Category Archives: Uncategorized

Authors: Dr. Suhas Mache, Bhagyashree Ingale

Abstract: Globally, music streaming services have completely changed how people listen to music. This study uses Power BI- based data analysis to investigate Spotify user behavior and listening habits. Using dynamic dashboards and visual aids, the study looks at regional preferences, artist performance, track patterns, and genre popularity. With the goal of assisting artists, marketers, and producers in making defensible decisions based on streaming data, business intelligence approaches provide actionable insights.

DOI: https://doi.org/10.5281/zenodo.15836070

 

Published by: vikaspatanker

Authors: Dyaga Suresh,

Abstract: – Cyclone separators are widely used in industrial applications to remove particulate matter from gaseous streams. The performance of a cyclone is highly dependent on operational parameters such as inlet velocity and particle size. In this study, Computational Fluid Dynamics (CFD) is utilized to simulate and evaluate the performance of an industrial cyclone separator. Various inlet velocities (10 m/s to 25 m/s) and particle diameters (1 µm to 50 µm) were analyzed to determine their effects on separation efficiency and pressure drop. The simulations reveal that both inlet velocity and particle size significantly influence cyclone performance. This work helps optimize cyclone design parameters to improve dust removal efficiency while minimizing energy losses.

 

 

 

Published by: vikaspatanker

Authors: K.Ganesh, Assistant Professor K.Abhiram

Abstract: With these new tools, we can only speculate as to the level of intelligence that the next generation will achieve by modifying current methods. More and more, society benefits from increasingly sophisticated computing techniques. This article explores and discusses the smart road traffic system, which is one of the advantages. Using these state-of-the-art computational approaches will undoubtedly make the control system for road traffic lights easier and more efficient in the future. In order to optimize the overall trip time, the road traffic system takes into account several parameters, such as total travel time, wait time or delay time in the traffic line, vehicle speed, etc. There are a few issues with the road traffic flow, such as drivers not obeying the regulations of the road, accidents, and congestion. The real issue with traffic congestion is the lack of a better model for managing traffic on roads, which necessitates the dedication of researchers to finding a solution. The current traffic light control system has a few limitations, such as not being able to adjust the delay time based on the density of traffic, not being able to prioritize lane flow when emergency vehicles like fire trucks and ambulances are on the road, and so on. These studies aim to find solutions to the aforementioned traffic issues and, using the aforementioned factors, to optimize the overall travel time in a way that causes minimal delay or congestion. To address these issues, this study employs a probabilistic traffic queue analytical model to find a computationally efficient traffic model. An improved traffic light management system is developed by simulating a model that takes vehicle categorization into account and tests it with various traffic conditions. The model accounts for a variable time delay.

Published by: vikaspatanker

Authors: M. Ramesh Reddy, Assistant Professor K.Abhiram

Abstract: Here we offer a study that falls under the umbrella of regional studies. While ideas like regional development and resources—with a focus on transportation infrastructure—have been around for a while, regional science is a more recent subfield of economics. Nearly everyone is more worried about regional economic planning now than they were a decade ago. A plethora of new concerns and challenges have recently come to light, stemming from the experiences of both industrialized and poor nations. The desirability of various sites for different activities has altered due to the integration of economic activity. Both regional planning on an individual level and coordinated regional planning at the system level have recently garnered increased attention from the governments of a number of nations. A big problem for regional economists has been the increased need for comprehensive information brought about by this interest in economic planning. A nation or area needed a specific amount of transportation infrastructure to make the most of its resources at any particular point in its economic growth. Adami (1987) 1. The effectiveness of the transportation network is a key component of the regional economic structure. In order to reach both local and foreign markets, a country's production and distribution system relies on its transportation network, particularly its road network. This network must be both adequate and efficient. In addition to the particular function it provides, the transport network is important because of the integrating and uniting effect it has on society and the economy.

Published by: vikaspatanker

Authors: B.Dileep, Assistant Professor Mudigonda Harish Kumar

Abstract: This paper proposes hybrid traffic flow prediction techniques using Parametrical Doped Learning (PDL) and Truncated Dual Flow Optimization (TDFO) along with Adaptive Wildfire Optimization (AWO) and Spatial Pattern Super Learning (SPSL). These techniques are validated using datasets from LTPP and PeMS. Performance comparison with traditional algorithms like TrAdaBoost, KLT, and others shows superior outcomes in terms of accuracy, F1-score, sensitivity, and recall.

 

Published by: vikaspatanker

Authors: Dr. M.M. Janeela Therasa, Gayathri CL

Abstract: Mobile Edge Computing (MEC) enables low-latency data processing by bringing computation closer to users. However, it faces critical challenges such as limited storage capacity, unpredictable data patterns, network instability, and increasing volumes of duplicate data. These factors lead to performance degradation, increased retrieval latency, and inefficient resource utilization. To tackle these issues, a robust optimization-based deduplication framework is proposed. This system leverages two algorithms: UEDDE-C (Uncertainty-based Edge Data Deduplication with Column and Constraint Generation), which provides high accuracy in detecting exact duplicates, and UEDDE-A (Approximation-based), which is computationally lightweight and effective for identifying near duplicates. Furthermore, since data security is a pressing concern in edge environments, the proposed system integrates AES encryption to safeguard sensitive information before the deduplication process. This ensures not only confidentiality and integrity but also standardizes data into consistent formats for more efficient handling. The proposed framework significantly reduces redundant storage, lowers network traffic, speeds up data access, ensures security compliance, and enhances overall MEC system reliability under uncertain and dynamic conditions.

DOI: https://doi.org/10.5281/zenodo.15834266

 

Published by: vikaspatanker

Authors: Dnyneshwar Gawade

Abstract: Video games have evolved from simple enter- tainment to complex digital environments with significant implications for mental health. This paper explores the dual nature of video games, highlighting their potential benefits, such as cognitive enhancement, stress relief, and social con- nectivity, alongside risks like addiction, social isolation, and increased aggression. Drawing on recent studies, we examine how game genres, play duration, and player demographics influence mental health outcomes. We also discuss future directions, including the development of therapeutic games and the need for nuanced research to inform policy and game design. The findings suggest that moderate gaming can foster mental well-being, while excessive use poses significant risks, necessitating tailored interventions.

DOI: https://doi.org/10.5281/zenodo.15836400

Published by: vikaspatanker

Authors: Vinodhkumar S, Pravin P, Siva Sankaralingam G

Abstract: The occurrence of strokes through a model and prediction helps to find out the utilizing data on demographic aspects, lifestyle, and other parameters of a fairly well-known and public healthcare dataset containing information about age, gender, hypertension, heart disease, smoking, BMI, and average glucose level. Preprocessing of the data involved dealing with missing values, encoding the categorical variables, and balancing the data through the Synthetic Minority Oversampling Tech- nique (SMOTE) to overcome the problem of imbalance. Then, several algorithms were trained and tested, including Logistic Regression, Decision Trees, Random Forest, SVM, and Naive Bayes, and the performance was evaluated in terms of accuracy, precision, recall, and F1 score. The results show that ensemble and tree-based algorithms obtain high precision with more than 90% accuracy in predicting who could have a main risk for stroke. Onset feature importance shows age, hypertension, heart disease, and glucose level as important predictors. The gists from the results show that potential exists in machine-learning methods for early risk assessment of stroke and strongly support the implementation of data-driven tools in clinical decision-making to provide timely intervention to reduce stroke morbidity and mortality.

DOI: https://doi.org/10.5281/zenodo.15833732

 

Published by: vikaspatanker

Authors: Mrs. Alpana Meena, Dr. Neelesh Jain

Abstract: Text is categorized using machine learning algorithms based on the sentiment polarity of the text. These machine learning-based approaches approach sentiment classification as a problem akin to document or subject classification. Nevertheless, this method has drawbacks including hard feature extraction, dimensionality expansion, and sparse feature vectors. In this article, we have combined machine learning and deep learning algorithms and proposed ensemble based framework to classify the personality. We have done different experiments with machine learning, deep learning and proposed model and found that our proposed model provided significant average accuracy about 67.452.

DOI: https://doi.org/10.61137/ijsret.vol.11.issue4.102

Published by: vikaspatanker

Authors: Pravin P, Vinodhkumar S,, Siva Sankaralingam G

Abstract: The occurrence of strokes through a model and prediction helps to find out the utilizing data on demographic aspects, lifestyle, and other parameters of a fairly well-known and public healthcare dataset containing information about age, gender, hypertension, heart disease, smoking, BMI, and average glucose level. Preprocessing of the data involved dealing with missing values, encoding the categorical variables, and balancing the data through the Synthetic Minority Oversampling Tech- nique (SMOTE) to overcome the problem of imbalance. Then, several algorithms were trained and tested, including Logistic Regression, Decision Trees, Random Forest, SVM, and Naive Bayes, and the performance was evaluated in terms of accuracy, precision, recall, and F1 score. The results show that ensemble and tree-based algorithms obtain high precision with more than 90% accuracy in predicting who could have a main risk for stroke. Onset feature importance shows age, hypertension, heart disease, and glucose level as important predictors. The gists from the results show that potential exists in machine-learning methods for early risk assessment of stroke and strongly support the implementation of data-driven tools in clinical decision-making to provide timely intervention to reduce stroke morbidity and mortality.

DOI: http://doi.org/

 

 

Published by: vikaspatanker