SACM - United Kingdom
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9667
Browse
3 results
Search Results
Item Restricted Enhancing Stock Price Prediction Using Machine Learning Models: A Comparative Study of SVM, LSTM, and GRU(University College London, 2024-08) AlMohamdy, Razan; Andrea, DucciThis study evaluates the effectiveness of three machine learning models—Support Vector Machine (SVM), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRU)—in predicting the stock prices of Saudi Aramco. Using historical stock price data and technical indicators, the models were assessed based on their accuracy in both long-term and short-term predictions. The findings reveal that LSTM and GRU significantly outperform SVM, with LSTM showing superior performance in capturing long-term dependencies and GRU offering a balance between accuracy and computational efficiency. Specifically, LSTM achieved a Root Mean Squared Error (RMSE) of 0.0516 and a Mean Absolute Error (MAE) of 0.0323, while GRU recorded an RMSE of 0.0539 and an MAE of 0.0234. In contrast, SVM exhibited a much higher RMSE of 0.1712 and an MAE of 0.1079, indicating its struggles with market volatility. The 30-day prediction analysis further highlighted the strengths of LSTM and GRU in short-term forecasting, with both models maintaining an R² value above 0.993, while SVM lagged behind at 0.9332. Despite their advantages, the study identified limitations such as the exclusion of external economic factors and the models' varying effectiveness across different time horizons. These findings contribute to the growing field of financial forecasting, offering practical insights for investors and analysts on model selection. Future research is recommended to incorporate broader economic indicators, explore cross-market validation, and enhance the models' responsiveness to short-term market fluctuations.22 0Item Restricted Feature Selection for High Dimensional Healthcare Data(University of Surrey, 2024-01) Alayed, Abdulrahman; Kouchaki, SamanehIn today’s digital landscape, researchers frequently encounter the complexity of handling highdimensional datasets. At times, data mining and machine learning methods struggle when confronted with immense datasets, leading to inefficiencies. The presence of extensive raw data with numerous features can negatively impact machine learning algorithms, affecting accuracy, increasing overfitting, and amplifying complexity. This is primarily due to the inclusion of redundant and irrelevant data, which hampers the learning process. However, employing feature selection techniques can effectively address these challenges. By selectively choosing relevant features, these techniques enable machine learning algorithms to operate more efficiently. They contribute to faster training, reduce model complexity, enhance accuracy, and mitigate overfitting issues. The primary objective of this project is to create an automatic variable selection pipeline by choosing the best features among various innovative feature selection techniques. The pipeline incorporates different categories of variable selection methods: Filter methods, Wrapper methods, Embedded methods, and Hybrid Method. The variable selection techniques are applied to the MIMIC-III (Medical Information Mart for Intensive Care) dataset, which is reachable at no cost. This database is well-suited for the project's goals, as it is a centralized database containing details about patients admitted to the critical care unit of a vast regional hospital. The dataset is particularly useful for forecasting the likelihood of death pst-ICU admission during hospital stay. To achieve this goal, the project employs six classification techniques: Logistic Regression (LR), K-nearest Neighbours (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The project systematically evaluates and compares the model's performance using various assessment metrics.34 0Item Restricted Supervised Machine Learning Assessment of Dementia Using Feature Selection Filter Methods(Spring Nature, 2023-10-30) Rajab, Mohammed Dabash; Wang, DennisThe prevalence of dementia is increasing globally. Due to the massive resources required, this issue is pressuring governments and private healthcare systems. Accurate diagnosis by clinicians on the cause of dementia, such as Alzheimer’s disease (AD), is difficult because of the time and assessments needed like neuropathological. The issue becomes more challenging when considering if various brain lesions contribute to the pathological assessment of dementia, the relationship of these lesions to the various dementia conditions, how they interact, and how to quantify them. Thereby, systematically assessing neuropathological measures by their degree of association with dementia, especially AD, may lead to better diagnostic systems and treatment targets. One promising approach that can answer these challenges is to develop data-driven solutions with core functions of feature evaluation and automatic subject classification based on machine learning (ML). Recent research studies in medical diagnosis, including dementia research, reveal that ML techniques, when used with feature selection, can identify critical features of Alzheimer-related pathologies and their association with the disease’s diagnosis and prognosis. The feature selection removes noisy features from the dementia data to increase the predictive performance and improve interpretability while reducing the dimensionality and computational complexity. However, filter-based feature selection methods can generate dissimilar feature rankings and may be sensitive to the correlations among themselves. This thesis investigates dementia with a focus on AD neuropathological assessments from a data-driven perspective to develop mechanisms to assist pathologists during these clinical assessments. The thesis investigation comprises phases such as feature ranking, feature-feature correlation, and classification. The work determines the impact of neuropathological feature-features correlations on the feature ranking for better biomarker identification. The investigation assesses real datasets related to dementia, the Cognitive Function and Aging Studies (CFAS) and the Alzheimer’s Disease Neuroimaging Initiative (ADNI), using filter methods and classification techniques. The results showed that classification models generated from the CFAS and ADNI sets of chosen neuropathological features were strong in terms of sensitivity, accuracy, and other measures when mined by different classification techniques. In the ADNI dataset results, the significant neuropathological features contributing to AD included neocortical neuritic plaques, Braak stage, Thal phase, diffuse plaques, and cerebral amyloid angiopathy (CAA), all of which showed a high correlation with AD’s diagnostic label. In the CFAS dataset, the results were consistent with those derived from the ADNI dataset. Moreover, among the filter methods considered, reliefF had the strongest correlation with feature-feature correlations in both ADNI and CFAS datasets, less sensitive to feature-feature correlations. However, no filter method had clear dominance over ADNI results. More essentially, the results indicated limited consistency in feature rankings between ADNI and CFAS. However, reliefF had the most agreement, while the Gain Ratio method had less consistency in ranking the features in both datasets. In summary, this thesis provided valuable insights into the application of filter methods and neuropathology data for developing classification models for dementia conditions’ diagnosis. The study demonstrated the significance of considering feature-feature correlations when selecting influential features and the impact of different filter methods on feature ranking and classification performance. These findings suggest that the proposed approach could effectively minimise the discrepancy of feature ranking and generate an impactful set of features for classification algorithms. These results had practical implications for pathologists in improving the understanding of AD pathology. Furthermore, the study has highlighted the potential for future research to leverage diverse filter methods to identify more reliable biomarkers and enhance the detection of dementia, particularly for AD.26 0