http://dspace.ewubd.edu:8080/handle/123456789/3663 Sun, 05 Apr 2026 23:20:01 GMT 2026-04-05T23:20:01Z http://dspace.ewubd.edu:8080/handle/123456789/4349 Augmented Reality and Virtual Reality for Learning Solar System Rafsan, Rashik Buksh; Fahim, Hasib Ar Rafiul; Islam, Fahadul; Nahid, Md. Fayjul Islam The purpose of this study was to determine how well-augmented reality and virtual reality technology may improve the comprehension of the solar system among elementary school children. Twenty students were divided into two groups, one for conventional classroom instruction and the other for augmented reality and virtual reality. In contrast to the augmented reality and virtual reality group, which utilized two apps to engage in interactive solar system exploration, the traditional group got classroom instruction using textbooks. Both Unity and Unreal engine were used to create the applications. To gauge students' understanding of the solar system, pre-and post-tests were given; meanwhile, a survey was employed to gauge their interest in the subject. The outcomes revealed that when compared to the traditional group, the augmented reality and virtual reality groups had significantly higher post-test scores and indicated better levels of engagement. The study emphasizes how augmented reality and virtual reality technologies might improve students' scientific learning outcomes and motivation. These results imply that using these tools in the classroom can be a successful way to teach difficult scientific ideas, like the solar system. This thesis submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering of East West University, Dhaka, Bangladesh Sun, 25 Dec 2022 00:00:00 GMT http://dspace.ewubd.edu:8080/handle/123456789/4349 2022-12-25T00:00:00Z http://dspace.ewubd.edu:8080/handle/123456789/3686 Development of an Automated System for Detecting Cannibalism and Water Ecosystem Monitoring for Crabs Basak, Bijoy; Chakraborty, Simonta; Ahmed, Farhan Cannibalism and crucial water parameters of crabs are two major obstacles for the crab farmers to gain maximum yield when fattening in a pond. Our project aims to help minimize the cannibalism rate of crabs as well as to give farmers more control over their water. We created a machine learning model to identify possible crab sounds that are produced by crabs when they feel threatened or in danger. The model will notify the farmer when it detects crab sounds continuously. A water parameter monitoring system is also implemented which uses various sensors (temperature, pH, salinity, DO) to monitor the water parameters. When a parameter reaches or exceeds its tolerance level, the system notifies the farmer. There is a user interface that can be accessed to view all the system status and sensor readings. The project aims to give farmers more control over when they are fattening in ponds. This thesis submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering of East West University, Dhaka, Bangladesh Tue, 16 Aug 2022 00:00:00 GMT http://dspace.ewubd.edu:8080/handle/123456789/3686 2022-08-16T00:00:00Z http://dspace.ewubd.edu:8080/handle/123456789/3664 Domain-Independent, User-centric Text Classification, and Clustering Framework Yeasmin, Sumona; Afrin, Nazia; Saif, Kashfia Traditional text document clustering and classification methods represent documents with uncontextualized word embeddings and vector space models. Recent text clustering and classification techniques often rely on word embeddings as a transfer learning component. We have explored the existing text document clustering and classification methodologies and evaluated their strengths and weaknesses. We have started with models based on Bag of Words and shifted towards transformer-based architectures. We have concluded that transformer-based embedding will be necessary to capture the contextual meaning. BERT's (Bidirectional Encoder Representations from Transformers) architecture produces robust word embeddings analyzing both from left to right and proper context. Several classification and clustering algorithms have been applied to the word embeddings of the pre-trained state-of-art BERT model. This research has conducted experimental analysis on both classification and clustering algorithms to examine the output on two different datasets. The result analysis of the classification algorithm shows that the random forest classifier obtains around 75% accuracy which is higher than the decision tree and k-nearest neighbor (KNN) algorithms. Furthermore, the obtained results have been compared with existing similar work and show up to 50% improvement in accuracy. The clustering analysis shows that the K-Means has obtained a maximum of 0.654 in Dunn index measurement and 0.135 in Silhouette coefficient, and DBSCAN has obtained a maximum of 0.115. Our capstone project introduces a novel domain-independent, user-centric text clustering, and classification framework. With a Multi-domain text clustering search system, an agent will perform based on user behavior with the user profile. Users will explore document collections by selecting multiple repositories. Users can upload an un-categorized document, and the developed Framework will find similar documents. The developed prototype provides context to the similarity and also finds similar documents within the same domain based on user preferences. This thesis submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering of East West University, Dhaka, Bangladesh Thu, 30 Jun 2022 00:00:00 GMT http://dspace.ewubd.edu:8080/handle/123456789/3664 2022-06-30T00:00:00Z