http://dspace.ewubd.edu:8080/handle/123456789/3 2026-04-05T23:21:22Z 2026-04-05T23:21:22Z Jaman, Farhana Khan, Noshin Tasnim Chowdhury, Ayesha Lisa, Fima Faria http://dspace.ewubd.edu:8080/handle/123456789/4466 2024-12-11T06:24:48Z 2024-11-28T00:00:00Z

Tour Planning: A Time-Conscious End-to-End Tourist Places Recommendation System Jaman, Farhana; Khan, Noshin Tasnim; Chowdhury, Ayesha; Lisa, Fima Faria Tourism today plays an important role in world economies and cultural exchange, with millions of tourists traveling to places for unique experiences that fit their needs and schedules. A dynamic and complete travel recommendation system seems very much essential for this reason. Existing systems usually don’t account for users’ available time or provide a full route for multi-destination trips, resulting in less efficient and enjoyable travel experiences. This study addresses this gap by developing a "Time-Conscious Tourist Places Recommendation System" that optimizes routes based on user preferences, available time, starting location, and desired end destination. Using data from 13,813 tourist spots across Bangladesh, the system applies several optimization algorithms, including Dijkstra's for shortest path and a Knapsack optimization algorithm, which scored the highest in our tests. Based on its performance, we selected the Knapsack algorithm as the final choice for optimizing travel routes under time constraints. Results show that the system significantly improves travel planning by suggesting routes that maximize user satisfaction within given time limits. This tool is valuable for travelers and tourism agencies seeking more efficient itinerary planning. By focusing on time-aware, end-to-end route planning, this project fills a major gap in current systems, providing a new and practical solution for organized travel. 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.

2024-11-28T00:00:00Z Newaz, Asif http://dspace.ewubd.edu:8080/handle/123456789/4442 2024-10-09T05:00:30Z 2024-09-27T00:00:00Z

Exploring New Frontiers in Imbalanced Learning: Data Complexity-Based Solutions Newaz, Asif Class imbalance is a frequently occurring scenario in classification tasks. Learning from imbalanced data poses quite a challenge which has instigated a lot of research in this area. Various techniques have been developed over the years to tackle this problem. These approaches are broadly classified into two categories: Data-level modification and Algorithm-level modification. In data-level modification, the original class distribution in the data is altered through resampling techniques. In algorithm-level modification, the traditional classification algorithms are adjusted to the imbalanced scenarios by changing the cost function and making them cost-sensitive (CS). A lot of different data resampling and CS techniques have been proposed by researchers in the past decade. To understand their strengths and weaknesses, a comprehensive experimental analysis is first conducted to obtain insights about these techniques. Several limitations have been identified that limit the performance of these approaches. Most of these techniques do not take into consideration data intrinsic characteristics that complicate the learning process. Several data difficulty factors have been identified in some previous studies which are rarely addressed in most cases. Moreover, the application of many of these techniques overfits the data and causes a loss of generalization, producing poor performance while testing. They are also unable to provide well-generalized performance on a wide range of imbalanced scenarios. In this study, novel strategies have been developed to address these issues. Solutions have been proposed to limit the effects of different data difficulty factors and enhance prediction performance. Moreover, attempts have been made to overcome the shortcomings of the established approaches and obtain better generalization. Three different methods have been proposed in this study. First, a novel data resampling technique that takes into consideration data intrinsic characteristics to effectively balance the dataset. Second, an instance complexity-based CS technique which is an advanced modification to the original CS approach. Third, a hybrid framework combining resampling and CSL. Rigorous experiments have been conducted on a wide range of imbalanced datasets to validate the performance of the proposed approaches. The results have been evaluated on eight different performance measures and compared with other state-of-the-art techniques used in imbalanced learning. Superior results have been obtained from the proposed techniques on different imbalanced scenarios. The results demonstrate the efficacy of the proposed models in learning from imbalanced data. To conclude, this research delineates new trajectories in the field of the imbalanced domain. New approaches have been proposed that introduce fresh perspectives and directions in imbalanced learning. The proposed strategies are remarkably successful, ensuring well-generalized performance when addressing imbalanced data. This thesis submitted in partial fulfillment of the requirements for the degree of Masters of Science in Computer Science and Engineering of East West University, Dhaka, Bangladesh

2024-09-27T00:00:00Z Kamal, Tahseen http://dspace.ewubd.edu:8080/handle/123456789/4431 2024-09-25T04:06:55Z 2006-04-30T00:00:00Z

An Application Specific Integrated Circuit for Optimization of Fixed Polarity Reed-Muller Expressions Kamal, Tahseen There are many ways a Boolean function can be The most popular one is a truth table representation. size the truth table increases exponentially with the increase n Another commonly used approach AND-OR represent also known as the Sum-of-Products than During last two decade researchers focused their eyes logic functions using EXOR-based circuits which is more compact than AND-OR representation. example, for representing a function an AND-OR AND-EXOR representation takes n product In this chapter, classification of AND-OR AND-EXOR logic is presented along with details description. 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.

2006-04-30T00:00:00Z Ahmed, Parvez Siddiquee, Abu Ashif Islam, Md.Shahinur Nahar, Syeda Nazmun http://dspace.ewubd.edu:8080/handle/123456789/4430 2024-09-25T04:06:45Z 2008-04-25T00:00:00Z

Web Based Shoppers' Catalog Ahmed, Parvez; Siddiquee, Abu Ashif; Islam, Md.Shahinur; Nahar, Syeda Nazmun Web based Shoppers' Catalog is a based solution that facilitates the shop owners to rendered their business with very less effort and creates opportunities for the shoppers to do shopping sitting at home. This software helps shop owners to create a website which their product catalog. Shop owner can customize their website, edit their profile update and upload their product information that can by shoppers. shoppers can information about different shop, view various products uploaded by owners and can order product from their home. Shop owner maintain customer's information. 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.

2008-04-25T00:00:00Z