• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.686-697
• /
• 2018

Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.562-569
• /
• 2019

Raman spectroscopy has been receiving increased attention as a standoff explosive detection technique. In addition, there is a growing need for a fast search method that can identify raman spectrum for measured chemical substances compared to known raman spectra in large database. By far the most simple and widely used method is to calculate and compare the Euclidean distance between the given spectrum and the spectra in a database. But it is non-trivial problem because of the inherent high dimensionality of the data. One of the most serious problems is the high computational complexity of searching for the closet spectra. To overcome this problem, we presented the MPS Sort with Sorted Variance+PDS method for the fast algorithm to search for the closet spectra in the last paper. the proposed algorithm uses two significant features of a vector, mean values and variance, to reject many unlikely spectra and save a great deal of computation time. In this paper, we present two new methods for the fast algorithm to search for the closet spectra. the PCA+PDS algorithm reduces the amount of computation by reducing the dimension of the data through PCA transformation with the same result as the distance calculation using the whole data. the Hierarchical Cluster Tree algorithm makes a binary hierarchical tree using PCA transformed spectra data. then it start searching from the clusters closest to the input spectrum and do not calculate many spectra that can not be candidates, which save a great deal of computation time. As the Experiment results, PCA+PDS shows about 60.06% performance improvement for the MPS Sort with Sorted Variance+PDS. also, Hierarchical Tree shows about 17.74% performance improvement for the PCA+PDS. The results obtained confirm the effectiveness of the proposed algorithm.

• 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 Korean Society of Forest Science
• /
• v.107 no.4
• /
• pp.486-496
• /
• 2018

Pine wilt disease (PWD) in Gyeonggi province was first detected in Gwangju in 2007, and ever since has caused extensive damage. Insect vector and host tree in Gyeonggi province are Monochamus saltuarius and Pinus koraiensis, respectively, which are different from the southern region that consist of Monochamus alternatus and Pinus densiflora. Consequently, spread and mortality characteristics may be different, but our understanding is limited. In this research, we utilized the spatial data of newly infected trees in Gyeonggi province from 2008 to 2015 to analyze how it is related to various environmental and human factors, such as elevation, forest type, and road network. We also analyzed the minimum distance from newly infected tree to last year's closest infected tree to examine the dispersal characteristics based on new outbreak locations. Annual number of newly infected trees rapidly increased from 2008 to 2013, which then stabilized. Number of administrative districts with infected trees was 5 in 2012, 11 in 2013, and 15 in 2014. Most of the infected trees was Pinus koraiensis, with its proportion close to 90% throughout the survey period. Mean distance to newly infected trees dramatically decreased over time, from 4,111 m from 2012 to 2013, to approximately 600 m from 2013 to 2014 and 2014 to 2015. Most new infections occurred in higher elevation over time. Distance to road from newly infected trees continuously increased, suggesting that natural diffusion dispersal is increasingly occurring compared to human-influenced dispersal over time.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.2
• /
• pp.208-225
• /
• 2019

To understand the mean surface circulation and surface currents in the East Sea, trajectories of surface drifters passed through the East Sea from 1991 to 2017 were analyzed. By analyzing the surface drifter trajectory data, the main paths of surface ocean currents were grouped and the variation in each main current path was investigated. The East Korea Warm Current (EKWC) heading northward separates from the coast at $36{\sim}38^{\circ}N$ and flows to the northeast until $131^{\circ}E$. In the middle (from $131^{\circ}E$ to $137^{\circ}E$) of the East Sea, the average latitude of the currents flowing eastward ranges from 36 to $40^{\circ}N$ and the currents meander with large amplitude. When the average latitude of the surface drifter paths was in the north (south) of $37.5^{\circ}N$, the meandering amplitude was about 50 (100) km. The most frequent route of surface drifters in the middle of the East Sea was the path along $37.5-38.5^{\circ}N$. The surface drifters, which were deployed off the coast of Vladivostok in the north of the East Sea, moved to the southwest along the coast and were separated from the coast to flow southeastward along the cyclonic circulation around the Japan Basin. And, then, the drifters moved to the east along $39-40^{\circ}N$. The mean surface current vector and mean speed were calculated in each lattice with $0.25^{\circ}$ grid spacing using the velocity data of surface drifters which passed through each lattice. The current variance ellipses were calculated with $0.5^{\circ}$ grid spacing. Because the path of the EKWC changes every year in the western part of the Ulleung Basin and the current paths in the Yamato Basin keep changing with many eddies, the current variance ellipses are relatively large in these region. We present a schematic map of the East Sea surface current based on the surface drifter data. The significance of this study is that the surface ocean circulation of the East Sea, which has been mainly studied by numerical model simulations and the sea surface height data obtained from satellite altimeters, was analyzed based on in-situ Lagrangian observational current data.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.198-209
• /
• 2021

This study evaluated the effects of the dimensional characteristics of containers on the nitrogen status of Quercus serrata, Fraxinus rhynchophylla, and Zelkova serrata in the container nursery stage. Seedlings were grown using 16 container types [four growing densities (100, 144, 196, and 256 seedlings/m²) × four cavity volumes (220, 300, 380, and 460 cm³/cavity)]. Two-way ANOVA was performed to test the differences in nitrogen concentration and seedling content among container types. Additionally, we performed multiple regression analyses to correlate container dimensions and nitrogen content. Container types had a strong influence on nitrogen concentration and the content of the seedling species, with a significant interaction effect between growing density and cavity volume. Cavity volumes were positively correlated with the nitrogen content of the three seedling species, whereas growing density negatively affected those of F. rhynchophylla. Further, nutrient vector analysis revealed that the seedling nutrient loading capacities of the three species, such as efficiency and accumulation, were altered because of the different fertilization effects by container types. The optimal ranges of container dimension by each tree species, obtained multiple regression analysis with nitrogen content, were found to be approximately 180-210 seedlings/m² and 410-460 cm³/cavity for Q. serrata, 100-120 seedlings/m² and 350-420 cm³/cavity for F. rhynchophylla, and 190-220 seedlings/m² and 380-430 cm³/cavity for Z. serrata. This study suggests that an adequate type of container will improve seedling quality with higher nutrient loading capacity production in nursery stages and increase seedling growth in plantation stages.

• Journal of Korea Water Resources Association
• /
• v.52 no.10
• /
• pp.743-752
• /
• 2019

The flow in the meandering channel is characterized by the spiral motion of secondary currents that typically cause the erosion along the outer bank. Hydraulic structures, such as spur dike and groyne, are commonly installed on the channel bottom near the outer bank to mitigate the strength of secondary currents. This study is to investigate the effects of submerged vanes installed in a $90^{\circ}$ meandering channel on the development of secondary currents through three-dimensional numerical modeling using the hybrid RANS/LES method for turbulence and the volume of fluid method, based on OpenFOAM open source toolbox, for capturing the free surface at the Froude number of 0.43. We employ the second-order-accurate finite volume methods in the space and time for the numerical modeling and compare numerical results with experimental measurements for evaluating the numerical predictions. Numerical results show that the present simulations well reproduce the experimental measurements, in terms of the time-averaged streamwise velocity and secondary velocity vector fields in the bend with submerged vanes. The computed flow fields reveal that the streamwise velocity near the bed along the outer bank at the end section of bend dramatically decrease by one third of mean velocity after the installation of vanes, which support that submerged vanes mitigate the strength of primary secondary flow and are helpful for the channel stability along the outer bank. The flow between the top of vanes and the free surface accelerates and the maximum velocity of free surface flow near the flow impingement along the outer bank increases about 20% due to the installation of submerged vanes. Numerical solutions show the formations of the horseshoe vortices at the front of vanes and the lee wakes behind the vanes, which are responsible for strong local scour around vanes. Additional study on the shapes and arrangement of vanes is required for mitigate the local scour.

• Journal of Korean Society of Forest Science
• /
• v.100 no.3
• /
• pp.352-358
• /
• 2011

Field Cage plots ($1m{\times}1m{\times}1m$) were established (7 units) to find the lowest limit time about the tending of red pine forest (Pinus densiflora) which can no longer be used as a habitat by Monochamus alternatus, vector insect of pine wilt disease at the experimental forest of the southern forest research center of the Korea forest research institute in February in 2010. Thinning slashes (length, 1 m; diameter, 5~10 cm) tended at the different times were put in cages, and 4~6 couples of adult M. alternatus were put into each the cage in June. Presence or absence the larval entrance holes and larval were determined in November in 2010. Incase of the combination 24, 18, 12 and 6-month-old thinning slashes from thinning times to the time of adult emergence inside a single cage, larval entrance holes were found in the 6-month-old and 12-month-old thinning slashes but larvae were found only in the 6-month-old thinning slashes (treatment 1). In case of the combination 24, 18, 15 and 12-month-old thinning slashes inside a single cage, larval entrance holes were found in the 15-month-old and 12-month-old thinning slashes but larvae were found only in the 12-month-old (treatment 2). When 24, 18, 15, 12 and 6-month-old thinning slashes with treated dry and humid condition were put separately inside each cage, larval entrance holes were found in the 18, 15, 12, 6-month-old thinning slashes without the relation of the dry and humid conditions. But larvae were found in the 15, 12, 6-month-old thinning slashes in the dry conditions and only in the 6-month-old thinning slashes in the humid conditions. Results indicated the lowest limit time which can no longer be used as a habitat by M. alternatus is before 24 month from the time of adult emergence.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.17-32
• /
• 2021

Speaker recognition is generally divided into speaker identification and speaker verification. Speaker recognition plays an important function in the automatic voice system, and the importance of speaker recognition technology is becoming more prominent as the recent development of portable devices, voice technology, and audio content fields continue to expand. Previous speaker recognition studies have been conducted with the goal of automatically determining who the speaker is based on voice files and improving accuracy. Speech is an important sociolinguistic subject, and it contains very useful information that reveals the speaker's attitude, conversation intention, and personality, and this can be an important clue to speaker recognition. The final ending used in the speaker's speech determines the type of sentence or has functions and information such as the speaker's intention, psychological attitude, or relationship to the listener. The use of the terminating ending has various probabilities depending on the characteristics of the speaker, so the type and distribution of the terminating ending of a specific unidentified speaker will be helpful in recognizing the speaker. However, there have been few studies that considered speech in the existing text-based speaker recognition, and if speech information is added to the speech signal-based speaker recognition technique, the accuracy of speaker recognition can be further improved. Hence, the purpose of this paper is to propose a novel method using speech style expressed as a sentence-final ending to improve the accuracy of Korean speaker recognition. To this end, a method called sentence sequencing that generates vector values by using the type and frequency of the sentence-final ending appearing in the utterance of a specific person is proposed. To evaluate the performance of the proposed method, learning and performance evaluation were conducted with a actual drama script. The method proposed in this study can be used as a means to improve the performance of Korean speech recognition service.