Daily Archives: October 28, 2025

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