Category Archives: Uncategorized

Authors: Priyesh Mahajan, Nitin Namdev

Abstract: The rise of digital payments, credit card fraud has also grown, becoming a major challenge for the financial sector. To address this, more advanced detection systems are needed. Machine Learning (ML) and Deep Learning (DL) have proven to be powerful tools in this fight. These technologies learn from large volumes of transaction data, spotting patterns and unusual behavior that may signal fraud. Unlike traditional systems, ML and DL models can adapt and improve over time, making them effective against constantly changing fraud tactics. Integrating these models into fraud detection systems has already shown strong results, reducing the success rate of fraud attempts and helping to protect the security of credit card transactions. This review highlights the importance of ML and DL in strengthening fraud detection and improving trust in financial systems.

Published by: vikaspatanker

Authors: Prof. K.S.Tamboli, Gaiwad Nikhil Ganesh, Meher Karan Dnyandev, Kate Dhruv Balsabheb

Abstract: The global shift towards sustainable and eco-friendly transportation has intensified interest in electric vehicles (EVs) as a viable alternative to conventional internal combustion engine (ICE) vehicles. However, replacing every gasoline or diesel-powered vehicle with a brand-new EV is not only economically challenging but also environmentally taxing due to the resources and energy required for manufacturing new vehicles. As a practical and cost-effective solution, retrofitting existing vehicles into electric vehicles has emerged as an innovative approach to accelerate the transition to clean mobility. Retrofitting involves replacing the conventional drivetrain of a vehicle including the engine, fuel system, and exhaust with an electric motor, battery pack, and related control systems, thereby converting the vehicle into a fully electric one. This process extends the lifespan of vehicles, reduces emissions, and allows vehicle owners to enjoy the benefits of electric mobility without the need to purchase a new EV. This approach is especially relevant in developing countries, where the existing fleet of vehicles is large and often aging. Retrofitting not only helps in meeting stringent emission norms but also supports local industries and job creation by fostering a circular economy in the automotive sector. In this context, retrofitting serves as a bridge between current transportation realities and a more sustainable future, offering a promising pathway for reducing the carbon footprint of road transport while maximizing the utility of existing automotive assets.

Published by: vikaspatanker

Authors: Ms. Rasika R. Patil, Renuka S. Durge

Abstract: Cognitive computing represents an advanced approach in artificial intelligence that aim to simulate human reasoning, learning and decision-making process. Unlike traditional AI systems that follow fixed algorithm, cognitive systems learn from continuously learn from experiences, adapt to new data and response intelligently to changing a new context. These systems integrate disciplines such as machine learning, deep natural networks and natural language processing to analyze large volume of structured and unstructured information. Cognitive computing enhances human machine interaction by enabling contextual understanding, pattern recognition and predictive reasoning. This pepar explores this architecture, working principles, and real-world application of cognitive computing in healthcare, business analytics, and autonomous systems. It also discusses current challenges, including data privacy, interpretability, and ethical implementation. The study concludes that cognitive computing holds to potential to create adaptive, transparent, and human like intelligent systems that redefine the future of decision making and automations.

Published by: vikaspatanker

Authors: Mr. Akhilesh M. Bhagat, Prof. S. V. Raut

Abstract: The advancement of artificial intelligence and natural language processing has led to the development of intelligent voice assistants capable of performing a wide range of tasks. However, most existing systems such as Siri, Alexa, and Google Assistant lack emotional understanding and real-time adaptability. This paper presents an enhanced version of AURA AI, an intelligent voice assistant built using Python and GPT technology, integrated with emotion recognition and real-time web interaction. The proposed system detects the user's emotional state through speech tone and facial expressions, allowing it to respond more empathetically and contextually. Additionally, real-time web integration enables the assistant to access live information such as weather updates, news, and general knowledge through APIs, providing users with up-to- date and personalized responses. Experimental evaluation demonstrates that the enhanced AURA AI offers improved user engagement, adaptability, and interaction quality compared to traditional voice assistants. This approach contributes toward creating emotionally intelligent and human-like conversational systems for next-generation AI applications.

Published by: vikaspatanker

Authors: Vinod B. Ingale, Ashish Vankudre, Sagar mali , Dhanaji Jadhav, Pramod Shitole

Abstract: The proliferation of digital platforms has generated vast amounts of event-based temporal data, where user interactions are logged as discrete events in continuous time. Traditional recommendation systems often fail to capture the intricate dynamics of such data, including the exact timing, inter-event gaps, and evolving nature of user preferences. This paper proposes a novel hybrid neural architecture that synergistically integrates Temporal Point Processes (TPPs) with a Self-Attention mechanism to model user temporal behavior for next-item recommendation. Our model, the Temporal Self-Attentive Hawkes Process (TSAHP), leverages the self-attention mechanism to capture complex, long-range dependencies within user interaction sequences, while a neural Hawkes process models the continuous-time intensity of these interactions, inherently accounting for the excitement and decay effects of past events. We evaluate the proposed TSAHP model on two real-world datasets: Amazon Electronics and LastFM. Comparative analysis against state-of-the-art methods, including Time-Aware Matrix Factorization, GRU-based models, and standard Hawkes Process models, demonstrates the superiority of our approach. The TSAHP model achieves significant improvements, with an average increase of 12.5% in Hit Rate @10 and 15.3% in NDCG @10 on the Amazon dataset, and 9.8% in HR@10 and 11.7% in NDCG@10 on the LastFM dataset. The results indicate that explicitly modeling both the semantic context through self-attention and the temporal dynamics via point processes is crucial for accurate and timely recommendations in event-based systems.

Published by: vikaspatanker

Authors: Paul Oduor Oyile, Eric Sifuna Siunudh, Daniel Khaoya Muyobo, Anselemo Peters Ikoha

Abstract: This study examined the impact of prolonged digital device use on cognitive development and attention span among children aged 6-8 years in four counties of Western Kenya: Bungoma, Kakamega, Vihiga, and Busia. Employing a mixed-methods approach, the research combined surveys, interviews, and observational assessments to evaluate how exposure to tablets and computers affects cognitive skills, problem-solving abilities, and attention retention. Quantitative data were analyzed using descriptive and inferential statistics, while qualitative insights revealed behavioral patterns and parental mediation practices. Findings demonstrated a significant negative correlation between increased daily screen time and both cognitive and attention performance. Children exposed to less than one hour of screen time daily scored considerably higher on cognitive and attention measures compared to those with over four hours of exposure. Parental mediation emerged as a crucial moderating factor, with high parental engagement substantially buffering negative outcomes. Gender differences were subtle, though boys engaged more in recreational activities while girls favored educational content. The study supports the displacement hypothesis, suggesting that excessive screen use replaces developmentally essential activities. Results underscore the necessity for balanced technology integration in early education, evidence-based screen time guidelines, and collaborative efforts among policymakers, educators, and parents to maximize educational benefits while safeguarding children's cognitive development and attention capabilities.

DOI: https://doi.org/10.5281/zenodo.17463828

 

Published by: vikaspatanker

Authors: Vinod Ingale, Sayli Jadhav, Priyanka Telshinge, Rahin Tamboli, Ashwini Mahind

Abstract: The proliferation of digital platforms has led to an explosion of complex user interaction data, characterized by its sequential nature and rich contextual information. Traditional collaborative filtering (CF) methods often fall short by treating user preferences as static and ignoring the nuanced impact of temporal context and real-world events. This paper proposes a novel recommendation framework, the Temporal-Event-aware Support Vector Machine (TE-SVM), designed to effectively model the dynamic evolution of user preferences by integrating temporal dynamics and event-based contextual signals. The TE-SVM model formulates the recommendation task as a classification problem, where the objective is to find an optimal hyperplane that separates user preferences for items at a given time under specific event conditions. We engineer a comprehensive feature set that captures temporal patterns (e.g., time decay, periodicity) and event embeddings derived from external knowledge sources. A thorough comparative analysis is conducted against established models, including Matrix Factorization (MF), TimeSVD++, and Recurrent Neural Networks (RNN). Experimental results on a large-scale e-commerce dataset demonstrate that the proposed TE-SVM model achieves a significant improvement, with a 12.7% increase in Precision@10 and a 9.8% increase in NDCG@20 compared to the best-performing baseline. The findings underscore the efficacy of SVM in handling high-dimensional, heterogeneous feature spaces for temporal and event-aware recommendation tasks, providing a robust and interpretable alternative to deep learning-centric approaches.

Published by: vikaspatanker

Authors: Samarth D

Abstract: This project provides a comprehensive analysis and prediction of California housing prices using machine learning techniques. The project is implemented in Python and uses a Linear Regression model to predict housing prices based on various factors such as median income, housing median age, total rooms, population, and geographical location. The report is structured to provide an in-depth understanding of the problem, methodology, implementation, results, and potential future work. The accompanying Python code trains the model, evaluates its performance, and produces visualizations to aid in understanding the relationships between features and housing prices

Published by: vikaspatanker

Authors: Mr. Akash Godere, Mr. Javeed Khan

Abstract: Micro services architectures on cloud platforms offer scalability and flexibility, but performance optimization remains a key challenge. This paper presents a comparative study of different optimization techniques for cloud-based microservices, focusing on resource utilization, load balancing, and response time reduction. Experimental evaluation on AWS and Kubernetes demonstrates significant improvements in throughput and latency when employing container- level optimization, dynamic scaling, and efficient service orchestration. The study provides actionable insights for cloud architects and developers to achieve optimal performance in microservices deployments.

Published by: vikaspatanker

Authors: Mr. Akash Godre, Mr. Javeed Khan

Abstract: Cloud-native applications increasingly rely on microservices architectures to achieve scalability, fault tolerance, and maintainability. This paper presents a scalable microservices architecture design suitable for cloud platforms. The proposed architecture leverages containerization, orchestration, and dynamic scaling mechanisms to ensure high availability and optimal resource utilization. Performance evaluation demonstrates improved scalability, fault tolerance, and reduced response time compared to monolithic and traditional microservices designs. This work provides practical guidelines for deploying scalable microservices on cloud platforms like AWS, Azure, and Google Cloud.

Published by: vikaspatanker