• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.635-638
• /
• 2006

Regression of conventional prediction techniques in data mining uses the model which is generated from the training step. This model is applied to new input data without any change. If this model is applied directly to time series, the rate of prediction accuracy will be decreased. This paper proposes an incremental regression for time series prediction like typhoon track prediction. This technique considers the characteristic of time series which may be changed over time. It is composed of two steps. The first step executes a fractional process for applying input data to the regression model. The second step updates the model by using its information as new data. Additionally, the model is maintained by only recent data in a queue. This approach has the following two advantages. It maintains the minimum information of the model by using a matrix, so space complexity is reduced. Moreover, it prevents the increment of error rate by updating the model over time. Accuracy rate of the proposed method is measured by RME(Relative Mean Error) and RMSE(Root Mean Square Error). The results of typhoon track prediction experiment are performed by the proposed technique IMLR(Incremental Multiple Linear Regression) is more efficient than those of MLR(Multiple Linear Regression) and SVR(Support Vector Regression).

• Environmental Sciences Bulletin of The Korean Environmental Sciences Society
• /
• v.4 no.3
• /
• pp.149-156
• /
• 2000

This study presents an investigation of the changes that have occurred in the coastal ocean area of Kwangyang Bay located in the South Coastal region of Korea using remote sensing data based on Landsat Thematic Mapper (TM) multispectral digital data from 1988 and 1996. The coastal changes were detected using the digital histogram method and vector trace method. All the images were preprocessed, i.e. geometrically corrected, before the training set selection. when comparing the histograms of 7-band TM data, it was found that the band 5 image exhibited two critical Digital Number(DN) peaks, thereby indicating new coastal water and coastal land data. Based on this information, the coastal ocean area of the band 5 image was calculated using the vector tracing method supported by a CAD program. The result shows that the coastal ocean area decreased by about 5 % between 1988 to 1994. Accordingly, this gives a strong indication that the continuing land development will have a serious impact on the ecosystem of Kwangyang Bay.

• Journal of the Korean housing association
• /
• v.27 no.5
• /
• pp.25-35
• /
• 2016

he objective of this study was to investigate home network systems presently applied in multi-housing complexes and resident's usage to improve the utilization of these systems and services as well as maintenance methods. Subjects were 27 housing complexes equipped with home network systems in west Pangyo area. The investigation methods of communal network systems were observed and photographed. Unit systems were investigated through photography, interviews, and observation focusing on the utilization of Wall-Pads by visiting one unit of each housing complex. The results are as follows: (1) Most housing complexes that we investigated were built with high-grade IT infrastructure. Also, remote meter reading, electronic security, vehicle access, and building access systems were established. Wall-Pads with similar functions were installed in 23 housing complexes, excluding private rental housing complexes. (2) Even though people were well aware of the need for common systems within their housing complexes, only 10~20% of Wall-Pad menus were used. (3) Low utilization rates of home network stem from Wall-Pad menus which were user-unfriendly, and a lack of user training for the complex's common system and unit system. Therefore, to promote active use of home network systems, the systems must be diversified in accordance with user characteristics. In addition, the Wall-Pad menus should be reorganized to be user-friendly.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.10
• /
• pp.1275-1280
• /
• 2014

In this study, the performance of a real-time micro telescopic monitoring system is evaluated, in which an artificial neural network is adopted for the diagnoses of vibratory bodies, such as solid piping system or machinery. The structural vibration was measured by a non-contact remote sensing method, in which images of a high-speed high-definition camera were used. The structural vibration data that can be obtained by the PIV (particle image velocimetry) technique were used for training the neural network. The structures of the neural network are dynamically changed and their performances are evaluated for the constructed diagnosis system. Optimized structures of the neural network are proposed for real-time diagnosis for the piping system. It was experimentally verified that the performances of the neural network used for real-time monitoring are influenced by the types of the vibration data, such as minimum, maximum and average values of the vibration data. It concludes that the time-mean values are most appropriate for monitoring the piping system.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.286-289
• /
• 2007

This study is to develop a cloud detection algorit1un for COMS and it is currently tested by using MODIS level 2B and MTSAT-1R satellite radiance data. Unlike many existing cloud detection schemes which use a threshold method and traditional statistical methods, in this study a feed-forward neural network method with back-propagation algorit1un is used. MODIS level 2B products are matched with feature information of five-band MTSAT 1R image data to form the training dataset. The neural network is trained over the global region for the period of January to December in 2006 with 5 km spatial resolution. The main results show that this model is capable to detect complex cloud phenomena. And when it is applied to seasonal images, it shows reliable results to reflect seasonal characteristics except for snow cover of winter. The cloud detection by the neural network method shows 90% accuracy compared to the MODIS products.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.44 no.2
• /
• pp.141-147
• /
• 2008

Acoustic telemetry technique is one of useful tools to get behavioral information of the free-swimming fish. In this study, we conducted acoustic telemetry using coded acoustic transmitters to compare behavior characteristics between wild and cultured black seabream Acanthopagrus schlegeli, one of target species to promote resource in the marine ranching area. Two wild fish and five cultured fish were released in the marine ranching area after tagging surgically. Three of cultured fish were domesticated using the remote acoustic conditioning system for 3 weeks before being released. Two wild fish stayed at the released point for 2 hours and 9 days, respectively. One of wild fish was found about 10.8km away from the released point after 5 months. Two cultured fish stayed at the released point for 6 days and 75 days, respectively. One of acoustic conditioned fish stayed at the released point for 131 days and then was found about 10.1km away from the released point after 25 days. Others stayed at the released point during this study period(159 days).

• Journal of KIISE:Databases
• /
• v.31 no.2
• /
• pp.99-107
• /
• 2004

Education and training are expected to change dramatically due to the combined impact of the Internet, database, and multimedia technologies However, the distance learning is often impeded by the lack of effective tools and system to manage and retrieve the lecture contents effectively. This paper introduces a prototype system called COVA that enables remote users to access specific parts of interest by contents from a large lecture database. COVA includes several novel techniques to achieve the content-based lecture retrieval in distance teaming: (1) The XML-based semistructured model to represent lecture contents; (2) The technique to build structural summaries, i.e., schemas, of XML lecture databases; (3) Index structures to speed up the search to find appropriate lecture contents.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.67-69
• /
• 2004

This thesis attempts to investigate and analyze the structure of educational simulation devices implemented thus far. conducting a close analysis of their strengths and weaknesses. On this basis the author Presents and implements a new method of simulation, and continuously upgrades it for increased stability and convenience. The most important aspects of the educational simulation device described in this thesis are: first removing the editing function (scenarios. single line diagrams, and point DB), which the instructor finds time-consuming and inconvenient to use; second, developing and installing the program so as to calculate electric power flow that can measure fluctuations measurements after changing the system status; and third. implementing a Client/server mode to build a system that will make it possible to train many people at a time in remote locations. When compared to simulation devices of the Psst. the greatest differences are that algorithm-based scenarios make scenario inputs unnecessary. and that the amount of work required for the point DB and single line diagrams were minimized.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5404-5424
• /
• 2018

This work is mainly focused on two major topics in cloud platforms by using OpenStack as a case study: management and provisioning of resources to meet the requirements of a service demanded by remote end-user and relocation of virtual machines (VMs) requests to offload the encumbered compute nodes. The general framework architecture contains two subsystems: 1) An orchestrator that allows to systematize provisioning and resource management in OpenStack, and 2) A resource utilization based subsystem for vibrant VM relocation in OpenStack. The suggested orchestrator provisions and manages resources by: 1) manipulating application program interfaces (APIs) delivered by the cloud supplier in order to allocate/control/manage storage and compute resources; 2) interrelating with software-defined networking (SDN) controller to acquire the details of the accessible resources, and training the variations/rules to manage the network based on the requirements of cloud service. For resource provisioning, an algorithm is suggested, which provisions resources on the basis of unused resources in a pool of VMs. A sub-system is suggested for VM relocation in a cloud computing platform. The framework decides the proposed overload recognition, VM allocation algorithms for VM relocation in clouds and VM selection.

• Journal of Drive and Control
• /
• v.18 no.4
• /
• pp.9-18
• /
• 2021

This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user's desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.