R Sathya Bama Krishna

Scopus Publications

Assessing the Effectiveness of Machine Learning in Cyber Attack Mitigation: A Review
Gayathry V, R. Sathya Bama Krishna
Proceedings of 8th International Conference on Trends in Electronics and Informatics Icoei 2025, 2025
Cyberattacks are currently one of the most active areas of research and a serious criminal offence. In many industries, the number of people using the internet is increasing too quickly. The amount of time spent online has increased dramatically, and people and businesses are now doing many of their everyday activities online rather than in person. Despite the quick rise in the quantity of websites and applications, they remain vulnerable to attacks. Due to modern attacks and prevention techniques, traditional security features like firewalls, interruption location frameworks, antivirus software, access control records, and so on are currently ineffective in identifying these sophisticated attacks. Therefore, it is imperative to discover novel and more workable ways to stop cyberattacks. This paper's main goals are to inform academics and engineers about current threats and stimulate research on cybersecurity countermeasures for digital attacks. This study outlined the principal themes, seminal works, and major author cohorts in the field of digital attack research. In the future, the results should aid in broadening the focus of research to include a variety of subfields in the study of digital threats.
Federated Clustering Defense: Mitigating Data Exposure in Collaborative Learning
Anuja Radhakrishnan, Sathya Bama Krishna
Etis International Conference on Emerging Technologies for Intelligent Systems Etis 2025, 2025
The development of intelligent industrial applications is being driven globally by advancements in the next generation of Internet of Things (IoT) technologies. At the same time, artificial intelligence (AI) technologies like machine learning and deep learning are becoming more widely used. Conventional machine learning models primarily rely on large data sets. However, the vast data sets generated by network-edge devices are expensive, inefficient to acquire and handle, and they pose major privacy hazards. Federated learning (FL) is a novel paradigm for statistical model training on distributed edge networks that allows data to take part in the training of federated models without being localized. Traditional machine learning issues with low data usage, data privacy, and information security brought on by data isolation can be resolved with this method. We propose a novel Federated Clustering with Differential Privacy (FedCDP) algorithm designed to efficiently model user behavior in an unsupervised manner. This algorithm focuses on optimizing computation and storage requirements while minimizing data leakage through robust differential privacy mechanisms.
VidyaSevak - Bridging Knowledge with AI
Nandha Kishore Devabhakthuni, Srikar Akula, R Sathya Bama Krishna
Proceedings of 3rd IEEE International Conference on Knowledge Engineering and Communication Systems Ickecs 2025, 2025
The usage of new AI technologies has enabled a drastic improvement in the applications of natural language understanding, as well as advancing AI-assisted conversational agents. VidyaSevak is the innovative educational chatbot aimed primarily at bridging the gap between students and professionals through an interactive learning experience. It uses deep learning techniques for improving the efficiency of the dialogue so that students get contextually relevant and precise answers to their queries. VidyaSevak is built on TensorFlow and Keras and uses advanced deep learning frameworks to implement an efficient and effective chatbot. The system is equipped with an extensive database so that it understands and responds accurately to the questions posed by students. A JSON-based data structure is used, with the main advantage being that it can easily be integrated into the academic world and function seamlessly. The development process of VidyaSevak is quite structured, adjusting to every method from information gathering, preprocessing, model development, training and even evaluation. In order to enhance response accuracy, the text is tokenized, stemmed and certain punctuation marks are removed to enhance the overall quality of the response. VidyaSevak is a distinct academic aide that supports the enhanced interaction and engagement of students with the help of an intelligent learning environment provides an instant source of knowledge and guidance to the user, increasing their educational experience.
Medical Diagnosis through Machine Learning: Detecting Heart Disease, Lung and Breast Cancer
G. Satya Naga Deep, G. BalaKrishna, R Sathya Bama Krishna
6th International Conference on Mobile Computing and Sustainable Informatics Icmcsi 2025 Proceedings, 2025
Medical diagnostics for heart disease, lung cancer, and breast cancer using ML algorithms. The ML algorithms used in medical research have received considerable attention, motivated by their potential to revolutionize early analysis and enhance patient care. The relevancy of machine learning techniques to medical research in three significant conditions-breast cancer, lung cancer, and heart disease-is examined in this paper. This approach can improve the prompt diagnosis with better patient outcomes. In this work, it has adopted several machine learning techniques like naive Bayes, decision tree classification, k-nearest neighbor, support vector machines, linear discriminant analysis, and logistic regression. For heart disease, lung cancer, and breast cancer datasets, we evaluate all algorithms regarding their unique characteristics. We carefully assess the effectiveness of these algorithms utilizing a wide range of experimental conditions and comparison analysis. The review analyzes the processes of data preprocessing, feature selection, and model validation. Additionally, it offers a thorough analysis of current studies, providing information on earlier machine learning research on medical subjects.
Classification of Health of Foetus using Machine Learning
Ayushi Jayaraj, Shubham Kumar, B. Ankayarkanni, R. Sathyabama, Mercy Paul Selvan
Icoicc 2025 3rd International Conference on Intelligent and Cloud Computing, 2025
Pregnancy is a critical period during which vigilant monitoring of fetal and maternal health is essential to prevent complications and ensure positive outcomes. Traditional fetal health assessment methods such as cardiotocography (CTG), ultrasound imaging, and clinical evaluation, though effective, often suffer from interpretability issues, episodic monitoring, and dependency on expert judgment. This study proposes an advanced machine learning-based framework to classify fetal health status into normal and abnormal categories using CTG data, aiming to enhance diagnostic accuracy and clinical reliability. A comparative analysis was conducted using ensemble-based models—XGBoost and LightGBM—as well as support vector machines (SVM). Among these, XGBoost achieved the highest performance with 94.2% accuracy, 0.93 precision, and 0.94 recall. LightGBM followed closely, offering comparable results with faster computation. Furthermore, the study integrates explainable AI techniques to improve model transparency and facilitate trust among healthcare practitioners. The results demonstrate the potential of interpretable machine learning models to support obstetric decision-making, especially in settings lacking specialized medical expertise. This approach not only enhances fetal health classification but also lays the foundation for intelligent, data-driven prenatal care systems.
Multimodal Information Extraction:A systematic Review of subtask, modal types and applications based on Deep Learning in Banking sector
Samundiswary Srinivsan, R Sathya Bama Krishna
2024 5th International Conference for Emerging Technology Incet 2024, 2024
Deep Learning has been widely applied in all application domains namely Healthcare, Entertainment, Banking & finance, Agriculture, Aerospace & defence etc. Due to stupendous achievement of deep learning as a data processing technique has fascinated in all research areas. Handling of Deep learning in Banking and Financial sector is pervasive. Advancement of Information extraction especially because of different formats of information such as text, image, sound, video can be extracted simultaneously by the usage of deep learning techniques. This study reviews and analyses multimodal information extraction based on deep learning techniques especially on banking and financial sector. It aims to enhance the efficiency of document-intensive business tasks in the financial sector. Deep review analysis will be carried out to understand subtasks of Information extraction and techniques involved in Banking domain. Finally, how multimodal information extraction using deep learning enhances the efficiency than unimodal and its use cases in current AI based automation world will be highlighted.
Predictive Analytics For Sales Demand Forecasting Using HML Model
Sujithra J, Nithya Shree S, Sathyabama R
2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024
Demand forecasting is essential for strategic planning in various industries. Accurate sales forecasts enable better decisions in inventory management, resource allocation, and financial planning. By using advanced machine learning algorithms, sales forecasting can be significantly enhanced. The idea of advancement is creating a Demand Forecasting Software that utilises HML - Hybrid Machine Learning Model (LSTM and XGBoost algorithms) to deliver precise and actionable sales predictions. This software processes datasets from sources like historical sales data, market trends, and customer behaviour. LSTM, a specialised recurrent neural network, captures complex temporal correlations, making it ideal for predicting sales influenced by seasonality, promotions, and other time-dependent factors. XGBoost, excels at identifying interactions between different dataset features, improving predictive accuracy by recognizing intricate patterns. The accuracy rate from the HML model is about 92.5%. This empowers firms to optimise sales strategies and maximise profits by adapting to market changes and continuously learning from new data.
Detecting Cracks in Concrete Surfaces using Convolutional Neural Networks and Resnet 50
Christopher Cyrus, Harini T, Sathya Bama Krishna
7th International Conference on Inventive Computation Technologies Icict 2024, 2024
The maintenance and lifespan of structures made of concrete depend on the early detection and timely treatment of cracks, which can compromise the building's strength and need costly repairs. The study presents a novel approach for crack identification on surfaces of concrete using deep learning algorithms. The suggested approach makes use of convolutional neural networks (CNNs) to computationally identify and classify cracks in high-quality photographs of concrete flooring. The process begins with compiling a sizable dataset of distinct surface photos of concrete with varying crack dimensions, trends, and ambient conditions. It is easier to do supervised learning when a collection of data is thoroughly annotated. A preliminary processing workflow is built up to standardize input data and strengthen the appearance of images in order to achieve the highest potential accuracy of the model. A pretrained CNN model structure called Resnet 50 is developed, modified, and utilizes transfer learning to leverage the information from already trained algorithms on substantial image collections. With robust generalization to unseen data and outstanding accuracy in crack identification, the trained model demonstrates superior abilities in this area. The model's usefulness is increased by capturing pictures of concrete substrates in a variety of lighting environments and perspectives. The recommended method shows resilience to disturbances, variations in illumination, along with other external variables, indicating its applicability in practical scenarios. When comparing the effectiveness of the developed model with classic methods for image analysis, deep learning operates better in crack searches. The results indicate that not exclusively is the approach suggested powerful, but it also holds the assurance of significantly reducing the duration and assets required for personal inspection and planned preventive maintenance. All things considered, this work presents a unique method for surveillance of infrastructure through presenting an adaptable and robust deep-learning system for concrete's outer crack identification. The amalgamation of Zorin OS 16.3, x86-64 architecture, NVIDIA GPU support, and Linux kernel 5.15.0-83-generic enhances the computational capacity needed to enable efficient development and operation of a deep-learning approach for detecting concrete crack recognition. The study outlines how the advocated deep learning approach could be applied in practical conditions.
Explainable AI in Large Language Models: A Review
Sauhandikaa S, R Bhagavath Narenthranath, R Sathya Bama Krishna
2nd International Conference on Emerging Research in Computational Science Icercs 2024, 2024
Explainable AI in Large Language Models (LLMs) represents an exciting frontier in Artificial Intelligence. In recent times, LLMs provides various AI applications ranging from chatbots to content generation. While these applications are exciting, their decision-making process behind the intelligent systems plays a major role. These processes are also a mystery and they operate as "Black boxes", where the processes are often challenging to interpret. This paper helps to give a sense of the processes that occurs behind these decisions. It helps to understand why the AI has chosen one sentence rather than the other. It explores key breakthroughs of XAI techniques that helps in solving these complexities. Methods such as Attention Visualization, Feature Importance Analysis and Counterfactual Explanations provide insights on why certain decisions are made. These techniques provide a voice to the intricate processes and address real-world challenges, which makes it more reliable. This enables better transparency and makes it trust-worthy. XAI has the potential to address ethical concerns, enhance user trust and improve Human-AI collaboration. This research highlights how better transparency in AI is not merely a technical challenge but a foundational step towards building a future where humans and AI work together seamlessly and responsibly.
Intelligent Control of Power Converters using Reinforcement Learning
R. Sathya Barna Krishna, Sudharani R, S. Rukmani Devi, Pramodkurnar H. Kulkarni, Rohini. G, M. Sindhu
Proceedings of 9th International Conference on Science Technology Engineering and Mathematics the Role of Emerging Technologies in Digital Transformation Iconstem 2024, 2024
Power converter control techniques must evolve to accommodate power system complexity and renewable energy integration. Traditional control methods may be difficult to adapt to these dynamic and uncertain systems. Reinforcement learning (RL) can build optimal control policies in complex and unpredictable situations, making it a promising intelligent control solution in this scenario. This research examines how reinforcement learning can control power converters in energy systems. Advanced reinforcement learning methods, notably deep reinforcement learning, are used to improve power converter efficiency in varied operational scenarios. This research examines the integration of reinforcement learning (RL)-based controllers into power converter systems, focusing on their autonomous learning and adaptation. The explored method uses Reinforcement Learning (RL) flexibility to address power system time-varying conditions, non-linearities, and uncertainties. This research considers practical concerns such RL-based control's effects on real-time execution, processing requirements, and safety. The report concludes with suggestions for future research including expanding RL-based intelligent control systems to power system applications. Reinforcement learning keywords include stability, efficiency, reliability, renewable energy, deep reinforcement learning, power converters, intelligent control, and energy systems.
Review of Next-Generation Wireless Devices with Self-Energy Harvesting for Sustainability Improvement
James Deva Koresh Hezekiah, Karnam Chandrakumar Ramya, Sathya Bama Krishna Radhakrishnan, Vishnu Murthy Kumarasamy, Malathi Devendran, Avudaiammal Ramalingam, Rajagopal Maheswar
Energies, 2023
Predictive Analytics: Leveraging Data Science to Drive Business Decisions
N Nazhath Nafizza, B Mukilan, R Sathyabama Krishnan
Proceedings of the 7th International Conference on Intelligent Computing and Control Systems Iciccs 2023, 2023
Private Document Vault with Server-Side Encryption in Cloud AWS S3 Bucket
Daliparthi Jeevana Aditya, Sunki Laxmanraj, R. Sathya Bama Krishna
Proceedings of the 8th International Conference on Communication and Electronics Systems Icces 2023, 2023
A Review of Intelligent Traffic Management Systems
R Ashwath Ramanathan, BalaMurugan R, R Sathya Bama Krishna, Mercy Paul Selvan
7th International Conference on Trends in Electronics and Informatics Icoei 2023 Proceedings, 2023
Assessing Lifespan of Lithium-Ion Rechargeable Batteries through Hybrid CNN-LSTM-DNN Method
S. Prince Mary, M D Anto Praveena, Albert Mayan J, D Usha Nandini, R Sathya Bama Krishna
Proceedings of the International Conference on Circuit Power and Computing Technologies Iccpct 2023, 2023
A Joint Optimization Approach for Security and Insurance Management on the Cloud
L. K. Joshila Grace, S. Vigneshwari, R. Sathya Bama Krishna, B. Ankayarkanni, A. Mary Posonia
Lecture Notes in Networks and Systems, 2022
Coronavirus Pandemic Analysis Using Deep Learning Techniques A Study
Victor Abilash, Vino Geoffrey, Sathya Bama R Krishna
Proceedings of the 5th International Conference on Trends in Electronics and Informatics Icoei 2021, 2021
Smart District Analysis and Complaint Website
Monal Nagar, M.Bhuvaneshwar Reddy, Usha Nandini, Albert Mayan, Sathyabama Krishna, S.Prince Mary
Proceedings of the 5th International Conference on Trends in Electronics and Informatics Icoei 2021, 2021
Uber related data analysis using machine learning
Rishi Srinivas, B. Ankayarkanni, R. Sathya Bama Krishna
Proceedings 5th International Conference on Intelligent Computing and Control Systems Iciccs 2021, 2021
A study on virtual intelligence
R. Sathya Bama Krishna, D. Anto Praveena, N Nazhath Nafizza, J Naveena Ramesh Vardhini
Journal of Physics Conference Series, 2021
Examining and predicting helpfulness of reviews based on naive bayes
M. D. Anto Praveena, A. Christy, L.Suji Helen, R.Sathyabama Krishna, D. Usha Nandini
Journal of Physics Conference Series, 2021
Online Crime Reporting System—A Model
Mriganka Debnath, Suvam Chakraborty, R. Sathya Bama Krishna
Lecture Notes in Electrical Engineering, 2021
Question Paper Generator and Result Analyzer
R. Sathya Bama Krishna, Talupula Rahila, Thummala Jahnavi
Lecture Notes in Electrical Engineering, 2021
Predicting the Farmland for Agriculture from the Soil Features Using Data Mining
Kada Harshath, Kamalnath Mareedu, K. Gopinath, R. Sathya Bama Krishna
Lecture Notes in Electrical Engineering, 2021
A Survey on Image Segmentation Using Deep Learning
S. Prince Mary, Ankayarkanni, Usha Nandini, Sathyabama, S. Aravindhan
Journal of Physics Conference Series, 2020
Hybrid Method for Moving Object Exploration in Video Surveillance
R. Sathya Bama Krishna, B. Bharathi, Mohamed Uvaze Ahamed. A, B. Ankayarkanni
Proceedings of 2019 International Conference on Computational Intelligence and Knowledge Economy Iccike 2019, 2019
IoT based vehicle for industrial environment monitoring
D. Usha Nandini, S. Prince Mary, R. Hari Krishna, B. Bharathi, V. Maria Anu, et al.
International Journal of Recent Technology and Engineering, 2019
Neural computation based general disease prediction model
, S.Prince Mary, B. Bharathi, , S. Vigneshwari, , R. Sathyabama, and
International Journal of Recent Technology and Engineering, 2019
Classification of diabetes mellitus using soft computing and machine learning techniques
International Journal of Innovative Technology and Exploring Engineering, 2019
A study on unsupervised feature selection
Journal of Advanced Research in Dynamical and Control Systems, 2019
Big data deployment for an efficient resource prerequisite job
S. Prince Mary, D. Usha Nandini, B. Ankayarkanni, R. Sathyabama Krishna
Journal of Computational and Theoretical Nanoscience, 2019
A resourceful information collecting system using smart black box
D. Usha Nandini, R. Sathyabama Krishna, M. Nithya, R. Pavithra
Journal of Computational and Theoretical Nanoscience, 2019
Security prediction of ranking fraud with guarantee solution for mobile apps
International Journal of Pharmacy and Technology, 2016
Unsupervised spectral sparse regression feature selection using social media datasets
R. Sathya Bama Krishna, M. Aramudhan
ACM International Conference Proceeding Series, 2016
Prognostic classification of tumor cells using an unsupervised model
Biomedical Research India, 2016
Study of distance-based outlier detection
Arpn Journal of Engineering and Applied Sciences, 2016
Comparative analysis on spectral unsupervised feature selection: A review
International Journal of Applied Engineering Research, 2015
Hybrid method for moving object exploration in dynamic scene: A study
Global Journal of Pure and Applied Mathematics, 2015
Feature selection based on information theory for pattern classification
R. Sathya Bama Krishna, M. Aramudhan
2014 International Conference on Control Instrumentation Communication and Computational Technologies Iccicct 2014, 2014
Decision support system using fuzzy min-max neural network with the modified genetic algorithm
International Review on Computers and Software, 2014

R Sathya Bama Krishna

RESEARCH, TEACHING, or OTHER INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS