A multi strategy optimization framework using AI digital twins for smart grid carbon emission reduction S. Sakthivel, M. Arivukarasi, G. Charulatha, J. Nithisha, B. Abirami, et al. Scientific Reports, 2026 This research presents an AI-enabled digital twin framework to achieve carbon neutrality in smart grids through optimal management of heterogeneous energy storage systems. The proposed structure integrates battery, thermal, and hydrogen storage technologies with AI-driven forecasting models to address the challenge of renewable integration, while maintaining grid stability and economic viability. This paper presents a comparative analysis of three distinct optimization methodologies, like a rule-based (RB) heuristic approach, Model Predictive Control (MPC) with look-ahead capability, and a multi-objective Genetic Algorithm (GA). Simulation results that demonstrate the AI-optimized multi-energy storage (MES) integration significantly enhance the renewable utilization and reduce carbon emissions by approximately 30% compared to conventional approaches. Specifically, the MPC achieves a 29.9% reduction in carbon footprint (1741.1 kgCO₂ vs. 2485.2 kgCO₂ baseline) with corresponding operational cost savings of 30%, while GA shows a comparable 28.2% improvement. The comparative analysis discloses a critical trade-off between computational complexity, optimization performance, and practical implementability, with MPC emerging as a balanced method for a real-world application. This work has contributed to sustainable energy systems by providing a comprehensive framework for MES optimization, imparting treasured insights for grid operators and policymakers. The outcomes highlight the important role of AI-enabled digital twin in designing next-generation smart grid infrastructure, which is capable for supporting excessive renewable penetration at the same time as ensuring reliability and sustainable economic growth.
OXY SENSE-WEAR: A REAL-TIME IOT-BASED WEARABLE PLATFORM FOR CONTINUOUS MULTI-PARAMETER HEALTH MONITORING M.N. Vimal Kumar Archives for Technical Sciences, 2025 Purpose- The main objective of the proposed paper is to create and implement a real-time wearable health monitoring system based on IoT, i.e., Oxy Sense-Wear, that will enable the constant control of the main physiological parameters, such as ECG, EMG, SpO2, body temperature, and physical activity. The system is aimed at long-term surveillance of the elderly, bedridden, and long-term chronic disease patients, and this allows the patient to identify abnormal health conditions in time and provide proper medical care. Design/methodology/approach-The given device is a soft wearable chest strap with built-in biomedical sensors and powered by an ESP32 microcontroller. Live information is collected, analyzed, and sent through Wi-Fi to a cloud-based server and Android smartphone application. Physiological alerts will activate the buzzer and instant mobile notification when the physiological thresholds are surpassed. The software was used to design and simulate the hardware that was being developed with Proteus and create firmware in the Arduino IDE and the mobile application on Android Studio. Findings- There is a reliable real-time performance as experimental assessment shows heart rate changes with a deviation of +/-2 BPM, SpO 2 values were always in the range of 96-98, and body temperature was monitored accurately between 36.0 o C and 38.8 o C. Fall events were identified with great success at acceleration levels more than 2.5 g, and low false positives. The system recorded a mean alert latency of less than 500 ms and could operate continuously (8 to 12 hours, depending on charge) and thus proved to be viable in the case of personal and clinical remote healthcare monitoring. Originality/value-The proposed Oxy Sense-Wear platform is the first to offer a single multi-parameter sensing, real-time alerting, cloud synchronization, mobile connectivity, and OTA-enhanced platform in a small and wearable size. The work done in the future will be on the implementation of more sophisticated machine-learning algorithms for predictive health analytics, improving the security of the collected data by using encrypted authentication to provide more connection options with the use of the BLE and 5G technology to support the large-scale implementation and integration with the hospital information system. In an effort to be more concise and clearer, this manuscript lays emphasis on system-level insights, comparative appraisal, and quantitative performance assessment rather than a description of the components at a much more detailed level.
Application of Machine Learning Algorithms in Predicting the Heart Disease in Patients Razia Sulthana A, Jaithunbi A K, Sunraja P 2023 3rd International Conference on Advances in Electrical Computing Communication and Sustainable Technologies Icaect 2023, 2023 Healthcare services save the life of human beings by making timely effective decisions. The use of data mining tools is crucial for decision making, forecasting, and disease prediction. In this study, data mining algorithms are applied to predict heart disease. The dataset contains 14 attributes such as age, gender, blood pressure, blood fat, etc. These parameters are analyzed to predict the probability of patients prone to heart disease in future. Initially, the relationship between the parameters is analyzed. Following which Naïve Bayes, decision trees and Naïve Bayes with k-means clustering are applied over it for classification and prediction. These algorithms were employed to train the dataset and create a binary classification. The proposed system shows a better prediction of heart disease. The performance measures of the system are measured, and the obtained results illustrate the system can forecast the probability of developing the heart diseases.
Sentiment Analysis on Movie Reviews Dataset Using Support Vector Machines and Ensemble Learning Razia Sulthana A., Jaithunbi A. K., Haritha Harikrishnan, Vijayakumar Varadarajan International Journal of Information Technology and Web Engineering, 2022 The internet makes it easier for people to connect to each other and has become a platform to express ideas and share information with the world. The growth of the internet has indirectly led to the development of social networking sites. The reviews posted by people on these sites implies their opinion, and analysis over reviews is required to understand their intent. In this paper, natural language processing technique and machine learning algorithms are applied to classify the text data. The contributions of the proposed approach are three-fold: 1) chi square selector is applied to select the k-best features, 2) support vector machines is executed to classify the reviews (hyperparameters of the SVM classifier are tuned using GridSearch approach), and 3) bagging algorithm is applied with the base classifier over the newly built SVM classifier. The number of base classifiers of the bagging algorithm is varied accordingly. The results of the proposed approach are compared to the similar existing work, and hence, it is found to achieve better results as compared to the existing systems.
