The Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods and Machine Learning (ML) algorithms have greatly contributed to the growth of data-driven forecasting systems that provide cost-effective solutions and improved performance in simulating the complex physical processes of floods using mathematical expressions. To make improvements to flood prediction for the Red River of the North, this paper presents effective approaches that make use of a classical statistical method, a classical ML algorithm, and a state-of-the-art Deep Learning method. Respectively, the methods are seasonal autoregressive integrated moving average (SARIMA), Random Forest (RF), and Long Short-Term Memory (LSTM). We used hourly level records from three U.S. Geological Survey (USGS), at Pembina, Drayton, and Grand Forks stations with twelve years of data (2007–2019), to evaluate the water level at six hours, twelve hours, one day, three days, and one week in advance. Pembina, at the downstream location, has a water level gauge but not a flow-gauging station, unlike the others. The floodwater-level-prediction results show that the LSTM method outperforms the SARIMA and RF methods. For the one-week-ahead prediction, the RMSE values for Pembina, Drayton, and Grand Forks are 0.190, 0.151, and 0.107, respectively. These results demonstrate the high precision of the Deep Learning algorithm as a reliable choice for flood-water-level prediction.

No abstract

No abstract

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder and the most commonly diagnosed cause of dementia, and it is the fifth leading cause of death among people aged 65 and older. During the years, the early diagnosis of AD patients has been a significant concern for researchers, in view of the fact that early diagnosis not only can lead to saving lives of the AD patients but also could bring a considerable amount of saving in health and long-term care expenditures for both people and the government. Mild cognitive impairment (MCI), defined as a transitional state between being healthy and having AD, is considered an established risk factor for AD. Hence, an accurate and reliable diagnosis of MCI and, consequently, discrimination between healthy people, MCI individuals, and AD patients can play a crucial role in the early diagnosis of AD. In recent years, analysis of blood gene expression data has been grabbed more attention than the conventional AD diagnosis method because it provides the opportunity to investigate the biochemical pathways, cellular functions, and regulatory mechanisms for finding the key genes associated with MCI and AD. Therefore, in this study, we employed blood gene expression data from Alzheimer's Disease Neuroimaging Initiative (ADNI), two feature selection methods for determining the most prominent genes related to MCI and AD, and three classifiers for the most accurate discrimination between three groups of healthy, MCI and AD. The proposed method yielded the selection of top ten genes from more than 49,000 genes and the best overall classification result between healthy and AD patients with average values of the area under the curve (AUC) of 0.77 +- 0.08. Furthermore, gene ontology (GO) analysis revealed that four genes were enriched with the GO terms of regulation of cell proliferation, negative regulation of cell population proliferation, signaling receptor binding, biological adhesion, and cytokine production.

No abstract