar J. Parmar, Tejas Chandulal Chauhan, T. Premavathi Advances in Computational Intelligence for Climate Change Security and Sustainability, 2025 Subsequently, AI has been instrumental toward suppressing the climate change issue considering it sets creative techniques across the various quandaries associated with the global changes. The following areas of use have been identified: energy control, reduction of greenhouse gas emissions, climatic simulation, and prediction of storms. The strength of AI that is its suitability to work on vast, intertwined datasets can be used to explain patterns and findings which would help researchers and policymakers in eradicating climate change. Looking at the impact of climate change, AI is employed to improve energy, and decrease its usage as well as adopt to green energy. AI systems, by nature, are highly dependent on data, underline the motivating computational requirements and energy utilization, in general, and are linked with the carbon footprint. In addition, lack of data, data quality issues, and relevance and originality of professional practice could also avert the application of intelligent climate solutions based on artificial intelligence, particularly in the developing world.
Optimizing CNN-Based Video Summarization With Digital Twin Framework for Adaptive Probability Thresholding Rachit Adhvaryu, Munindra Lunagaria, Ambresh Bhadrashetty, Sudhir Anakal, Deepak Gupta, Rubal Jeet, Tejas Chauhan, Dipesh Kamdar, Aditi Sharma IEEE Communications Standards Magazine, 2025 The rapid growth of video data necessitates efficient summarization techniques to extract critical insights while minimizing computational overhead. This study investigates three pre-trained CNN models—AlexNet (61 M parameters), GoogLeNet (6.8M), and SqueezeNet (1.24M)—with respective inference speeds of 23.8 ms/frame, 18.4 ms/frame, and 12.6 ms/frame. These computational differences significantly affect real-time summarization performance. A probability-driven thresholding mechanism was introduced to optimize object detection, effectively reducing false positives and enhancing classification accuracy. Among the models, GoogLeNet achieved the best trade-off between accuracy (98.96%) and computational efficiency, while AlexNet attained the highest detection accuracy (99.12%) but exhibited a higher false detection rate (5.6%). SqueezeNet, though lightweight and resource-efficient, reached an accuracy of 94.26% but faced limitations in fine-grained recognition tasks. Probability versus correct detection analysis indicated that a threshold of 0.7 maximized accuracy while reducing misclassifications. The proposed adaptive thresholding framework demonstrates strong applicability in real-world scenarios such as wildlife monitoring, intelligent surveillance, and IoT-enabled video analytics. By bridging CNN-based architectures with scalable IoT-driven solutions, this research advances the development of robust, accurate, and efficient video summarization systems for next-generation intelligent environments.
Service level agreement parameter matching in cloud computing Tejas Chauhan, Sanjay Chaudhary, Vikas Kumar, Minal Bhise Proceedings of the 2011 World Congress on Information and Communication Technologies Wict 2011, 2011 Cloud is a large pool of easily usable and accessible virtualized resources (such as hardware, development platforms and/or services). It provides an on-demand, pay-as-you-go computing resources and had become an alternative to traditional IT Infrastructure. As more and more consumers delegate their task to cloud providers, Service Level Agreement (SLA) between consumer and provider becomes an important aspect. Due to the dynamic nature of cloud the matching of SLA templates need to be dynamic and continuous monitoring of Quality of Service (QoS) is necessary to enforce SLAs. SLA template contains many parameters like cloud's resources (physical memory, main memory, processor speed etc.) and properties (availability, response time etc.). This work addresses the issue of matching SLA parameters to find suitable cloud provider for particular application.
