• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Journal of Yeungnam Medical Science
• /
• v.24 no.1
• /
• pp.41-54
• /
• 2007

Background : The causes of chest pain vary but the leading cause of chest pain is ischemic heart disease. Mortality from ischemic chest pain has increased more than two fold over the last ten years. The purpose of this study was to determine the data necessary for rapid treatment of patients with signs and symptoms of ischemic chest pain in the emergency department (ED). Materials and Methods : We interviewed 170 patients who had ischemic chest pain in the emergency department of Yeungnam University Hospital over 6 months with a protocol developed for the evaluation. The protocol used included gender, age, arriving time, prior hospital visits, methods of transportation to the hospital, past medical history, final diagnosis, and outcome information from follow up. Results : Among 170 patients, there were 118 men (69.4%) and the mean age was 63 years. The patients diagnosed with acute myocardial infarction (AMI) were 106 (62.4%) and with angina pectoris (AP) were 64 (37.6%). The patients who had visited another hospital were 68.8%, twice the number that came directly to this hospital (p<0.05). The ratio of patients who visited another hospital were higher for the AMI (75.5%) than the AP (59.4%) patients (p<0.05). The median time spent deciding whether to go to hospital was 521 minutes and for transportation was 40 minutes. With regard to patients that visited another hospital first, the median time spent at the other hospital was 40 minutes. The total median time spent before arriving at our hospital was 600 minutes (p>0.05). The patients who had a total time delay of over 6 hours was similar 54.8% in the AMI group and 57.9% in the AP group (p>0.05). As a result, only 12.2% of the patients with an AMI received thrombolytics, and 48.8% of them had a simultaneous percutaneous coronary intervention (PCI). In the emergency department 8.5% of the patients with an AMI died. Conclusion : Timing is an extremely important factor for the treatment of ischemic heart disease. Most patients arrive at the hospital after a long time lapse from the onset of chest pain. In addition, most patients present to a different hospital before they arrive at the final hospital for treatment. Therefore, important time is lost and opportunities for treatment with thrombolytics and/or PCI are diminished leading to poor outcomes for many patients in the ED. The emergency room treatment must improve for the identification and treatment of ischemic heart disease so that patients can present earlier and treatment can be started as soon as they present to an emergency room.