• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.

• Journal of Korean Neurosurgical Society
• /
• v.61 no.6
• /
• pp.761-766
• /
• 2018

Objective : Chronic subdural hematoma (CSDH) is a rare complication of unruptured intracranial aneurysm (UIA) clipping surgery. To prevent postoperative CSDH by reducing subdural fluid collection, we applied the modified arachnoid plasty (MAP) during the UIA clipping surgery to seal the dissected arachnoid plane. Methods : This retrospective study included 286 patients enrolled from July 2012 to May 2015. We performed arachnoid plasty in all patients, with MAP used after June 17, 2014. Patients were divided into two groups (non-MAP vs. MAP), and by using uni- and multivariate analyses, baseline characteristics, and relationships with postoperative CSDH between the two groups were analyzed. The degree of preoperative brain atrophy was estimated using the bicaudate ratio (BCR) index. Results : Ten patients (3.5%) among 286 patients had postoperative CSDH after clipping. Nine (3.1%) were in the non-MAP group, and one (0.9%) was in the MAP group. The higher BCR index showed statistical significance with occurrence of postoperative CSDH in both uni- (p=0.018) and multivariate (p=0.012; odds ratio [OR], 8.547; 95% confidence interval [CI], 1.616-45.455) analyses. MAP was associated with a lower risk of postoperative CSDH (p=0.022; OR, 0.068; 95% CI, 0.007-0.683). Conclusion : This study shows that the degree of preoperative brain atrophy is associated with an increased occurrence of CSDH after clipping and that MAP could help reduce the risk of postoperative CSDH after unruptured aneurysm clipping via a lateral supraorbital approach.

• Bulletin of the Korean Mathematical Society
• /
• v.35 no.3
• /
• pp.533-545
• /
• 1998

In this paper, we prove the existence of solutions of the heat equation for harmonic map on a compact manifold with a boundary when the target manifold is allowed to have positively curved parts.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.459-470
• /
• 2012

In this paper, we propose a method to upsample a low-resolution depth map to a high-resolution version. While conventional camera sensors produce high-resolution color images, the sizes of the depth maps of range/depth sensors are usually low. In this paper, we consider the utilization of high-frequency components to the conventional depth map interpolation methods such as bilinear, bicubic, and bilateral. The proposed method is composed of the three steps: high-frequency component extraction, high-frequency component application, and interpolation. Two objective evaluation measures such as sharpness degree and blur metric are used to examine the performance. Experimental results show that the proposed method significantly outperforms other conventional methods by a factor of 2 in terms of sharpness degree. As well, a blur metric is reduced by a factor of 14 %.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.03a
• /
• pp.87-92
• /
• 2002

Engineering geological studies were conducted for igneous rocks in southeast Korean peninsula. The purpose of the study is to establish zoning in view of engineering geology in ground construction. For engineering geological implication, lithology, lineament structure and discontinuities were surveyed and analysed. Using constructed data, We compared geological and engineering geological characteristics and made out the detailed engineering geological map. The map responses engineering characteristics such as weathering degrees, discontinuity systems of different rock types.

• The Korean Journal of Ecology
• /
• v.26 no.1
• /
• pp.19-22
• /
• 2003

In order to determine the degree of anthropogenic disturbance potentiality (ADP) of the area a rapid ecoassessment technique was developed on the basis of actual vegetation map. ADP degree of relevant unit cell was computed by using four criteria of land use patterns such as forested area, open water and stream, agricultural area, and urbanized area. Ultimate ADP degree of each cell was obtained by means of direct and indirect computation process. Finally the map of ADP was drawn and analyzed. Vulnerable cell and disturbance nuclei were determined according to disturbance vector which is a kind of potential disturbance pressure of relevant cell influenced by surrounding cell. A case study was accomplished in the Gijang area of Pusan metropolitan city. 973 meshes (500m×500m) were analyzed and a total of 79 meshes were currently threatened. Present technique of rapid ecoassessment was practically useful for diagnosing and planning land use.

• The Journal of Korea Robotics Society
• /
• v.6 no.1
• /
• pp.42-48
• /
• 2011

It is very important for a mobile robot to recognize and model its environments for navigation. However, the grid map constructed by sonar sensors cannot accurately represent the environment, especially the narrow environment, due to the angular uncertainty of sonar data. Therefore, we propose a map building scheme which combines sonar sensors and IR sensors. The maps built by sonar sensors and IR sensors are combined with different weights which are determined by the degree of translational and rotational motion of a robot. To increase the effectiveness of sensor fusion, we also propose optimal sensor arrangement through various experiments. The experimental results show that the proposed method can represent the environment such as narrow corridor and open door more accurately than conventional sonar sensor-based map building methods.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.15 no.2
• /
• pp.31-40
• /
• 2012

The Environmental Conservation Value Assessment Map (ECVAM) is a five grade assessment map created with nationally integrated environmental information and environmental values. The map is made through the evaluation of 65 items, including greenbelt area and naturalness. Naturalness means original state of nature, and it is one of the most important evaluation items for conserving nature. The criteria of naturalness includes the Degree of Green Naturality (DGN) made by MOE. Using the data which has been not updated is a problem of accuracy for ECVAM. Therefore, this study would like to improve the criteria of naturalness. To improve the criteria, the study examined the effectiveness of DGN using field survey. The results of analysis the naturalness without DGN, some area changed grade of naturalness have been already damaged or cleared for agriculture and industrial purposes. The grade of naturalness should be included the concept of vegetation transition like DGN. The study suggested a improved method using vegetation type (natural and planted forest), forest age, and the grade of vegetation conservation. The method was reviewed by experts and field survey. After applying the method in South Korea, the grade of naturalness were distributed evenly like GradeI is 38.87%, GradeII is 37.62%, GradeIII is 23.51%, respectively. From the results of field survey, over 4 grade of forest age in natural forest showed similar pattern of structure and composition in original forests. Therefore, the improved criteria explained the naturalness better than existing criteria, and the accuracy of ECVAM has been improved more.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 1998.11a
• /
• pp.34-36
• /
• 1998

In Korea, the initial installation of GIS requires lots of cost, time, and human efforts, If the accuracy of GIS data does not meet the certain standard for use, the system may not work as expected. So, it needs to be investigated for the accuracy of raw data. However, there is little study for the accuracy of raw data in Korea. Therefore, the purpose of this study is to review the data accuracy of raw data - geologic map, 1:5,000 and 1:25,000 scale topographic map, forest stand map, degree of green naturality(DGN) map, and detailed survey data of DGN map - for fulfilling the expected use in Korea. After this study, some errors in data were surveyed and following conclusions were derived. (1) There is a lack of data, e. g, wildlife habitat map. (2) Some data are misinterpreted depending on the location in the geologic map. (3) Some data are not updated after change of topography in the topographic map. (4) Some data are not edited properly in the forest stand map. (4) DGN classification system does not reflect the characteristic of Korean vegetation community. So, it needs to be refined and restructured.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.1129-1133
• /
• 2007

Assessment of noise exposed population is a method for checking the degree of environmental noise and social influence in order to reduce the risks such as annoyance and disturbance that are generated by environmental noise. Also, this method suggests the preferential noise reduction policy and action plan by accurately assessing the area that noise causes harm to human health. Recently, a noise map, which can predict noise in comprehensive areas, is used for the assessment of noise exposed population, breaking from the methods using existing measures. In particular, countermeasure for the noise can be considered more effectively by using assessment methods of noise exposed population for specific noise levels, areas, and building types which are the main input factors in noise maps. In this study, Assessment methods of noise exposed population by using 2D noise map are compared with those by 3D noise map.