Daily Archives: May 22, 2025

Landslide Prediction Using Machine Learning and GisBased Approaches – A Comprehensive Review
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 pr vides insights into what’s working, what’s not, and how ML and GIS can help improve landslide risk management.

DOI: 10.61137/ijsret.vol.11.issue3.113

Published by: Kajal Tripathi

Authors: Nandhini P,, Ms. N. Sukanya

 

 

Abstract: Virtual Reality (VR) technologies are increasingly integrated into diverse domains, necessitating a deeper understanding of user experience and emotional engagement. This study explores an AI-based emotion detection framework that leverages biofeedback signals—such as heart rate variability, skin conductance, and facial expression data—within immersive VR environments. Machine learning algorithms are employed to analyze these multimodal inputs in real-time, enabling the detection and classification of user emotions. Preliminary results suggest improved immersion and user satisfaction, highlighting the potential of biofeedback-driven AI in creating emotionally intelligent VR . This study explores an AI-based emotion detection framework that leverages biofeedback signals—such as heart rate variability (HRV), skin conductance response (SCR), and facial expression data—within immersive VR environments. The proposed framework integrates sensor fusion techniques to combine diverse signal modalities, addressing challenges related to data synchronization, noise reduction, and individual variability. Experimental evaluations were conducted in controlled VR scenarios, assessing emotion recognition performance and its impact on user immersion and satisfaction.Preliminary results demonstrate the effectiveness of in emotion-aware applications such as therapeutic interventions, adaptive learning systems, and emotionally intelligent game design. This work contributes to the growing field of affective computing in VR by presenting a robust, real-time emotion detection model grounded in biofeedback and artificial intelligence.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Kuldeep Yadav, Deepak Singh Purviya, Ayush Rajpoot

Abstract: With the growing emphasis on personal health and fitness,technology-driven solutions have emerged to provide intelligent workout assistance. Our project, the AI-Powered Fitness Tracking Application, leverages Artificial Intelligence (AI), Machine Learning (ML), and Computer Vision to offer users a personalized and real- time fitness training experience. This application aims to analyze user movements, correct posture, track progress, and generate AI-based workout recommendations .Traditional fitness applications lack adaptability and personalized coaching, making it difficult for individuals to follow structured and effective fitness routines. Our AI-based fitness tracker solves this by using real-time movement analysis to provide instant feedback on exercises and posture correction. By integrating deep learning models and computer vision technologies, the application ensures a more engaging, accurate, and efficient workout experience.This research paper explores the development process, core functionalities, methodology, and future prospects of AI-powered fitness applications. The paper highlights the importance of ai in personal fitness, focusing on how technology can revolutionize the way people work out.

 

 

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.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Daniel Antwi Owusu

Abstract: In A Good Man Is Hard to Find, Flannery O’Connor grapples with the concept of goodness, questioning whether it is determined by social norms, religious grace, or self-awareness. The characters in the story, particularly the Grandmother and the Misfit, embody contradictions that challenge conventional ideas of morality. Through a series of darkly ironic events, O'Connor suggests that true goodness may be rooted in self-awareness, humility, and grace, rather than superficial respectability. This paper examines these qualities and their significance, highlighting O'Connor’s use of Southern Gothic elements to convey the often complex and unexpected nature of redemption and moral understanding. This paper employs ethical and moral literary criticism to analyze the tension between outward virtue and internal transformation, offering a nuanced reading of goodness in O’Connor’s world.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: J.Pradeep, Dr. A. Swaroopa Rani, P. JaiDeep Reddy

 

 

Abstract: This study focuses on formulating and evaluating "Berry Blast GoliSoda," an iron-rich functional beverage aimed at combating iron deficiency in young adults. Made from beetroot, pomegranate, and strawberry extracts, along with ferrous gluconate, the drink offers a natural source of iron, vitamin C, and antioxidants. Natural carbonation enhances its sensory appeal. The optimized formulation was assessed for physicochemical properties, iron content, antioxidant activity, microbial safety, and sensory acceptability. Results showed high iron bioavailability, good stability, and favorable sensory scores, highlighting its potential as a nutritious and appealing health beverage. This study focuses on formulating and evaluating "Berry Blast GoliSoda," an iron-rich functional beverage aimed at combating iron deficiency in young adults. Made from beetroot, pomegranate, and strawberry extracts, along with ferrous gluconate, the drink offers a natural source of iron, vitamin C, and antioxidants. Natural carbonation enhances its sensory appeal. The optimized formulation was assessed for physicochemical properties, iron content, antioxidant activity, microbial safety, and sensory acceptability. Results showed high iron bioavailability, good stability, and favorable sensory scores, highlighting its potential as a nutritious and appealing health beverage.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Faweya. O, OYELAKIN O.P, Odukoya E.A, Aladejana A.E

Abstract: This research estimates the parameters of the Fréchet distribution for extreme rainfall data using two widely recognized statistical approaches: Maximum Likelihood Estimation (MLE) and Least Squares Estimation (LSE). The objectives include estimating the Fréchet distribution parameters using both methods, conducting a comparative evaluation of their performance, and identifying the more accurate and reliable technique. The comparative analysis demonstrated that the Maximum Likelihood Estimation method outperformed the Least Squares Estimation method. MLE produced parameter estimates with lower standard errors and biases, indicating greater precision and reduced variability. The model evaluation criteria, used include the Negative Log-Likelihood (NLLH), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC), further supported the preference for MLE over LSE. The MLE method yielded an NLLH of 98.7, AIC of 71.08, and BIC of 74.06, indicating a better overall fit than LSE ,As a result, the study concludes that MLE is the more robust and dependable method for modeling extreme rainfall data using the Fréchet distribution. These findings highlight the importance of selecting appropriate estimation techniques for extreme value analysis, particularly in environmental and disaster risk management applications. By utilizing the strengths of the Fréchet distribution and the MLE approach, this study contributes to the expanding field of extreme value theory and its practical applications in hydrology and climatology. The findings have significant implications for enhancing predictive models, refining flood risk assessments, and strengthening resilience against climate-induced extreme weather events.

 

 

Published by: vikaspatanker

Authors: Faweya. O, OYELAKIN O.P, Odukoya E.A, Aladejana A.E

Abstract: This research estimates the parameters of the Fréchet distribution for extreme rainfall data using two widely recognized statistical approaches: Maximum Likelihood Estimation (MLE) and Least Squares Estimation (LSE). The objectives include estimating the Fréchet distribution parameters using both methods, conducting a comparative evaluation of their performance, and identifying the more accurate and reliable technique. The comparative analysis demonstrated that the Maximum Likelihood Estimation method outperformed the Least Squares Estimation method. MLE produced parameter estimates with lower standard errors and biases, indicating greater precision and reduced variability. The model evaluation criteria, used include the Negative Log-Likelihood (NLLH), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC), further supported the preference for MLE over LSE. The MLE method yielded an NLLH of 98.7, AIC of 71.08, and BIC of 74.06, indicating a better overall fit than LSE ,As a result, the study concludes that MLE is the more robust and dependable method for modeling extreme rainfall data using the Fréchet distribution. These findings highlight the importance of selecting appropriate estimation techniques for extreme value analysis, particularly in environmental and disaster risk management applications. By utilizing the strengths of the Fréchet distribution and the MLE approach, this study contributes to the expanding field of extreme value theory and its practical applications in hydrology and climatology. The findings have significant implications for enhancing predictive models, refining flood risk assessments, and strengthening resilience against climate-induced extreme weather events.

 

 

Published by: vikaspatanker

Authors: Faweya. O, OYELAKIN O.P, Odukoya E.A, Aladejana A.E

Abstract: This research estimates the parameters of the Fréchet distribution for extreme rainfall data using two widely recognized statistical approaches: Maximum Likelihood Estimation (MLE) and Least Squares Estimation (LSE). The objectives include estimating the Fréchet distribution parameters using both methods, conducting a comparative evaluation of their performance, and identifying the more accurate and reliable technique. The comparative analysis demonstrated that the Maximum Likelihood Estimation method outperformed the Least Squares Estimation method. MLE produced parameter estimates with lower standard errors and biases, indicating greater precision and reduced variability. The model evaluation criteria, used include the Negative Log-Likelihood (NLLH), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC), further supported the preference for MLE over LSE. The MLE method yielded an NLLH of 98.7, AIC of 71.08, and BIC of 74.06, indicating a better overall fit than LSE ,As a result, the study concludes that MLE is the more robust and dependable method for modeling extreme rainfall data using the Fréchet distribution. These findings highlight the importance of selecting appropriate estimation techniques for extreme value analysis, particularly in environmental and disaster risk management applications. By utilizing the strengths of the Fréchet distribution and the MLE approach, this study contributes to the expanding field of extreme value theory and its practical applications in hydrology and climatology. The findings have significant implications for enhancing predictive models, refining flood risk assessments, and strengthening resilience against climate-induced extreme weather events.

 

 

Published by: vikaspatanker

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