• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1144-1148
• /
• 1991

The problems occurred when developing a automatic wheel deburring system are to make effective flexibility in model change and the irregularity of the position/shape of the burr, to select optimal robotic manufacturing process and to develope optimal end effector. The locations where burr exists are on flange, rim and spoke. Here will be discussed the optimal solution for the removal of rim burr by using robot. The research can be summarized as the automatic robot path generation by recognizing rim contour and automatic deburring process technique. Various rim contour data is generated automatically when the sensor which is fixed to robot is moving with the parallel motion to the wheel center axis and this generated data is transferred to the data storage system and converted to the robot path data. The robotic tool system which is suitable to the rim deburring process is developed by integrating tool, compliance function and sensor. And factory automation system controlled by robot controller and PC is developed. This system shows good productivity and flexibility.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.2
• /
• pp.120-126
• /
• 2011

The fatigue damages in structural details of offshore plants can be accumulated due to various environmental loadings such as swell, wave, wind and current. It is known that load histories acting on mooring and riser systems show stationary and ergodic bimodal wide-banded process. This paper provides refined approach to obtain time signals representing stress range histories from wide-banded bimodal spectrum which consists of ideally narrow-banded and fully separated two spectrums. Variations of the probabilistic characteristics for time signals according to frequency and sampling time increments are compared with the reference data to be the probabilistic characteristics such as zero-crossing period, peak period, and irregularity factor obtained from an assumed ideal spectrum. It is proved that the sampling time increment more affects on the probabilistic characteristics than frequency increment. The fatigue damages according to the frequency and sampling time increments are also compared with the ones with minimum increment condition which are thought to be exact fatigue damage. It is concluded that the maximum sampling time increment to obtain reliable time signals should be determined that ratio of applied maximum sampling time increment and minimum period is less than approximately 0.08.

• The Korean Journal of Applied Statistics
• /
• v.16 no.1
• /
• pp.15-31
• /
• 2003

In this study, we will construct a statistical model which considered the irregularity of observed time sequence in order to analyze sets of bioindex data gathered from stations in Lake Ontario for a number of years. We fit a linear model to account for the trend and seasonal component in an exploratory way and draw variogram and correlogram for further confirmatory studies.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.12
• /
• pp.132-136
• /
• 1994

Presented is the study on design and implementation of a fuzzy system to approximately reason using measured actual storage rate in irrigation reservoirs. To design Fuzzy reasoning systems. Minimum Operation Rule by Mamdani was applied. Fuzzy variable and membership functions are determined after identifying storage-rate affecting factor and followed simulation. Hydrological model to express actual situation within drought areal boundary is generally too complex. Hereby, considering irregularity of time-rate storage change during irrigation, this system uses irrigation water and meteorological data as a IN-data. It was abvious the results were closely corresponding to the actual data observed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.482-484
• /
• 2019

Learning and analyzing 3D point clouds with deep networks is challenging due to the limited and irregularity of the data. In this paper, we present a data-driven point cloud augmentation technique. The key idea is to learn multilevel features per point and to reconstruct to a similar point set. Our network is applied to a projection loss function that encourages the predicted points to remain on the geometric shapes with a particular target. We conduct various experiments using ShapeNet part data to evaluate our method and demonstrate its possibility. Results show that our generated points have a similar shape and are located closer to the object.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1238-1249
• /
• 2020

Throughout the world, aging populations and doctor shortages have helped drive the increasing demand for smart healthcare systems. Recently, these systems have benefited from the evolution of the Internet of Things (IoT), big data, and machine learning. However, these advances result in the generation of large amounts of data, making healthcare data analysis a major issue. These data have a number of complex properties such as high-dimensionality, irregularity, and sparsity, which makes efficient processing difficult to implement. These challenges are met by big data analytics. In this paper, we propose an innovative analytic framework for big healthcare data that are collected either from IoT wearable devices or from archived patient medical images. The proposed method would efficiently address the data heterogeneity problem using middleware between heterogeneous data sources and MapReduce Hadoop clusters. Furthermore, the proposed framework enables the use of both fog computing and cloud platforms to handle the problems faced through online and offline data processing, data storage, and data classification. Additionally, it guarantees robust and secure knowledge of patient medical data.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.12 no.4
• /
• pp.2063-2077
• /
• 1970

The Purpose of this study is to give the hydrologically basic data for the development of water resources in Korea and a quantity of daily average precipitation and its frequency in a year are investigated to study the presumption which is affected to river flow. Characteristics of precipitation is poor as source of water resources compared with its efficiency. So, because of such characteristics of precipitation, river flow also is in harmony and distribution of river flow comes to the result of irregularity, that is, range of river coefficiet between the quantity of maximum river flow and others river flow is big, and it is insufficient as source of water resources. Yearly river flow being expressed by daily unit indicates the ratio(%) of distribution to total yearly river flow, and the model of hydrograph is drawn up. The gives the basis to make yearly water balance sheet. This study is not completed, yet but in forth-coming days, the water will try continuously to give more correct basis for the development of water resources according to a great deal of data.

• Journal of the Korean Society for Railway
• /
• v.10 no.5
• /
• pp.607-612
• /
• 2007

In this paper, operation mode of train was divided into powering, coasting, and braking and rail wear phenomenon has been done comparative analysis by each section. Data of train velocity is transferred to acceleration and deceleration from ATO Logging data. Amount of rail wear has been done comparative analysis by traction force of acceleration and braking force of deceleration and a plan for management of track irregularity is come up with by the result of the analysis.

• Health Policy and Management
• /
• v.30 no.1
• /
• pp.15-25
• /
• 2020

While healthcare data sets include extensive information about patients, many researchers have limitations in analyzing them due to their intrinsic characteristics such as heterogeneity, longitudinal irregularity, and noise. In particular, since the majority of medical history information is recorded in text codes, the use of such information has been limited due to the high dimensionality of explanatory variables. To address this problem, recent studies applied word embedding techniques, originally developed for natural language processing, and derived positive results in terms of dimensional reduction and accuracy of the prediction model. This paper reviews the deep learning-based natural language processing techniques (word embedding) and summarizes research cases that have used those techniques in the health care field. Then we finally propose a research framework for applying deep learning-based natural language process in the analysis of domestic health insurance data.

• Journal of the Korean Society for Railway
• /
• v.19 no.6
• /
• pp.777-784
• /
• 2016

In this study, regulation of the performance test load of a vibration-proof fastening system used in urban railways was established through evaluation of the loads that it bears in the field. In order to investigate the range of the dynamic stiffness of the vibration-proof fastening system, dynamic stiffness tests were carried out for three types of vibration-proof fastening system that can be domestically supplied. Train and track interaction analyses in the frequency domain were carried out to evaluate the dynamic wheel loads. The track irregularity, which is a very important input factor in train and track interaction analysis, was considered as a PSD (Power Spectral Density) function, which was derived based on the measured data. The loads on the vibration-proof rail fastening system were evaluated considering various operating conditions in the urban railway. Regulation of the performance test load of the vibration-proof rail fastening system was established based on the evaluated loads.