Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
4 results
Search Results
Item Restricted Improving Sleep Health with Deep Learning: Automated Classification of Sleep Stages and Detection of Sleep Disorders(Saudi Digital Library, 2024-07-07) Almutairi, Haifa; Datta, AmitavaSleep consumes roughly one-third of a person’s lifetime, and it is characterized by distinct stages within sleep cycle. The sequence of these stages at night provides insights into the quality of sleep. Poor sleep quality can have numerous consequences, including drowsiness, reduced concentration, and fatigue. Beyond sleep quality, an analysis of the sequence of sleep stages can uncover the presence of sleep disorders. This thesis aims to focus on three key research problems related to sleep. Firstly, it focuses on the classification of sleep stages using a combination of signals and deep learning models. Sleep stages are categorized into five distinct stages, namely Wake (W), non-rapid eye movement (NREM) stages comprising N1, N2, and N3, and rapid eye movement (REM) stage. Throughout the duration of sleep, individuals experience multiple cycles of sleep stages. Each cycle contains a standard allocation of each stage. An unbalanced distribution of the stages can indicate the presence of sleep disorders. Previous studies primarily classified sleep stages using a single channel of electroencephalography (EEG) signals. However, incorporating a combination of signals from electromyography (EMG) and electrooculogram (EOG) alongside EEG data provides additional features. These features extracted from muscle activity and eye movements during sleep, thereby enhancing classification accuracy. In this thesis, a robust model called SSNet is proposed to accurately classify sleep stages from a fusion of EEG, EMG, and EOG signals. This model combine convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to extract the salient features from various physiological signals. The CNN architecture extracts spatial features from the input signals, while LSTM architecture captures the temporal features present in signals. This study has obtained encouraging outcomes in the classification of sleep stages through the fusion of physiological signals and deep learning techniques. Secondly, this thesis aim to detect obstructive sleep apnoea (OSA) from electrocardiography (ECG) signals using deep learning methods. Sleep disorder breathing (SDB) is categorized into three different types, which are OSA, central sleep apnoea, and mixed sleep apnoea. OSA is the most common form of SDB that is characterized by repeated interruptions in breathing during sleep, leading to fragmented sleep patterns and various health complications. Previous studies developed feature engineering methods and machine learning models for the detection of OSA. Feature engineering methods involve crafting relevant features to feed into machine learning models. However, feature engineering is time-consuming and requires domain expertise. In contrast, deep learning automatically extracts features from ECG signals for OSA detection, eliminating the need for manual feature engineering methods. In this thesis, three deep learning architectures are proposed, including standalone convolutional neural networks (CNN), CNN with long short-term memory (LSTM), and CNN with gated recurrent unit (GRU). Through rigorous experimentation and evaluation, the combination of CNN and LSTM architecture is the best-performing model for OSA detection. To further enhance the architecture’s performance, the hyperparameters of the CNN and LSTM models were tuned and tested over a large dataset to validate their effectiveness. The third research problem addressed in this thesis is detection of periodic leg movements (PLM) and SDB from NREM stage by using a combination of signals and deep learning models. PLM is characterized by involuntary leg movements during sleep. These movements can disrupt sleep and result in daytime sleepiness with reduced quality of life. Detecting PLM and SDB events during NREM stage allows for quantifying the severity of sleep disorders. Previous studies have focused on the development of signal-based models for detecting PLM or SDB. However, the models lacked the ability to distinguish these events within specific sleep stages. To address this problem, a novel deep learning architecture known as DeepSDBPLM is proposed. This architecture aims to detect PLM and SDB events during the NREM stage. This architecture incorporates novel input features called attention EMDRaw signals and utilizes a Residual Convolutional Neural Network (ResCNN) model. This thesis presents experimental results using publicly available datasets to evaluate the performance of the proposed deep learning models for classification of sleep stages, and detection of sleep disorders. The models were evaluated standard metrics. It includes accuracy, sensitivity, specificity, and F1 score. The empirical results establish the effectiveness of proposed approaches. The models can be a stepping stone towards more advanced techniques.14 0Item Restricted Utilising Technical Analysis, Commodities Data, and Market Indices to Predict Stock Price Movements with Deep Learning(Cardiff University, 2024) Aloraini, Osama Mohammed A; Sun, XianfangThis study investigates the efficacy of deep learning models, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), for forecasting stock price movements in the U.S. stock market. The dataset used includes 133 stocks across 19 different sectors and covers the period from 2010 to 2023. Moreover, to enrich the dataset, eleven technical indicators and their corresponding trading strategies, represented as vectors, were integrated along with market indices and commodities data. Consequently, various experiments were conducted to assess the effectiveness of different feature combinations. The findings reveal that the CNN model outperforms the LSTM model in both accuracy and profitability, achieving the highest accuracy of 59.7%. Furthermore, models demonstrated an ability to identify significant trend-changing points in stock price movements. Another finding shows that translating trading strategies into vector form plays a critical role in enhancing the performance of both models. However, it was observed that incorporating external features like market indices and commodities data led to model overfitting. Conversely, relying only on stock-specific features triggered a risk of model underfitting.68 0Item Restricted Predicting the Uptake of a New Medicine in England using Classification(Saudi Digital Library, 2023-12-01) Alsoghayer, Sara; Tabassum, FaizaThe National Healthcare Service (NHS) is experiencing delays of the uptake of a new medicine within their formularies, despite the National Institute for Health and Care Excellence (NICE) recommendations. Such delays not only affect pharmaceutical companies’ during the launch stage but also contribute to potential harm in patients’ health, and low global competitiveness in the life sciences sector. This study investigates the viability of predicting the speed of uptake of a new drug on a formulary level using classification algorithms. Three types of machine learning models: XGBoost, random forest, and logistic regression were employed and evaluated. The results suggest the predictive model, XGBoost, is operating on a market entry level, showing generalized predictions across various formularies. The findings also indicate there is no correlation between the formulary medicine uptake and the number of partnered organizations of a formulary, or the size of patient population.51 0Item Restricted Investigating Rule Induction Methods in Machine Learning for Improving Medical Dementia Prediction(2023-08-04) Albalawi, Hadeel; Lambrou, TryphonAlzheimer’s Disease (AD) is a neurodegenerative disease related to dementia that predominantly affects the elderly population with symptoms including, but not limited to, cognitive impairment and memory loss. Detecting AD and other conditions like Mild Cognitive Impairment (MCI) can lengthen the lifespan of patients and help them to access the medical services. One approach to achieve a rapid and early diagnosis of AD is using data mining (DM) techniques, which can search various characteristic traits related to Cognitively Normal (CN), AD, and MCI data observations to build classifiers that reveal contributors to the disease. Classifiers developed by DM techniques are used by medical professionals during dementia clinical processes to help make correct diagnosis. In this research, we amend a process based on DM that evaluates characteristics related to dementia conditions, in particular AD. The novelty of the proposed process lies in the classification algorithm that we have named ‘Rules-based Uncertainty Reduction Algorithm’ (RURA). RURA develops classifiers with rules, which strengthen the decisions that can be invoked by the medical professional when evaluating patients with dementia. Empirical evaluation, using several DM algorithms were conducted on biological marker (biomarkers) and behavioral characteristics of data subjects collected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data project to analyze the effectiveness of the proposed classification algorithm. The results show that RURA perform over 90% in predicting AD when compared with classifiers developed by other DM algorithms. Furthermore, the results show that delayed word recall and orientation are effective cognitive factors that contribute to the ability to detect dementia early. For the biomarkers, ABETA and neurofibrillary tangles in the neurons showed some associations with AD although fewer than those of the cognitive elements. Moreover, the results obtained show that the classifiers developed by the RURA algorithm from psychological attributes (Subset 2) are higher in accuracy than the other DM algorithms. The results from Subset 2, show that RURA’s classifiers are higher with 11.28%, 1.18%, 1.88%, 3.75%, 1.70%, and 0.27% than PRISM, Nnge, kNN, Naïve Bayes, ORule, and Ridor, separately. Also, RURA developed higher accurate classifiers than the remaining DM algorithms on Subset 12 which includes cognitive attributes and biomarker attributes. However, the performance of RURA did not improve when the general attributes were added to the psychological attributes and the accuracy decreased by 1.34% when mining Subset 2 (psychological attributes and general attributes). More considerably, the results indicate that specific biomarkers in the ADNI-MERGE dataset when used alone by a DM algorithm that we considered for dementia detection often will not result in acceptable predictive systems. For example, when DM algorithms were trained on MRI and PET attributes (Subset 5), the classifiers created had classification accuracies of 42–55% which are relatively low. So, utilizing neuroimaging attributes in the ADNI-MERGE dataset to detect dementia is not ideal using the DM techniques, especially when a baseline visit is used to represent each data subject. Therefore, the biomarkers attributes must be accompanied with psychological elements to improve the detection rate of dementia.12 0