Browsing by Subject "Support Vector Machine"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    Analysis of Machine Learning Algorithms for Time Series Prediction
    (2021) Naidoo, Kimendree; Moodley, Deshendran
    Due to the rapidly increasing prominence of Artificial Intelligence in the last decade and the advancements in technology such as processing power and data storage, there has been increased interest in applying machine learning algorithms to time series prediction problems. There are many machine learning algorithms that can be used for time series prediction problems but selecting an algorithm can be challenging due to algorithms not being suitable to all types of datasets. This research investigates and evaluates machine learning algorithms that can be used for time series prediction. Experiments were carried out using the Artificial Neural Network (ANN), Support Vector Regressor (SVR) and Long Short-Term Memory (LSTM) algorithms on eight datasets. An empirical analysis was carried out by applying each machine learning algorithm to the selected datasets. A critical comparison of the algorithm performance was carried out using the Mean Absolute Error (MAE), the Mean Squared Error (MSE), the Root Mean Squared Error (RMSE) and the Mean Absolute Scaled Error (MASE). The second experiment focused on evaluating the stability and robustness of the optimal models identified in the first experiment. The key dataset characteristics identified; were the dataset size, stationarity, trend and seasonality. It was found that the LSTM performed the best for majority of the datasets, due to the algorithm's ability to deal with sequential dependency. The performance of the ANN and SVR were similar for datasets with trend and seasonality, while the LSTM overall proved superior to the aforementioned algorithms. The LSTM outperformed the ANN and SVR due to its ability to handle temporal dependency. However, due to its stochastic nature, the LSTM and ANN algorithms can have poor stability and robustness. In this regard, the LSTM was found to be a more robust algorithm than the ANN and SVR.
  • Thumbnail Image
    Item
    Open Access
    Parallel changes in gene expression in peripheral blood mononuclear cells and the brain after maternal separation in the mouse
    (BioMed Central Ltd, 2009) van Heerden, Johan; Conesa, Ana; Stein, Dan J; Montaner, David; Russell, Vivienne; Illing, Nicola
    BACKGROUND: The functional integration of the neuro-, endocrine- and immune-systems suggests that the transcriptome of white blood cells may reflect neuropsychiatric states, and be used as a non-invasive diagnostic indicator. We used a mouse maternal separation model, a paradigm of early adversity, to test the hypothesis that transcriptional changes in peripheral blood mononuclear cells (PBMCs) are paralleled by specific gene expression changes in prefrontal cortex (PFC), hippocampus (Hic) and hypothalamus (Hyp). Furthermore, we evaluated whether gene expression profiles of PBMCs could be used to predict the separation status of individual animals.FINDINGS:Microarray gene expression profiles of all three brain regions provided substantial evidence of stress-related neural differences between maternally separated and control animals. For example, changes in expression of genes involved in the glutamatergic and GABAergic systems were identified in the PFC and Hic, supporting a stress-related hyperglutamatergic state within the separated group. The expression of 50 genes selected from the PBMC microarray data provided sufficient information to predict treatment classes with 95% accuracy. Importantly, stress-related transcriptome differences in PBMC populations were paralleled by stress-related gene expression changes in CNS target tissues. CONCLUSION: These results confirm that the transcriptional profiles of peripheral immune tissues occur in parallel to changes in the brain and contain sufficient information for the efficient diagnostic prediction of stress-related neural states in mice. Future studies will need to evaluate the relevance of the predictor set of 50 genes within clinical settings, specifically within a context of stress-related disorders.