• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1388-1389
• /
• 2015

Electropulsegraphy is a medical device that was invented by an orient medical physician and a few engineers to help the physicians to diagnose patients in more systematic way by analyzing waveforms generated from the device. Data generated form the device has been collected for over several decades, and undergoes functional upgrades today. The device generates 33 waveforms that reflect the states of patients. As one of those upgrading efforts, we strive to develop an intelligent algorithm that makes the diagnostic process automatically, which was previously done manually for a long period of time. The logistic regression algorithm is used for our classification problems, which is one of those well-known algorithms for various classification problems such as character recognition systems. Out of the 33 waveforms, we only use 5 waveform data (Type1 toType5) as training data sets to estimate the parameters of the logistic regression. And the parameters are used to classify waveform inputs chosen at random.

• Journal of Korean Society on Water Environment
• /
• v.35 no.3
• /
• pp.248-256
• /
• 2019

Most of the lakes in Korea are artificial, and their limnological characteristics are significantly different from those of natural lakes in other countries. In this study, the relationship between trophic state parameters was investigated, based on summer average data of the upper layer, in 81 lakes in Korea, 2013-2017. Compared with trends of foreign natural lakes, chlorophyll a (Chl.a) concentration was slightly lower at the same total phosphorus (TP) concentration, and transparency (Secchi depth, SD) was noticeably lower at the same Chl.a concentration. This is because of excessive allochthonous loading of non-algal material during the monsoon period, and the reduction in phosphorus availability to algal growth, by light limitation and short hydraulic residence time. Considering these characteristics, we suggested site-specific thresholds of trophic state classification for Chl.a, TP and SD, based on annual average data at the upper layer of lakes ($3-10{\mu}g\;L^{-1}$ of Chl.a measured by UNESCO method; $13-33{\mu}g\;L^{-1}$ of TP; 1.6-3.2 m of SD for mesotrophic state class, respectively). The threshold value of TP for each trophic state class, corresponded to the upper value of previously reported range, and that of SD was out of the range. We suggested applying only TP and Chl.a in assessment of trophic state of lakes in Korea, excluding SD.

• Geomechanics and Engineering
• /
• v.29 no.3
• /
• pp.249-258
• /
• 2022

A disc cutter is an excavation tool on a tunnel boring machine (TBM) cutterhead; it crushes and cuts rock mass while the machine excavates using the cutterhead's rotational movement. Disc cutter wear occurs naturally. Thus, along with the management of downtime and excavation efficiency, abrasioned disc cutters need to be replaced at the proper time; otherwise, the construction period could be delayed and the cost could increase. The most common prediction models for TBM performance and for the disc cutter lifetime have been proposed by the Colorado School of Mines and Norwegian University of Science and Technology. However, design parameters of existing models do not well correspond to the field values when a TBM encounters complex and difficult ground conditions in the field. Thus, this study proposes a series of machine learning models to predict the disc cutter lifetime of a shield TBM using the excavation (machine) data during operation which is response to the rock mass. This study utilizes five different machine learning techniques: four types of classification models (i.e., K-Nearest Neighbors (KNN), Support Vector Machine, Decision Tree, and Staking Ensemble Model) and one artificial neural network (ANN) model. The KNN model was found to be the best model among the four classification models, affording the highest recall of 81%. The ANN model also predicted the wear rate of disc cutters reasonably well.

• Journal of Wind Energy
• /
• v.14 no.3
• /
• pp.34-42
• /
• 2023

The reduction of operation and maintenance (O&M) costs is a critical factor in determining the competitiveness of wind energy. Predictive maintenance based on the estimation of remaining useful life (RUL) is a key technology to reduce logistic costs and increase the availability of wind turbines. Although a mechanical component usually has sudden changes during operation, most RUL estimation methods use the trend of a state index over the whole operation period. Therefore, overestimation of RUL causes confusion in O&M plans and reduces the effect of predictive maintenance. In this paper, two RUL estimation methods (load based and data driven) are proposed for the bearings of a wind turbine with the results of trend classification, which differentiates constant and increasing states of the state index. The proposed estimation method is applied to a bearing degradation test, which shows a conservative estimation of RUL.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.8
• /
• pp.405-411
• /
• 2000

When faults occur in transmission lines, the classification of faults is very important. If the fault is HIF(High Impedance Fault), it cannot be detected or removed by conventional overcurrent relays (OCRs), and results in fire hazards and causes damages in electrical equipment or personal threat. The fast discrimination of fault needs to effective protection and treatment and is important problem for power system protection. This paper propolsed the fault detection and discrimination algorithm for LIFs(Low Impedance Faults) and HIFs(High Impedance Faults). This algorithm uses artificial neural networks and variation of 3-phase maximum currents per period while faults. A double lines-to-ground and line-to-line faults can be detected using Neural Network. Also, the other faults can be detected using the value of variation of maximum current. Test results show that the proposed algorithms discriminate LIFs and HIFs accurately within a half cycle.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1995.10a
• /
• pp.293-299
• /
• 1995

A methodology is applied to identify tile learning trend related to the safety and availability of U.S. commercial nuclear power plants. The application is intended to aid in reducing likelihood of human errors. To assure that tile methodology ran be easily adapted to various types of classification schemes of operation data, a data bank classified by the Transient Analysis Classification and Evaluation(TRACE) scheme is selected for the methodology. The significance criteria for human-initiated events affecting tile systems and for events caused by human deficiencies were used. Clustering analysis was used to identify the learning trend in multi-dimensional histograms. A computer rode is developed based on tile K-Means algorithm and applied to find the learning period in which error rates are monotonously decreasing with plant age.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.147-150
• /
• 2008

This study refers to develop a semi-automatic extraction of agricultural land use and vegetation information using high resolution satellite images. Data of IKONOS satellite image (May 25 of 2001) and QuickBird satellite image (May 1 of 2006) which resembles with the spatial resolution and spectral characteristics of KOMPSAT3. The precise agricultural land use classification was tried using ISODATA unsupervised classification technique and the result was compared with on-screen digitizing land use accompanying with field investigation. For the extraction of vegetation information, three crops of paddy, com and red pepper were selected and the spectral characteristics were collected during each growing period using ground spectroradiometer. The vegetation indices viz. RVI, NDVI, ARVI, and SAVI for the crops were evaluated. The evaluation process is under development using the ERDAS IMAGINE Spatial Modeler Tool.

• The Korean Journal of Zoology
• /
• v.19 no.2
• /
• pp.51-62
• /
• 1976

A study on the classification of the Korean anthozoans is based on the materials which were collected during the period from October 1963 to May 1975 in the coastal seas of the South Sea and the East Sea of the South Korea. The results of the identification were turned out to be eight species, five genera, three families and one order. They are all unrecorded species in Korean anthozoan fauna. The newly recorded species are as follows: Family Alcyoniidae: 1. Bellonella rubra Brundin, 1896; 2. B. rigida Putter, 1900; 3. B. unicolor (Kukenthal, 1906); 4. Alcyonium gracillimum Kukenthal, 1906; Family Nephtheidae: 5. Paraspongodes spiculosa (Kukenthal, 1906); 6. P. hirotai (Utinomi, 1951); 7. Dendronephthya pectinata (Holm, 1985); Family Nidaliidae: 8. Siphonogorgia dofleini Kukenthal, 1906.

• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.61-64
• /
• 2001

This paper describes a basic study for the classification of cognitive mental states as a basic research of a human-computer interface technique. To recognize the mental states, we obtained 22 subjects’brain waves in course of two types of experiments. One of the experiments is to choose an answer among yes, no or reject buttons, to underlying questions and the other is to select an icon displayed in a monitor screen. After acquiring the brain wave signals, we construct a feature set with the percent power increase for a given segment with respect to that of the reference period. The linear discriminative algorithm is used to classify the cognitive yes/no mental states.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.5 no.5
• /
• pp.22-29
• /
• 2002

This study was conducted to suggest develop revegetation methods and to classification of cutting-rock slopes revegetation type. The data was collected from pre-experienced data, reports and journal. Also research result was reflected from field research for the conditions of construction, vegetation types and field conditions. As the result of analyze, the factors affecting the plant coverage rates of cutting-rock slopes were period of construction, revegetation methods, slope gradient and slope length. Classification of cutting-rock slopes revegetation type was fourth from material of revegetation measures and spray type. It is recommended to adjust the proposed factor as environment, field condition and characteristic related with revegetation measures on slopes for the presentation of revegetation standard.