Daily Archives: May 26, 2025

Authors: Professor Smita Chunamari, Sahil Tejam, Bhavesh Sonawane, Yash Daund, Janhvi Pawar

Abstract: Paraphrase detection is a crucial task in Natural Language Processing (NLP) that helps systems understand when two sentences mean the same thing, even if they’re phrased differently. While this has been explored extensively in English and a few other global languages, regional languages—rich in diversity and nuance—remain significantly underrepresented. In this study, we explore the challenges and opportunities of building paraphrase detection systems for regional languages, focusing on the unique linguistic features such as dialect variations, code- mixing, and syntactic differences. We develop a multilingual model trained on both parallel and non-parallel regional datasets, enhanced with data augmentation techniques and semantic similarity measures. We also introduce a small but diverse paraphrase corpus for select Indian languages as a benchmark. Our results show that transformer-based models fine-tuned on language-specific data outperform traditional ap- proaches, highlighting the importance of contextual embeddings in low-resource settings. This work not only advances the field of NLP in regional languages but also opens the door for more inclusive and accessible language technologies, ranging from intelligent search systems to educational tools that truly understand the linguistic richness of everyday users.

Published by: vikaspatanker

Authors: Professor Sheetal N. Mindolkar, Mr. Naveen Gamanagatti, Mr. Pratap R Goudar, Mr. Sammed Belavi

Abstract: Controlling a robot arm can be made simple and intuitive using basic electronic components like potentiometers and an Arduino microcontroller. By directly linking each potentiometer’s rotation to a specific joint on the robotic arm, users experience a tangible and immediate connection between their input and the arm’s movement. This straightforward setup offers an accessible introduction to robotics, ideal for beginners exploring mechatronics, sensor interfacing, and basic control principles. The affordability and ease of the Arduino platform further enhance its educational value, allowing hands-on learning without complex equipment. Building and operating the system reveals the essential control loop of robotics: the robot "senses" user input via electrical signals from potentiometers, the Arduino processes this data, and servo motors execute the movements. While this open-loop system lacks advanced accuracy and autonomy, it provides a clear, practical understanding of how robots respond to control signals, laying the foundation for more sophisticated robotics concepts in the future./

Published by: vikaspatanker

Authors: Dr. A. Saravanakumar

Abstract: The advent of new technologies has streamlined business transactions, enhancing the buying experience for both companies and customers. Digital marketing, in particular, has enabled mutual fund companies to expand their investor base while providing potential investors with convenient access to information. In this context, the primary objective of this study is to examine the impact of digital marketing on investors' decisions to invest in mutual funds, with a focus on identifying key demographic factors influencing online investments.

 

 

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

 

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

 

Published by: vikaspatanker

Authors: Assistant Professor Mrs. Priyanka Bamne, Nimesh Agrawal

Abstract: The increasing volume of products on online platforms has made product recommendation systems (PRS) essential for enhancing user experience and driving sales. This survey paper provides a comprehensive review of PRS, focusing on their necessity, implementation methods, and relevance in e-commerce and digital marketplaces. We explore the motivation behind recommendation systems, emphasizing their role in improving customer satisfaction, personalization, and business profitability. Various implementation techniques, including collaborative filtering, content-based filtering, hybrid filtering, and deep learning methods, are analyzed with a discussion on their advantages and limitations. Furthermore, we examine real-world applications, challenges such as cold start and scalability, and emerging trends in AI-driven recommendations. To establish the relevance of these concepts, we review key research papers, industry applications, and case studies from platforms like Amazon, Netflix, and Spotify. Finally, we highlight future directions, including explainable AI, privacy-aware recommendations, and real-time personalization, offering insights for researchers and practitioners aiming to enhance recommender systems.

 

Published by: vikaspatanker

Authors: Dr. Nitin Kumar Patel

Abstract: Cloud computing's extensive adoption has made Virtual Machine (VM) placement a critical aspect of resource management. Beyond performance and cost optimization, securing VM placement is paramount to mitigating several threats, including co-residency attacks, data breaches, and denial- of-service attacks. This article offers a comprehensive analysis of techniques designed to enhance VM placement security in cloud environments. I explore a variety of security considerations, encompassing physical security, logical isolation, and data protection, and examine how they influence VM placement strategies. Specifically, we delve into techniques like anti-collocation policies, affinity and anti-affinity rules, trust-based VM placement, security-aware scheduling algorithms, and dynamic VM migration strategies. Furthermore, I analyse the trade-offs between security, performance, and cost associated with each technique. By evaluating the strengths and weaknesses of existing approaches, this paper identifies research gaps and highlights promising directions for future research in securing VM placement. I accomplish this by advocating for a holistic, multi-layered approach to VM placement security that integrates diverse techniques and adapts dynamically to evolving threat landscapes in cloud computing environments. This research purposes to provide valuable insights for cloud providers and consumers seeking to enhance the security posture of their cloud infrastructure through optimized VM placement strategies.

 

 

Published by: vikaspatanker