• 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 Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.458-468
• /
• 2019

This research attempted to estimate monthly sales of food and beverage at the passenger terminal of Incheon int'l airport from June of 2015 to December 2020. This paper used ARIMA-Intervention model which can estimate the change of the sales amount suggesting the predicted monthly food and beverage sales revenue. The intervention variable was travel-ban policy against south Korea from P.R. China since July 2016 to December 2017 due to THAAD in south Korea. According to ARIMA, it was found normal predicted sales amount showed the slow growth increase rate until 2020 due to the effect of intervened variable. However, the monthly food sales in July and August 2019 was 20.3 and 21.2 billion KRW respectively. Each amount would increase even more in 2020 and the amount would increase to 21.4 and 22.1 billion KRW. The sales amount in 2019 would be 7.7 and 8.1 billion KRW and climb up 7.9 and 8.2 billion KRW in 2020. It was expected LCC passengers tend to spend more money for F&B at airport due to no meal or drink service of LCC or the paid-in meal and beverage service of LCC. The growth of sales of food and beverate will be accompanied with the growth of LCC according to estimated data.

• Journal of Climate Change Research
• /
• v.3 no.4
• /
• pp.225-234
• /
• 2012

This study analyzes domestic and overseas companies' Scope 3 verification, level of management, source and industry characteristics based on the responses of domestic excellent companies and rated 90 points or more global excellent companies which are included in CDP Korea 200 and CDP Global 500. The result of analysis conveys that global excellent companies' Scope 3 management source achieved the average of 2.7 which is one more than domestic excellent companies', according to the Scope 3 guideline of World Resource Institute and World Business Council of Sustainable Development. For domestic companies are tend to focus on business travel, employee commuting, etc. but didn't manage capital goods, leased assets and investments. Global companies' Scope 3 source is similar to domestic companies but shows more actively managing on investment and use of sold products. It seems that domestic companies should actively develop Scope 3 source especially for the capital related items and respond to the future regulations on inter-enterprise management through the Scope 3.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.867-878
• /
• 2018

As the era of AVs (Automated Vehicles) comes to a close, many researches related to AVs have been conducted. Up until now, research on traffic flow impact of AVs has been the main topic, and research on traffic management for AVs is still in beginning stage. This study analyzed the effect of Dynamic Merge Control (DMC) in manual vehicle (MV) and AV environment at work zone. Dynamic Late Merge (DLM) and DLM with Dynamic Early Merge (DEM) are compared by simulation. Simulation results showed that DLM improves travel time and work zone throughput compared to no merge control case in both MV and AV environment. In the case of additional operation of DEM, the improvement effect was not observed in MV environment, but it was improved in AV environment. As a result, DMC operation in AV environment was as effective as the improvement in transition from MV to AV environment. Therefore congestion reduction at freeway work zone by DMC will be possible in future AV environment, and the improvement of DMC can be suggested.

• Fire Science and Engineering
• /
• v.32 no.6
• /
• pp.46-54
• /
• 2018

A total of 19 elevators for evacuation were installed in the Lotte World Tower and it is planned to operate the shuttle using the manual key from five refuge floors to the 1st floor in an emergency. In the event of a fire or other disaster, it is necessary to conduct intensive analysis to determine how much RSET reduction could be achieved using the evacuation elevator compared to the existing evacuation plans. When the optimal transportation sharing ratio by the evacuation elevators was 40% at the Lotte World Tower, the RSET of the evacuation scenario in parallel with the elevators in the entire building was calculated to be 1 hour and 2 minutes. The RSET of a conventional evacuation scenario (Walking along the stairs without using the elevators) was calculated to be 1 hour 29 minutes, therefore, the former evacuation scenario were found to have a shortening effect of approximately 27 minutes compared to the latter. On the other hand, to maintain this effect, each part of the evacuation route using the elevator must have the capability to protect the evacuee from any hazards caused by fires, such as smoke, flame, and radiant heat during the evacuation. Moreover, the evacuation route should be continuous from the residence position of the elevator user to the final evacuation site, and be recognized easily.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.1
• /
• pp.63-71
• /
• 2019

The two-fluid model proposed by Herman and Prigogine is useful for analyzing macroscopic traffic flow in a network. The two-fluid model is used for analyzing a network through the relationship between the ratio of stopped vehicles and the average moving speed of the network, and the two-fluid model has also been applied in the urban transportation network where many signalized or unsignalized intersections existed. In general, the average travel speed and moving speed of a network decrease, and the ratio of stopped vehicles and low speed vehicles in network increase as the traffic demand increases. This study proposed the two-fluid model considering congested and uncongested traffic situations. The critical velocity and the weight factor for congested situation are calibrated by minimizing the root mean square error (RMSE). The critical speed of the Seoul network was about 34 kph, and the weight factor of the congestion on the network was about 0.61. In the proposed model, $R^2$ increased from 0.78 to 0.99 when compared to the existing model, suggesting that the proposed model can be applied in evaluating network performances or traffic signal operations.

• Journal of the Korea Convergence Society
• /
• v.10 no.7
• /
• pp.133-139
• /
• 2019

This study investigated what type of destination image on Facebook increases positive attitude towards the destination and desire to travel. More specifically, we hypothesized that Facebook user's public self-consciousness will moderate the advertising effect, so we tested the difference in attitude towards the destination and willingness to visit and recommend based on the type of destination image (presence/absence of a tourist in the image) and user's public self-consciousness (high/low). As a result, when a tourist was present in the photo, positive attitude toward destination was higher than when absent. In addition, the high public self-consciousness group showed greater attitude toward destination and higher willingness to visit and recommend than low public self-consciousness group when a tourist was present in the image. However, the low public self-consciousness group showed no difference depending on the presence of a tourist. This research not only is academically significant as it experimentally tested advertising effect depending on type of destination image and Facebook user's public self-consciousness, but also holds practical significance as it suggests advertisement method to consider consumer's predisposition.

• Journal of Oriental Neuropsychiatry
• /
• v.30 no.3
• /
• pp.209-220
• /
• 2019

Objectives: As a general emotion, everyone can temporarily experience depression, but depressive disorder is a disease that excessively affects daily life. Among the various causes of depression, the deficiency of monoamine-based neurotransmitters such as serotonin and epinephrine are considered significant. Thus, antidepressants that target monoamines are used frequently. However, side effects such as nausea, vomiting, insomnia, anxiety, and sexual dysfunction are observed. Thus, it is necessary to develop a new therapeutic agent with fewer side effects. In this study, we investigated the antidepressant effect of JG02, used to treat depression by normalizing the flow of qi (氣) in Korean medicine. Methods: C57BL/6 mice were selected and randomly divided into six groups: normal, control, amitriptyline, and JG02 (50, 125, 250 mg/kg), respectively. Except for normal, depression was induced by applying restraint stress at the same time for six hours daily for 14 consecutive days. Saline, amitriptyline or JG02 samples were orally administered two hours before applying the stress. After that, a forced swimming test and an open field test were performed. Additionally, serum corticosterone, serotonin mRNA, BDNF mRNA, and protein in the hippocampal region were measured and compared. Results: JG02 decreased immobility time rate in the FST and increased the zone transition number and travel distance in the OFT. Also, JG02 inhibited the release of serum corticosterone, and increased serotonin, BDNF gene expression, and BDNF protein in the hippocampus. Conclusions: In this study, JG02 showed significant antidepressant effects on the chronic restraint stress mice model. When further research is performed based on JG02, the development of a new antidepressant is considered highly possible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.1-18
• /
• 2019

A short-turn bus is a bus that is operated within a subsection of an existing bus line. Previous studies regarding short-turn buses decided optimal turn-back points for a single bus line rather than a bus network. Also, in-vehicle crowding which has a significant impact on transit convenience was rarely considered. Therefore, this study aimed to develop a methodology to set priorities for the introduction of short-turn buses of bus lines and sections, considering crowding. To achieve this objective, we calculated occupancies and crowding alleviation benefits of existing bus lines overlapping a new short-turn route based on transit card data, before and after the introduction of short-turn strategy. Also, operator and social costs caused by the introduction of short-turn buses were calculated. Those procedures were iterated over bus lines and sections to operate a short-turn service, and a section whose benefit-to-cost ratio (B/C) is the largest in a line was selected to operate a short-turn service in the line. After, priorities of bus lines to introduce short-turn services could be determined based on B/C values, and the optimum total fleet size could be determined when a short-turn strategy is applied in multiple lines.

• 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.