• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.377-391
• /
• 2018

In order to efficiently monitor red tide over a wide range, the need for red tide detection using remote sensing is increasing. However, the previous studies focus on the development of red tide detection algorithm for ocean colour sensor. In this study, we propose the use of multi-sensor to improve the inaccuracy for red tide detection and remote sensing data in coastal areas with high turbidity, which are pointed out as limitations of satellite-based red tide monitoring. The study area were selected based on the red tide information provided by National Institute of Fisheries Science, and spatial fusion and spectral-based fusion were attempted using GOCI image as ocean colour sensor and Landsat OLI image as terrestrial sensor. Through spatial fusion of the two images, both the red tide of the coastal area and the outer sea areas, where the quality of Landsat OLI image was low, which were impossible to observe in GOCI images, showed improved detection results. As a result of spectral-based fusion performed by feature-level and rawdata-level, there was no significant difference in red tide distribution patterns derived from the two methods. However, in the feature-level method, the red tide area tends to overestimated as spatial resolution of the image low. As a result of pixel segmentation by linear spectral unmixing method, the difference in the red tide area was found to increase as the number of pixels with low red tide ratio increased. For rawdata-level, Gram-Schmidt sharpening method estimated a somewhat larger area than PC spectral sharpening method, but no significant difference was observed. In this study, it is shown that coastal red tide with high turbidity as well as outer sea areas can be detected through spatial fusion of ocean colour and terrestrial sensor. Also, by presenting various spectral-based fusion methods, more accurate red tide area estimation method is suggested. It is expected that this result will provide more precise detection of red tide around the Korean peninsula and accurate red tide area information needed to determine countermeasure to effectively control red tide.

• Journal of Korea Water Resources Association
• /
• v.40 no.11
• /
• pp.887-898
• /
• 2007

A physically based semi-distributed model, SWAT was applied to the Chungju Dam upstream watershed in order to investigate the spatial and temporal characteristics of watershed sediment yields. For this, general features of the SWAT and sediment simulation algorithm within the model were described briefly, and watershed sediment modeling system was constructed after calibration and validation of parameters related to the runoff and sediment. With this modeling system, temporal and spatial variation of soil loss and sediment yields according to watershed scales, land uses, and reaches was analyzed. Sediment yield rates with drainage areas resulted in $0.5{\sim}0.6ton/ha/yr$ excluding some upstream sub-watersheds and showed around 0.51 ton/ha/yr above the areas of $1,000km^2$. Annual average soil loss according to land use represented the higher values in upland areas, but relatively lower in paddy and forest areas which were similar to the previous results from other researchers. Among the upstream reaches, Pyeongchanggang and Jucheongang showed higher sediment yields which was thought to be caused by larger area and higher fraction of upland than other upstream sub-areas. Monthly sediment yields at the main outlet showed same trend with seasonal rainfall distribution, that is, approximately 62% of annual yield was generated during July to August and the amount was about 208 ton/yr. From the results, we could obtain the uniform value of sediment yield rate and could roughly evaluate the effect of soil loss with land uses, and also could analyze the temporal and spatial characteristics of sediment yields from each reach and monthly variation for the Chungju Dam upstream watershed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.4107-4107
• /
• 2001

Previous works have shown the viability of NIRS technology for the prediction of fatty acids in Iberian pig fat, but although the resulting equations showed high precision, in the predictions of new samples important fluctuations were detected, greater with the time passed from calibration development to NIRS analysis. This fact makes the use of NIRS calibrations in routine analysis difficult. Moreover, this problem only appears in products like fat, that show spectrums with very defined absorption peaks at some wavelengths. This circumstance causes a high sensibility to small changes of the instrument, which are not perceived with the normal checks. To avoid these inconveniences, the software WinISI 1.04 has a mathematic algorithm that consist of create a “Repeatability File”. This file is used during calibration development to minimize the variation sources that can affect the NIRS predictions. The objective of the current work is the evaluation of the use of a repeatability file in quantitative NIRS analysis of Iberian pig fat. A total of 188 samples of Iberian pig fat, produced by COVAP, were used. NIR data were recorded using a FOSS NIRSystems 6500 I spectrophotometer equipped with a spinning module. Samples were analysed by folded transmission, using two sample cells of 0.1mm pathlength and gold surface. High accuracy calibration equations were obtained, without and with repeatability file, to determine the content of six fatty acids: miristic (SECV$\sub$without/=0.07% r$^2$$\sub$without/=0.76 and SECV$\sub$with/=0.08% r$^2$$\sub$with/=0.65), Palmitic (SECV$\sub$without/=0.28 r$^2$$\sub$without/=0.97 and SECV$\sub$with/=0.24% r$^2$$\sub$with/=0.98), palmitoleic (SECV$\sub$without/=0.08 r$^2$$\sub$without/=0.94 and SECV$\sub$with/=0.09% r$^2$$\sub$with/=0.92), Stearic (SECV$\sub$without/=0.27 r$^2$$\sub$without/=0.97 and SECV$\sub$with/=0.29% r$^2$$\sub$with/=0.96), oleic (SECV$\sub$without/=0.20 r$^2$$\sub$without/=0.99 and SECV$\sub$with/=0.20% r$^2$$\sub$with/=0.99) and linoleic (SECV$\sub$without/=0.16 r$^2$$\sub$without/=0.98 and SECV$\sub$with/=0.16% r$^2$$\sub$with/=0.98). The use of a repeatability file like a tool to reduce the variation sources that can disturbed the prediction accuracy was very effective. Although in calibration results the differences are negligible, the effect caused by the repeatability file is appreciated mainly when are predicted new samples that are not in the calibration set and whose spectrum were recorded a long time after the equation development. In this case, bias values corresponding to fatty acids predictions were lower when the repeatability file was used: miristic (bias$\sub$without/=-0.05 and bias$\sub$with/=-0.04), Palmitic (bias$\sub$without/=-0.42 and bias$\sub$with/=-0.11), Palmitoleic (bias$\sub$without/=-0.03 and bias$\sub$with/=0.03), Stearic (bias$\sub$without/=0.47 and bias$\sub$with/=0.28), oleic (bias$\sub$without/=0.14 and bias$\sub$with/=-0.04) and linoleic (bias$\sub$without/=0.25 and bias$\sub$with/=-0.20).

• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.235-243
• /
• 2023

Due to the revision of the River Act and the enactment of the Act on the Investigation, Planning, and Management of Water Resources, a regular bed change survey has become mandatory and a system is being prepared such that local governments can manage water resources in a planned manner. Since the topography of a bed cannot be measured directly, it is indirectly measured via contact-type depth measurements such as level survey or using an echo sounder, which features a low spatial resolution and does not allow continuous surveying owing to constraints in data acquisition. Therefore, a depth measurement method using remote sensing-LiDAR or hyperspectral imaging-has recently been developed, which allows a wider area survey than the contact-type method as it acquires hyperspectral images from a lightweight hyperspectral sensor mounted on a frequently operating drone and by applying the optimal bandwidth ratio search algorithm to estimate the depth. In the existing hyperspectral remote sensing technique, specific physical quantities are analyzed after matching the hyperspectral image acquired by the drone's path to the image of a surface unit. Previous studies focus primarily on the application of this technology to measure the bathymetry of sandy rivers, whereas bed materials are rarely evaluated. In this study, the existing hyperspectral image-based water depth estimation technique is applied to rivers with vegetation, whereas spatio-temporal hyperspectral imaging and cross-sectional hyperspectral imaging are performed for two cases in the same area before and after vegetation is removed. The result shows that the water depth estimation in the absence of vegetation is more accurate, and in the presence of vegetation, the water depth is estimated by recognizing the height of vegetation as the bottom. In addition, highly accurate water depth estimation is achieved not only in conventional cross-sectional hyperspectral imaging, but also in spatio-temporal hyperspectral imaging. As such, the possibility of monitoring bed fluctuations (water depth fluctuation) using spatio-temporal hyperspectral imaging is confirmed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.69-88
• /
• 2022

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.101-114
• /
• 2023

In the wartime, aircraft carrying out a mission to strike the enemy deep in the depth are exposed to the risk of being shoot down. As a key combat force in mordern warfare, it takes a lot of time, effot and national budget to train military flight personnel who operate high-tech weapon systems. Therefore, this study studied the path problem of predicting the route of emergency escape from enemy territory to the target point to avoid obstacles, and through this, the possibility of safe recovery of emergency escape military flight personnel was increased. based problem, transforming the problem into a TSP, VRP, and Dijkstra algorithm, and approaching it with an optimization technique. However, if this problem is approached in a network problem, it is difficult to reflect the dynamic factors and uncertainties of the battlefield environment that military flight personnel in distress will face. So, MDP suitable for modeling dynamic environments was applied and studied. In addition, GIS was used to obtain topographic information data, and in the process of designing the reward structure of MDP, topographic information was reflected in more detail so that the model could be more realistic than previous studies. In this study, value iteration algorithms and deterministic methods were used to derive a path that allows the military flight personnel in distress to move to the shortest distance while making the most of the topographical advantages. In addition, it was intended to add the reality of the model by adding actual topographic information and obstacles that the military flight personnel in distress can meet in the process of escape and escape. Through this, it was possible to predict through which route the military flight personnel would escape and escape in the actual situation. The model presented in this study can be applied to various operational situations through redesign of the reward structure. In actual situations, decision support based on scientific techniques that reflect various factors in predicting the escape route of the military flight personnel in distress and conducting combat search and rescue operations will be possible.

• Informatization Policy
• /
• v.30 no.2
• /
• pp.22-45
• /
• 2023

In research on the use of AI-based voice assistant services, problems related to the user's trust and privacy protection arising from the experience of service use are constantly being raised. The purpose of this study was to investigate empirically the effects of individual trust in AI and online privacy concerns on the continued use of AI-based voice assistants, specifically the impact of their interaction. In this study, question items were constructed based on previous studies, with an online survey conducted among 405 respondents. The effect of the user's trust in AI and privacy concerns on the adoption and continuous use intention of AI-based voice assistant services was analyzed using the Heckman selection model. As the main findings of the study, first, AI-based voice assistant service usage behavior was positively influenced by factors that promote technology acceptance, such as perceived usefulness, perceived ease of use, and social influence. Second, trust in AI had no statistically significant effect on AI-based voice assistant service usage behavior but had a positive effect on continuous use intention. Third, the privacy concern level was confirmed to have the effect of suppressing continuous use intention through interaction with trust in AI. These research results suggest the need to strengthen user experience through user opinion collection and action to improve trust in technology and alleviate users' concerns about privacy as governance for realizing digital government. When introducing artificial intelligence-based policy services, it is necessary to disclose transparently the scope of application of artificial intelligence technology through a public deliberation process, and the development of a system that can track and evaluate privacy issues ex-post and an algorithm that considers privacy protection is required.

• Journal of Distribution Research
• /
• v.16 no.2
• /
• pp.119-138
• /
• 2011

Internet commerce has been growing at a rapid pace for the last decade. Many firms try to reach wider consumer markets by adding the Internet channel to the existing traditional channels. Despite the various benefits of the Internet channel, a significant number of firms failed in managing the new type of channel. Previous studies could not cleary explain these conflicting results associated with the Internet channel. One of the major reasons is most of the previous studies conducted analyses under a specific market condition and claimed that as the impact of Internet channel introduction. Therefore, their results are strongly influenced by the specific market settings. However, firms face various market conditions in the real worlddensity and disutility of using the Internet. The purpose of this study is to investigate the impact of various market environments on a firm's optimal channel strategy by employing a flexible game theory model. We capture various market conditions with consumer density and disutility of using the Internet.