http://20.198.91.3:8080/jspui/handle/123456789/79 2026-04-05T20:54:40Z 2026-04-05T20:54:40Z Bhattacharjee, Ranadeep http://20.198.91.3:8080/jspui/handle/123456789/9092 2025-10-31T05:48:56Z 2023-01-01T00:00:00Z

Title: An advanced technique for primality test with quantum computation and its relevance in cryptography Authors: Bhattacharjee, Ranadeep Abstract: Several classical algorithms exist to detect prime numbers. All such algorithms are NP-hard. In the Quantum Computation domain also, a few algorithms like Shor’s Algorithm exist, which are mainly based on the quantum version of Discrete Fourier Transformation. In this thesis a different approach (i.e. other than Fourier Transformation) has been made to detect Safe prime and Sophie Germain prime by establishing a correlation between balanced -constant function & prime number. Here we use the concept of balanced and constant function i.e. promise algorithm or more precisely, a type of Deutsch Jozsa (DJ) algorithm, a generalized version of Deutsch’s algorithm. Shor’s algorithm has been integrated with the quantum concept of Phi function to overcome its limitations. We have concentrated on detecting the prime property of a number i.e. ‘a given number is prime or not’ without having any interest in identifying its factors.

2023-01-01T00:00:00Z Roy, Amartya http://20.198.91.3:8080/jspui/handle/123456789/9091 2025-10-31T05:40:50Z 2023-01-01T00:00:00Z

Title: Studies on bengali text classification using machine learning and deep learning Authors: Roy, Amartya Abstract: This study focuses on Bengali text classification using machine learning and deep learning techniques. The research explores the efficacy of multilingual pre-trained models for Bengali text classification tasks and proposes algorithms to address challenges related to base classifier selection and input length constraints in existing models. The findings contribute to the advancement of Bengali text classification techniques by identifying effective pre-trained models, optimizing ensemble model selection, and bypassing the input length constraint of BERT models. The outcomes of this research have practical implications for improving the accuracy and efficiency of Bengali text classification in various applications

2023-01-01T00:00:00Z Saha, Debam http://20.198.91.3:8080/jspui/handle/123456789/9090 2025-10-31T05:29:12Z 2023-01-01T00:00:00Z

Title: JUIVCDv1: Development of a still-image based Dataset for Indian Vehicle Classification Authors: Saha, Debam Abstract: Designing an automatic vehicle classification system from still images or videos would be highly beneficial for developing a traffic control system. On automatic vehicle classification, numerous articles have been published in the literature. Over the years, researchers in this subject have created and used a variety of databases, but most often, these databases are not found to be appropriate in Indian scenarios due to the specific peculiarities of the road conditions, nature of congestion, and vehicle types usually seen in India. This thesis primary goal is to create a new still image database called the JUIVCDv1 that contains 12 different vehicle classes that were gathered utilising mobile phone cameras in a variety of ways for developing an automated traffic management system. We have also mentioned the characteristics of the current databases and the various factors we took into account when creating the database for the Indian scenario. Apart from this, we have benchmarked the results on this database using a five-base model architecture. Five base models are used: Efficient- Net, InceptionV3, DenseNet121, MobileNetV2, and VGG19. Among these five-base models, EfficientNet achieved the best accuracy, i.e., 93.82%.

2023-01-01T00:00:00Z Chowdhury, Ankita http://20.198.91.3:8080/jspui/handle/123456789/9089 2025-10-30T11:06:27Z 2023-01-01T00:00:00Z

Title: Wiki summary: a consensus approach for keyword extraction from multiple summarization algorithms Authors: Chowdhury, Ankita Abstract: Modern times have seen a massive increase in the amount of text data coming from various sources. The fast expansion of the Internet has made it increasingly challenging to access vast volumes of information eficiently. This lengthy article is a valuable source of knowledge and information that must be skillfully summarized in order to draw out the intriguing details that are concealed inside. We require ef icient and powerful technologies in order to manage the enormous amount of information.The primary goal of this effort is to condense a given text into fewer sentences while maintaining the key themes of the original text. With minimal context and information loss, text summarization is a potent text mining technique for extracting the useful information from a document. By removing the less important information, it shortens the language and encourages the user to

2023-01-01T00:00:00Z