Category Archives: Uncategorized

Authors: Priyanka N Godiyal, Rutuja Amrale, Revati Ma’am, Archana Ma’am.

Abstract: Road traffic accidents are a leading cause of mortality worldwide, with India recording over 1.5 lakh fatalities annually. Identifying 'black spots' — specific road segments with disproportionately high accident frequency — is critical for targeted infrastructure intervention. Traditional methods of black spot identification rely on statistical thresholds applied to historical data, which are often reactive and location-agnostic. This paper proposes an integrated framework combining Machine Learning (ML) and Geographic Information Systems (GIS) for predictive black spot detection. We review and compare ML algorithms including Random Forest, XGBoost, Support Vector Machines (SVM), and Deep Neural Networks applied to multi-source data comprising accident records, road geometry, traffic volume, and environmental factors. Spatial analysis techniques such as Kernel Density Estimation (KDE) and spatial autocorrelation are used for feature engineering. Results show that ensemble methods achieve accuracy above 90%, with XGBoost yielding the highest AUC-ROC of 0.94. GIS-integrated output maps provide actionable, zone- specific risk rankings to support road safety planning.

DOI: https://doi.org/10.5281/zenodo.20118287

Published by: vikaspatanker

Authors: Harini . K, Assistant Professor S.Janani

Abstract: The rapid growth of Over-The-Top (OTT) platforms has fundamentally changed the way users consume multimedia content on the internet. Streaming services like Netflix have set a highstandard for user experience, interface design and content discovery. This project, titled “Netflix Clone – Web Application Using HTML, CSS, JavaScript, React and Vite” . The backend is built using Node.js, providing RESTful APIs to handle user interactions and data management. PostgreSQL is used as the relational database for storing user data, movie details, and other application information., aims to design and implement a responsive and interactive web interface that emulates the core look and feel of the Netflix platform using modern front-end technologies. The primary objective of this project is to build a single-page application (SPA) that allows users to browse a catalogue of movies and series, view categorized lists such as “Popular”, “Trending” and “Top Rated”, and navigate to detailed information pages for each title. The user interface isimplemented using HTML5 for structure, CSS3 for styling, and JavaScript for dynamic behavior. React is used as the front-end library to efficiently manage UI components and state, whileserves as a fast and optimized build tool and development server. The system implements CRUD (Create, Read, Update, Delete) operations for managing users, movies, and preferences. The application is developed using Visual Studio Code and follows modern web development practices. Together, these tools provide a modern, modular and scalable environment for building the Netflix clone. The project follows a structured approach including requirement analysis, interface design, component design, implementation, and basic testing. Emphasis is placed on responsive design to ensure that the application works across desktops, laptops and mobile devices. Features such as reusable React components, props and state, routing (if used), and API-like data retrieval from static JSON or mock data are incorporated to simulate real-world application behaviours

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Nimisa Bhagchandani

Abstract: The rapid growth of digital commerce and the increasing use of artificial intelligence have significantly changed the way consumers make purchase decisions online. One of the most common applications of AI in this space is the use of personalization algorithms, which provide users with tailored product recommendations based on their preferences and past behaviour. While these systems are designed to improve convenience and enhance user experience, they may also create unintended challenges for consumers. This study examines the impact of personalization algorithms on consumer decision fatigue and purchase decision-making in digital commerce contexts. The research focuses on understanding whether personalized recommendations simplify the decision-making process or contribute to cognitive overload. Decision fatigue is considered as a key factor that may influence how consumers respond to multiple product options and recommendations. The findings of the study are expected to provide insights into how personalization influences consumer behaviour beyond its intended benefits. It highlights the need for digital platforms to balance personalization with user comfort and cognitive ease. The study contributes to a better understanding of the psychological effects of personalization and its role in shaping online consumer decision-making.

DOI: https://zenodo.org/records/20099925

Published by: vikaspatanker

Authors: Sonal Saral, Anurag Gangwar

Abstract: Agricultural residue burning is a major contributor to seasonal air pollution in northwestern India, significantly affecting air quality across the Indo-Gangetic Plain. This study presents a comprehensive Spatio-temporal and seasonal analysis of crop residue burning in Punjab and Haryana during 2021–2025 using satellite-derived fire count data (MODIS and VIIRS), with a focus on pre-monsoon (Rabi: April–May) and post-monsoon (Kharif: October–November) periods. The results indicate that post-monsoon burning dominates total fire activity, accounting for approximately 70–75% of annual fire counts, with Punjab alone contributing more than 80% of regional fire events. Peak Kharif fire activity exceeded 170,000 events in Punjab, while Haryana recorded comparatively lower counts (~21,000 events). In contrast, Rabi burning remained relatively stable, averaging ~85,000–90,000 fires in Punjab and ~25,000–26,000 fires in Haryana. Temporal trends reveal a substantial decline in Kharif fire counts, with reductions of nearly 90–94% between 2021 and 2025, indicating the effectiveness of policy interventions and residue management technologies. However, Rabi burning exhibited limited reduction, highlighting a critical gap in mitigation strategies. Spatial analysis shows dense clustering of fires in central and northwestern Punjab, whereas Haryana exhibits more dispersed burning patterns. The strong seasonal concentration and magnitude of fire activity confirm that biomass burning remains a dominant driver of particulate pollution. These findings emphasize the need for crop-specific, season-targeted mitigation strategies to achieve sustained improvements in regional air quality.

DOI: https://zenodo.org/records/20096389

Published by: vikaspatanker

Authors: Ankita Tripathi, Anurag Gangwar

Abstract: This study investigates the spatial and temporal variability of aerosols over Western and Central India using satellite-derived Aerosol Optical Depth (AOD) and Ångström Exponent (AE) for the period 2016–2025. AOD provides information on aerosol loading, while AE is used to infer particle size distribution. The analysis was carried out at monthly, seasonal, and annual scales using a zonal approach to distinguish regional characteristics. The results reveal significant seasonal variation in aerosol properties. AOD shows maximum values during the pre-monsoon season, particularly over Western India (~0.47), attributed to enhanced dust activity and dry atmospheric conditions. In contrast, AOD decreases during the monsoon season due to wet scavenging processes. AE exhibits an opposite trend, with higher values during monsoon and post-monsoon seasons (up to ~1.63 in Central India), indicating the dominance of fine-mode aerosols from anthropogenic emissions and biomass burning. Monthly analysis further confirms this inverse relationship between AOD and AE, reflecting the transition from coarse to fine particles across seasons. Interannual analysis indicates relatively stable aerosol patterns with noticeable fluctuations, including a decline in AOD during 2020, likely associated with reduced anthropogenic activities. A clear regional contrast is observed, where Western India is dominated by coarse-mode dust aerosols (high AOD, low AE), while Central India shows a higher influence of fine-mode anthropogenic aerosols (moderate AOD, high AE). Overall, the combined assessment of AOD and AE provides critical insights into aerosol behavior, sources, and seasonal dynamics. The findings are relevant for improving air quality management, understanding aerosol–climate interactions, and supporting environmental policy development in India

DOI: https://zenodo.org/records/20096175

Published by: vikaspatanker

Authors: Harsh Vardhan, Aanurag Gangwar

Abstract: Air pollution continues to be one of the most important environmental problems in fast-growing parts of the Indo- Gangetic Plains (IGP), such as Agra and Noida, characterized by declining air quality levels. The current paper offers a comparative analysis of the Air Quality Index (AQI) temporal and seasonal trends in the cities of Agra and Noida based on the daily data from the Central Pollution Control Board (CPCB) for the period of 2021–2025. The descriptive statistical analysis demonstrates that AQI is higher and more variable in Noida than Agra, which implies that Noida is under higher levels of pollution. The time-series analysis reveals considerable AQI dynamics in the two cities, including peaks of the parameter under discussion during winter months. The results of the monthly and seasonal analysis also suggest strong seasonality, according to which AQI scores peak during winter and post-monsoon months, while monsoon months are associated with improved air quality. In terms of AQI categories, Noida witnesses more days classified as “Poor,” “Very Poor,” and “Severe,” while Agra shows a larger number of “Moderate” and “Satisfactory” days. Finally, the autocorrelation analysis demonstrates a high level of AQI dependence on the time dimension in both cities. These differences have been observed due to variations in the sources of emission, population density, pollution transport dynamics, and weather conditions. In conclusion, the analysis shows that Noida is more heavily and variably polluted than Agra. This study offers valuable guidance for designing air quality management plans specific to regions and helps frame effective measures for pollution-prone urban areas.

DOI: https://zenodo.org/records/20095989

Published by: vikaspatanker

Authors: Harsh Vardhan, Aanurag Gangwar

Abstract: Air pollution continues to be one of the most important environmental problems in fast-growing parts of the Indo- Gangetic Plains (IGP), such as Agra and Noida, characterized by declining air quality levels. The current paper offers a comparative analysis of the Air Quality Index (AQI) temporal and seasonal trends in the cities of Agra and Noida based on the daily data from the Central Pollution Control Board (CPCB) for the period of 2021–2025. The descriptive statistical analysis demonstrates that AQI is higher and more variable in Noida than Agra, which implies that Noida is under higher levels of pollution. The time-series analysis reveals considerable AQI dynamics in the two cities, including peaks of the parameter under discussion during winter months. The results of the monthly and seasonal analysis also suggest strong seasonality, according to which AQI scores peak during winter and post-monsoon months, while monsoon months are associated with improved air quality. In terms of AQI categories, Noida witnesses more days classified as “Poor,” “Very Poor,” and “Severe,” while Agra shows a larger number of “Moderate” and “Satisfactory” days. Finally, the autocorrelation analysis demonstrates a high level of AQI dependence on the time dimension in both cities. These differences have been observed due to variations in the sources of emission, population density, pollution transport dynamics, and weather conditions. In conclusion, the analysis shows that Noida is more heavily and variably polluted than Agra. This study offers valuable guidance for designing air quality management plans specific to regions and helps frame effective measures for pollution-prone urban areas.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Hanathika T, Gayatri K

Abstract: Diabetic retinopathy (DR) is a major cause of avoidable vision loss worldwide, and deep learning approaches have shown promising results on large-scale retinal image datasets such as EyePACS. However, many existing works mainly emphasize overall accuracy or referable DR detection, while giving less importance to factors like model reliability, interpretability, and performance on noisy real-world data. To address these limitations, this study presents a Multi-Attention Residual Network (MARN) built upon EfficientNet-B0 for simultaneous DR grading and referable DR classification using a resized version of the EyePACS Kaggle dataset. The proposed architecture integrates a residual fully connected head with dropout regularization and is trained using class-balanced sampling along with cross-entropy loss. The model is evaluated on both a five-class DR grading task and a clinically significant binary classification task (referable DR ≥ moderate versus non-referable DR). Experimental results on a subset of 6,081 images show that MARN improves five-class validation accuracy from 0.4618 to 0.4881 and increases the macro-F1 score from 0.4905 to 0.5195 when compared to a strong EfficientNet-B0 baseline. For referable DR detection, the model achieves an accuracy of 0.780, with sensitivity of 0.776 and specificity of 0.783, demonstrating a slight improvement in specificity while preserving high sensitivity. Further analysis indicates notable performance gains in Severe and Proliferative DR categories, with ROC-AUC scores of 0.865 and 0.915, respectively. In addition, Grad-CAM visualizations highlight that the model focuses on clinically relevant lesion regions, while t-SNE representations show improved clustering of advanced DR features. Overall, the proposed MARN framework delivers consistent improvements in classification performance, effective identification of vision-threatening DR, and enhanced interpretability, making it a reliable and explainable tool for clinical decision support rather than a purely black-box model.

Published by: vikaspatanker

Authors: Shubham Aher, Atharva Lambate

Abstract: Adaptive traffic signal control is an important requirement for reducing urban congestion and improving traffic flow in smart cities. Traditional fixed-time signal systems work on pre-defined schedules and cannot respond effectively to sudden changes in traffic demand, peak-hour congestion, road incidents, or uneven lane usage. This research paper presents an intelligent traffic signal control system that combines Reinforcement Learning (RL) with vehicle-mounted Internet of Things (IoT) sensors. In the proposed system, vehicles provide anonymized and aggregated traffic information such as position, speed, lane approach, queue formation, and movement direction. This information is collected by roadside aggregation units and used by reinforcement learning agents to dynamically select signal phases at intersections. The main objective of the system is to reduce average waiting time, queue length, unnecessary stops, vehicle idling, and unfair lane delays while maintaining data privacy. A multi-agent Advantage Actor-Critic based approach is considered for controlling multiple intersections, and other RL algorithms such as Q-learning, Deep Q-Network, and Proximal Policy Optimization may also be applied depending on the traffic environment. The system is evaluated through SUMO-based traffic simulation. The study shows that RL-based signal control can improve performance compared with fixed-time and threshold-based control methods, with preliminary simulation results indicating approximately 30% improvement in waiting time and queue length. The paper also discusses methodology, deployment process, scalability, communication challenges, privacy protection, limitations, and future scope of RL-IoT based intelligent traffic management.

DOI: https://doi.org/10.5281/zenodo.20095635

Published by: vikaspatanker

Authors: Ayura Ajinath Athare, Prof.Sweety Wanave-

Abstract: Abstract- Artificial Intelligence (AI) is rapidly transforming the global pursuit of sustainability by enabling intelligent, data-driven decision-making across urban development, renewable energy, and environmental monitoring. This paper explores AI’s applications in building smart cities, optimizing renewable energy systems, and advancing climate change monitoring, with a focus on India’s smart grid journey. Smart city initiatives integrate AI for traffic management, waste handling, and energy distribution, creating resource-efficient ecosystems. Renewable energy systems benefit from AI’s predictive analytics in demand forecasting, renewable integration, and energy storage, particularly relevant for India’s National Smart Grid Mission. AI also plays a pivotal role in climate monitoring by processing satellite imagery, IoT sensor data, and big data models to predict weather patterns, detect environmental degradation, and enable disaster preparedness. However, ethical concerns such as bias, transparency, privacy, and equitable access must be addressed to ensure inclusive adoption. A literature review of over 20 scholarly works and policy frameworks highlights current advancements, gaps, and future opportunities. The proposed framework integrates technical, ethical, and governance considerations for sustainable AI. By combining AI innovation with ethical governance, nations can accelerate progress toward the United Nations Sustainable Development Goals (SDGs) while ensuring fairness and resilience.

Published by: vikaspatanker