A hybrid CNN model for multi-class freshness and disease detection in local spinach varieties Aniket K. Shahade, Priyanka V. Deshmukh, Vidula V. Meshram, Vishal A. Meshram, Disha S. Wankhede, Makarand R. Shahade BMC Plant Biology, 2026 Ensuring the post-harvest quality and health of leafy vegetables is critical for minimizing economic loss, enhancing food security, and promoting sustainable agricultural practices. Spinach, a highly nutritious yet perishable crop, is particularly susceptible to rapid freshness degradation and foliar diseases. While computer vision and deep learning have shown promise for automated quality assessment, existing models often lack the robustness to handle the dual-task classification of both freshness and disease states across diverse local spinach varieties. To bridge this gap, this paper introduces a novel hybrid Convolutional Neural Network (CNN) architecture specifically designed for the multi-class detection of freshness and visual disease symptoms in local spinach leaves. The proposed model synergistically integrates a powerful feature extraction backbone with a tailored attention and fusion mechanism, enhancing its ability to capture discriminative spatial and textural features critical for fine-grained classification. It was trained and validated on a curated dataset comprising high-resolution images of three prominent local varieties (Malabar, Water, and Red spinach) in both fresh and non-fresh conditions. The proposed hybrid model achieved a classification accuracy of 98.36%, significantly outperforming benchmark state-of-the-art models including DenseNet121, ResNet50, and EfficientNetB0. Furthermore, explainable AI (XAI) techniques visually validated the model’s decision-making process, confirming its focus on biologically relevant leaf regions. The results demonstrate that the proposed hybrid framework offers a highly accurate, reliable, and interpretable tool for non-destructive, real-time quality monitoring. This work provides a significant contribution towards intelligent post-harvest management systems, capable of reducing waste and supporting the value chain for local spinach cultivation.
PreventativeTestPro: A Scalable Hybrid Testing Framework Utilizing Observability and Generative AI for Proactive Software Quality Engineering Soham Patel, Kailas Patil, Vishal Meshram, Prawit Chumchu Journal of Visualized Experiments, 2026 This paper introduces a sophisticated, scalable testing system that integrates observability-driven automation with AI-augmented proactive quality engineering to tackle contemporary software delivery difficulties. The suggested system enhances PreventativeTestPro, an open-source, hybrid testing platform that combines black-box and white-box methodologies, by incorporating an innovative observability-based test orchestration layer. The platform utilizes logs, metrics, events, and traces alongside browser and server-side monitoring to promptly identify anomalies, enhance test case selection, and automate the creation of functional, performance, and security test suites. A distinctive characteristic is the incorporation of large language models (LLMs) to provide root cause insights and autonomously construct new test cases based on production behaviors and identified abnormalities, thus providing adaptive regression coverage and intelligent remediation. The system facilitates concurrent test execution with instantaneous AI-driven log analysis, fostering a continuous feedback loop between operations and testing. It has been validated in several enterprise scenarios, including microservices-based SaaS platforms and SAP BTP ecosystems. Empirical findings from four production deployments and a beta group of 49 engineers indicate a decrease of up to 30% in mean time to resolution, over 95% compliance with SLAs, and substantial improvements in both test coverage and defect traceability. The effortless connection with industry-standard tools illustrates its plug-and-play capability. This research presents a comprehensive, tool-independent, and forward-looking quality engineering methodology consistent with agile and DevOps principles. Future endeavors encompass dynamic anomaly classification through machine learning, extension to mobile and user experience-oriented systems, and augmented large language model capabilities for domain-specific test development and failure forecasting.
Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging Vidula V. Meshram, Vishal A. Meshram, Pallavi Rege, Kailas Patil, Shrikant Jadhav, Gandharva Thite Journal of Visualized Experiments, 2025 Conventional deep learning models have demonstrated denoising potential, but face challenges such as extensive computational load, energy usage, and training time. This study presents an energy-efficient denoising methodology that integrates image enhancement and K-means clustering as preprocessing techniques to improve input quality before applying neural networks. This study proposes an energy-efficient denoising pipeline integrating image enhancement using sharpening kernels and image segmentation through K-means clustering before the application of a convolutional autoencoder. The preprocessing steps enabled the model to identify anatomical boundaries and separate noise-affected regions, thereby improving the input quality and enhancing training convergence. Preprocessing sharpens key image features and distinguishes noise-affected regions, enabling adaptive thresholding and more effective denoising with reduced computational cost. The proposed model was evaluated using publicly available CT and MRI datasets. Performance was assessed through Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and classification accuracy. The results showed that PSNR improved from 21.52 dB to 28.14 dB; SSIM increased from 0.7619 to 0.8690, and validation accuracy also improved. The integrated preprocessing reduced training time by ~20% and lowered GPU utilization, thus supporting reproducibility and deployment in computationally constrained environments. The methodology supports sustainable medical imaging practices by minimizing radiation exposure, reducing repeat scans, and extending the lifespan of older imaging equipment. This pipeline contributes to sustainable medical imaging by minimizing radiation exposure, reducing repeat scans, and extending the lifespan of legacy imaging equipment. It is also suitable for remote diagnostics, enhancing telemedicine workflows in low-resource settings. Additionally, the approach supports remote diagnostics, making it suitable for telemedicine applications in low-resource settings.
Applications of machine learning in oilseed crops and industries Vishal Meshram, Vidula Meshram, Reshma Pise, Yogesh Suryawanshi, Kailas Patil Oil Seed Crops, 2025 Oilseed crops, such as soybeans, canola, and sunflowers, are important source of vegetable oil and protein. The production and processing of these crops involves various stages, including planting, harvesting, and refining, which can be improved through the application of machine learning. The challenges faced by farmers in each stage of the oilseed crop are different than the challenges faced by the industry while processing the oil seeds. The contemporary technology in the computer field and a subset of artificial intelligence called as machine learning has already proven its potential to solve complex problems. Machine leaning has been widely used to solve the complex problems in the different domains like healthcare, finance sector, and cyber security. Machine learning algorithms can help farmers and industries in different ways while taking production and processing of oilseed crops. In this chapter, we will review the current state of the art in the use of machine learning for oilseed crop production and processing, highlighting the benefits and challenges of these approaches.
Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation Rohini Jadhav, Vishal Meshram, Amol Bhosle, Kailas Patil, Sital Dash, Shrikant Jadhav Frontiers in Artificial Intelligence, 2025 Fake-news detection requires systems that are multilingual, multimodal, and explainable—yet the majority of the existing models are English-centric, text-only, and opaque. This study introduces two key innovations: (i) a new multilingual–multimodal dataset of 74,000 news articles in Hindi, Gujarati, Marathi, Telugu, and English with paired images, and (ii) Hybrid Explainable Multimodal Transformer Fake (HEMT-Fake) that integrates text, image, and relational signals with hierarchical explainability. The architecture combines transformer embeddings, a convolutional neural network–bidirectional long short-term memory (CNN–BiLSTM) text encoder, residual network (ResNet) image features, and graph sample and aggregate (GraphSAGE) metadata, all of which are fused via multi-head attention. Its explainability module unites attention, Shapley Additive exPlanations (SHAP), and local interpretable model-agnostic explanations (LIME) to provide token-, sentence-, and modality-level transparency. Across four languages, HEMT-Fake delivers a ~ 5% Macro-F1 improvement over Cross-Lingual Language Model with RoBERTa (XLM-R) architecture and Multilingual Bidirectional Encoder Representations From Transformers (mBERT), with gains of 7–8% in low-resource languages. The model achieves 85% accuracy under adversarial paraphrasing and 80% on artificial intelligence (AI)-generated fake news, halving robustness losses compared to baselines. Human evaluation reveals that 82% of explanations are judged to be meaningful, confirming transparency and trust for fact-checkers.
Review of Self-driving Car Based on NEAT Algorithm Om Hotkar, Prahas Nambiar, Amol Dhumane, Shwetambari Chiwhane, Aditi Sharma, Deepak Dharrao, Vishal Meshram Lecture Notes in Networks and Systems, 2025
Mitigating urban heat island and enhancing indoor thermal comfort using terrace garden Girish Visvanathan, Kailas Patil, Yogesh Suryawanshi, Vishal Meshram, Shrikant Jadhav Scientific Reports, 2024 The United Nations advocates for sustainable urban planning and design, emphasizing green infrastructure initiatives to mitigate urban heat island effects and enhance the resilience and livability of cities globally. To address urban heat challenges, a study was conducted in Chennai, India, from April to June 2023. The study focused on assessing temperature dynamics on a building's terrace by comparing a well-maintained garden area with an exposed region. Temperature and humidity sensors were deployed in both the garden and exposed areas of the terrace, as well as within rooms beneath it, to monitor hourly temperature fluctuations. The findings indicate a significant reduction in internal room temperatures in areas with rooftop gardens, ranging from 4 to 11 °C, depending on the time of year and sun's position, compared to rooms with fully exposed roof configurations. Additionally, simulation studies were performed to validate these findings, suggesting that optimizing the distribution of soil beds and plant density across the roof could yield an additional temperature reduction of 3–4 °C, resulting in an overall difference of up to 14–15 °C. The study highlights the efficacy of rooftop gardens in providing cooling effects during daylight hours and maintaining temperature parity post-sunset. Through analysis of sensor data, the research elucidates the intricate relationship between green infrastructure and thermal comfort, offering insights for energy-efficient building design and resilient urban planning. The findings underscore the potential of rooftop gardens in fostering a more comfortable, energy-efficient, and sustainable urban living environment.
Retraction Notice: Texture Based Image and Video Analysis (2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) DOI: 10.1109/ICCCNT61001.2024.10723926) Mohan Garg, J Joyce Jacob, Tusha, Gopalakrishna V Gaonkar, Vishal A. Meshram, T. Kuppuraj 2024 15th International Conference on Computing Communication and Networking Technologies Icccnt 2024, 2024 Texture-based picture and video analysis is a field of PC vision and photograph processing that explores the use of textures as visible descriptors for the characterization and analysis of virtual pictures. This consists of techniques for extraction of textural capabilities, class and segmentation of images, and synthesis of texture-based total consequences. It is useful for a myriad of programs in numerous domain names, including clinical imaging, robotic navigation, video surveillance, anomaly detection, and biometric identification. The principle strategies utilized in texture-based picture and video analysis include mathematical morphology, Gabor filters, Markov random fields, wavelets, and scaling capabilities, gray-stage co-incidence matrices (GLCMs), vicinity and shape functions, and texture synthesis. Mathematical morphology is used for processing geometrical systems in a photo by setting policies for combining pixels in a normal or irregular grid. Gabor filters are used for developing strength profiles of pixels by means of convolving a photograph with sinusoidal capabilities. Markov random fields are used for modeling the spatial interactions inside a photo with the purpose of explaining the statistical houses of the boundary pixels. Wavelets and scaling features are used for decomposing a photo into multiresolution coefficients.
Texture Based Image and Video Analysis Mohan Garg, J Joyce Jacob, Tusha, Gopalakrishna V Gaonkar, Vishal A. Meshram, T. Kuppuraj 2024 15th International Conference on Computing Communication and Networking Technologies Icccnt 2024, 2024
Integrated Dashboard for Generative AI Model Ruthik Jadhav, Shivam Tikone, Mayur Bahiram, Amol Dhumane, Vishal Meshram, Vidula Meshram, Tanupriya Choudhury, Ayan Sar Lecture Notes in Networks and Systems, 2024
Maximum Bandwidth Allocation in Underwater Fibre Optic Networks Vishal A. Meshram, Dhananjay Yadav, Vinitha A, Krishn Murari, Hitesh Kalra, Srisathirapathy S 1st International Conference on Emerging Research in Computational Science Icercs 2023 Proceedings, 2023
Smart Low Cost Fruit Picker for Indian Farmers Vishal Meshram, Kailas Patil, Vidula Meshram, Amol Dhumane, Sudeep Thepade, Dinesh Hanchate 2022 6th International Conference on Computing Communication Control and Automation Iccubea 2022, 2022
Artificial intelligence for early endometrial cancer diagnosis using multimodal clinical data: integrating deep learning, explainability, and data privacy S Dash, K Patil, A Bali, IR Raskar, Y Dongre, A Bhosle, V Meshram Frontiers in Artificial Intelligence 9, 1787508 , 2026 2026
PreventativeTestPro: A Scalable Hybrid Testing Framework Utilizing Observability and Generative AI for Proactive Software Quality Engineering S Patel, K Patil, V Meshram, P Chumchu JoVE (Journal of Visualized Experiments), e69316 , 2026 2026
A hybrid CNN model for multi-class freshness and disease detection in local spinach varieties AK Shahade, PV Deshmukh, VV Meshram, VA Meshram, DS Wankhede, ... BMC Plant Biology , 2026 2026
Dual-Task Convolutional Neural Network for Fruit Classification and Ripeness Prediction VV Meshram, K Patil, VA Meshram, AS Chhajed, R Jadhav, R Tanksale International Conference on Sustainable Innovation with Artificial … , 2026 2026
Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation R Jadhav, V Meshram, A Bhosle, K Patil, S Dash, S Jadhav Frontiers in Artificial Intelligence 8, 1690616 , 2025 2025 Citations: 7
A Dual-Layer, Content-Aware Framework to Validate Online Student Engagement via ML-Based Comprehension Assessment. P Chate, VA Meshram, K Patil Ingénierie des Systèmes d'Information 30 (10) , 2025 2025
Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging VV Meshram, VA Meshram, P Rege, K Patil, S Jadhav, G Thite JoVE (Journal of Visualized Experiments), e68968 , 2025 2025
Exponential Similarity Measure Based Selection of Cloud Service Provisioning in Cloud. VA Meshram, SS Pawar, VV Meshram, A Kale, KS Tiwari, S Ambadekar, ... Mathematical Modelling of Engineering Problems 12 (5) , 2025 2025
Applications of Machine Learning in Oilseed Crops and Industries V Meshram, V Meshram, R Pise, Y Suryawanshi, K Patil Oilseed Crops, 455-467 , 2025 2025
Automatic Topic Classification And Document Clustering Using Lda Based Machine Learning Techniques K Yuvaraj, N Setia, P Goyal, T PK, VA Meshram 2024 Global Conference on Communications and Information Technologies (GCCIT … , 2024 2024
A Comparative Analysis of Routing Protocols in Vehicular Delay-Tolerant Networks J Khurana, R Roopashree, VA Meshram, NV Balaji, S Gupta, R Reena 2024 15th International Conference on Computing Communication and Networking … , 2024 2024
Texture Based Image and Video Analysis M Garg, JJ Jacob, GV Gaonkar, VA Meshram, T Kuppuraj 2024 15th International Conference on Computing Communication and Networking … , 2024 2024
Exploring the Potential of Machine Learning in Automated Real-Time Data Analysis Systems P Chandrakala, VA Meshram, M Meena, MS Nithya, I Alam, VM Kumar 2024 15th International Conference on Computing Communication and Networking … , 2024 2024
Analyzing the Efficiency of Cross-Layer Design for Location-Aware Ad Hoc Networks S Srividhya, R Jain, K Preetham, VA Meshram, K Yuvaraj, M Singh 2024 15th International Conference on Computing Communication and Networking … , 2024 2024
Review of Self-driving Car Based on NEAT Algorithm O Hotkar, P Nambiar, A Dhumane, S Chiwhane, A Sharma, D Dharrao, ... International Conference on Advances in Information Communication Technology … , 2024 2024
Mitigating urban heat island and enhancing indoor thermal comfort using terrace garden G Visvanathan, K Patil, Y Suryawanshi, V Meshram, S Jadhav Scientific Reports 14 (1), 9697 , 2024 2024 Citations: 36
Integrated Dashboard for Generative AI Model R Jadhav, S Tikone, M Bahiram, A Dhumane, V Meshram, V Meshram, ... International Conference on Universal Threats in Expert Applications and … , 2024 2024 Citations: 2
Detection of cardiovascular diseases using machine learning approach A Dhumane, S Chiwhane, M Tamboli, S Ambala, P Bagane, V Meshram International Advanced Computing Conference, 171-179 , 2023 2023 Citations: 4
Maximum Bandwidth Allocation in Underwater Fibre Optic Networks VA Meshram, D Yadav, K Murari, H Kalra 2023 International Conference on Emerging Research in Computational Science … , 2023 2023
Face mask wearing image dataset: A comprehensive benchmark for image-based face mask detection models Y Suryawanshi, V Meshram, V Meshram, K Patil, P Chumchu Data in Brief 51, 109755 , 2023 2023 Citations: 7
MOST CITED SCHOLAR PUBLICATIONS
Machine learning in agriculture domain: A state-of-art survey V Meshram, K Patil, V Meshram, D Hanchate, SD Ramteke Artificial Intelligence in the Life Sciences, 100010 , 2021 2021 Citations: 541
An Astute Assistive Device for Mobility and Object Recognition for Visually Impaired People VV Meshram, K Patil, VA Meshram, FC Shu IEEE Transactions on Human-Machine Systems , 2019 2019 Citations: 165
FruitNet: Indian fruits image dataset with quality for machine learning applications V Meshram, K Patil Data in Brief 40, 107686 , 2021 2021 Citations: 105
Sen-2 LULC: Land use land cover dataset for deep learning approaches S Sawant, RD Garg, V Meshram, S Mistry Data in Brief 51, 109724 , 2023 2023 Citations: 37
Mitigating urban heat island and enhancing indoor thermal comfort using terrace garden G Visvanathan, K Patil, Y Suryawanshi, V Meshram, S Jadhav Scientific Reports 14 (1), 9697 , 2024 2024 Citations: 36
MNet: A framework to reduce fruit image misclassification. VA Meshram, K Patil, SD Ramteke Ingénierie des systèmes d Inf. 26 (2), 159-170 , 2021 2021 Citations: 27
A survey on ubiquitous computing V Meshram, V Meshram, K Patil ICTACT Journal on Soft Computing 6 (2), 1130-1135 , 2016 2016 Citations: 26
Fruitsgb: top Indian fruits with quality V Meshram, K Thanomliang, S Ruangkan, P Chumchu, K Patil IEEE Dataport , 2020 2020 Citations: 25
SmartMedBox: A smart medicine box for visually impaired people using IoT and computer vision techniques VV Meshram, KR Patil, VA Meshram, S Bhatlawande Revue d'Intelligence Artificielle 36 (5), 681 , 2022 2022 Citations: 23
Addressing misclassification in deep learning: a merged net approach V Meshram, Y Suryawanshi, V Meshram, K Patil Software Impacts 17, 100525 , 2023 2023 Citations: 16
A comprehensive dataset of damaged banknotes in Indian currency (Rupees) for analysis and classification V Meshram, V Meshram, K Patil, Y Suryawanshi, P Chumchu Data in Brief 51, 109699 , 2023 2023 Citations: 15
FruitNet: Indian fruits dataset with quality (good bad & mixed quality) V Meshram, K Patil Mendeley Data 1 , 2021 2021 Citations: 15
Border-Square net: a robust multi-grade fruit classification in IoT smart agriculture using feature extraction based Deep Maxout network V Meshram, K Patil Multimedia Tools and Applications 81 (28), 40709-40735 , 2022 2022 Citations: 14
A Comparative Analysis of Intrusion Detection Techniques: Machine Learning Approach VM Komal Rasane, Laxmi Bewoor Proceedings of International Conference on Communication and Information … , 2019 2019 Citations: 14
Dry fruit image dataset for machine learning applications V Meshram, C Choudhary, A Kale, J Rajput, V Meshram, A Dhumane Data in Brief, 109325 , 2023 2023 Citations: 13
Smart low cost fruit picker for Indian farmers V Meshram, K Patil, V Meshram, A Dhumane, S Thepade, D Hanchate 2022 6th International Conference On Computing, Communication, Control And … , 2022 2022 Citations: 13
Evaluation of top pretrained models using transfer learning on banknote dataset with quality parameter V Meshram, K Patil, V Meshram Ingénierie des Systèmes d'Information 28 (3), 693 , 2023 2023 Citations: 9
Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation R Jadhav, V Meshram, A Bhosle, K Patil, S Dash, S Jadhav Frontiers in Artificial Intelligence 8, 1690616 , 2025 2025 Citations: 7
Face mask wearing image dataset: A comprehensive benchmark for image-based face mask detection models Y Suryawanshi, V Meshram, V Meshram, K Patil, P Chumchu Data in Brief 51, 109755 , 2023 2023 Citations: 7
Dataset of indian and thai banknotes V Meshram, P Thamkrongart, K Patil, P Chumchu, S Bhatlawande IEEE Dataport , 2020 2020 Citations: 6
