Jnaneshwar Pai Maroor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jnaneshwar Pai Maroor has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Deepak Kumar
Manav Rachna International Institute of Research and Studies
3 shared publications - Mangal Singh
Department of Electronics and Telecommunication Engg, Symbiosis International (Deemed University), Symbiosis Institute of Technology, Pune, India
3 shared publications - Ramakrishna Kolikipogu
Department of Information Technology, Chaitanya Bharathi Institute of Technology, Hyderabad, Telangana, India
2 shared publications - Reddy
Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, India
2 shared publications - Syed Hauider Abbas
Department of Computer Science & Engineering, Integral University, Lucknow, India
2 shared publications - Bhagavan Konduri
Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, India
1 shared publication
Latest Publications
- 26 June 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 35 (05)
EnsembleXAI Framework for Real-Time Intelligent Data Security, Distributed Computing, and Explainable Cloud Storage Applications
The rapid expansion of distributed computing and cloud storage has increased the demand for intelligent and explainable data security frameworks. Traditional anomaly detection models often function as black boxes, providing little to no insight into decision-making processes, thus limiting their adoption in critical infrastructures where transparency and compliance are mandatory. This study introduces the EnsembleXAI Framework, an integrated architecture combining ensemble learning, explainable artificial intelligence (XAI), federated learning, and distributed edge–cloud computing. The methodology incorporates parallel CNN, LSTM, and Transformer pipelines to extract deep spatiotemporal features, fused through attention gating and ensemble classifiers such as Random Forests and deep neural networks. Interpretability is ensured using SHAP, LIME, and Integrated Gradients, allowing local and global explanations for anomaly detection outcomes. Privacy preservation is achieved via federated learning with differential privacy and homomorphic encryption, while blockchain mechanisms guarantee model update integrity. The proposed framework achieves 98.1% detection accuracy, 97.6% precision, 97.0% recall, and 97.3% F1-score, significantly outperforming baseline CNN, LSTM, and Transformer-only models. Furthermore, explainability fidelity exceeds 93%, ensuring regulatory compliance and user trust. Edge–fog deployment reduces latency to 41.2 ms, enabling real-time inference and dynamic access control for secure cloud storage. Overall, the framework delivers scalable, secure, and interpretable solutions for distributed IoT and cloud ecosystems, advancing the state of trustworthy AI in cybersecurity.
- 26 June 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 35 (05)
EnsembleXAI Framework for Real-Time Intelligent Data Security, Distributed Computing, and Explainable Cloud Storage Applications
The rapid expansion of distributed computing and cloud storage has increased the demand for intelligent and explainable data security frameworks. Traditional anomaly detection models often function as black boxes, providing little to no insight into decision-making processes, thus limiting their adoption in critical infrastructures where transparency and compliance are mandatory. This study introduces the EnsembleXAI Framework, an integrated architecture combining ensemble learning, explainable artificial intelligence (XAI), federated learning, and distributed edge–cloud computing. The methodology incorporates parallel CNN, LSTM, and Transformer pipelines to extract deep spatiotemporal features, fused through attention gating and ensemble classifiers such as Random Forests and deep neural networks. Interpretability is ensured using SHAP, LIME, and Integrated Gradients, allowing local and global explanations for anomaly detection outcomes. Privacy preservation is achieved via federated learning with differential privacy and homomorphic encryption, while blockchain mechanisms guarantee model update integrity. The proposed framework achieves 98.1% detection accuracy, 97.6% precision, 97.0% recall, and 97.3% F1-score, significantly outperforming baseline CNN, LSTM, and Transformer-only models. Furthermore, explainability fidelity exceeds 93%, ensuring regulatory compliance and user trust. Edge–fog deployment reduces latency to 41.2 ms, enabling real-time inference and dynamic access control for secure cloud storage. Overall, the framework delivers scalable, secure, and interpretable solutions for distributed IoT and cloud ecosystems, advancing the state of trustworthy AI in cybersecurity.
- 13 January 2025
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 8 (2) , 387-399
Improving Food Safety by IoT-based Climate Monitoring and Control Systems for Food Processing Plants
- 13 January 2025
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 8 (2) , 387-399
Improving Food Safety by IoT-based Climate Monitoring and Control Systems for Food Processing Plants
- 18 December 2024
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 8 (1) , 74-83
Improving Smart Agriculture Through the Use of Machine Learning to Offer Tailored Crop Forecasts
- 18 December 2024
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 8 (1) , 74-83
Improving Smart Agriculture Through the Use of Machine Learning to Offer Tailored Crop Forecasts
- 18 September 2024
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 7 (4) , 443-456
Climate Impact Prediction: Whale-Optimized Conv-XGBoost with Remote Sensing and Sociological Data
- 18 September 2024
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 7 (4) , 443-456
Climate Impact Prediction: Whale-Optimized Conv-XGBoost with Remote Sensing and Sociological Data
- Open Access
- 26 March 2023
- Published by Igor Sikorsky Kyiv Polytechnic Institute in Известия высших учебных заведений. Радиоэлектроника
- Vol. 66 (3) , 174-184
Платформа поглибленого навчання для аналізу лікувальних факторів в інтернеті медичних речей
The introduction of IoT technologies, such as those used in remote health monitoring applications, has revolutionized conventional medical care. Furthermore, the approach utilized to obtain insights from the scrutiny of lifestyle elements and activities is crucial to the success of tailored healthcare and disease prevention services. Intelligent data retrieval and classification algorithms allow for the investigation of disease and the prediction of aberrant health states. The Convolutional-neural-network(CNN) strategy is utilized to forecast such anomaly because it can successfully recognize the knowledge significant to disease anticipation from amorphous medical heath records. Conversely, if a fully coupled network-topology is used, CNN guzzles a huge memory. Furthermore, the complexity analysis of the model may rise as the number of layers grows. Therefore, we present a CNN target recognition and anticipation strategy based on the Pearson-Correlation-Coefficient(PCC) and standard pattern activities to address these shortcomings of the CNN-model. It is built in this framework and used for classification purposes. In the initial hidden layer, the most crucial health-related factors are chosen, and in the next, a correlation-coefficient examination is performed to categorize the health factors into positively &negatively correlated groups. Mining the occurrence of regular patterns among the categorized health parameters also reveals the behaviors of regular patterns. The model's output is broken down into obesity, hypertension, and diabetes-related factors with known correlations. To lessen the impact of the CNN-typical knowledge discovery paradigm, we use two separate datasets. The experimental results reveal that the proposed model outperforms three other machine learning techniques while requiring less computational effort.
- 26 March 2023
- Published by Igor Sikorsky Kyiv Polytechnic Institute in Известия высших учебных заведений. Радиоэлектроника
- Vol. 66 (3) , 174-184
Open AccessПлатформа поглибленого навчання для аналізу лікувальних факторів в інтернеті медичних речей
The introduction of IoT technologies, such as those used in remote health monitoring applications, has revolutionized conventional medical care. Furthermore, the approach utilized to obtain insights from the scrutiny of lifestyle elements and activities is crucial to the success of tailored healthcare and disease prevention services. Intelligent data retrieval and classification algorithms allow for the investigation of disease and the prediction of aberrant health states. The Convolutional-neural-network(CNN) strategy is utilized to forecast such anomaly because it can successfully recognize the knowledge significant to disease anticipation from amorphous medical heath records. Conversely, if a fully coupled network-topology is used, CNN guzzles a huge memory. Furthermore, the complexity analysis of the model may rise as the number of layers grows. Therefore, we present a CNN target recognition and anticipation strategy based on the Pearson-Correlation-Coefficient(PCC) and standard pattern activities to address these shortcomings of the CNN-model. It is built in this framework and used for classification purposes. In the initial hidden layer, the most crucial health-related factors are chosen, and in the next, a correlation-coefficient examination is performed to categorize the health factors into positively &negatively correlated groups. Mining the occurrence of regular patterns among the categorized health parameters also reveals the behaviors of regular patterns. The model's output is broken down into obesity, hypertension, and diabetes-related factors with known correlations. To lessen the impact of the CNN-typical knowledge discovery paradigm, we use two separate datasets. The experimental results reveal that the proposed model outperforms three other machine learning techniques while requiring less computational effort.
- 1 March 2023
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 66 (3) , 146-154
Deep Learning Framework for Analysis of Health Factors in Internet-of-Medical Things
The introduction of IoT technologies, such as those used in remote health monitoring applications, has revolutionized conventional medical care. Furthermor
- 1 March 2023
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 66 (3) , 146-154
Deep Learning Framework for Analysis of Health Factors in Internet-of-Medical Things
The introduction of IoT technologies, such as those used in remote health monitoring applications, has revolutionized conventional medical care. Furthermor