Research Publications
Browse peer-reviewed journal articles, conference papers, and scholarly publications. Use the filters below to refine results by type, author, year, or research area.
1.
Monika, M.; Kumar, A.; Kelwade, K.; John, T. J.; Prasad, Krishna; Nerlekar, T.
Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331512118 (ISBN), (0).
@proceedings{636,
title = {Hybrid Bidirectional GRU Approach for Crop Yield Prediction and Climate Change Impact Assessment in Agriculture},
author = {M. Monika and A. Kumar and K. Kelwade and T. J. John and Krishna Prasad and T. Nerlekar},
url = {https://ieeexplore.ieee.org/document/11140711},
doi = {10.1109/ICCMC65190.2025.11140711},
isbn = {9798331512118 (ISBN)},
year = {2025},
date = {2025-01-01},
pages = {1458-1463,},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The impacts of climate change induced by humans will be felt most acutely by the agriculture sector due to its extreme dependence on weather. To ensure a steady supply of food, it is necessary to study and anticipate the effects of climate change on agricultural output. The impact of climate change on agricultural yield predictions is examined in this study using a novel methodology. In the proposed model, preprocessing, feature extraction, and training are the main processes. Data pretreatment guarantees quality by cleaning and normalising the data, while the PCC is utilised for feature selection. The model utilises AM and BiGRU for usage with large datasets. Using word vectors, the word embedding layer improves contextual awareness. Experiment findings show that the model is accurate to within 98.31% and can withstand a wide range of climate conditions. Current state-of-the-art methods are vastly outperformed by it, with performance measures like as R2 = 0.921%},
note = {0},
keywords = {MCA},
pubstate = {published},
tppubtype = {proceedings}
}
The impacts of climate change induced by humans will be felt most acutely by the agriculture sector due to its extreme dependence on weather. To ensure a steady supply of food, it is necessary to study and anticipate the effects of climate change on agricultural output. The impact of climate change on agricultural yield predictions is examined in this study using a novel methodology. In the proposed model, preprocessing, feature extraction, and training are the main processes. Data pretreatment guarantees quality by cleaning and normalising the data, while the PCC is utilised for feature selection. The model utilises AM and BiGRU for usage with large datasets. Using word vectors, the word embedding layer improves contextual awareness. Experiment findings show that the model is accurate to within 98.31% and can withstand a wide range of climate conditions. Current state-of-the-art methods are vastly outperformed by it, with performance measures like as R2 = 0.921%
2.
Ramamoorthy, S. K.; Ratan, J.; Alkhafajy, Z.; Hn, M.; Ravikumar, K.
Edge Load Balancing and Offloading Architecture Using Dynamic Graph Neural Networks in Internet of Things Proceedings
Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331536794 (ISBN), (0).
@proceedings{678,
title = {Edge Load Balancing and Offloading Architecture Using Dynamic Graph Neural Networks in Internet of Things},
author = {S. K. Ramamoorthy and J. Ratan and Z. Alkhafajy and M. Hn and K. Ravikumar},
url = {https://ieeexplore.ieee.org/document/11168554},
doi = {10.1109/ICDSNS65743.2025.11168554},
isbn = {9798331536794 (ISBN)},
year = {2025},
date = {2025-01-01},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {In recent years, the rapid expansion of EdgeInternet of Things (IoT) networks has enabled real-times services in domains such as healthcare, smart cities, and industrial automation. However, the existing Binary LinearWeightJAYA (BLWJAYA) task scheduling algorithm is restricted to static decisions and lacks predictive load balancing solutions which degraded Quality of Service (QoS) respectively. To overcome these limitations, this research presents Edge Load Balancing and Offloading Architecture using Dynamic Graph Neural Networks (ELOAD-GNN); an energy-efficient framework for intelligent task scheduling in dynamic Edge-IoT environments. Initially, the proposed model constructs a dynamic construct graph representation of the network where nodes and edges reflect the real-time availability of resources and costs of communication. Then, it utilizes a Multimodal GNN to capture spatiotemporal variation in load, while a transformer-based task classifier prioritizes tasks based on urgency and resource demand. Offloading decisions are made using Multi-Agent Reinforcement Learning (MARL), and an energy-aware controller enforces Dynamic Voltage and Frequency Scaling (DVFS)-based load balancing. Experimental results demonstrate that ELOAD-GNN achieves in terms of energy consumption (65.23%), resource utilization (96.92%) when compared to BLWJAYA model.},
note = {0},
keywords = {MCA},
pubstate = {published},
tppubtype = {proceedings}
}
In recent years, the rapid expansion of EdgeInternet of Things (IoT) networks has enabled real-times services in domains such as healthcare, smart cities, and industrial automation. However, the existing Binary LinearWeightJAYA (BLWJAYA) task scheduling algorithm is restricted to static decisions and lacks predictive load balancing solutions which degraded Quality of Service (QoS) respectively. To overcome these limitations, this research presents Edge Load Balancing and Offloading Architecture using Dynamic Graph Neural Networks (ELOAD-GNN); an energy-efficient framework for intelligent task scheduling in dynamic Edge-IoT environments. Initially, the proposed model constructs a dynamic construct graph representation of the network where nodes and edges reflect the real-time availability of resources and costs of communication. Then, it utilizes a Multimodal GNN to capture spatiotemporal variation in load, while a transformer-based task classifier prioritizes tasks based on urgency and resource demand. Offloading decisions are made using Multi-Agent Reinforcement Learning (MARL), and an energy-aware controller enforces Dynamic Voltage and Frequency Scaling (DVFS)-based load balancing. Experimental results demonstrate that ELOAD-GNN achieves in terms of energy consumption (65.23%), resource utilization (96.92%) when compared to BLWJAYA model.
3.
Srinivas, T. A. S.; Monika, M.; Aparna, N.; Kumar, K. K.; Rao, C. N.; Ramprabhu, J.
Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 978-166547451-1 (ISBN), (1).
@proceedings{171,
title = {A Methodology to Predict the Lung Cancer and its Adverse Effects on Patients from an Advanced Correlation Analysis Method},
author = {T. A. S. Srinivas and M. Monika and N. Aparna and K. K. Kumar and C. N. Rao and J. Ramprabhu},
doi = {10.1109/IDCIoT56793.2023.10053531},
isbn = {978-166547451-1 (ISBN)},
year = {2023},
date = {2023-01-01},
journal = {IDCIoT 2023 - International Conference on Intelligent Data Communication Technologies and Internet of Things, Proceedings},
pages = {964-970,},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Using symptoms as a basis for diagnosing lung cancer. Lung cancer detection is accomplished by using different machine learning techniques and regression algorithms. By comparing the efficacy of different regression algorithms for predicting lung cancer, various factors including age, gender, chest discomfort, shortness of breath, alcohol intake, chronic illness, trouble swallowing, anxiety, and peer pressure are taken into consideration. Lung cancer prediction and evaluation are accomplished by using different regression methods such as linear algorithm, polynomial regression, logistic regression, logarithmic regression and multiple regression. With a predictive accuracy of 96%, multiple regression remains superior to other regression techniques when it comes to lung cancer prediction. The R-squared value can be calculated by using a number of regression approaches, which may also be used to evaluate the association between various symptoms and lung cancer. Lung cancer is diagnosed by using the R squared value, which is calculated by using several algorithms and considers symptoms including chronic illness. © 2023 IEEE.},
note = {1},
keywords = {MCA},
pubstate = {published},
tppubtype = {proceedings}
}
Using symptoms as a basis for diagnosing lung cancer. Lung cancer detection is accomplished by using different machine learning techniques and regression algorithms. By comparing the efficacy of different regression algorithms for predicting lung cancer, various factors including age, gender, chest discomfort, shortness of breath, alcohol intake, chronic illness, trouble swallowing, anxiety, and peer pressure are taken into consideration. Lung cancer prediction and evaluation are accomplished by using different regression methods such as linear algorithm, polynomial regression, logistic regression, logarithmic regression and multiple regression. With a predictive accuracy of 96%, multiple regression remains superior to other regression techniques when it comes to lung cancer prediction. The R-squared value can be calculated by using a number of regression approaches, which may also be used to evaluate the association between various symptoms and lung cancer. Lung cancer is diagnosed by using the R squared value, which is calculated by using several algorithms and considers symptoms including chronic illness. © 2023 IEEE.
4.
Saravanan, S.; Lavanya, M.; Srinivas, C. M. V.; Arunadevi, M.; Arulkumar, N.
Secure IoT protocol for implementing classified Electroencephalogram (EEG) signals in the field of smart healthcare Book Chapter
In: pp. 111-129,, CRC Press, 2022, ISBN: 978-100073855-1 (ISBN); 978-103206620-2 (ISBN), (2).
@inbook{141,
title = {Secure IoT protocol for implementing classified Electroencephalogram (EEG) signals in the field of smart healthcare},
author = {S. Saravanan and M. Lavanya and C. M. V. Srinivas and M. Arunadevi and N. Arulkumar},
doi = {10.1201/9781003203087-5},
isbn = {978-100073855-1 (ISBN); 978-103206620-2 (ISBN)},
year = {2022},
date = {2022-01-01},
journal = {Cyber Security Applications for Industry 4.0},
pages = {111-129,},
publisher = {CRC Press},
note = {2},
keywords = {MCA},
pubstate = {published},
tppubtype = {inbook}
}
5.
Kumar, R. L.; Ranjini, K. S.; Sindhu, S.; Udhayakumar, R.
Efficient authenticated key establishment protocol for telecare medicine information systems Proceedings
American Institute of Physics Inc., vol. 2519, 2022, ISBN: 0094243X (ISSN); 978-073544204-7 (ISBN), (0).
@proceedings{178,
title = {Efficient authenticated key establishment protocol for telecare medicine information systems},
author = {R. L. Kumar and K. S. Ranjini and S. Sindhu and R. Udhayakumar},
doi = {10.1063/5.0117522},
isbn = {0094243X (ISSN); 978-073544204-7 (ISBN)},
year = {2022},
date = {2022-01-01},
journal = {AIP Conference Proceedings},
volume = {2519},
pages = {020006+},
publisher = {American Institute of Physics Inc.},
abstract = {Secure checked based three person affirmation plot for records trade telecare remedy facts structures permits two customers simply store their verifiers prepared from their certifiable thriller state in approval verifiers informational index. By then the confirmation professional can test the clients' verifiers and help them to exchange electronic medical records or electronic prosperity statistics securely and favorably. In this work, we must suggested protocol based on SPSD. © 2022 Author(s).},
note = {0},
keywords = {MCA},
pubstate = {published},
tppubtype = {proceedings}
}
Secure checked based three person affirmation plot for records trade telecare remedy facts structures permits two customers simply store their verifiers prepared from their certifiable thriller state in approval verifiers informational index. By then the confirmation professional can test the clients' verifiers and help them to exchange electronic medical records or electronic prosperity statistics securely and favorably. In this work, we must suggested protocol based on SPSD. © 2022 Author(s).
6.
Dasgupta, S.; Karmakar, S.
Food recommendation using classifier and modified Apriori algorithm Journal Article
In: International Journal of Innovative Technology and Exploring Engineering, vol. 8, pp. 3967-3970,, 2019, ISBN: 22783075 (ISSN), (1).
@article{246,
title = {Food recommendation using classifier and modified Apriori algorithm},
author = {S. Dasgupta and S. Karmakar},
doi = {10.35940/ijitee.L3471.1081219},
isbn = {22783075 (ISSN)},
year = {2019},
date = {2019-01-01},
journal = {International Journal of Innovative Technology and Exploring Engineering},
volume = {8},
pages = {3967-3970,},
publisher = {Blue Eyes Intelligence Engineering and Sciences Publication},
abstract = {In today’s world, computer technologies have advanced a lot. One of its greatest gifts to the world is Artificial Intelligence. Natural Language Processing (NLP) and Machine Learning (ML) are two of its subdomains. In this paper, modified versions of two common NLP and ML algorithms have been used to classify food reviews and provide suitable recommendations from them. Currently, reviews can be classified into positive and negative reviews, but it becomes difficult when one review says positive about item A and negative about item B. Moreover, the current Apriori algorithm doesn’t consider the feedbacks from customers (reviews). Modified classifier algorithm and consequently, modified Apriori algorithm has been used to classify each statement part by part and provide recommendations, not just on previous purchases but also using the reviews about above-mentioned purchases. The algorithms can be used for purposes other than food analysis also – wherever purchases and reviews are involved. For e.g., e-commerce companies can use the algorithms to predict and recommend suitable items a user may be interested in. © BEIESP.},
note = {1},
keywords = {MCA},
pubstate = {published},
tppubtype = {article}
}
In today’s world, computer technologies have advanced a lot. One of its greatest gifts to the world is Artificial Intelligence. Natural Language Processing (NLP) and Machine Learning (ML) are two of its subdomains. In this paper, modified versions of two common NLP and ML algorithms have been used to classify food reviews and provide suitable recommendations from them. Currently, reviews can be classified into positive and negative reviews, but it becomes difficult when one review says positive about item A and negative about item B. Moreover, the current Apriori algorithm doesn’t consider the feedbacks from customers (reviews). Modified classifier algorithm and consequently, modified Apriori algorithm has been used to classify each statement part by part and provide recommendations, not just on previous purchases but also using the reviews about above-mentioned purchases. The algorithms can be used for purposes other than food analysis also – wherever purchases and reviews are involved. For e.g., e-commerce companies can use the algorithms to predict and recommend suitable items a user may be interested in. © BEIESP.
