• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• Journal of the Society of Disaster Information
• /
• v.17 no.1
• /
• pp.25-38
• /
• 2021

Purpose: To reduce the damage caused by continuously occurring typhoons, we proposed a standardized grid so that it could be actively utilized in the prevention and preparation stage of typhoon response. We established grid-based convergence information on the typhoon risk area so that we showed the effectiveness of information used in disaster response. Method: To generate convergent information on typhoon hazard areas that can be useful in responding to typhoon situation, we used various types of data such as vector and raster to establish typhoon hazard area small grid-based information. A standardized grid model was applied for compatibility with already produced information and for compatibility of grid information generated by each local government. Result: By applying the grid system of National branch license plates, a grid of typhoon risk areas in Seoul was constructed that can be usefully used when responding to typhoon situations. The grid system of National branch license plates defines the grid size of a multi-dimensional hierarchical structure. And a grid of typhoon risk areas in Seoul was constructed using grids of 100m and 1,000m. Conclusion: Using real-time 5km resolution grid based weather information provided by Korea Meteorological Administration, in the future, it is possible to derive near-future typhoon hazard areas according to typhoon travel route prediction. In addition, the national branch number grid system can be expanded to global grid systems for global response to various disasters.

• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1119-1130
• /
• 2020

Flood disasters have been recently increasing worldwide due to climate change and extreme weather events. Since flood damage recovery has been conducted as a common coping strategy to flood disasters in the Republic of Korea, it is necessary to predict the regional flood damage costs by rainfall characteristics for a preventative measure to flood damage. Therefore, the purpose of this study is to present the regression functions for human and economic flood damage assessments for the 7 metropolises in the Republic of Korea. A comprehensive regression analysis was performed through the total 48 simple regression models on the two types of flood damage records for human and economic costs over the past two decades from 1998 to 2017 using the four kinds of nonlinear equations with each of the six rainfall variables. The damage assessment functions for each metropolis were finally selected by the evaluation of the regression results with the coefficient of determination and the statistical significance test, and then used for the human and economic flood damage assessments for 100-year rainfall in the 7 metropolises. The results of this study are expected to provide the basic information on flood damage cost assessments for flood damage mitigation measures.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1167-1181
• /
• 2021

In relation to the algae bloom, four types of blue-green algae that emit toxic substances are designated and managed as harmful Cyanobacteria, and prediction information using a physical model is being also published. However, as algae are living organisms, it is difficult to predict according to physical dynamics, and not easy to consider the effects of numerous factors such as weather, hydraulic, hydrology, and water quality. Therefore, a lot of researches on algal bloom prediction using machine learning have been recently conducted. In this study, the characteristic importance of water quality factors affecting the occurrence of Cyanobacteria harmful algal blooms (CyanoHABs) were analyzed using the random forest (RF) model for Bohyeonsan Dam and Yeongcheon Dam located in Yeongcheon-si, Gyeongsangbuk-do and also predicted the occurrence of harmful blue-green algae using the machine learning and deep learning models and evaluated their accuracy. The water temperature and total nitrogen (T-N) were found to be high in common, and the occurrence prediction of CyanoHABs using artificial neural network (ANN) also predicted the actual values closely, confirming that it can be used for the reservoirs that require the prediction of harmful cyanobacteria for algal management in the future.

• Membrane Journal
• /
• v.32 no.2
• /
• pp.133-139
• /
• 2022

As the issue of reducing greenhouse gases is emerging due to global warming and extreme weather, research on materials capable of radiative cooling without energy consumption is being actively conducted. Among them, silk is known as a natural self-cooling material, but in the conventional mixing process using chemically powdered silk, there is a problem that the radiative cooling effect disappears by the collapses of the intrinsic crystal structure of silk fibroin, so it is difficult to manufacture it in the form of a film or coating agent for radiative cooling. In this study, various types of membranes were manufactured using silk powder that went through a physical pulverization process that does not damage the intrinsic structure of silk fibroin, and the study was conducted to examine its applicability as a coating agent. Electrospun membranes and flat sheet membranes were prepared by using silk fibroin powder for this purpose, and it was observed that the viscosity of the solution had a significant effect on the membrane fabrication and its properties.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.313-320
• /
• 2022

The light buoy installed on the sea is always flexible, because it is affected by the weather as well as passing vessels. The position of the light buoy can be cached through the AtoN AIS (Automatic Identification System) and RTU (Remote Terminal Unit). This study analyzed the position data of the light buoys for the last five years (2017-2021), as well as the distribution of the light buoys within the maximum separated position. As a result, there was a basic error of 17.9% in the position data. Additionally, the separated position error of 197 light buoys to be analyzed was 70.64%, and the AtoN RTU was worse than the AtoN AIS by equipment. On the other hand, as a result of the plotting the position data of the light buoy, it was classified into four types. The most common percussion center type, the percussion center dichotomous type in which the position is divided into two zones based on the chimney, the central movement type with a fluctuating center, and the drag type, in which the position is deviated from the center for a certain period. Except for Type-1, the type was determined according to the position at which the light buoy was installed. This study is the first to analyze the position data of the light buoy, and it is expected that it will contribute to the improvement of the quality of the position data of the light buoy.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.36 no.5
• /
• pp.383-393
• /
• 1991

Lodging of rice plant is the most important damage by unfavourable weather conditions in rice cultivation. High levels of nitrogen application and growing of Japonica rice variety is one factor to increase the lodging damage. Lodging of rice plant decreasing grain yield; 34% at milky. 21% at dough. 20% at yellow stage. decreasing grain Quality. increasing green rice. and increasing labor cost to harvest. To decrease lodging damage. the lodging resistant varieties will be selected and cultural practices such as amount and time of nitrogen application. planting density. water management. and disease and pest control methods have to be study for the short and strong culm. and good rooting system. Also. application methods such amount and time of plant growth regulators and new types of chemicals will be develop for the reducing lodging of rice plant. To decrease the lodging damage in direct seeding cultivation. first identifying the differences of lodging mechanisms between hand transplanting and direct seeding, second establish the suitable direct seeding methods such as seedling establishement. fertilization. and water menagement.

• Science of Emotion and Sensibility
• /
• v.26 no.2
• /
• pp.129-140
• /
• 2023

Following ISO 20471, in this study, first, two sets of safety clothes and safety vests were made by designing and attaching animal and bird patterns preferred by children to retroreflective films and black fabrics on those fluorescent fabrics and retroreflective materials prescribed by international standards. Second, by mounting a smart photonic device on the safety clothing so that the body can be recognized from a distance even without an ambient light source at night, children can emit three types of light depending on the situation with just one-touch of the button. From a result of comparison with visibility a day and night by dressing a mannequin in the made smart safety clothing, the difference in visibility was evident at night, it was confirmed that we can see the figure of a person even at a distance of approximately 70 m. Therefore, it is expected to contribute to the prevention of traffic and other accidents on the road, as the drivers driving at night or in bad weather can recognize a person from a distance. Third, in case of the energy is exhausted and cannot maintain the stability of the light-emitting function of the optical faber, we can use energy harvesting device, and the light-emitting time will be extended. As a result it comes up to emit light stably for a long time. And this prove that smart photonic safety clothing can also be used for night workers. Therefore, optical fiber safety clothing is expected to be highly wearable not only in real life but also in dark industrial sites due to stable charging by applying the energy harvesting provided by solar cells.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.4
• /
• pp.5-11
• /
• 2023

Impulse waves generated by landslides near water bodies can lead to fatal damage to human life and surrounding infrastructure. These impulse waves are generally called landslide-impulsed waves and occur without being limited to a specific area. Recently, localized torrential rains have frequently occurred due to the influence of abnormal weather, both the frequency and scale of landslides occurring in Korea are increasing. Therefore, in this study, the experiments were conducted according to the mass ratio of the landslide models, and among the characteristics of the generated landslide-impulse waves. And the wave amplitude was observed and analyzed. In this study, a total of 75 experiments were conducted by repeating the experiment 5 times for 15 cases with mass ratios of 5 landslide models and 3 types of slope angles. As a result of experiments with different mass ratios of landslide models, if the landslides have the same initial energy, the size of the landslide-impulse waves generated by mixing granular and block forms is higher than the size of the landslide-impulse waves generated by pure granular and block landslides. It is analyzed that the size may be larger.

• Journal of Navigation and Port Research
• /
• v.47 no.3
• /
• pp.128-133
• /
• 2023

In order for Aids to Navigation to provide sustainable services to users, it is possible when there is no Aids to Navigation accident. If an Aids to Navigation accident occurs, the manager should efficiently manage it to prevent the same accident. However, the current Aids to Navigation accident management only specifies the cause and type of the accident. There are no separate guidelines. Thus, the accident is recorded differently depending on the manager. Therefore, this study attempted to redefine Aids to Navigation accident. To this end, Aids to Navigation accidents that have occurred over the past 23 years (year 2000 to years 2022), IALA's Aids to Navigation information standard, S-201, and categories of accidents (traffic accidents and marine accidents) were analyzed. Causes of Aids to Navigation accidents were divided into internal and external causes. Accidents were divided into three types: Light tower accident, buoy accident, and equipment accident. By further subdividing primary items, the cause of accident was reestablished into 7 items such as mooring and bad weather and 11 items such as Light tower damage, buoy loss, and equipment breakdown. These research results can be used as basic data to provide future Aids to Navigation accident statistics.