Aswathy K. Cherian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aswathy K. Cherian has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- M. Vaidhehi
SRM Institute of Science and Technology
6 shared publications - J. Briskilal
Department of Computing Technologies, SRM Institute of Science and Technology, Chengalpattu Dt, India
3 shared publications - M. K. Vidhyalakkshmi
SRM Institute of Science and Technology
3 shared publications - Radhakrishnan Shanthi Priya
SRM Institute of Science and Technology
2 shared publications - Ramalingam Senthil
Department of Mechanical Engineering, SRM Institute of Science and Technology, Kattankulathur, Chennai 603203, India
2 shared publications S. Ushasukhanya
SRM Institute of Science and Technology, India
2 shared publications
Latest Publications
- Open Access
- 12 October 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1435
Explainable deep learning framework for real-time insect pest detection in smart agriculture
Global losses of crop production due to insect pest infestations are estimated to be around 20–40% annually, which represents one of the highest threats to agricultural productivity, farmer livelihoods and food security. Current manual scouting is labor intensive, subjective and non-scalable, and many automated scouting methods suffer when they come to deal with different field conditions and offer little insight into decision making. To tackle these challenges, this study proposes Crop Protection in Smart Agriculture—Real-time Insect Pest Detection using Continual Spatio-Temporal Graph Convolutional Network (CPSA-RIPD-CSTGCN), a unified and interpretable deep learning framework that combines the four synergistic components: (i) the Ensemble Transform Schmidt–Kalman Filter (ETSKF) for image preprocessing, including resizing, normalization, and noise suppression; (ii) data augmentation using rotation, flipping, scaling, shearing, and contrast adjustment, which enhances generalization and reduces overfitting; (iii) the Continual Spatio-Temporal Graph Convolutional Network (CSTGCN) that jointly models the spatial dependency across crop regions and temporal evolution of pest dynamics to achieve robust feature extraction and classification; and (iv) the Revolution Optimization Algorithm (ROA) for hyperparameter optimization of CSTGCN weights to adaptively adjust the network. Further, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization is introduced to give post-hoc explainability as it shows regions that are relevant to the biological process and areas that are affected by pests. This framework was tested on IP102 benchmark dataset with 60%-40%-split train-test with 10 economically important classes of pests with 97% accuracy, 98% precision, 98% recall and 98% F1 score, mean ± 0.32% accuracy, across 5-fold cross validation. Among other baseline models, these results consistently outperform VGG16 (82%), InceptionV3 (85%), MobileNetV2 (87%), DenseNet121 (88%), EfficientNetB0 (89%) and task-specific models like EDCP-DIA-RNN(Early Disease and Crop Pest—Diagnosis/Detection using Image Analysis RNN) (94%), EPCY-TPA-ANN (Efficient Prediction of Crop Yield—Through Parameter Analysis ANN) (91%) and ICPM-ESA-CNN (Interactive Crop and Pest Management Enhanced Soil Analysis CNN) (90%). The results of ablation studies showed the solitary effects of each module of the Ensemble Transform Schmidt–Kalman Filter pre-processing and Revolution Optimization Algorithm optimization, and the confusion matrix analysis demonstrated high per-class reliability and only a small amount of misclassification, implying that the proposed method could be applied to real-time, large-scale smart agriculture deployments.
- 12 October 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1435
Open AccessExplainable deep learning framework for real-time insect pest detection in smart agriculture
Global losses of crop production due to insect pest infestations are estimated to be around 20–40% annually, which represents one of the highest threats to agricultural productivity, farmer livelihoods and food security. Current manual scouting is labor intensive, subjective and non-scalable, and many automated scouting methods suffer when they come to deal with different field conditions and offer little insight into decision making. To tackle these challenges, this study proposes Crop Protection in Smart Agriculture—Real-time Insect Pest Detection using Continual Spatio-Temporal Graph Convolutional Network (CPSA-RIPD-CSTGCN), a unified and interpretable deep learning framework that combines the four synergistic components: (i) the Ensemble Transform Schmidt–Kalman Filter (ETSKF) for image preprocessing, including resizing, normalization, and noise suppression; (ii) data augmentation using rotation, flipping, scaling, shearing, and contrast adjustment, which enhances generalization and reduces overfitting; (iii) the Continual Spatio-Temporal Graph Convolutional Network (CSTGCN) that jointly models the spatial dependency across crop regions and temporal evolution of pest dynamics to achieve robust feature extraction and classification; and (iv) the Revolution Optimization Algorithm (ROA) for hyperparameter optimization of CSTGCN weights to adaptively adjust the network. Further, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization is introduced to give post-hoc explainability as it shows regions that are relevant to the biological process and areas that are affected by pests. This framework was tested on IP102 benchmark dataset with 60%-40%-split train-test with 10 economically important classes of pests with 97% accuracy, 98% precision, 98% recall and 98% F1 score, mean ± 0.32% accuracy, across 5-fold cross validation. Among other baseline models, these results consistently outperform VGG16 (82%), InceptionV3 (85%), MobileNetV2 (87%), DenseNet121 (88%), EfficientNetB0 (89%) and task-specific models like EDCP-DIA-RNN(Early Disease and Crop Pest—Diagnosis/Detection using Image Analysis RNN) (94%), EPCY-TPA-ANN (Efficient Prediction of Crop Yield—Through Parameter Analysis ANN) (91%) and ICPM-ESA-CNN (Interactive Crop and Pest Management Enhanced Soil Analysis CNN) (90%). The results of ablation studies showed the solitary effects of each module of the Ensemble Transform Schmidt–Kalman Filter pre-processing and Revolution Optimization Algorithm optimization, and the confusion matrix analysis demonstrated high per-class reliability and only a small amount of misclassification, implying that the proposed method could be applied to real-time, large-scale smart agriculture deployments.
- Open Access
Artificial Intelligence in Smart Photovoltaic Systems for High-Efficiency Energy Conversion: A Systematic Review
Artificial intelligence (AI) is transforming photovoltaic (PV) systems from passive generators into self-forecasting, self-diagnosing, and self-optimizing energy assets. This review synthesizes 170 Scopus-indexed documents published between 2020 and 2026 across six technical domains: solar resource and PV power forecasting; intelligent monitoring, fault diagnosis, and cybersecurity; AI-driven control and design optimization; smart grid integration and real-time energy management; AI-assisted PV materials, devices, and manufacturing; and cross-sectoral smart PV applications. Quantitative synthesis shows that hybrid deep learning forecasters reduce root mean square error by 31.9–43.9% relative to persistence and single-model baselines. Attention-based architectures achieve mean absolute percentage errors of up to 5%. Machine learning classifiers achieve fault detection accuracies of 92.3–99.4% with protection response times below 100 ms, enabling predictive maintenance at the fleet scale. Reinforcement learning energy management lowers electricity costs by 20–55%, reduces peak demand by 13–31.5%, and raises PV self-sufficiency from 71.5% to 89.7%. AI-optimized thermal and material interventions deliver efficiency gains of up to 22.2%, and indoor perovskite devices exceed 40% conversion efficiency. Reported performance metrics are derived from heterogeneous datasets, horizons, and baselines; they are therefore synthesized as indicative ranges rather than directly comparable benchmarks. Persistent barriers include data scarcity, model opacity, cybersecurity vulnerabilities, edge deployment constraints, and energy justice concerns. These barriers are mapped to research directions in explainable AI, federated and transfer learning, digital twins, and blockchain-enabled energy markets. A roadmap to 2040 consolidates the findings and charts the transition toward high-efficiency, resilient, and sustainable solar energy conversion.
Open AccessArtificial Intelligence in Smart Photovoltaic Systems for High-Efficiency Energy Conversion: A Systematic Review
Artificial intelligence (AI) is transforming photovoltaic (PV) systems from passive generators into self-forecasting, self-diagnosing, and self-optimizing energy assets. This review synthesizes 170 Scopus-indexed documents published between 2020 and 2026 across six technical domains: solar resource and PV power forecasting; intelligent monitoring, fault diagnosis, and cybersecurity; AI-driven control and design optimization; smart grid integration and real-time energy management; AI-assisted PV materials, devices, and manufacturing; and cross-sectoral smart PV applications. Quantitative synthesis shows that hybrid deep learning forecasters reduce root mean square error by 31.9–43.9% relative to persistence and single-model baselines. Attention-based architectures achieve mean absolute percentage errors of up to 5%. Machine learning classifiers achieve fault detection accuracies of 92.3–99.4% with protection response times below 100 ms, enabling predictive maintenance at the fleet scale. Reinforcement learning energy management lowers electricity costs by 20–55%, reduces peak demand by 13–31.5%, and raises PV self-sufficiency from 71.5% to 89.7%. AI-optimized thermal and material interventions deliver efficiency gains of up to 22.2%, and indoor perovskite devices exceed 40% conversion efficiency. Reported performance metrics are derived from heterogeneous datasets, horizons, and baselines; they are therefore synthesized as indicative ranges rather than directly comparable benchmarks. Persistent barriers include data scarcity, model opacity, cybersecurity vulnerabilities, edge deployment constraints, and energy justice concerns. These barriers are mapped to research directions in explainable AI, federated and transfer learning, digital twins, and blockchain-enabled energy markets. A roadmap to 2040 consolidates the findings and charts the transition toward high-efficiency, resilient, and sustainable solar energy conversion.
- Open Access
Artificial Intelligence in Thermal Energy Storage Systems for Buildings to City-Scale Energy Flexibility: A Review
Buildings account for roughly 37% of energy-related CO2 emissions, and space cooling already consumes nearly 10% of global electricity. Cooling demand is rising fastest in tropical cities, where air-conditioning could reach 45% of peak load, especially in India by 2050. This review critically examines thermal energy storage (TES) as a flexibility resource across three distinct scales: individual buildings, district heating and cooling networks, and city-level multi-energy systems. Using a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based search of Scopus, Web of Science, and IEEE Xplore with primary and supplementary strings, 4447 records were identified, of which 174 were included. Each quantitative study was classified by validation level (simulation, laboratory, pilot, or operational) and by the centrality of thermal storage. Sensible, latent, and thermochemical storage technologies are compared using energy density (10–500 kWh/m3), efficiency (40–95%), cycle stability, and technology readiness. The review then evaluates the role of artificial intelligence (AI), machine learning, and Internet of Things platforms in forecasting, predictive control, and operational optimization of TES networks. Thirteen method families, grouped into AI and machine learning methods, optimization methods, control methods, and digital enabling technologies, are assessed against six explicitly defined criteria with evidence-coded scores. Among 47 quantitative studies, 37 (78.7%) are simulation-only, and only four (8.5%) report operational data. Direct TES-AI studies report simulated energy savings of 8–64% and peak load reductions of about 35%, whereas field-validated intelligent control reports 17% energy savings in a single real building experiment. The review also identifies inherent drawbacks of artificial intelligence-based operations, including limited interpretability, high data and computational demands, concept drift, and cyber vulnerabilities that increased peak electric load by 17.4% in a simulated attack. A structural imbalance in the literature is evident: most validated deployments remain at the building-scale, whereas urban-scale evidence is confined to district cooling, aquifer and pit storage, and multi-energy hub studies; no study reports the coordinated operation of distributed TES assets across multiple districts. A conceptual framework and a staged roadmap linking building, district, and urban scales are proposed. Priority research needs include urban-scale pilots in tropical climates, techno-economic assessment, interpretable and drift-robust AI, and interoperability standards that support United Nations’ Sustainable Development Goals 7, 11, and 13.
Open AccessArtificial Intelligence in Thermal Energy Storage Systems for Buildings to City-Scale Energy Flexibility: A Review
Buildings account for roughly 37% of energy-related CO2 emissions, and space cooling already consumes nearly 10% of global electricity. Cooling demand is rising fastest in tropical cities, where air-conditioning could reach 45% of peak load, especially in India by 2050. This review critically examines thermal energy storage (TES) as a flexibility resource across three distinct scales: individual buildings, district heating and cooling networks, and city-level multi-energy systems. Using a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based search of Scopus, Web of Science, and IEEE Xplore with primary and supplementary strings, 4447 records were identified, of which 174 were included. Each quantitative study was classified by validation level (simulation, laboratory, pilot, or operational) and by the centrality of thermal storage. Sensible, latent, and thermochemical storage technologies are compared using energy density (10–500 kWh/m3), efficiency (40–95%), cycle stability, and technology readiness. The review then evaluates the role of artificial intelligence (AI), machine learning, and Internet of Things platforms in forecasting, predictive control, and operational optimization of TES networks. Thirteen method families, grouped into AI and machine learning methods, optimization methods, control methods, and digital enabling technologies, are assessed against six explicitly defined criteria with evidence-coded scores. Among 47 quantitative studies, 37 (78.7%) are simulation-only, and only four (8.5%) report operational data. Direct TES-AI studies report simulated energy savings of 8–64% and peak load reductions of about 35%, whereas field-validated intelligent control reports 17% energy savings in a single real building experiment. The review also identifies inherent drawbacks of artificial intelligence-based operations, including limited interpretability, high data and computational demands, concept drift, and cyber vulnerabilities that increased peak electric load by 17.4% in a simulated attack. A structural imbalance in the literature is evident: most validated deployments remain at the building-scale, whereas urban-scale evidence is confined to district cooling, aquifer and pit storage, and multi-energy hub studies; no study reports the coordinated operation of distributed TES assets across multiple districts. A conceptual framework and a staged roadmap linking building, district, and urban scales are proposed. Priority research needs include urban-scale pilots in tropical climates, techno-economic assessment, interpretable and drift-robust AI, and interoperability standards that support United Nations’ Sustainable Development Goals 7, 11, and 13.
- 30 January 2026
- Published by Springer Nature
- p. 81-103
Fuzzy Applications in Game Manufacturing
- 2 January 2026
- Published by Springer Nature
- p. 271-282
Sustainable Practices in the Metaverse Ecometaverse: Virtual Carbon Footprint Tracker
- 2 January 2026
- Published by Springer Nature
- p. 271-282
Sustainable Practices in the Metaverse Ecometaverse: Virtual Carbon Footprint Tracker
- 14 March 2025
- Published by IGI Global Scientific Publishing
- p. 325-344
Optimizing Remote Research and Learning With AI Technologies
This chapter delves into the pivotal role of artificial intelligence (AI) in transforming remote experimentation and learning analytics within modern education. As institutions increasingly adopt remote learning environments, the integration of AI emerges as a critical factor in enhancing the design and execution of experiments as well as the analysis of learning data. The chapter begins by tracing the evolution of remote labs and learning analytics, highlighting the convergence of these fields through AI. It explores key AI technologies, such as machine learning, neural networks, and real-time data analysis that are revolutionizing how experiments are conducted and how educational outcomes are assessed. Moreover, the chapter discusses the ethical challenges, data privacy concerns, and accessibility issues that accompany the rise of AI in education. By examining case studies and practical applications, the chapter provides insights into the current state and future potential of AI in shaping personalized, adaptive learning experiences in remote and hybrid educational settings.
- 14 March 2025
- Published by IGI Global Scientific Publishing
- p. 325-344
Optimizing Remote Research and Learning With AI Technologies
This chapter delves into the pivotal role of artificial intelligence (AI) in transforming remote experimentation and learning analytics within modern education. As institutions increasingly adopt remote learning environments, the integration of AI emerges as a critical factor in enhancing the design and execution of experiments as well as the analysis of learning data. The chapter begins by tracing the evolution of remote labs and learning analytics, highlighting the convergence of these fields through AI. It explores key AI technologies, such as machine learning, neural networks, and real-time data analysis that are revolutionizing how experiments are conducted and how educational outcomes are assessed. Moreover, the chapter discusses the ethical challenges, data privacy concerns, and accessibility issues that accompany the rise of AI in education. By examining case studies and practical applications, the chapter provides insights into the current state and future potential of AI in shaping personalized, adaptive learning experiences in remote and hybrid educational settings.
- 12 August 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (8) , 5041-5054
Enhancing Medical Image Security: A Deep Learning Approach with Cloud-based Color Space Scrambling
- 12 August 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (8) , 5041-5054
Enhancing Medical Image Security: A Deep Learning Approach with Cloud-based Color Space Scrambling
- 26 June 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (6) , 3703-3722
Generative adversarial networks with stochastic gradient descent with momentum algorithm for video-based facial expression
- 26 June 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (6) , 3703-3722
Generative adversarial networks with stochastic gradient descent with momentum algorithm for video-based facial expression
- 21 June 2024
- Published by IGI Global Scientific Publishing
- p. 226-252
Green Cloud Computing
Green cloud computing has emerged as a critical area of research and development in response to the escalating environmental impact of traditional data centers. This chapter investigates the opportunities and challenges associated with the adoption of environmentally sustainable practices in cloud computing. The ever-growing demand for computational resources necessitates a paradigm shift towards more energy-efficient and eco-friendly solutions. The opportunities presented by green cloud computing lie in the potential to significantly reduce carbon footprints and energy consumption. The integration of renewable energy sources, energy-efficient hardware, and optimized resource allocation techniques contribute to minimizing the environmental impact of cloud infrastructure. Additionally, the implementation of virtualization and consolidation strategies enhances server utilization, further improving energy efficiency. However, the realization of these opportunities is accompanied by a set of challenges.
- 21 June 2024
- Published by IGI Global Scientific Publishing
- p. 226-252
Green Cloud Computing
Green cloud computing has emerged as a critical area of research and development in response to the escalating environmental impact of traditional data centers. This chapter investigates the opportunities and challenges associated with the adoption of environmentally sustainable practices in cloud computing. The ever-growing demand for computational resources necessitates a paradigm shift towards more energy-efficient and eco-friendly solutions. The opportunities presented by green cloud computing lie in the potential to significantly reduce carbon footprints and energy consumption. The integration of renewable energy sources, energy-efficient hardware, and optimized resource allocation techniques contribute to minimizing the environmental impact of cloud infrastructure. Additionally, the implementation of virtualization and consolidation strategies enhances server utilization, further improving energy efficiency. However, the realization of these opportunities is accompanied by a set of challenges.