Theses - Undergraduate

Permanent URI for this collection

https://repository.northsouth.edu/handle/123456789/103

Browse

Recent Submissions

Now showing 1 - 5 of 205
  • Thumbnail Image
    Item
    Embargo
    Stock Market Price Forecasting Service using LSTM
    (North-south University, 2019-04-30) Md. Mahabubul Hasan; Pritom Roy; Sabbir Sarker; Dr. Mohammad Monirujjaman Khan; 1421274042; 1430378042; 1420134042
    In recent years we’ve seen in Bangladesh that the Stock market is not stable at all. In 2011 Stocks continued to tumble amid jitters over banks' liquidity crisis. After starting the day at 5,710, DSEX, the benchmark index of the Dhaka Stock Exchange, plunged to below 5,700 points in less than half an hour. Eventually, it lost 81.92 points to close the day at 5,623.64. People invest a lot in stock market. Many people just lost their hard-earned money in a blink of an eye because of investing at the wrong place. But we’ve seen the vice versa situation from the stock market as well. Stockify comes in play here. Stockify is dedicated to show accurate predicated prices of market shares. 70% accuracy have been achieved via training the algorithm Using LSTM which is an artificial neural network. Deep learning algorithm library TensorFlow have been implemented to show us predicted price using the closing prices of a day. Currently we are providing free service via our website and application. It would be on subscription based when the site will be more enriched in a business level. Thus, we hope to help people to make a profit in stock market and upraise the stock market of Bangladesh.
  • Thumbnail Image
    Item
    Embargo
    E-learning App with Augmented Reality
    (North South University, 2019-04-30) Md Nazmus Shakib; Safin Mahmud; Polash Chakrabarty; Abdullah All Noman Abir; Dr. Shazzad Hosain; 1511336042; 1510903042; 1520579042; ID # 1521047042
    Smartphone has become a great tool for teaching kids. As kids nowadays spend a lot of time on a smartphone. Preschool education is considered pivotal for a child’s development. Mobile learning is a new way to access learning content. Mobile learning is very popular among preschool kids. Because it really motivates kids to learn if they can use mobile phones or tablets. That's why we have developed a marker-based AR application, which will help children to learn or study the basics of Alphabets with fun. While using our app, kids will learn interactively with the help of Augmented Reality. Our app will help the parents teach their kids without much effort.
  • Thumbnail Image
    Item
    Embargo
    Chiral and Plasmonic dimers: Broadband reversal of optical binding force
    (North South University, 2022-12-31) Missing information; Missing Information
    The behavior between the chiral –plasmonic nanoparticles and their optical binding force in near and far field has not been investigated in the literature yet. There is no generic way to reverse the far field optical binding force for chiral and plasmonic (sphere) heterodimers. Also the behavior of Fano resonance and the reversal of far field optical binding force of chiral plasmonic heterodimers with and without plasmonic substrates have not been studied so far. In this article, for chiral and plasmonic heterodimers, we have demonstrated a general way to control the reversal of far field binding force. However, if the chiral-plasmonic nanoparticles are located at different distance, positive and reversal of optical binding force occurs in far field. We have varied the wavelength of the dimers. We have also observed Fano resonance at both near and far field without substrate .Also while applying the same set-up over a plasmonic substrate, stable Fano resonance occurs along with the reversal of far field optical binding force. It is observed that during such Fano resonance, stronger coupling occurs between the dimers and plasmonic substrate. The reversal of optical binding force occurs near the Fano dip position. Notably, for particle clustering and aggregation, controlling the far fled binding force can be a key factor. Our proposed idea can be confirmed by simple experiment.
  • Thumbnail Image
    Item
    Open Access
    Sleep Apnea Detection From Raw Ecg Signal Using Deep Learning And Machine Learning
    (North South University, 2023) Salem Shamsul Alam; Sumit Saha; Md. Shahriar Hussain; 1931849642; 1931415042
    Sleep apnea, a prevalent yet underdiagnosed sleep disorder, necessitates robust and accurate diagnostic tools. In this project, we undertook an in-depth exploration of machine learning (ML) and deep learning (DL) models for sleep apnea detection, specifically utilizing raw electrocardiogram (ECG) signals. Our comparative analysis encompassed a range of ML models, including Random Forest, Logistic Regression, Decision Tree, AdaBoost, and XGBoost, and a specialized 1D-CNN model within the DL domain. Results underscore the exceptional performance of the 1D-CNN model, achieving a remarkable accuracy of 99.56%, sensitivity of 96.05%, and specificity of 99.66%. This outperforms traditional ML models, signifying the prowess of DL in extracting intricate patterns from raw ECG signals for accurate sleep apnea detection. The 1D-CNN model's ability to discern subtle features proves crucial for accurately identifying apnea events. Our study not only emphasizes the effectiveness of the 1D-CNN model for sleep apnea detection and highlights the transformative potential of deep learning in healthcare diagnostics. This research contributes valuable insights into the optimal choice of models for sleep apnea detection, paving the way for enhanced diagnostic accuracy and improved patient care.
  • Thumbnail Image
    Item
    Open Access
    Developing a Mobile Application using Deep Learning for Cataract Classification
    (North South University, 2023) Tasnia Ishrat Khan; Fatima Ibrahim; Mohammad Monirujjaman Khan; 1911539642; 2121340642
    One of the leading global causes of vision loss and blindness is the cataract. The percentage of blind people is around 50%. As a result, early cataract detection and prevention may limit vision loss and blindness. Contrary to cataract, artificial intelligence (AI) has made significant progress in the treatment of glaucoma, macular degeneration, diabetic retinopathy, corneal abnormalities, and age-related eye diseases. However, the vast majority of cataract detection algorithms in use are built using common machine learning techniques. On the other hand, manual extraction of retinal features is a laborious method that needs a skilled ophthalmologist. In order to detect cataracts, we have built the framework of an Android application. We then used algorithms to extract accuracy, graphs, trainable and untrainable parameters, and differentiation of cataract and non-cataract eye images from a gathered dataset. In order to identify the cataract using color fundus images, we presented the VGG19 (Visual Geometry Group), and digital image we presented Inception V3, which is a CNN (convolutional neural network) model. This will be incorporated into an Android application. The results of fundus image, the training procedure demonstrate that the model attained a flawless accuracy of 1.0000 on the training data for epochs 10 to 15. It scored an accuracy of 0.963 on the validation set, which is still quite high. With values ranging from 0.25 to 0.27, the validation loss was similarly largely consistent. The model is doing well and has mastered correctly classifying the photos. On the test data, the model produced a loss of 0.25735 and an accuracy of 0.9241. The result of the digital image, accuracy is 0.973 on the validation set, which is quite high and on the test data, the model produced a loss of 0.26753 and accuracy of 0.93491. The significance of these results is that the model performs effectively, can reliably categorize test photos with high accuracy, and will be trustworthy for patients to utilize.