Authors: G.Parvathidevi, L.Vishnu,K, Hanshithasai, J.Amarnath

Abstract: In the water resource management sector, ground water level prediction is a crucial issue to ensure sustainable water availability and prevent over- extraction. In this paper, machine learning techniques are used to predict groundwater levels by analyzing environmental and geological factors such as historical water levels, soil characteristics, topography, and climate conditions. Various predictive models, including GA-ANN, ICA-ANN, ELM, and ORELM, are applied to the dataset to improve accuracy in groundwater forecasting. The performance of these models is evaluated using metrics such as accuracy, precision, and F1-score, with the ORELM model achieving the highest accuracy of 92%. These AI-driven insights help in identifying optimal well locations, ensuring efficient water resource management and long-term sustainability.

 

 

Published by: vikaspatanker

Authors: Miss.Dhanalakshmi, Mr.Saranprasath, Mr.Santhuru, Mr.Pavinkishore, Mrs.Mythili Priya

 

 

Abstract: This project proposes the development of a GPS-based web application for government buses to provide real-time tracking and enhance the public transport experience. The system provides passengers with real- time information on bus locations, expected arrival times, and available seating via an intuitive interface. Integrated route details, including starting and ending points, help users plan their journeys efficiently. The application ensures transparency and improves safety by reducing waiting time and uncertainty. GPS and IoT technologies are leveraged to collect and transmit bus data to a centralized cloud system. Passengers can access real-time updates on their smartphones or through public displays at bus stops.The admin panel allows authorities to monitor bus operations and manage fleet logistics effectively. Alerts and notifications keep passengers informed about delays or route changes. The system promotes digital transformation in public transport with a focus on reliability and user convenience. Overall, the solution aims to improve trust, accessibility, and efficiency in government-operated bus services.

 

 

 

Published by: vikaspatanker

Authors: Akerele Olalekan Victor, Abegunde-Abikoye O.S, Omojogberun Veronica Y2

Abstract: Many buildings available today are built without considering whether they are energy efficient or not. This gives rise to either over-estimation or under-estimation of energy (electricity) to be used by the building. Hence, a way of estimating the total energy consumption of a building is to properly account for the variables that demand energy usage from a building and then calculate the resultant energy used using a suitable computer application. The energy performance of two two-bedroom bungalows was estimated using a developed computer application. The computer application allowed input of various building parameters such as geometry (height, breadth, and width), roof type, building orientation, window shading, cooling load, and other electrical appliances. The estimation was done during the peak hour of the day (Cooling Load Temperature Difference between 11 am and 3 pm) for one hour with the building facing due west to efficiently ascertain how energy efficient the building would perform under peak load. The results from computed data show that the building required more energy to keep it cool due to excessive sunlight incident on the building. Also, the roofing material and window shading contributed to the poor energy performance of the building. With an estimated value of 16kW, it can be concluded that the energy performance of the building was below average as a result of the poor selection of building materials and building orientation.

 

 

Published by: vikaspatanker

Authors: Brendon Lalchawimawia, Abhishek Mandal

Abstract: The study aimed in enhancing the efficiency of MIL-53(Al) in the remediation of tricyclazole from aqueous matrices through the application of RSM, ANN and GA. In order to enhance the remediation efficiency of tricyclazole by MIL-53(Al) process parameter- pH (2-11), adsorbate concentration (0.01-3 ppm), equilibration time (5 min, 10, 20, 30 and 1, 2, 3, 6h), adsorbent dosage (0.01-0.7 mg) were optimized by statistical modelling. An investigation of the batch methods of adsorption was carried out. The finding reports indicated that the RSM-ANN model's projection values exhibited greater agreement with experimental results as compared to RSM alone. The RSM-ANN model showed greater coefficients of determination than the RSM. As compared to RSM, which showed R2Adj = 0.980 for tricyclazole removal optimization, the RSM-ANN reported R2Adj and RMSE values of 0.998 and 0.0725. When genetic algorithm was introduced as a hybrid coupling to the RSM model it was found that amongst all the three optimization models RSM-GA model showed the best optimization, with an R2, R2Adj and Cross-validated R2Adj value of 0.9985, 0.9981, and 0.9963, respectively.

 

 

Published by: vikaspatanker

Authors: Dasari Sai Vishnu Babu, Shaik Mustafa, Molla Baji, P.Parthiban

 

 

Abstract: : Slurry-Infiltrated Fibrous Concrete (SIFCON) is a high-performance cementitious composite recognized for its outstanding ductility, impact resistance, and strength. This study evaluates the effects of varying hooked-end steel fiber content (1%, 3%, 5%, 7%, and 9%) and partial fly ash replacement on the flexural behavior of SIFCON. Designed to enhance sustainability and structural efficiency, the research explores how different fiber volumes and matrix compositions influence mechanical performance. Using simply supported beams tested under three-point bending, key parameters such as load capacity, deflection, crack patterns, and energy absorption are assessed. The findings reveal that flexural strength and toughness improve with increased fiber content, peaking at 8% volume. However, higher fiber concentrations lead to workability challenges and fiber clustering, which hinder stress uniformity. The study concludes that fly ash-based SIFCON with optimized fiber reinforcement offers a sustainable and robust solution for structural applications requiring superior flexural performance.

 

 

 

Published by: vikaspatanker

Authors: Dasari Sai Vishnu Babu, Shaik Mustafa, Molla Baji, P.Parthiban

 

 

Abstract: : Slurry-Infiltrated Fibrous Concrete (SIFCON) is a high-performance cementitious composite recognized for its outstanding ductility, impact resistance, and strength. This study evaluates the effects of varying hooked-end steel fiber content (1%, 3%, 5%, 7%, and 9%) and partial fly ash replacement on the flexural behavior of SIFCON. Designed to enhance sustainability and structural efficiency, the research explores how different fiber volumes and matrix compositions influence mechanical performance. Using simply supported beams tested under three-point bending, key parameters such as load capacity, deflection, crack patterns, and energy absorption are assessed. The findings reveal that flexural strength and toughness improve with increased fiber content, peaking at 8% volume. However, higher fiber concentrations lead to workability challenges and fiber clustering, which hinder stress uniformity. The study concludes that fly ash-based SIFCON with optimized fiber reinforcement offers a sustainable and robust solution for structural applications requiring superior flexural performance.

 

 

 

Published by: vikaspatanker

Authors: Krishna Birla, Siddarth Patil, Prof. Vaibhav Srivastava

Abstract: Landslides are a serious natural hazard that cause major social, economic, and environmental damage around the world. To reduce their impact, it’s crucial to accurately predict where they might happen. In recent years, combining Geographic Information Systems (GIS) with Machine Learning (ML) has greatly improved landslide prediction and mapping. GIS helps organize and visualize complex spatial data, while ML can find hidden patterns between the factors that lead to landslides. This review looks at different ML models used for landslide prediction, including Logistic Regression, Support Vector Machines, Random Forest, as well as ensemble methods like Bagging, Boosting, and Stacking. It also explores newer Deep Learning approaches. We discuss common challenges such as limited data, difficulty in understanding models, and how to handle changing conditions. Finally, we highlight future directions like Explainable AI (XAI) and real-time monitoring. By bringing together findings from recent studies, this review provides insights into what’s working, what’s not, and how ML and GIS can help improve landslide risk management.

 

 

Published by: vikaspatanker

Authors: Krishna Birla, Siddarth Patil, Prof. Vaibhav Srivastava

 

Abstract: Landslides are a serious natural hazard that cause major social, economic, and environmental damage around the world. To reduce their impact, it’s crucial to accurately predict where they might happen. In recent years, combining Geographic Information Systems (GIS) with Machine Learning (ML) has greatly improved landslide prediction and mapping. GIS helps organize and visualize complex spatial data, while ML can find hidden patterns between the factors that lead to landslides. This review looks at different ML models used for landslide prediction, including Logistic Regression, Support Vector Machines, Random Forest, as well as ensemble methods like Bagging, Boosting, and Stacking. It also explores newer Deep Learning approaches. We discuss common challenges such as limited data, difficulty in understanding models, and how to handle changing conditions. Finally, we highlight future directions like Explainable AI (XAI) and real-time monitoring. By bringing together findings from recent studies, this review provides insights into what’s working, what’s not, and how ML and GIS can help improve landslide risk management.

DOI: http://doi.org/

 

Published by: vikaspatanker

Authors: Krishna Birla, Siddarth Patil, Prof. Vaibhav Srivastava

 

Abstract: Landslides are a serious natural hazard that cause major social, economic, and environmental damage around the world. To reduce their impact, it’s crucial to accurately predict where they might happen. In recent years, combining Geographic Information Systems (GIS) with Machine Learning (ML) has greatly improved landslide prediction and mapping. GIS helps organize and visualize complex spatial data, while ML can find hidden patterns between the factors that lead to landslides. This review looks at different ML models used for landslide prediction, including Logistic Regression, Support Vector Machines, Random Forest, as well as ensemble methods like Bagging, Boosting, and Stacking. It also explores newer Deep Learning approaches. We discuss common challenges such as limited data, difficulty in understanding models, and how to handle changing conditions. Finally, we highlight future directions like Explainable AI (XAI) and real-time monitoring. By bringing together findings from recent studies, this review provides insights into what’s working, what’s not, and how ML and GIS can help improve landslide risk management.

DOI: http://doi.org/

 

Published by: vikaspatanker

Authors: Mrs. R. BHUVANESHWARI, Ms. T. MISHA

 

 

Abstract: Predicting house prices is both vital and complex due to the ever-changing nature of the real estate market. Conventional statistical approaches often fall short in identifying intricate data trends, making machine learning a more suitable solution. This project adopts the Support Vector Machine (SVM) algorithm to forecast housing prices by analyzing historical data and key market influences. Known for its ability to manage high-dimensional datasets and model nonlinear relationships, SVM proves to be a dependable method for accurate price prediction. The system evaluates multiple factors including geographic location, property dimensions, prevailing market trends, and economic conditions to improve prediction precision. Through SVM’s capabilities in both classification and regression, the model delivers strong, data-informed insights that assist homebuyers, sellers, and investors in navigating the dynamic real estate environment effectively

DOI: http://doi.org/

 

 

Published by: vikaspatanker