http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/5543 2026-04-08T06:44:59Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/15145 Rice Leaf Diseases Classification Using Convolutional Neural Networks. Rimi, Sadia Afrin Rice is one of the major developed crops in Bangladesh which is influenced by different infections at different stages of its cultivation. It is exceptionally troublesome for the farmers to manually identify these infections precisely with their constrained knowledge. Recent improvements in Profound Learning appear that Automatic Image Acknowledgment frameworks utilizing Convolutional Neural Network (CNN) models can be exceptionally advantageous in such issues. Since rice leaf malady picture dataset is not effortlessly accessible, we have created our possess dataset which is little in measure subsequently we have used Transfer Learning to create our profound learning show. I use primary data which are collected from different cultivation field in Tangail. The proposed CNN engineering is based on InceptionResnetV2 and is trained and tried on the dataset collected from rice areas. The exactness of the proposed demonstrate is 93.12%. Thesis 2022-12-17T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/14145 Sentiment Analysis on Bengali Comments of YouTube’s Bangla Drama to Predict Emotions: A TF-IDF Approach Sarkar, A. B. M. Kibria Sentiment Analysis (SA) is indeed a rapidly growing field within computer science, particularly in the realm of natural language processing (NLP). It involves the automated analysis of text to determine the underlying sentiment or emotion expressed within it. This capability holds significant importance in various applications such as social media monitoring, customer feedback analysis, market research, and more. In my specific study, I have focused on sentiment analysis in the context of the Bengali language, which is a valuable contribution considering the relatively limited research in this area. By examining emotions such as happiness and anger, I am addressing fundamental aspects of human expression within the linguistic context of Bengali. My methodology involves employing different machine learning techniques to train a dataset for sentiment analysis. Let's delve into the techniques I have utilized and the corresponding accuracies: Logistic Regression (LR): This is a statistical method used for modeling binary outcomes, making it suitable for sentiment analysis tasks where the goal is to classify text into positive or negative sentiments. My LR model achieved an accuracy of 79.80%, indicating its effectiveness in capturing the nuances of sentiment in Bengali text. Decision Tree (DT): Decision trees are a popular machine learning algorithm for classification tasks. They partition the feature space into smaller regions based on certain criteria, making them interpretable and easy to visualize. My DT model achieved an accuracy of 78.44%, demonstrating its capability in discerning sentiment patterns in Bengali text. Random Forest (RF): Random Forest is an ensemble learning technique that combines multiple decision trees to improve predictive performance and reduce overfitting. My RF model achieved a similar accuracy to LR, further validating its effectiveness in sentiment analysis tasks. Bernoulli Naive Bayes (BNB): Naive Bayes classifiers are based on Bayes' theorem and assume independence between features. Bernoulli Naive Bayes specifically works well with binary features, making it suitable for sentiment analysis where the presence or absence of certain words may indicate sentiment. My BNB model achieved an accuracy of 79.73%, demonstrating its competitiveness with other techniques. K-Nearest Neighbors (KNN): Classifying instances according to the majority class among their K nearest neighbors (KNN) is the basis of the straightforward and user-friendly KNN classification technique. While my KNN model achieveda lower accuracy of 68.02%, it still provides valuable insights into sentiment patterns in Bengali text. Support Vector Classifier (SVC): SVC is a powerful classification algorithm that works by finding the hyperplane that best separates different classes in the feature space. My SVC model outperformed the other techniques with an accuracy of 81.48%, indicating its effectiveness in capturing complex sentiment patterns in Bengali text. Thesis 2024-05-14T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/14144 Credit Card Transaction Fraud Detection Using Machine Learning Hassan, Md. Mehedi Credit card fraud is a major challenge for Bank, business owners, credit card users, and transactions services companies, causing every year substantial and growing financial losses. Detecting fraud patterns in credit card transactions is very common problem which is hard to solve. With the ever-growing amount of data generated by credit card transactions, it has become impossible for a human analyst to detect fraudulent patterns in transaction data sets. As a result, the design of credit card fraud detection techniques has increasingly focused in the last decade on approaches based on machine learning (ML) techniques that automate the process of identifying fraudulent patterns from large volumes of data. This project focuses on predictions of whether a credit card transaction is fraudulent or no. To solve this problem, we first build a machine learning model. Then, use existing training data to train the model and evaluate how good its accuracy is. Thesis 2024-05-04T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/14143 Measuring Cybersecurity Awareness in Somalian Organizations Abdlaahe, Hamza Ahmed The rise in Cybercrime is a result of technological breakthroughs and inventions, which has led many cyber specialists and researchers to focus more on Cybersecurity. Software, hardware, and other computer components are all protected by Cybersecurity. Cybercrimes may be committed as a result of cyber attackers gaining access to communication controls and remote-control weapons. Cybersecurity should therefore not be taken lightly; rather, careful thought should go into its implementation. In this research, I employed a quantitative approach to gather quantifiable data from employees in different Somalian organizations using Google Form to distribute meticulously thought-out survey questionnaire to investigate how employees in different Somalian companies perceive and feel about Cybersecurity. The techniques utilized to analyze the data that was gathered include Pearson correlation, variance analysis, and independent t-test. The findings indicated that the alternate hypothesis, which was accepted, is connected to the beta value forage applied to the attitude towardCybercrime and Cybersecurity in business. This suggests a positive significance and, consequently, suggests that the age of the employees had a significant influence on the attitude toward Cybercrime and Cybersecurity in business. "Gender," which is linked to the null hypothesis being accepted, did not demonstrate any relevance, suggesting that there was no gender-related positive attitude on Cybersecurity in company. The phrases "position at work" and "experience" indicate that the significance was sufficiently positive to lead to the employees' general good attitude toward their varied office jobs and experiences. Therefore, our research can help Somalian companies strengthen their cyber defenses and guard against online fraud when conducting business. Thesis 2024-10-21T00:00:00Z