Publications
An Efficient Supervised Machine Learning Model Approach for Forecasting of Renewable Energy to Tackle Climate Change
This paper presents a machine learning model to accurately forecast renewable energy usage in the EU, focusing on solar and wind energy. The approach uses live data from the ENTSOE transparency platform, utilizing algorithms such as linear regression, random forest, and support vector machines. The system is deployed via a user-friendly web app, allowing users to select a country and time span to predict energy consumption trends. The model’s precision is validated by achieving low SMAPE values (1-2%), making it reliable for real-time decision-making and climate strategy. This tool aims to support the shift towards carbon neutrality by 2050, aligning energy forecasting with climate goals.
Elements of Nature Optimized into Smart Energy Grids using Machine Learning
This paper explores the use of machine learning to predict solar energy output by analyzing data like temperature, humidity, and wind direction. Using data from a weather station in Hawaii, the study applies algorithms such as linear regression, random forest, and support vector machines to predict solar radiation patterns, helping to balance energy supply in smart grids. The best-performing model was a hyper-parameterized random forest with a cross-validation score of 72%, attributed to its ability to accurately track daily cycles. The research highlights how machine learning enhances solar energy integration by making predictions more reliable, aiding the shift toward sustainable energy systems.
AI Based Nose for Trace of Churn in Assessment of Captive Customers
This paper examines using AI to predict customer churn by identifying key factors that indicate when captive customers may leave a service. The approach leverages various machine learning models to analyse customer behaviour patterns, allowing businesses to detect early signs of churn and take pre-emptive actions. Key metrics like customer engagement, service usage, and satisfaction are assessed to enhance prediction accuracy. The study suggests that AI-based churn prediction can significantly improve retention strategies by providing actionable insights, enabling companies to address potential issues before customers decide to leave, thus optimizing customer loyalty and revenue stability.
Delve into the Realms with 3D Forms: Visualization System Aid Design in an IOT-Driven World
This document presents “Delve 3D,” a project that uses 3D modelling and visualization techniques to enhance data interpretation and analysis. The study explores how 3D models can provide a more immersive experience for understanding complex data sets, particularly in fields like architecture, urban planning, and engineering. By transforming traditional data into interactive 3D forms, Delve 3D enables users to examine and manipulate data in real-time, fostering a deeper comprehension of spatial relationships and structural details. This approach aims to bridge gaps in traditional data analysis by integrating visual depth and interactivity, paving the way for more insightful decision-making processes in various industries.
Innovative Smart Water Management System Using Artificial Intelligence
This paper presents an AI-driven smart water management system designed to optimize water usage and conservation. The system uses sensors and machine learning to track water consumption at the household level, with real-time data stored in the cloud. It predicts future usage through time series analysis and employs various machine learning algorithms, including Random Forest and Gradient Boosting, to enhance accuracy. Additionally, the system includes features for leakage detection and usage monitoring via a custom mobile app. This innovative approach aims to reduce wastage, promote sustainable water practices, and potentially extend to applications in industries like food processing and chemical manufacturing for precise liquid handling.
A Cloud Native Machine Learning based Approach for Detection and Impact of Cyclone and Hurricanes on Coastal Areas of Pacific and Atlantic Ocean
This paper introduces a cloud-based machine learning approach for detecting and analysing the impact of cyclones and hurricanes on coastal areas along the Pacific and Atlantic Oceans. By leveraging data from hurricane databases and using models such as Random Forest, Decision Tree, and Gradient Boosting, the study identifies the most accurate prediction methods, with Random Forest achieving the highest performance (96-98% accuracy). The system is deployed on Microsoft Azure, creating a predictive web service accessible via API for real-time monitoring. Additionally, the Folium library is used to map storm severity and landfall locations, offering a visual tool for disaster preparedness. This approach aims to enhance early warning systems, helping mitigate storm-related damages in vulnerable regions.