• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3B
• /
• pp.279-289
• /
• 2006

The reconstruction of low dimension nonlinear behavior from the hydrologic time series has been an active area of research in the last decade. In this study, we present the applications of a powerful state space reconstruction methodology using the method of Support Vector Machines (SVM) to the Great Salt Lake (GSL) volume. SVMs are machine learning systems that use a hypothesis space of linear functions in a Kernel induced higher dimensional feature space. SVMs are optimized by minimizing a bound on a generalized error (risk) measure, rather than just the mean square error over a training set. The utility of this SVM regression approach is demonstrated through applications to the short term forecasts of the biweekly GSL volume. The SVM based reconstruction is used to develop time series forecasts for multiple lead times ranging from the period of two weeks to several months. The reliability of the algorithm in learning and forecasting the dynamics is tested using split sample sensitivity analyses, with a particular interest in forecasting extreme states. Unlike previously reported methodologies, SVMs are able to extract the dynamics using only a few past observed data points (Support Vectors, SV) out of the training examples. Considering statistical measures, the prediction model based on SVM demonstrated encouraging and promising results in a short-term prediction. Thus, the SVM method presented in this study suggests a competitive methodology for the forecast of hydrologic time series.

• Transactions of Materials Processing
• /
• v.30 no.4
• /
• pp.172-178
• /
• 2021

The cold forging process induces material deformation in an enclosed space, generating a very high forging load. Therefore, it is mainly designed as a multi-stage process, and fatigue failure occurs in forging die due to cyclic load. Studies have been conducted previously to quantitatively predict the fatigue limit of cold forging dies, however, there was a limit to field application due to the large error range and the need for expert intervention. To solve this problem, we conducted a study on the introduction of a real-time forging load measurement technology and an automated system for quantitative prediction of die life cycle. As a result, it was possible to reduce the error range of the quantitative prediction of die life cycle to within ±7%, and it became possible to use the die life cycle calculation algorithm into an automated system.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.857-870
• /
• 2017

The use of shield TBM is gradually increasing due to the urbanization of social infrastructures. Reliable estimation of advance rate is very important for accurate construction period and cost. For this purpose, it is required to develop the prediction model of advance rate that can consider the ground properties reasonably. Based on the database collected from field, statistical prediction procedure for field penetration index (FPI) was modularized in this study to calculate penetration rate of shield TBM. As output parameter, FPI was selected and various systems were included in this module such as, procedure of eliminating abnormal dataset, preprocessing of dataset and ridge regression with best subset selection. And it was finally validated by using field dataset.

• Journal of the Korean Institute of Landscape Architecture International Edition
• /
• no.1
• /
• pp.59-66
• /
• 2001

The tremendous growth of population and physical development in the largest urban agglomeration in Indonesia -the Jakarta Metropolitan Region, also known as Jabotabek (Jakarta, Bogor, Tanggerang, Bekasi)- has created many environmental problems, such as land use conversion, increasing urban temperature, water and air pollution, intrusion of seawater, and flooding. These problems have become more serious as the urban green space (trees, shrubs, and groundcovers) has decreased rapidly with the urbanization process. Urban green space directly benefits the urban environment through ameliorating air pollution, controlling temperature, contributing to the balance of the hydrological system, and providing space for recreation and relaxation. Because there is little hard data to support the claim of decreasing greenery in Jabotabek, it is necessary to measure the amount of urban green space. The paper describes the spatial analysis of urban green space within Jabotabek through the use of a geographical information system (GIS). We used GIS and remote sensing to determine land cover change and predicted greenery percentage. Interpretation of Landsat data for 1972, 1983, 1990, and 1997 showed that Jabotabek has experiences rapid development and associated depletion of green open space. The proportion of green open space fell by 23% from 1972 to 1997. We found a low percentage of urban green space in the center of Jakarta but a high percentage in fringe area. The amount of greenery is predicted by the Ratio Vegetation Index (RVI) model: predicted greenery (%) = [146.04] RVI - 134.96. We consider that our result will be useful for landscape planning to improve the environment of Jabotabek.

• International Journal of Aeronautical and Space Sciences
• /
• v.10 no.1
• /
• pp.98-103
• /
• 2009

The forecasting, mitigation and preparedness of the natural disaster impacts require relevant information regarding the disaster desirable in real time. In the meantime it is requiring the rapid and continuous data and information generation or gathering for possible prediction and monitoring of the natural disaster. Since disasters that cause huge social and economic disruptions normally affect large areas or territories and are linked to global change. The use of traditional and conventional methods for management of the natural disaster impact can not be effectively implemented for intial data col1ection with the further processing. The space technology or remote sensing tools offer excellent possibilities of collecting vital data. The main reason is capability of this technology of collecting data at global and regional scales rapidly and repetitively. This is unchallenged advantage of the space methods and technology. The satellite or remote sensing techniques can be used to monitor the current situation, the situation before based on the data in sight. as well as after disaster occurred. They can be used to provide baseline data against which future changes can be compared while the GIS techniques provide a suitable framework for integrating and analyzing the many types of data sources required for disaster monitoring. Developed GIS is an excellent instrument for definition of the social impact status of the natural disaster which can be undertaken in the future database developments. This methodology is a good source for analysis and dynamic change studies of the natural disaster impacts.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.3
• /
• pp.3-12
• /
• 2019

Since offline contact becomes a strong differentiator as online market expands, the shopping mall calls for more complex and diverse tenant combinations and deployment plan strategies. There is, however, few practical research and causal verification of Tenant Mix, i.e., the combination and placement of tenant and users' behavior, has been conducted which is a key factor in spatial configuration. In practice, Tenant Mix is limited in prediction of consumption behavior of customers by the MD planners's experience and depends only on qualitative arbitrary plan. The purpose of this study is to find out the interrelationship between the spatial configuration and the users' behavior of Tenant Mix in shopping mall, and to present an objective basis in MD planning. According to the analysis, it was possible to know that there are differences in the relationship between the spatial configuration and the users' behavior dependent on the Tenant Mix, which is the space planning of shopping mall. It was also possible to find out the characteristics and differences in the users' behavior which is dependent on the spatial configuration for each tenant. Through this study, it was possible to know the impact of space organization on the users' behavior and the interrelationship between the use's behavior and spatial configuration by tenant together with their characteristics. We prove that the current MD planning has limitation due to lack of objective research on the combination and arrangement of space in the commercial space and only done empirically. This analysis can show the practical plan of combination and placement of tenant which is emphasized in complex and larger shopping malls, and contribute to the revitalization of shopping mall by better use of tenant.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.734-735
• /
• 2015

Currently, effective energy management of buildings is necessary because of accelerated global climate change and resource crisis. Especially, in the case of South Korea, city gas consumption occupies 11.8% of the total energy and 39.6% is residential use among them. Therefore, for reducing the city gas consumption, the effectiveness of residential use is needed. To address this issue, the objective of this study is to analyze the difference of the city gas consumption according to the space arrangement in the apartment building. To achieve this objective, an apartment complex having over 1,000 households was selected then, according to the space arrangement such as south-east and south-west, the data of 59.97m2 and 84.96m2 were analyzed by using statistics method. As a result, in 59.97m2 and 84.96m2, the total city gas amount in 2012 showed that 9.2% and 8.4% were more increased at south-west than southeast respectively. In the future, the findings of this study can be used to develop the prediction model of city gas consumption in apartment building.

• Information and Communications Magazine
• /
• v.15 no.9
• /
• pp.97-106
• /
• 1998

It is crucial to predict the variabilities of the near-earth space environment associated with the solar activity, which cause enormous socio-economic impacts on mankind. The geomagnetic storm prediction scheme adopted in this study is designed to predict such variabilities in terms of the geomagnetic indices, AE and Dst, the cross-polar cap potential difference, the energy dissipation rate over the polar ionosphere and associated temperature increase in the thermosphere. The prediction code consists of two parts; prediction of the solar wind and interplanetary magnetic field based upon actual flare observations and estimation of various electrodynamic quantities mentioned above from the solar wind-magnetosphere coupling function 'epsilon' which is derivable through the predicted solar wind parameters. As a test run, the magnetic storm that occurred in early November, 1993, is simulated and the results are compared with the solar wind and the interplanetary magnetic field measured by the Japanese satellite, Geotail, and the geomagnetic indices obtained from ground magnetic observatories. Although numerous aspects of the code are to be further improved, the comparison between the simulated results and the actual measurements encourages us to use this prediction scheme as the first appoximation in forecasting the disturbances of the near-earth space environment associated with solar flares.

• KIEAE Journal
• /
• v.10 no.1
• /
• pp.65-72
• /
• 2010

The use of natural light has the potential for improving both the energy efficiency and indoor environmental quality in buildings. A light-pipe system can introduce daylight to spaces that would otherwise not be able to benefit from the advantages of daylight penetration. For the light-pipe system to be widely used in Korea, it is important to quantify its daylighting performance with due consideration regarding the effects imposed by the local climate conditions. This paper presents the evaluation results of existing semi-empirical models to predict daylighting performance of a light-pipe system. The evaluation of the existing models was based on the monitoring data obtained from a underground parking lot in which the light-pipe system was installed. Comparisons were made between the predicted and the monitored data obtained from the study. The results indicated that semi-empirical models which was developed using the experimental data obtained under the Korean climatic conditions had a good prediction performance. We also quantified the effects caused by sky conditions, solar altitudes, room dimensions, and the aspect ratio of a light-pipe system on both the daylighting performance of the light-pipe system and the indoor illuminance distributions of the space using the semi-empirical model. Finally, this paper provides the design guideline of the light-pipe system for its application to an underground parking lot space.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.4
• /
• pp.368-373
• /
• 2010

A new indoor mobile robot localization method is presented. Robot recognizes well designed single color landmarks on the ceiling by vision system, as reference to compute its precise position. The proposed likelihood prediction based method enables the robot to estimate its position based only on the orientation of landmark.The use of single color landmarks helps to reduce the complexity of the landmark structure and makes it easily detectable. Edge based optical flow is further used to compensate for some landmark recognition error. This technique is applicable for navigation in an unlimited sized indoor space. Prediction scheme and localization algorithm are proposed, and edge based optical flow and data fusing are presented. Experimental results show that the proposed method provides accurate estimation of the robot position with a localization error within a range of 5 cm and directional error less than 4 degrees.