• 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 Navigation and Port Research
• /
• v.42 no.6
• /
• pp.395-405
• /
• 2018

Seakeeping safety module in Korean e-Navigation system is one of the ship remote monitoring services that is employed to ensure the safety of ships by monitoring the ship's real time performance and providing a warning in advance when the abnormal conditions are encountered in seakeeping performance. In general, seakeeping performance has been evaluated by simulating ship motion analysis under specific conditions for its design. However, due to restriction of computation time, it is not realistic to perform simulations to evaluate seakeeping performance under real-time operation conditions. This study aims to introduce a reasonable and faster method to predict a ship's roll motion which is one of the factors used to evaluate a ship's seakeeping performance by using a machine learning-based surrogate model. Through the application of various learning techniques and sampling conditions on training data, it was observed that the difference of roll motion between a given surrogate model and motion analysis was within 1%. Therefore, it can be concluded that this method can be useful to evaluate the seakeeping performance of a ship in real-time operation.

• 한국노년학
• /
• v.37 no.1
• /
• pp.125-149
• /
• 2017

The purpose of this study is to analyse the mediating effects of spirituality on the relationship between functional capacity and depression among the elderly. The conceptual framework was based on the integrated theory by Brief et al.(1993) to life satisfaction. The sample was collected through convenience sampling of 413 elderly persons who were 65 years of age or older drawn from senior welfare centers, community senior centers, and religious institutions in Seoul, Incheon, and Gyeonggi Province. Data analysis was performed using Structural Equation Modeling(SEM). The main findings of the present study are as following: First, spirituality had the mediated effects on which depression and IADL influenced life satisfaction. Particularly, existential spirituality on life satisfaction had larger effect size than religious spirituality. Second, the results showed that religious spirituality had positive effects on existential spirituality. These findings demonstrate that the development and implementation of programs geared for fostering religious spirituality and existential spirituality of senior citizens are needed to improve life satisfaction in the field of social welfare. To this end, the foundation of spiritual practice in the field of social work with older people should be constructed through a spirituality-related system and professional training.

• 재활복지
• /
• v.21 no.2
• /
• pp.63-88
• /
• 2017

This study evaluated the actual status of special needs of the hearing-impaired person for disaster response. The analysis revealed a significant level of unmet needs in disaster response for hearing-impaired person. The 5 special needs in disaster response include: 1) communication needs, which involve securing the means to make an emergency rescue request and communicating information during the rescue process; 2) transportation needs, which indicate the effective evacuation capacity and the level of training; 3) medical needs, which address the degree of preparedness for physical and mental emergency measures and the delivery of health information for rescue and first aid process; 4) maintaining functional independence needs, which refer to the level of self-preparedness to minimize damage in disaster situations, and; 5) supervision needs, which correspond to a personalized support system provided to disaster-vulnerable groups.

• Journal of the Korean Regional Science Association
• /
• v.34 no.4
• /
• pp.3-18
• /
• 2018

These days, regional innovation draws more attention than ever as a growth engine for regional economies, and governments put a variety of efforts to establish Regional Innovation systems(RISs). In this circumstance, this study aims to analyze types of RISs and the combinations of the factors influencing innovation performance as measured by patent application. Most of previous works have depended on case-oriented or variable-oriented strategy to classify types of RISs or to analyze the effects on performance of innovation factors, having some limitations: Variable-oriented approaches fail to capture complex combinatory effects of factors, while case-oriented approaches tend to depend on subjective interpretation. This study made use of the recently proposed fs/QCA(Fuzzy-set Qualitative Comparative Analysis) to overcome the limitations of those strategies. Based on the theory of RIS, three factors for regional innovation-input, infrastructure, and network-are used to classify 16 Korean Provinces. The results show that eight types of regional innovation types are identified, and that most of the regions are classified into either IN-type, equipped with high levels of Input and Network, or F-type, with high levels of infrastructure. In addition, applying seven sub-variables of the three factors to the fussy-set combination factor analysis, we examine a combination of factors influencing patent application. The results show that regions with high levels of R&D expense, valid patent, industry-academia cooperation, IP budget, and TLO values, and low IP capital almost always have a high level of patent application. Therefore, for regional innovation, the public sector needs to provide institutional support for R & D personnel training. It is also important to for both the public and the private sectors to make efforts to stimulate IP financing.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.6
• /
• pp.39-48
• /
• 2018

Despite the fact that Daejeon has excellent technology infrastructures such as government-funded research institutes, Daedeok Innopolis, and KAIST, the infrastructure for initial investment and growth support for technological start-ups is not sufficient. In particular, the amount of venture capital supply in Daejeon is relatively low compared to other innovation infrastructures. The purpose of this study is to suggest the implications of the venture capital ecosystem in Daejeon area through the analysis of what evolution process has been undergoing and what improvements and complementary points are needed in the future. First, the role of public finance system should be strengthened in order to stimulate angel investment and private capital inflows to start-up companies. Second, in order to cultivate investment professionals in the region, it is necessary to grant local funds to local institutions, and to run investment expert training courses in universities. Third, cooperation between related agencies is needed to add accelerator functions to existing incubators and to foster new accelerators. Fourth, in order to expand the role of local governments, it is necessary to establish funds, to open innovation mindset of public officials, and to communicate effectively with the central government. Fifth, basic venture ecosystem infrastructures such as inflow of excellent manpower, prevention of technology deception, improvement of rechallenge environment should be expanded. Sixth, it is necessary to reorganize the step-by-step start-up financing policy of 'Establishment - Growth - Exit - Rechallenge'. This study is meaningful in that it has grasped the current status of venture start-up financial ecosystem in Daejeon, which is changing rapidly. In particular, it is different in that it identifies financial difficulties venture companies in Daejeon and finds ways to utilize existing financial ecosystem efficiently.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.299-316
• /
• 2019

The purpose of this study was to analyze landslide susceptibility in the Pyeongchang area using Weight of Evidence (WOE) and Evidential Belief Function (EBF) as probability models and Artificial Neural Networks (ANN) as a machine learning model in a geographic information system (GIS). This study examined the widespread shallow landslides triggered by heavy rainfall during Typhoon Ewiniar in 2006, which caused serious property damage and significant loss of life. For the landslide susceptibility mapping, 3,955 landslide occurrences were detected using aerial photographs, and environmental spatial data such as terrain, geology, soil, forest, and land use were collected and constructed in a spatial database. Seventeen factors that could affect landsliding were extracted from the spatial database. All landslides were randomly separated into two datasets, a training set (50%) and validation set (50%), to establish and validate the EBF, WOE, and ANN models. According to the validation results of the area under the curve (AUC) method, the accuracy was 74.73%, 75.03%, and 70.87% for WOE, EBF, and ANN, respectively. The EBF model had the highest accuracy. However, all models had predictive accuracy exceeding 70%, the level that is effective for landslide susceptibility mapping. These models can be applied to predict landslide susceptibility in an area where landslides have not occurred previously based on the relationships between landslide and environmental factors. This susceptibility map can help reduce landslide risk, provide guidance for policy and land use development, and save time and expense for landslide hazard prevention. In the future, more generalized models should be developed by applying landslide susceptibility mapping in various areas.

• Journal of the Korean Institute of Gas
• /
• v.22 no.6
• /
• pp.90-103
• /
• 2018

This paper presents the development of two ANN models which can predict an optimum production rate by controlling choke size in oil well, and gas injection rate in gas-lift well. The input data was solution gas-oil ratio, water cut, reservoir pressure, and choke size or gas injection rate. The output data was wellhead pressure and production rate. Firstly, a range of each parameters was decided by conducting sensitive analysis of input data for onshore oil well. In addition, 1,715 sets training data for choke size decision model and 1,225 sets for gas injection rate decision model were generated by nodal analysis. From the results of comparing between the nodal analysis and the ANN on the same reservoir system showed that the correlation factors were very high(>0.99). Mean absolute error of wellhead pressure and oil production rate was 0.55%, 1.05% with the choke size model, respectively. And the gas injection rate model showed the errors of 1.23%, 2.67%. It was found that the developed models had been highly accurate.

• Journal of The Korean Association For Science Education
• /
• v.39 no.1
• /
• pp.73-88
• /
• 2019

The purpose of this study is to explore elementary teachers' difficulties on teaching science by analyzing questions that have been posted for a long time in an autonomous online teacher community named Indischool. For this purpose, 409 question postings(the 2007 and 2009 revised curriculum, third to sixth grade) were analyzed using the framework for analyzing questions about elementary teachers' science teaching(modified from Alake-Tuenter et al., 2013). The study revealed that there were more science-SMK questions than science-PCK questions, and most of the questions were 'about lenses' and 'in 2014 and 2015, when the curriculum was changing from the 2007 to the 2009 revised curriculum'. The long-standing difficulties in science-SMK were 'an application of facts and concepts in lenses' and 'an unexpected experimental error in electricity'. In particular, there are the principle of transparent cup-shaped objects acting as lenses, the process of image formation by convex lenses, experimental errors of 'compass movement due to current flow change' and experimental errors 'serial connection of bulbs'. The long-standing difficulties in science-PCK were 'understanding and response to context' and 'understanding and response to aims mentioned in standard document' and these are not related to physical units but to others. In particular, there are request class materials, activity ideas at the end of the semester and understanding the national curriculum guidelines. These teachers' difficulties should be reflected in the science teaching support system like a teacher's guide compilation, teacher's training curriculum development, etc.

• Journal of The Korean Association For Science Education
• /
• v.39 no.2
• /
• pp.233-248
• /
• 2019

This study shows that the Argovian Cantonal School in Aarau, Switzerland, which Albert Einstein attended from 1895 to 1896, had been closely related to the ideological education controversy in German Gymnasium throughout the 19th century. Due to this controversy, Einstein hardly received a formal science education in Bavaria. Despite the lack of formal education in Germany, he had a habit of self-studying from an early age and continued with this practice all through his life. He had a hard time at the authoritarian school in Munich, but at the democratic school in Aarau, where freedom and autonomy were secured, he was able to achieve emotional stability. For a long time, the city Aarau prevailed as a location of tolerance and multi-culturalism, without religious, regional, and national discrimination. This was possible due to the influence of external and unrestricted social mobility, as well as the Enlightenment from France. As a result, this small public school was able to acquire a mass of qualified human resources from outside of Switzerland. As a consequence of the controversy regarding the educational ideology, the Cantonal School adopted practical thoughts and the Enlightenment that fit the spirit of the times. The school consisted of two independent educational organizations: the Gymnasium, where the 'neuhumanistsch' education for the elite training was conducted, and the 'Gewerbeschule', where a more realistic education system was set up to suit the citizen life. In particular, after 1835, the Gymnasium changed gradually from the pure humanistic education to the 'utraquistisch' ways by introducing practical subjects such as natural history. Thereafter, the Cantonal School became an institution that was able to achieve a genuine humanity, academic, and civic life education. Einstein, who attended the 'technische Abteilung' of the 'Gewerbeschule,' considered this school as a role model of an institution that realized true democracy, and that left an unforgettable impression on him.