MPhil Thesis

Browse

Search Results

Now showing 1 - 10 of 29

Improved Explainable Educational Data Mining System for Enhancing Programming Skills
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-18) Mohamud, Mohamed Abdulle
Forecasting student academic performance benefits from the extremely effective method known as educational data mining (EDM), which also helps to find important links within educational data. Evaluating and improving students' programming competency has been the main emphasis of many recent studies. Still, there are chances for constant development in this field. In this work, we provide an improved and understandable Educational Data Mining (EDM) approach for spotting and improving students' programming capacity. This proposed EDM system seeks to investigate a very effective feature engineering approach, a suitable classification technique, and the use of Explainable Artificial Intelligence (XAI) tools for model explanation. We do ablation study to find the best feature engineering method. The categorizing process decides students' current programming state. Six basic Machine Learning (ML) algorithms—decision tree, Support Vector Machine, Random Forest (RF), artificial neural network, Naive Bayes Classifier, k-Nearest Neighbor, and Ensemble method—are the main subjects of this module. Many criteria—including accuracy, precision, recall, f1-score, ROC curve, McNamar test, and others—are used to assess the performance of these algorithms. The experimental results show that among the many models, the Random Forest (RF) and the Stacking-SRDA ensemble technique can classify the students with more accuracy than others. To improve the interpretability of the model, we have finally used XAI technologies like Eli5, SHAPASH, and Local Interpretable Model Agnostic Explanations
Analysis of Reusability of Used Clothes Using Machine Learning Algorithms
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-01-28) Rubel, Md. Salauddin
With $45 billion in apparel exports in 2022, Bangladesh is the second-ranked country in the world for apparel exports also the second largest producer of textile waste. The Bangladeshi apparel sector is expected to generate US$10.15 billion in revenue by 2023. Purchasing power of Bangladeshi people have increased and expenses on apparel product has also increased. The habit of repeating clothes that worn once has decreased which makes our wardrobe filled with lots of rarely used clothes and after a certain time we throw them as a wastage. Our study is aimed to develop a machine learning algorithm to predict clothing reusability. For our model we use clothing type, fabric type, usage duration, damage, distortion and color information of a used cloths. We use Classification algorithms for constructing our predictive model. We have applied five classification machine learning algorithm which are Decision Tree, Random Forest, Naïve Bayes, Logistic Regression and SVM. With the given information of a used cloth our model can predict the reusability option for it, the options are: resale, reuse and turn into jhoot product. By reselling a used cloths one can earn save some money and on the other hand people having less money can get a good product. Reusing clothing items means using to create a new apparel item or using in home craft. The last option of reusing is turning into jhoot products, cloths which have used more than their average life cycle are used in jhoot. This research achieved model accuracy between 79% to 85% on predicting reusability of different apparel items. Future study will explore new machine learning approaches with larger dataset and also enable a system that will be useful for textile industry to achieve sustainability in clothing wastage.
Customer Churn Prediction For Telecommunication Industry
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-10) Afroz, Naznin
Customer churn prediction for telecommunication industry Thesis I used 2 models from dataset KAHHLE to do the work. .K- nearest neighbor algorithm, Decision tree Algorithm Two Datasets are working well but I think K Neighbors is giving good results this system is working well so this dataset I think this dataset will work well. With the rapid development of Telecommunication Industry, the service providers are inclined more towards expansion of the subscriber base. To meet the need of surviving in the competitive environment, the retention of existing customers has become a huge challenge. In the survey done in the Telecom industry, it is stated that the cost of acquiring a new customer is far more that retaining the existing one. Therefore, by collecting knowledge from the telecom industries can help in predicting the association of the customers as whether or not they will leave the company. The required action needs to be undertaken by the telecom industries in order to initiate the acquisition of their associated customers for making their market value stagnant. Our paper proposes a new framework for the churn prediction model and implements it using the WEKA Data Mining software. The efficiency and the performance of Decision tree and Logistic regression techniques have been compared.
Postpartum Depression Detection And Its Features Analysis By Machine Learning Approach
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-10) Khanom, Khadiza
Postpartum depression (PPD) poses a significant health concern affecting mothers globally, yet early detection remains a challenge. This research explores a pioneering approach to PPD detection and feature analysis using machine learning algorithms. Leveraging a dataset sourced from Kaggle, encompassing 1503 records obtained through a medical hospital questionnaire, the study meticulously examines ten selected attributes, with "Feeling Anxious" as the target variable. Notably, the dataset holds a 65% prevalence of anxiety and 35% non-anxiety cases. The study employed three machine learning algorithms – Decision Tree, Random Forest, and K-Nearest Neighbors (KNN) – showcasing promising results. Decision Tree achieved an accuracy of 98.01%, Random Forest excelled with 98.67%, and KNN demonstrated 92.03% accuracy. The precision, recall, and F1 scores complemented these outcomes, affirming the models' robustness. Feature importance analyses were conducted, unraveling insights into the factors contributing to PPD. Notable features included trouble sleeping at night, problems of bonding with the baby, and feelings of guilt. The algorithmic output, coupled with permutation feature importance, elucidated the nuanced relationships between these attributes and PPD. Furthermore, an exploration of age categories revealed distinctive patterns, with mothers aged 30-35 and 40-45 displaying higher susceptibility. The discussion extends to the interplay of variables like trouble sleeping, overeating, and irritability, contributing to a comprehensive understanding of PPD indicators
Stress Classification From Wearable Multimodal Physiological Signals: Deep Learning Approach
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-10) Halder, Aninda
Stress is a common problem with serious consequences for health and well-being, especially among healthcare workers such as nurses. Chronic stress in this population can lead to burnout, affecting both their personal well-being and patient care. Traditional stress assessment methods are limited in their ability to provide continuous, objective monitoring, highlighting the need for innovative solutions. Wearable technology, such as the `Empatica E4` smartwatch, offers a promising avenue for real-time stress monitoring through the measurement of physiological signals. In our study, we developed a stress classification model utilizing data collected from the `Empatica E4` smartwatch worn by nurses in a hospital setting. The model uses physiological signals to effectively classify stress levels using Long Short-Term Memory (LSTM) neural networks. The study begins by exploring the physiological and psychological aspects of stress, emphasizing the challenges faced by nurses in high-stress environments and the potential of wearable technology for stress monitoring. Utilizing a publicly available dataset consisting of physiological signals, including heart rate, electrodermal activity (EDA), skin temperature, and the physical activity of nurses, and preprocessing it for analysis. The results demonstrate the model's effectiveness in both binary and multiclass classification tasks, with notable performance differences observed across stress categories. In multiclass classification, the model exhibits high precision and recall for "no stress" (precision: 0.88, recall: 0.90) and "high stress" (precision: 0.94, recall: 0.94) categories but shows reduced performance for "low stress" (precision: 0.74, recall: 0.71). This gap could be related to signal ambiguity and class imbalance. In binary classification, merging "low stress" with "no stress" simplifies the task and results in consistent performance across both classes, with stress detection achieving precision of 0.91 and recall of 0.96 and "no stress" classification precision of 0.90 and recall of 0.82. This research not only advances our understanding of stress monitoring in the healthcare environment but also furthers the exploration of stress diagnosis using smartwatch data. The developed stress classification model offers potential applications in real-time stress monitoring systems, personalized feedback mechanisms, and intervention strategies to mitigate stress among healthcare professionals. These findings have broader implications for improving well-being and patient care quality in high-stress environments beyond healthcare
Customer Satisfaction Sentiment Analysis For Online Transactions In Bangladesh Using Machine Learning
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-10) Pias, Md. Almahmud
Online transactions are becoming increasingly popular in Bangladesh, starting from shopping, we transact online. Online payment plays a very important role in paying any shopping bill. To find any possible problems and enhance the user experience as a whole, it is crucial to comprehend the degree of client satisfaction with these kinds of transactions. With an emphasis on aspects including platform usability, transaction security, and overall customer experience, the poll sought to determine Bangladesh's degree of customer satisfaction with online transactions. A report based on a sample of customers through which we understood how customers are satisfied with online payment and got an idea to understand their opinion. survey's findings indicate that Bangladesh's mean consumer satisfaction rating for online transactions is 6.2096813773 out of 10. Through this we came to know that all the customers of Bangladesh are satisfied with online shopping and everyone can improve from everyone's place. Through this test, we can know more about the value and satisfaction of online transactions in Bangladesh. They have largely responded to improving customer experience and digital transactions. All in all, a satisfactory established informed that online shopping plays an important role
A Machine Learning Approach for Early Detection and Improved Decision-Making for Lung Cancer Diagnosis
(Daffodil International University, 2024-02-03) Hasan, Km. Zayedul
Lung cancer is presently the leading cause of cancer-related mortalities worldwide. Environmental conditions, lifestyle habits, and genetics are the main causes of lung cancer. Early detection of lung cancer is pivotal in preventing its severe consequences. The integration of machine learning algorithms in the healthcare industry has led to significant advancements in disease diagnosis. These algorithms help medical professionals diagnose lung cancer accurately in the early stages. In this study, we propose using Quadratic Discriminant Analysis to improve the accuracy of lung cancer diagnosis by analyzing the symptoms of lung cancer patients. Our proposed technique is more suitable for diagnosing lung cancer with higher accuracy and precision compared to previous techniques. The methodology has demonstrated an impressive overall accuracy of 98% based on empirical results.
Detection Of Depression And Anxiety Symptoms In University Students Using Machine Learning
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-14) Akter, Tahmina
This report explores the application of machine learning techniques for the detection of depression and anxiety symptoms among university students. The prevalence of mental health issues in this demographic poses significant challenges to academic success and overall well-being. Traditional methods of identifying and addressing these concerns often fall short due to limitations such as stigma, subjective assessments, and resource constraints. Using diverse datasets encompassing demographic information, academic performance metrics, social media activity, and smartphone usage patterns, machine learning models are trained to recognize patterns indicative of mental health issues. The study evaluates various machine learning algorithms, including Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), k-Nearest Neighbors (KNN), and Naive Bayes (NB), to determine their effectiveness in predicting depression and anxiety symptoms. Ethical considerations such as data privacy, bias mitigation, and responsible model deployment are also addressed. The findings offer insights into the potential of machine learning to revolutionize mental health assessment in university settings, providing opportunities for early intervention and personalized support for students.
Predictive Modeling of Heart Failure: Integrating Clinical Data with Machine Learning
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-14) Ahmed, Tanvir
Heart failure is a critical health condition that poses significant challenges to the medical community due to its high mortality rate and substantial healthcare costs. Early predictionofheart failure can greatly improve patient outcomes by enabling timely interventions andpersonalized treatment plans. This study focuses on leveraging machine learning algorithmsto predict heart failure at an early stage, utilizing a comprehensive set of clinical dataandpatient metrics. In this research, I employ various machine learning algorithms, with a particular emphasisonthe Random Forest algorithm, renowned for its robustness and accuracy in classificationtasks. Our model is trained and validated using multiple datasets, including those sourcedfromestablished medical repositories, to ensure its reliability and applicability across different patient populations. Key performance metrics such as accuracy, precision, recall, andF-measure are utilized to evaluate the model's effectiveness. The findings of our study indicate that the Random Forest algorithmexcels in predictingheart failure, delivering significant improvements in prediction accuracy and reliability. Themodel not only identifies high-risk patients but also provides actionable insights forhealthcare professionals to implement preventative measures and optimize treatment strategies early in the care continuum. The proposed machine learning-based approach to heart failure prediction offers a powerful tool for enhancing clinical decision-making processes. By integrating this predictive model into healthcare systems, medical practitioners can reduce hospital readmission, lowerhealthcare costs, and improve overall patient care quality
Optimizing Customer Trust And Satisfaction In E-Commerce With Machine Learning Techniques
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-07-14) Uddin, Kamal
Establishing trust is vital for sustainable success in a constantly changing e-commerce marketplace, particularly in locations such as Bangladesh where trust among customers is usually lacking. This research study focuses on assessing the sentiment of customer reviews in Bangladesh's e-commerce industry. It employs several Machine Learning approaches, with a primary emphasis on Natural Language Processing (NLP). The major purpose is to evaluate patterns and sentiments in Bengali review in order to give organizations with insights into customer preferences and enhance the quality of their offerings, ultimately establishing trust. This study investigates the usefulness of Natural Language Processing in managing a substantial number of Bengali e-commerce reviews, while taking into consideration particular linguistic and contextual distinctive characteristics. The study attempts to acquire key insights from consumer opinions in order to better products and services, enhance customer happiness, and achieve an advantage over others in the e-commerce industry of our country. Also, the anticipated outputs of the sentiment analysis could serve to boost the accomplishment and progress of Bangladesh's ecommerce business by overcoming potential barriers associated to data-driven initiatives that depend mostly on feedback from users. The study methodology is made up acquiring data from Kaggle and successfully preparing the text employing natural language processing techniques. To increase the statistical results of the models, the Decision Tree Classifier, K-nearest Neighbor approach, Random Forest Classifier, Logistic Regression, and Naive Bayes Classifier methods use unigram, bigram, and trigram data. The study produced an accuracy rate of 80.59% by applying the Logistic Regression algorithm by incorporating the trigram feature.

MPhil Thesis

Browse

Filters

Settings

Sort By

Results per page

Search Results