• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.279-284
• /
• 2005

The casting defects that are caused by molten metal were cold shut formation, entrapment of air, gas, and inclusion. But the control of casting defects has been based on the experience of the foundry engineers. In this thesis, the computer simulation analyzed the flow of molten metal. The quantitative analyses which proposed the effective mold design was executed Flow patterns of 0.15-0.16m/s molten metal in 15 mm thin plate casting were investigated in order to optimize die-casting process. As increasing ingate velocity in thin plate casting, cold shot was decreased. The parameters of runner shape that affected on the optimized conditions that was calculated with simple equation were investigated. These die casting process control techniques of automobile valve body mid-plate have achieved good agreement with the experimental data of tensile strength, hardness test, and material structure photographies satisfactory results.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.1
• /
• pp.24-33
• /
• 2003

Finding epileptogenic zone is the most important step for the successful epilepsy surgery. F-18 fluorodeoxyglucose positron emission tomography (FDG-PET) and single photon emission computed tomography (SPECT) can be used in the localization of epileptogenic foci. In medial temporal lobe epilepsy, the diagnostic sensitivity of FDG-PET and ictal SPECT is excellent. However, detection of hippocampal sclerosis by MRI is so certain that use of FDG-PET and ictal SPECT in medial temporal lobe epilepsy is limited for some occasions. In neocortical epilepsy, the sensitivities of FDG-PET or ictal SPECT are fair. However, FDG-PET and ictal SPECT can have a crucial role in the localization of epileptogenic foci for non-lesional neocortical epilepsy. Interpretation of FDG-PET has been recently advanced by voxel-based analysis and automatic volume of interest analysis based on a population template. Both analytical methods can aid the objective diagnosis of epileptogenic foci. Ictal SPECT was analyzed using subtraction methods and voxel-based analysis. Rapidity of injection of tracers, ictal EEG findings during injection of tracer, and repeated ictal SPECT were important technical issues of ictal SPECT. SPECT can also be used in the evaluation of validity of Wada test.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.1041-1044
• /
• 2019

자동통번역의 성능을 평가하는데 가장 잘 알려진 자동평가 기술은 BLEU이다. 그러나 BLEU로는 자동통번역 결과의 어느 부분이 강점이고 약점인지를 파악할 수 없다. 본 논문에서는 자동통번역 시스템의 언어 현상별 자동평가 방법을 소개하고자 한다. 언어 현상별 자동평가 방법은 BLEU가 제시하지 못하는 언어 현상별 자동평가가 가능하며 개발자로 하여금 해당 자동통번역 시스템의 언어 현상별 강점과 약점을 직관적으로 파악할 수 있도록 한다. 언어 현상별 정확도 측정은 Google 과 Naver Papago 를 대상으로 실시하였다. 정확률이 40%이하를 약점이라고 간주할 때, Google 영한 자동번역기의 약점은 스타일(32.50%)번역이었으며, Google 영한 자동통역기의 약점은 음성(30.00%)인식, 담화(30.00%)처리였다. Google 한영 자동번역기 약점은 구문(34.00%)분석, 모호성(27.50%)해소, 스타일(20.00%)번역이었으며, Google 한영 자동통역기 약점은 담화(30.00%)처리였다. Papago 영한 자동번역기는 대부분 정확률이 55% 이상이었으며 Papago 영한 자동통역기의 약점은 담화(30.00%)처리였다. 또한 Papago 한영 자동번역기의 약점은 구문(38.00%)분석, 모호성(32.50%)해소, 스타일(20.00%)번역이었으며, Google 한영 자동통역기 약점은 담화(20.00%)처리였다. 언어 현상별 자동평가의 궁극적인 목표는 자동통번역기의 다양한 약점을 찾아내어 약점과 관련된 targeted corpus 를 반자동 수집 및 구축하고 재학습을 하여 자동통번역기의 성능을 점증적으로 향상시키는 것이다.

• Journal of Intelligence and Information Systems
• /
• v.6 no.1
• /
• pp.73-82
• /
• 2000

This study examined the characteristicso f the knowledge discovery and data mining algorithms to demonstrate how they can be used to predict health outcomes and provide policy information for hypertension management using the Korea Medical Insurance Corporation database. Specifically this study validated the predictive power of data mining algorithms by comparing the performance of logistic regression and two decision tree algorithms CHAID (Chi-squared Automatic Interaction Detection) and C5.0 (a variant of C4.5) since logistic regression has assumed a major position in the healthcare field as a method for predicting or classifying health outcomes based on the specific characteristics of each individual case. This comparison was performed using the test set of 4,588 beneficiaries and the training set of 13,689 beneficiaries that were used to develop the models. On the contrary to the previous study CHAID algorithm performed better than logistic regression in predicting hypertension but C5.0 had the lowest predictive power. In addition CHAID algorithm and association rule also provided the segment characteristics for the risk factors that may be used in developing hypertension management programs. This showed that data mining approach can be a useful analytic tool for predicting and classifying health outcomes data.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.4
• /
• pp.92-95
• /
• 2019

Automation control and the data for control of industrial equipment for the diagnosis and prediction is a key to success in the 4th industrial revolution. It increases process efficiency and productivity through data collection, realtime monitoring, and the data analysis. However, university and research environment are still suffering from logging the data in manual way, and we occasionally loss the equipment data logging due to the lack of automatic data logging system. State variable presents the current condition of the equipment operation which is closely related to process result, and it is valuable to monitor and analyze the data for the equipment health monitoring. In this paper, we demonstrate the collection of equipment state variable data via programmable logic controller (PLC) and the visualization of the collected data over the Web access supervisory control and data acquisition (SCADA). Test vehicle for the implementation of the suggested SCADA system is a relay switched physical vapor deposition system in the university environment.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.11-20
• /
• 2015

Typically welded bellows are checked with human eye and microscope, and then go through leakage test of gas. The proposed system alternates these heuristic techniques using support vector machines. Image procedures in the proposed method can cover the irregularity problem induced from human being. To get easy observation through microscope, 3D display system is also exploited. Experimental results from this automatic measurement show the welding detection is done within one tenth of permitted error range.

• Annual Conference of KIPS
• /
• 2012.04a
• /
• pp.1235-1238
• /
• 2012

오늘날 소프트웨어가 가지는 규모와 복잡성은 날로 심화되고 있으며, 소프트웨어 개발 시 결함을 찾아 내기 위한 테스트에 많은 시간이 소모되고 있는 실정이다. 이러한 문제점을 해결하기 위해 중요한 기술 중 하나가 결함 위치 추적(Fault Localization)이다. 이 기법을 이용하여 결함을 추적하기 위해서는 다량의 테스트 케이스를 필요로 하며, 추가로 테스트 케이스를 작성하는 것은 또 다른 개발 부하이다. 본 논문에서는 이를 해결하기 위해서 분기별 입력 조합 기반 테스트 케이스 생성방법과 시드 결과 기반 테스트 케이스 생성방법을 제안하였다. 개발자는 본 생성방법을 통해 테스트 케이스 생성에 대한 비용 절감을 기대 할 수 있다. 제안하는 내용의 효용성을 검증하기 위해 실제 예제 코드에 적용하여 평가하였다. 두 가지 방법 모두 무작위 생성한 테스트 케이스에 비해 개발자가 직접 생성하는 것과 유사한 테스트 케이스를 생성하고, 제안 방법으로 생성한 테스트 케이스의 신뢰성을 확인하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.957-968
• /
• 2021

To improve the data on reliability of the onshore fish farm water quality monitoring system and operate the system efficiently, the water quality data of the onshore seawater fish farms which are progressing test operation, and the marine environmental information network(Wando tidal station) were compared and analyzed. Furthermore, data validation, data range filters, and data displacement checks were applied to analyze the data in a way that eliminates the data errors in water quality monitoring systems and increases the reliability of measurement data.

• Journal of Biomedical Engineering Research
• /
• v.40 no.4
• /
• pp.132-136
• /
• 2019

This study proposes an auto-titrating algorithm for auto-titrating positive airway pressure (APAP). The process of the proposed algorithm is as follows. First, sleep apnea-hypopnea and snoring events were detected using nasal pressure. Second, APAP base pressure and SDB events were used for automatic titration of optimal pressure. And, auto-titrating algorithm is built into M3 (MEK-ICS CO. Ltd., Republic of Korea) for evaluation. The detection results of SDB showed mean sensitivity (Sen.) and positive predictive value (PPV.) of 85.7% and 87.8%, respectively. The mean pressure and apnea-hypopnea index (AHI) of auto-titrating algorithm showed $13.0{\pm}5.2cmH_2O$ and $3.0{\pm}2.4$ events/h, respectively. And, paired t-test was conducted to verify whether the performance of our algorithm has no significant difference with AutoSet S9 (p>0.05). These results represent better or comparable outcomes compared to those of previous APAP devices.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.341-350
• /
• 2019

Garlic is one of the most popular seasoning bulb vegetables in Korea and is the most commonly used food ingredient. However, the cultivation areas are decreasing every year as the price drops due to imported garlic, and labor is insufficient to produce garlic by conventional methods. Cultivation requires various tasks until garlic is harvested. Seeding is one of the important and laborious tasks; thus, mechanization is necessary. When seeding garlic, the sprout should face upwards; otherwise, it may rot or produce poor quality garlic. This study investigated the extent of growth of northern- and southern-type garlic in eight different positions. The results show when the roots were not planted properly, the stems were weak, and the garlic bulbs were small. A simple garlic planter was manufactured with a crank-press mechanism to plant garlic in an upright position. Using this machine, a three-fold experiment was carried out with 100 strips of garlic. The test results showed that 99.4% of the planted garlic strips were positioned upright or close to being upright, and 0.6% failed to take root. An image processing algorithm was developed to locate the root part of the garlic, and the result showed a success rate of 81%. A future study will develop an automatic garlic upright planting system with a viewing system.