Volume 12 | Issue 5 |

 Abstract

Traffic accidents pose significant threats to public safety and infrastructure. Predicting accident risk is crucial for implementing preventive measures and enhancing road safety. This study proposes a machine learning approach to predict traffic accident risk.The methodology involves the collection of extensive historical accident data, including factors such as weather conditions, road types, time of day, and traffic volume. Various machine learning algorithms are employed, including decision trees, random forests, and neural networks, to analyze and model the complex relationships between these factors and accident occurrence. Feature engineering techniques are applied to extract meaningful patterns and improve model performance. The performance of the models is evaluated using metrics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Traffic Accident Prediction Using Machine Learning.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Integrating Generative adversarial Networks (GANs) with Twitter sentiment analysis for stock market prediction. GANs are hired to generate sensible market situations, while sentiment analysis of Twitter information provides actual-time insights into public sentiment. by combining those strategies, the version ambitions to beautify prediction accuracy and seize market dynamics prompted via social media sentiment. The experiment evaluates the effectiveness of this method the use of ancient market data and Twitter sentiment analysis. consequences exhibit the capability of GAN-primarily based models in improving stock marketplace prediction by way of incorporating real-time sentiment analysis from social media structures like Twitter

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Stock Market Prediction, Generative Adversarial Networks (GANs)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Climate warming is making wildfires a greater menace. This project handles smoke and fire detection using a deep learning model built with Mobile-Net, a robust yet efficient architecture perfect for real-time applications. The model is trained using a vast library of images and videos that depict fire, smoke, and commonplace situations. Its great degree of precision in consistently differentiating between these groups makes it appropriate for a wide range of applications. Through the analysis of images and even live webcam feeds, the technology offers real-time fire and smoke detection. It can be utilized with surveillance systems, fire alarms, and emergency response systems due to its versatility. All things considered, by offering a precise and intuitive deep learning solution for smoke and fire detection, our research advances safety and security in a variety of scenarios

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Wildfire, Machine Learning, Fire Detection, Mobile-Net, Smoke, Video.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Diabetes, a widespread chronic condition globally, has spurred interest in using machine learning for prognosis and management. This effort aims to develop a predictive framework using machine learning tools, analyzing various data sources to identify at-risk individuals. By employing XGBoost and other machine learning algorithms, it processes large datasets efficiently. Additionally, it integrates a diabetes forecasting chatbot, offering personalized guidance based on individual risk factors. This system shows promise in enhancing diabetes management and health outcomes by accurately identifying high-risk individuals and providing tailored support. Overall, it underscores the potential of machine learning and chatbot technologies in improving chronic disease management.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Diabetes, Prediction, Machine Learning, Chat Bot.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A deals on accident detection, wherein we identify the characteristic attributes of objects in addition to detecting them as belonging to a class. More precisely, our goal is concurrently identifying the status of item class bounding boxes--safe, harmful, or crashed--and their detection on roadways. In order to accomplish this, we create a brand-new dataset and suggest a baseline technique for comparing accident detection tasks. Our Attention R-CNN accident detection network is designed with two streams: one for computing characteristic properties and the other for object detection with classes. We incorporate global contexts that are taken advantage of from the scene into the stream for object detection as an attention mechanism that gathers contextual information in the scene.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bounding Boxes, image processing, Attention RCNN, Object Detection

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The field of healthcare analytics has emerged as a transformative discipline that combines data analysis, machine learning, and clinical expertise to improve patient outcomes and optimize the delivery of healthcare services. In recent years, the rapid digitization of healthcare records and the widespread adoption of Electronic Health Records (EHRs) have generated an unprecedented volume of clinical and demographic data. This wealth of data provides an opportunity to move beyond traditional healthcare practices by leveraging computational models for disease prediction, risk assessment, and personalized treatment planning. By integrating machine learning algorithms with clinical knowledge, healthcare analytics enables the extraction of meaningful insights from large datasets, uncovering hidden patterns and relationships that may not be evident through conventional clinical observation. The increasing complexity of patient care, coupled with the growing prevalence of chronic and lifestyle-related diseases, highlights the critical need for predictive models that can assist healthcare professionals in making timely and informed decisions. Traditional healthcare approaches often rely on manual assessment and isolated diagnostic procedures, which can be time-consuming, subjective, and prone to human error. By contrast, machine learning models trained on EHR data can provide automated, accurate, and scalable predictions, helping clinicians identify high-risk patients, anticipate disease progression, and design personalized intervention strategies. This shift towards data-driven decision-making not only enhances the efficiency of healthcare delivery but also enables precision medicine, where treatments and preventive measures are tailored to individual patient profiles, considering factors such as demographics, clinical history, laboratory results, and comorbidities. The primary objective of this research is to develop and evaluate multiple machine learning models for predicting critical health outcomes, specifically focusing on cancer, diabetes, diabetic retinopathy, and heart disease. These conditions are selected due to their high prevalence, significant morbidity and mortality, and potential for early intervention. Using demographic and clinical data obtained from EHRs, the study applies a comparative approach to evaluate the performance of Support Vector Machines (SVM), Decision Trees (DT), Logistic Regression (LR), and Random Forests (RF). By testing these models on diverse datasets, the research aims to determine which algorithms provide the highest accuracy, precision, and recall for each specific disease, thereby assisting clinicians in selecting the most reliable predictive tools for real-world applications. Experimental results indicate promising performance across all selected diseases. Support Vector Machines and Decision Trees achieved exceptional accuracy in predicting cancer (97.08%) and diabetes (97.33%), respectively. For diabetic retinopathy, Logistic Regression demonstrated a notable accuracy of 76.52%, highlighting its effectiveness in structured datasets where linear relationships exist. Heart disease prediction benefited most from Decision Trees, achieving 86.41% accuracy, while SVM applied to the Pima diabetes dataset produced an accuracy of 79.746%. These findings underline the importance of comparative model analysis, as no single algorithm consistently outperforms others across all disease types. By analyzing multiple models, healthcare professionals can identify the optimal approach for each clinical context, improving predictive reliability and supporting evidence-based interventions. Beyond numerical performance metrics, the research emphasizes the practical application of these models in healthcare settings. The system is designed to integrate with clinical workflows, enabling physicians to access risk assessments, visualize patient trends, and receive actionable recommendations. Furthermore, the use of robust evaluation metrics such as accuracy, precision, and recall ensures that predictions are not only statistically sound but also clinically relevant. By bridging the gap between computational modeling and clinical decision-making, this research contributes to enhanced patient care, early diagnosis, and preventive healthcare strategies. In conclusion, this study represents a significant step forward in healthcare analytics by demonstrating the potential of machine learning to transform disease prediction and personalized medicine. By leveraging EHR data and conducting a comparative evaluation of multiple predictive models, the research provides a framework for integrating advanced analytics into routine clinical practice. The high accuracy achieved for critical diseases underscores the feasibility of AI-driven solutions in improving patient outcomes, reducing healthcare costs, and supporting clinicians in making timely, informed decisions. The proposed system lays the foundation for future developments in precision medicine, offering scalable, reliable, and interpretable predictive tools that can adapt to evolving healthcare needs.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Skin Lesion Classification, Multimodal Learning, Transfer Learning, Ensemble Models, Chatbot-based Healthcare.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The industrial sector is going through a major change right now thanks to the smart automation that AI can do. This synergy makes things much more efficient and makes it easy to make decisions based on data. These benefits make it easier to allocate resources and improve the accuracy of production planning. This paper aims to provide the most up-to-date information on AI in manufacturing and what is happening right now. The review also looks at the main ways that AI is being used in manufacturing, like predictive maintenance, quality control, process optimisation, supply chain management, robotics and automation, and intelligent decision support systems. The review also looks at the problems that the manufacturing industry faces and how AI might be able to help with them. This work also goes into great detail about recent advances in AI, such as explainable AI, human-robot collaboration, edge computing, and the Internet of Things (IoT) integration. The review ends with suggestions, a list of best practices, and ideas for possible ways to work together.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Smart Manufacturing, Predictive Maintenance, Industrial Automation, and Human-Robot Collaboration

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Nai Shiksha Niti Ke Niyam Aur Avasanrachna Ki Kami

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Nai Shiksha Niti Ke Niyam Aur Avasanrachna Ki Kami

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study delves into the vital role of forest resources in sustaining livelihoods among tribal communities in the Jangalmahal region of Sarenga block, Bankura district, West Bengal, India. Amidst dry-deciduous forests, Non-Timber Forest Products (NTFPs) such as Sal leaves, Mahua flowers, fuelwood, and fodder emerge as lifelines, offering economic resilience for forest-dependent households facing agricultural uncertainties and climate challenges. Drawing on primary data from 92 households collected in 2023 via structured surveys, focus group discussions, key informant interviews, and secondary sources, the research employs a mixed-methods approach. Quantitative analysis using Python-based tools (e.g., descriptive statistics, correlation, OLS regression, paired t-tests and Gini coefficients) quantifies contributions, while qualitative insights explore socio-economic dynamics. Key findings reveal that forest resources account for 20.21% of total household income (mean Rs. 7,583 annually), ranking third after agriculture and labor. NTFPs drive 63.73% of forest earnings, generating 81.4 mandays of self-employment per household (Rs. 4,845/year), far outpacing seasonal direct employment from the Forest Department (13.45 mandays, Rs. 2,757/year). Regression shows each NTFP manday yields Rs. 60 in income, with NTFPs reducing income inequality by 15% (Gini drop from 0.20 to 0.17). The study underscores NTFPs' potential for poverty alleviation and biodiversity conservation through sustainable practices. Policy recommendations include formalizing markets, capacity building, expanding Joint Forest Management, and climate-adaptive strategies to elevate NTFP contributions to 30-40% of income, fostering inclusive development for marginalized tribes like Santhals.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Non-Timber Forest Products (NTFPs), Jangalmahal, Sarenga block, Manday, Direct employment, Joint forest management (JFM)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The philosophy of Mahatma Ghandhi is most powerful and relevant in Indian context. Mahatma Gandhi's philosophy of truth, non-violence, and moral politics continues to hold significance in the present-day political arena. In an era marked by rising authoritarianism, corruption, identity-based conflicts, and environmental crises, Gandhian principles offer an ethical alternative that emphasizes decentralization, participatory governance, communal harmony, and sustainable development. This paper explores the relevance of Gandhian thought in modern democratic politics, analyses its application in movements across the globe, and examines how it can shape ethical governance and people-centered leadership today. As long as there is strife, hostilities, ethnic cleansing, religious unrest, internal conflicts and threats of military occupation, people will turn to Gandhi. His usefulness will not end unless conflict ceases.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Non-Violence, Truth, Moral polities, Sustainable development & Gandhian philosophy.

  License

Creative Commons Attribution 4.0 and The Open Definition