Comilla University Academic Repository

Browse

Now showing 1 - 20 of 138

5G Technology and Future in Bangladesh
(Comilla University, 1-Feb-2025) Hasan, Md. Faysal
A Comparative Analysis of Identifying Multi Class Toxic Comment Classification Utilizing Deep Learning and Machine Learning Technologies
(Comilla University, Jan-2025) Sarker, Sajib
Despite extensive efforts to prevent and manage malicious human behavior, there are still many compelling issues in cyber platforms. When such individuals live in a world where technology is rapidly developing and where various online social media platforms like Twitter, Facebook,Instagram, etc. are widely accessible, those nefarious human acts rise. Because of this, extremely dangerous crimes like toxic comments, which pose a threat to users, groups, and even
A Comparative Analysis of Identifying Multi Class Toxic Comment Classification Utilizing Deep Learning and Machine Learning Technologies
(Comilla University, 1-Jan-2025) Sarker, Sajib
Despite extensive efforts to prevent and manage malicious human behavior, there are still many compelling issues in cyber platforms. When such individuals live in a world where technology is rapidly developing and where various online social media platforms like Twitter, Facebook, Instagram, etc. are widely accessible, those nefarious human acts rise. Because of this, extremely dangerous crimes like toxic comments, which pose a threat to users, groups, and even governments, have increased in frequency. This study aims to identify such harmful comments in Bangla text that are posted on social media sites, classify them using machine learning and deep learning algorithms, and take preventative measures. By combining TF-IDF with various machine learning algorithms, such as Naive Bayes, Decision Tree, Random Forest, AdaBoost Classifier, Stochastic Gradient Descent Classifier, Logistic Regression, KNN, and Support Vector Machine, we were able to detect toxic comments with an accuracy of 76.5%, 78.2%, 75.0%, 75.1%, 76.2%, 77.7%, 70.2%, and 78.5%, respectively. In comparison to previous machine learning techniques, we achieved an accuracy of 89% by employing deep learning algorithms
A Deep Learning Model for Classifying Bangladeshi Food and Estimating Calories
(Comilla University, 1-Feb-2025) Nayeem, Md Najmul Islam
Accurate food calorie estimation is essential for managing dietary intake, particularly for
A Project Report on COMILLA UNIVERSITY HALL MANAGEMENT SYSTEM
(Comilla University, 1-Feb-2025) Hasan, Md Mahedi; Rahman, Marfater
Comilla University Hall Management System is a software developed for managing colorful conditioning in the residence. There are five resident halls for the scholars of Comilla University. As the number of halls are adding up, the number of scholars abiding in those caravansaries are also adding. As a result, the people managing the halls are under a lot of stress. Software or applications aren’t generally used in this environment. Generally, in Bangladesh perspective no digital systems or applications are used, most of the halls or residences are managed manually. In early days, managing manually was not very tough. But at present manual system is tedious. This specific design addresses the challenges of hall management and circumvents the issues that arise when carried out by hand. When the drawbacks of the current system are recognized, lead us to the design of a motorized system that will work with the existing system and the system that is additionally easily grasped and more GUI acquainted. We can ameliorate the effectiveness of the system and therefore overcome the downsides of the being system. Comilla University Hall Management System targeted for sale operation of the hall for better control and timely response. This eliminates time day and paper deals being marked. The Warden is handed with a better control over the deals like adding the details of new scholar in the hall, modifying the details of the scholars, deleting the scholars, viewing the pupil’s details abiding in the hall, adding or removing rooms, checking available seats. scholars can also check if there's any room available or not, look for better seats. As the main target of this application is to do efficient management by storing scholar’s data, MongoDB is used as database as it offers numerous benefits, especially its ability to manage unstructured data, its straightforward process for horizontal scaling, and its quicker performance in insert and update tasks, which makes it perfect for applications that require rapidly evolving data structures and handle large volumes of data. In the future, we can implement online fee payments, integrate various load balancers, develop a mobile application, and establish a backup database for improved security. This design’s main aphorism is to reduce the effect of wardens and give better service to the scholars. The main thing of this design is to develop a system for the robotization of the hall affiliated information
A Study on Determinants of workers’ Remittance Inflow in Bangladesh
(Comilla University, 1-Dec-2020) Debbarman, Shantanu; Dey, Sucheta
Remittance inflows of workers to their country of birth is one of the most influential factors contributing to the economic growth of developing countries. Remittance has a significant impact on the economic growth of Bangladesh. In also a vital source of foreign exchange earnings for Bangladesh. This study aims to identify the determinants of worker’s remittance in Bangladesh using time series data from 1976 to 2018. The Augmented Dickey-Fuller Test checks the stationarity of data.
A Study on the Pedagogical Barriers of Tertiary Level Education in Bangladesh
(Comilla University, 1-Jun-2018) Begum, Sumayya; Amzad Hossain Sarker, Mohammad
The prime objective of the research was to identify and investigate the impact of various pedagogicol barriers on effective tertiary level education. Other objectives were to find out the pedagogical barriers in tertiary level education and to portrait current pedagogical practices of higher studies institutions like public and private universities. For achieving the above objectives primary data were collected through verified structured questionnaire. A total number of 70 respondents have chosen as sample by convenience sampling technique. Sample respondents were taken from five public universities and two private universities. Data were analyzed by using SPSS-16 version by adopting the statistical techniques, correlation and multiple regression analysis. The findings of the study revealed that except the SPA (social and psychological attachment) all of the independent variables have on significant effect on tertiary level education system in Bangladesh. Therefore, ministry of education, university grants commission and university authorities should take necessary steps to overcome the effect of these barriers to develop effective tertiary level education system. Thus, this study recommended the required actions for addressing and resolving those barriers effectively for ensuring quality education in the terliary level.
A Time-Nonlocal Optimization Approach for Image classification
(Comilla University, 1-Feb-2025) Das, Hridoy Chandra; Hafsa, Akter
Image classification remains a fundamental problem in artificial intelligence, with applications
Academic Assistant :
(Comilla University, 1-Feb-2025) Parves, K. M. Tousif Bin; Islam, Saqiul
The Academic Assistant is an AI-powered robot designed to enhance educational
AI Chatbot For Solving Mathematical Problems Using Large Language Models and Retrieval-Augmented Generation (Rag) With Custom Dataset Integration
(Comilla University, 1-Feb-2025) Ahmed, Junaid; Mahin, Md. Mohiuddin Khan
Mathematical problem-solving is a fundamental skill in education, and recent advancements in artificial intelligence (AI) offer innovative ways to automate this process. This paper presents an AI-powered chatbot developed using Google Vertex AI Agent Builder, designed to solve mathematical problems across various domains. By leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), the chatbot integrates a custom dataset to enhance its problem-solving capabilities, allowing it to generate accurate and contextually relevant solutions. The RAG technique enables the model to retrieve external information dynamically, improving the chatbot's ability to handle a wide range of mathematical problems. The integration of a custom dataset ensures that the model can effectively tackle specific problem types, making it adaptable to different scenarios. This work demonstrates the potential of AI-driven tools, powered by Google AI Agent Builder, to provide instant, reliable mathematical assistance, offering valuable support for students and educators alike
“An Analysis of Banking Crime Prevention Measures: A Case Study on Agrani Bank PLC”
(Comilla University, 26-May-2025) Islam, Labiba
In recent years, banking crime has become a major global concern, particularly for financial
An Empirical Test of the Arbitrage Pricing Theory: The Case of Dhaka Stock Exchange (DSE)
(Comilla University, 1-Dec-2023) Farhana, Akter; Tandra, Mondal
This study empirically tested Arbitrage Pricing Theory (APT) in the Dhaka Stock Exchange [DSE) using five macroeconomic variables namely money supply, index of industrial production, crude oil price, remittance, and foreign exchange reserves. Monthly data from January 2013 to June 2021 was employed in the empirical analysis. The study adopted the Autoregressive Distributed Lag (ARDL) Model and Granger causality test. The long-run ARDL results indicate that none of the selected macroeconomic variables have statistically significant influence on stock return in the long term. Except for remittances, the other four variables are positively related to the stock return of DSE. The divergence of remittance may be attributed to its predominant allocation toward household consumption, land acquisition and other non-equity investments. In the short run, money supply and crude oil price have significant and positive impact on stock return while the other variables have insignificant effects. The study suggests that 118% of the disequilibrium in the return of DSE is adjusted monthly to get back to the long-run equilibrium. The Granger causality test result revealed a bi-directional causality between stock return and money supply and a unidirectional causality running from industrial production index, crude oil price, and remittances to stock return while another unidirectional causality running from the stock return to foreign exchange reserves. Overall, the findings of the results suggest that APT is valid in the DSE in the short run but not applicable in the long run.
An Internship Report On Financial Performance Analysis of IFIC Bank PLC
(Cumilla University, 25-May-2025) Oishi, Rabina Islam
IFIC Bank promotes a vibrant and welcoming workplace culture that encourages innovation, teamwork, and diversity. The company's dedication to collaboration, honest communication, and a strong feeling of community is frequently cited by IFIC BANK PLC employees. This culture encourages a supportive workplace atmosphere where people may flourish and help the business succeed. Through the internship program in IFIC BANK PLC, I go to experience and have acknowledgements about their financial operations and corporate culture. The study of the report highlight the whole experience at IFIC BANK PLC outlining all aspects.. This report is divided into several parts and discussed every possible parts from organization specific to focused topics of project. There are detailed manner discussions about organization, daily operations of different departments, business structures, strategies regarding their growth and success in competitive market. The company has maintained a healthy level of profitability, with a consistent gross and a net profit margin during the analysis period. In the focused part of findings and analysis, I have tried to hold up the reflection of financial issues and conditions in this sector through detailed study of IFIC BANK PLC. This report gives the overview of IFIC BANK PLC’s concerning areas to improve and current market position
An Unified Quantum Classical Model For Noisy Label Medical Image Binary Classification.
(Comilla University, 1-Feb-2025) Bhuiyan, Taki Jakera; Fahim , Jahid Karim
The presence of noisy labels in medical imaging datasets can severely impact diagnostic
Analysing the Effectiveness of Business Support to Enhance the Service Quality and Customer Satisfaction of Nagad Ltd.
(Comilla University, 29-Jun-2025) Asraf, Md. Shamim
This research investigates the role of the Business Support Division (BSD) in enhancing service quality and customer satisfaction at Nagad Ltd., a leading Mobile Financial Service (MFS) provider in Bangladesh. Using analysis of structural equation modelling (PLS-SEM) through SERVQUAL’s five dimensions (tangibles, reliability, responsiveness, assurance, and empathy), survey data from 301 Nagad head office employees have been analysed. The results demonstrate that Internal Service Effectiveness (ISE), achieved through several Business Support Division (BSD) functions, including interdepartmental coordination, vendor coordination, modelling, and compliance support, raises customer satisfaction (β = 0.532, *p* < 0.001). The three dimensions, which are named Empathy (personalised attention), Reliability (consistent service delivery), and Responsiveness (timely resolution), contribute significantly to ISE. BSD’s operational support (especially human-related aspects) enables customer-facing departments to improve service delivery. The BSD staff should be trained in empathy and reliability first. The internal KPIs used have to reflect the customer KPIs. Resources used for tangibility can also be applied to the other factors. The insights provide Nagad with actionable steps to enhance internal service quality and advance competitiveness in the MFS industry of Bangladesh, thereby increasing their customer-centricity. The internal service effectiveness of Nagad Ltd will be assessed using service quality dimensions based on the SERVQUAL model in Bangladesh.
Analysing the Impact of Capital Structure on Financial Performance: An Empirical Study of State-owned Commercial Banks in Bangladesh
(Comilla University, 26-May-2025) Islam, Sadia
This report focuses on the impact of capital structure on the profitability of state-owned
Analysis of Bank-Specific and Macroeconomic Factors on Non Performing Loans: A Study of commercial Banks in Bangladesh
(Comilla University, 26-May-2025) Akter, Farzana
The banking sector plays a vital role in Bangladesh’s economic development by mobilizing
“Analysis of Internal and External Determinants on the Profitability of Commercial Banks in Bangladesh”
(Comilla University, 26-May-2025) Akter, Norunehar
Using Return on Assets (ROA), this study looks at how economic and company-specific factors affect the profitability of 15 commercial banks in Bangladesh. A key measure of banking performance, profitability is influenced by both macroeconomic variables like GDP growth and internal factors like bank size, operating expense to total assets ratio, capital adequacy ratio, and total loans to total assets ratio. The study employs econometric techniques such as Pooled OLS, Fixed Effects, and Random Effects to ensure accurate estimation and address diagnostic concerns like heteroskedasticity, autocorrelation, and
Analyzing Marketing Mix Effects on Branding of Real Estate: A Comprehensive Study of Rancon FC Properties Ltd., Chattogram
(Comilla University, 29-Jun-2025) Das, Shayantha
The purpose of this study is to determine how Chattogram real estate businesses' branding is impacted by the marketing mix. A combination of convenience and random selection was used to choose 127 responders in all. Information from those working in the real estate industry was gathered for the study through questionnaires and interviews. According to the analysis, a lot of businesses struggle to establish a strong brand because they don't employ their marketing mix properly. Common issues include poor marketing, unjust prices, inadequate customer support, and a lack of obvious evidence of quality. According to the survey, real estate firms should increase the value of their products, provide reasonable prices, and concentrate on target-based advertising, adequately train staff, and guarantee robust customer service procedures. Enhancing confidence and branding can also be achieved by providing visible assets, such as showrooms or model apartments.
ANALYZING THE DRIVERS OF RISING CONSUMER PURCHASE INTENTIONS FOR REAL ESTATE HOUSING IN BANGLADESH: A STUDY ON SILVER DEVELOPERS LTD
(Comilla University, 29-Jun-2025) Hoque, Mohammad Azizul
Real Estate business is a growing arena in Bangladesh. At present, these are a number of good Real Estate companies in our country. Real Estate business is an important factor in Bangladesh at present situation. In Bangladesh, Dhaka is best segmented area for real estate business. Now it becomes familiar picture in very cities (like Cumilla) of Bangladesh. After 3 months internship of real estate sector, I have to make my internship paper for academic purpose. The major purpose of this paper is to examine the factors who have impact on buying intention of real estate business in order to develop an emotional connection with Silver Developers Ltd. A quantitative approach was employed and questionnaires was used to gather data. Questionnaires were distributed physically and online basis among the customer of Silver Developers Ltd. The sample size was