• Journal of Navigation and Port Research
• /
• v.42 no.6
• /
• pp.539-545
• /
• 2018

In recent years, research on shipping market forecasting with the employment of non-linear AI models has attracted significant interest. In previous studies, input variables were selected with reference to past papers or by relying on the intuitions of the researchers. This paper attempts to address this issue by applying the stepwise regression model and the random forest model to the Cape-size bulk carrier market. The Cape market was selected due to the simplicity of its supply and demand structure. The preliminary selection of the determinants resulted in 16 variables. In the next stage, 8 features from the stepwise regression model and 10 features from the random forest model were screened as important determinants. The chosen variables were used to test both models. Based on the analysis of the models, it was observed that the random forest model outperforms the stepwise regression model. This research is significant because it provides a scientific basis which can be used to find the determinants in shipping market forecasting, and utilize a machine-learning model in the process. The results of this research can be used to enhance the decisions of chartering desks by offering a guideline for market analysis.

• Journal of the Korean Society of Earth Science Education
• /
• v.12 no.1
• /
• pp.27-39
• /
• 2019

The purpose of this study is to develop a STEAM program for teaching climate change through CLAMP (Climate-Leaf Analysis Multivariate Program) paleoclimate inquiry in connection with high school 'Integrated Science' subject. In order to do so, we analyzed the 2015 revised national curriculum and science textbook in terms of the PDIE instructional design model, and developed the teaching-learning materials for 10 class hours through expert panel discussion and pilot test. According to the STEAM class procedure, in the situation presentation stage, the fossil leaves were collected from the dicotyledon plants near school, and the LMA (Leaf Margin Analysis) climate inquiry activity. was presented as the learning goal. During the creative design stage, students were taught about geology and leaf fossils in the study region, and CLAMP input data (31 characteristics of morphotype and leaf architectural of fossil leaves) were given. In the emotional experience and new challenge stage, we collected leaf fossils for outdoor learning, explored paleoclimate with CLAMP method, and promoted climatic literacy in the process of discussing tendencies and causes of Cenozoic's climate change. The validity of the development program was assessed (CVI .84) as being suitable for development purpose in all items through the process of establishing reliability among expert panel. In order to apply the program to the high school, a pilot test was conducted to supplement the discrepancies and to review the suitability. The satisfaction rate of the participants was 4.48, and the program was complemented with their opinions. This study will enable high school students to have practical knowledge and reacting volition for climate change, and contribute to fostering students' climate literacy.

• Journal of Climate Change Research
• /
• v.5 no.1
• /
• pp.21-36
• /
• 2014

Forest ecosystem provides variety goods and services for human being. Unlike goods, forest ecosystem services could not be easily priced by market mechanism. This uncertainty has been caused to conflict in decision-making related forest ecosystem services. Quantification of forest ecosystem services is required to understand the importance of ecosystem services and their contribution to decision-making. As a growing concern of climate change, it is necessary to quantify and calculate carbon storage and sequestration in forest. In this study, for quantifying carbon storage and sequestration, we compared scale, output, input data availability of the models and analyzed the applicability of the models to Korea. The results of this study show that most models are applicable for quantifying carbon storage and sequestration. However, relatively few models are applicable for other regulating services (air quality regulation, flood mitigation, erosion control, water quality, etc.) of forest. This study would be helpful for quantifying regulating services of forest ecosystem research.

• International Area Studies Review
• /
• v.22 no.2
• /
• pp.61-91
• /
• 2018

Credit Guarantee scheme is one of the most effective tools for the small business policy. The performance analysis on domestic institution level is relevant in terms of various factors of assisting tools factor. This study measured comparative global efficiency by DEA model and Super-efficiency model among 70 credit guarantee institutions in Japan, Taiwan, and Korea who are operating the schemes. At the result of the analysis, Korean credit guarantee institutions are comparatively efficient than Japanese institutions, and the DMU shows moderate in operation efficiency. The Super-efficiency ranked by Hiroshima, Taiwan SMEG, Pusan, Chiba, Shizuoka, Ulsan, and KOTEC. Most of the Credit Guarantee Institutions showed increasing returns to scale, and it indicates increasing input strategy. The statistical difference of efficiency level in Japan and Korea shows very meaning numbers. This research suggest that (1)Periodical Analysis are needed on Japanese Schemes, (2)The analysis on the impact of credit guarantee scale to the national economy and SME policy, (3) Analysis on the conclusive factors of the efficiency, (4)The policy direction has to be made by inefficient factor analysis, (5) The measurement tools of efficiency of the schemes in various aspects.

• Journal of Korea Water Resources Association
• /
• v.51 no.spc
• /
• pp.1135-1148
• /
• 2018

Previous studies on reservoir operation have been assumed that the climate in the future would be similar to that in the past. However, in the presence of climate non-stationarity, Robust Optimization (RO) which finds the feasible solutions under broader uncertainty is necessary. RO improves the existing optimization method by adding a robust term to the objective function that controls the uncertainty inherent due to input data instability. This study proposed Robust-SDP that combines Stochastic Dynamic Programming (SDP) and RO to estimate dam operation rules while coping with climate non-stationarity. The future inflow series that reflect climate non-stationarity were synthetically generated. We then evaluated the capacity of the dam operation rules obtained from the past inflow series based on six evaluation indicators and two decision support schemes. Although Robust-SDP was successful in reducing the incidence of extreme water scarcity events under climate non-stationarity, there was a trade-off between the number of extreme water scarcity events and the water scarcity ratio. Thus, it is proposed that decision-makers choose their optimal rules in reference to the evaluation results and decision support illustrations.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.161-170
• /
• 2019

Multi-product mass production small and medium enterprise factories have a wide variety of products and a large number of products, wasting manpower and expenses for inventory management. In addition, there is no way to check the status of inventory in real time, and it is suffering economic damage due to excess inventory and shortage of stock. There are many ways to build a real-time data collection environment, but most of them are difficult to afford for small and medium-sized companies. Therefore, smart factories of small and medium enterprises are faced with difficult reality and it is hard to find appropriate countermeasures. In this paper, we implemented the contents of extension of existing inventory management method through character extraction on label with barcode and QR code, which are widely adopted as current product management technology, and evaluated the effect. Technically, through preprocessing using OpenCV for automatic recognition and classification of stock labels and barcodes, which is a method for managing input and output of existing products through computer image processing, and OCR (Optical Character Recognition) function of Google vision API. And it is designed to recognize the barcode through Zbar. We propose a method to manage inventory by real-time image recognition through Raspberry Pi without using expensive equipment.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.8
• /
• pp.783-790
• /
• 2019

Cognitive science attempts to explain human intelligence on the basis of success of artificial neural network, which is called connectionism. The neural network, e.g., deep learning, seemingly promises connectionism to go beyond what it is. But those(Fodor & Pylyshyn, Fodor, & McLaughlin) who advocate classical computationalism, or symbolism claim that connectionism must fail since it cannot represent the relation between human thoughts and human language. The neural network lacks systematicity, so any output of neural network is at best association or accidental combination of data plugged in input units. In this paper, I first introduce structure of artificial neural network and what connectionism amounts to. Second, I shed light on the problem of systematicity the classical computationalists pose for the connectionists. Third, I briefly introduce how those who advocate connectionism respond to the criticism while noticing Smolensky's theory of vector product. Finally, I examine the debate of computationalism and connectionism on systematicity, and show how the problem of systematicity contributes to the development of connectionism and computationalism both.

• Journal of the Korean Society of Radiology
• /
• v.14 no.7
• /
• pp.991-1001
• /
• 2020

Supervised deep learning technologies for improving the image quality of computed tomography (CT) need a lot of training data. When input images have different characteristics with training images, the technologies cause structural distortion in output images. In this study, an imaging model based on the deep reinforcement learning (DRL) was developed for overcoming the drawbacks of the supervised deep learning technologies and reducing noise in CT images. The DRL model was consisted of shared, value and policy networks, and the networks included convolutional layers, rectified linear unit (ReLU), dilation factors and gate rotation unit (GRU) in order to extract noise features from CT images and improve the performance of the DRL model. Also, the quality of the CT images obtained by using the DRL model was compared to that obtained by using the supervised deep learning model. The results showed that the image accuracy for the DRL model was higher than that for the supervised deep learning model, and the image noise for the DRL model was smaller than that for the supervised deep learning model. Also, the DRL model reduced the noise of the CT images, which had different characteristics with training images. Therefore, the DRL model is able to reduce image noise as well as maintain the structural information of CT images.