• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.158-158
• /
• 2018

Drought is a recurrent natural hazard in Bangladesh. It has significant impacts on agriculture, environment, and society. Well-timed information on the onset, extent, intensity, duration, and impacts of drought can mitigate the potential drought-related losses. Thus, drought characteristics need to be explained in terms of frequency, severity, and duration. This paper aims to characterize the spatial and temporal pattern of meteorological drought using EDI and illustrated drought severity over Bangladesh. Twenty-seven (27) station-based daily rainfall data for the study period of 1981-2015 were used to calculate the EDI values over Bangladesh. The evaluation of EDI is conducted for 4 sub-regions over the country to confirm the historical drought record-developed at the regional scale. The finding shows that on average, the frequency of severe to extreme drought is approximately 0.7 events per year. As a result of the regional analysis, most of the recorded historical drought events were successfully detected during the study period. Additionally, the seasonal analysis showed that the extreme droughts were frequently hit in northwestern, middle portion of the eastern and small portion of central parts of Bangladesh during the Kharif(wet) and Rabi(dry) seasons. The severe drought was affected recurrently in the central and northern regions of the country during all cropping seasons. The study also points out that the northern, south-western and central regions in Bangladesh are comparatively vulnerable to both extreme and severe drought event. The study showed that EDI would be a useful tool to identify the drought-prone area and time and potentially applicable to the climate change-induced drought evolution monitoring at regional to the national level in Bangladesh. The outcome of the present study can be used in taking anticipatory strategies to mitigate the drought damages on agricultural production as well as human sufferings in drought-prone areas of Bangladesh.

• Journal of Korea Water Resources Association
• /
• v.40 no.4
• /
• pp.335-343
• /
• 2007

Drought characteristics need to be preceded before establishing a drought mitigation plan. In this study, using a Standardized Precipitation Index (SPI), a hydrologic drought was defined as an event during which the SPIs are continuously below a certain truncation level. Then, a methodology of drought frequency analysis was performed to quantitatively characterize droughts considering drought duration and severity simultaneously. The theory of runs was used to model drought recurrence and to determine drought properties like duration and severity. Short historical records usually do not allow reliable bivariate analyses. However, more than hundred years of precipitation data (1770 ${\sim}$ 1907) collected in Chosun Kingdom Age using an old Korean rain gage called Chukwooki can provide valuable information about past events. It is shown that a bivariate gamma distribution well represented the joint probabilistic properties of Korean drought duration and severity. The overall results of this study show that the proposed bivariate drought frequency analysis overcomes the drawbacks of the conventional univariate frequency analysis by providing a consistent representation of the drought recurrent property.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.1
• /
• pp.153-168
• /
• 1998

Background: The existing data indicate that obstructive sleep apnea syndrome contributes to the development of cardiovascular dysfunction such as systemic hypertension and cardiac arrhythmias, and the cardiovascular dysfunction has a major effect on high long-term mortality rate in obstructive sleep apnea syndrome patients. To a large extent the various studies have helped to clarify the pathophysiology of obstructive sleep apnea, but many basic questions still remain unanswered. Methods: In this study, the influence of obstructive sleep apnea on systemic blood pressure, cardiac rhythm and urinary catecholamines concentration was evaluated. Over-night polysomnography, 24-hour ambulatory blood pressure and ECG monitoring, and measurement of urinary catecholamines, norepinephrine (UNE) and epinephrine (UEP), during waking and sleep were undertaken in obstructive sleep apnea syndrome patients group (OSAS, n=29) and control group (Control, n=25). Results: 1) In OSAS and Control, UNE and UEP concentrations during sleep were significantly lower than during waking (P<0.01). In UNE concentrations during sleep, OSAS showed higher levels compare to Control (P<0.05). 2) In OSAS, there was a increasing tendency of the number of non-dipper of nocturnal blood pressure compare to Control (P=0.089). 3) In both group (n=54), mean systolic blood pressure during waking and sleep showed significant correlation with polysomnographic data including apnea index (AI), apnea-hypopnea index (AHI), arterial oxygen saturation nadir ($SaO_2$ nadir) and degree of oxygen desaturation (DOD). And UNE concentrations during sleep were correlated with AI, AHI, $SaO_2$ nadir, DOD and mean diastolic blood pressure during sleep. 4) In OSAS with AI>20 (n==14), there was a significant difference of heart rates before, during and after apneic events (P<0.01), and these changes of heart rates were correlated with the duration of apnea (P<0.01). The difference of heart rates between apneic and postapneic period (${\Delta}HR$) was significantly correlated with the difference of arterial oxygen saturation between before and after apneic event (${\Delta}SaO_2$) (r=0.223, P<0.001). 5) There was no significant difference in the incidence of cardiac arrhythmias between OSAS and Control In Control, the incidence of ventricular ectopy during sleep was significantly lower than during waking. But in OSAS, there was no difference between during waking and sleep. Conclusion : These results suggested that recurrent hypoxia and arousals from sleep in patients with obstructive sleep apnea syndrome may increase sympathetic nervous system activity, and recurrent hypoxia and increased sympathetic nervous system activity could contribute to the development of cardiovascular dysfunction including the changes of systemic blood pressure and cardiac function.