• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.62-67
• /
• 2019

The purpose of this study was to evaluate the performance of deep neural network model in order to determine whether there is a risk factor for coronary artery disease based on the cardiac variation parameter. The study used unidentifiable 297 data to evaluate the performance of the model. Input data consists of heart rate parameters, which are SDNN (standard deviation of the N-N intervals), PSI (physical stress index), TP (total power), VLF (very low frequency), LF (low frequency), HF (high frequency), RMSSD (root mean square of successive difference) APEN (approximate entropy) and SRD (successive R-R interval difference), the age group and sex. Output data are divided into normal and patient groups, and the patient group consists of those diagnosed with diabetes, high blood pressure, and hyperlipidemia among the various risk factors that can cause coronary artery disease. Based on this, a binary classification model was applied using Deep Neural Network of deep learning techniques to classify normal and patient groups efficiently. To evaluate the effectiveness of the model used in this study, Kernel SVM (support vector machine), one of the classification models in machine learning, was compared and evaluated using same data. The results showed that the accuracy of the proposed deep neural network was train set 91.79% and test set 85.56% and the specificity was 87.04% and the sensitivity was 83.33% from the point of diagnosis. These results suggest that deep learning is more efficient when classifying these medical data because the train set accuracy in the deep neural network was 7.73% higher than the comparative model Kernel SVM.

• International Journal of Aerospace System Engineering
• /
• 제2권1호
• /
• pp.18-23
• /
• 2015

Based on real jobs, this study was carried out the Railway maintenance works in Taiwan. It hopes to use Geographic Information System(GIS) and Building Information Modeling(BIM) for changing the maintenance model from "post-damage repair" to "preventive maintenance". Accordingly, this research will build a Railway Repairing Database that installs all repair data. This database will also connect to GIS so that can be the source of analysis and statistic for repair paln. The main results of research are as follows: I. All data stored on cloud space that raises the ability to manage and plan on repair. II. Simplify the file work and increase the quantity of case data to the manager who can get more reliable source. III. The data offer objective judgment to avoid subjective argument. IV. Add the GIS information to improve the maintenance because of good analisis.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.658-668
• /
• 2009

Earth-moving operation has a great impact on the overall budget and schedule of any heavy civil projects. More often than not, the operational decisions are made largely based on field personnel's experience and judgment. In particular, decisions on earth moving operations by scraper-dozer fleets have been heavily influenced by the following belief: "The longer a dozer pushes a scraper for loading, the better earth-moving productivity is gained by the fleet." Even though there is some truth to this notion, scraper-dozer earth moving operations involve a much complex process that requires a systematic analysis for predicting the maximum production. To this end, this paper presents a spreadsheet-based scraper-dozer fleet operation model for its production optimization. Various optimization techniques, including a genetic-algorithm method, are presented for comparison and each technique's pros and cons are discussed.

• Korean Journal of Radiology
• /
• 제24권2호
• /
• pp.155-165
• /
• 2023

Objective: Little is known about the effects of using different expert-determined reference standards when evaluating the performance of deep learning-based automatic detection (DLAD) models and their added value to radiologists. We assessed the concordance of expert-determined standards with a clinical gold standard (herein, pathological confirmation) and the effects of different expert-determined reference standards on the estimates of radiologists' diagnostic performance to detect malignant pulmonary nodules on chest radiographs with and without the assistance of a DLAD model. Materials and Methods: This study included chest radiographs from 50 patients with pathologically proven lung cancer and 50 controls. Five expert-determined standards were constructed using the interpretations of 10 experts: individual judgment by the most experienced expert, majority vote, consensus judgments of two and three experts, and a latent class analysis (LCA) model. In separate reader tests, additional 10 radiologists independently interpreted the radiographs and then assisted with the DLAD model. Their diagnostic performance was estimated using the clinical gold standard and various expert-determined standards as the reference standard, and the results were compared using the t test with Bonferroni correction. Results: The LCA model (sensitivity, 72.6%; specificity, 100%) was most similar to the clinical gold standard. When expert-determined standards were used, the sensitivities of radiologists and DLAD model alone were overestimated, and their specificities were underestimated (all p-values < 0.05). DLAD assistance diminished the overestimation of sensitivity but exaggerated the underestimation of specificity (all p-values < 0.001). The DLAD model improved sensitivity and specificity to a greater extent when using the clinical gold standard than when using the expert-determined standards (all p-values < 0.001), except for sensitivity with the LCA model (p = 0.094). Conclusion: The LCA model was most similar to the clinical gold standard for malignant pulmonary nodule detection on chest radiographs. Expert-determined standards caused bias in measuring the diagnostic performance of the artificial intelligence model.

• Journal of Advanced Research in Ocean Engineering
• /
• 제4권3호
• /
• pp.124-134
• /
• 2018

In this study, when the stability of the structure against the ocean wave is considered for designing the offshore structures in the Pacific, Indian ocean and Atlantic regions where the cyclone is largely generated, the ocean wave caused by the cyclone as well as the storm surge which called wind induced wave shall be predicted accurately for the purpose of judgment. The predicted wind induced wave was evaluated by comparing the outcome results the model test of Nobuhiro Matsunaga (1996) and Conventional Experiment forms such as Jonswap spectral forms(Carter, 1982), Simplified Donelan / Jonswap forms(Wilson 1965), Donelan spectral forms(Donelan 1980), Revised SPM forms(Schafer Lake 2005, 2007, 2008), SPM forms(CERC 1977), the CEM forms(Kazeminezhad et al., 2005), SMB forms(Sverdrup Munk and Bretschneider 1947,1954, 1970), and Revised Wilson forms(Wilson 1965, Goda 2003). Most of these conventional experiment forms confirmed a good match when the fetch length is less than 10 km. However, normal cyclone fetch length is more than 100km, With this fetch length, the comparison result is 10.4% of deviation when used Jonswap spectral forms(Carter, 1982) but the deviation of the other forms is around 74% due to boundary limit of fetch and wind duration. Therefore, in this study, we proposed the revised forms after comparing these results with the model results. We confirmed that the deviation range is around 10% based on revisited experiment forms. Since the model test was carried out in the small water tank, the scale up factor was applied to the mode test results in order to obtain similar results to the actual environment from revisited forms.

• 한국건설관리학회논문집
• /
• 제23권2호
• /
• pp.65-75
• /
• 2022

2020년 6월 11일 대법원은 대상 사건에 대해 계약특수조건에서 정한 하자보수 보증기간이 지났다고 하더라도 원고가 피고에게 불완전이행으로 인한 채무불이행책임을 주장할 수 있다는 원심의 판단을 정당하다고 판결하였다. 그러나 우리나라 민법학에서 하자담보책임에 대한 제척기간과 채무불이행책임에 대한 소멸시효의 경합이 인정되고, 제척기간과 소멸시효는 법리상 각각의 목적을 가지고 있으므로, 이 둘은 상호 연관 관계에 있음을 전제로 조화롭게 중용하여 판단되어야 한다. 대상 판결이 일반화될 경우 도급계약에서의 하자담보책임에 관한 약정은 더이상 존재할 이유가 없다. 본 연구는 하자담보책임과 채무불이행책임에 대한 일반론 및 선행판례 연구를 통해 대상 판결을 고찰하고, 대상 판결이 일반화될 경우 발생 가능한 문제점 도출하였다. 또한 현실적인 모델을 바탕으로 실무적 개선방안으로 도급계약 약정상 하자담보책임기간의 현실화하고 그 성격의 규정을 명문화할 것을 제시하였다.

• Nuclear Engineering and Technology
• /
• 제52권10호
• /
• pp.2183-2195
• /
• 2020

A mathematical model for the flowrate and rotation speed of RCP during idling was established. The numerical calculation method and dimensionless method were used to analyze the flow, head, torque and pressure and speed changes under idle conditions. Regularity, using the Q criterion vortex identification judgment method combined with surface flow spectrum morphology analysis to diagnose the vortex dynamic characteristics on RCP blade. On impeller blade, there is two oscillations in the pressure ratio on pressure surface in blade outlet region. The velocity on the suction surface is two times more oscillating than the inlet of blade, and there is an intersection with the velocity ratio curve on pressure surface. On blade of guide vane, the pressure ratio increases along the inlet to outlet direction, and the speed ratio decreases with the increase of idle time. There is a vortex that rotates counterclockwise on the suction surface, and the streamline on the suction surface of blade is subjected to the entrainment and blocking action of the vortex creates a large reverse flow in the main flow region. There are two vortices at the outlet of guide vane suction side and the vortices are in opposite directions.

• 한국건설관리학회논문집
• /
• 제8권1호
• /
• pp.87-95
• /
• 2007

건설공사의 시공공정을 관리자의 경험적 판단에 의하여 작업팀을 구성하여 운영하면, 시공공정의 진행이 비효율적으로 될 가능성이 많다. 그러나 시공계획단계에서 모의조작을 통하여 자원할당, 공사비, 공사기간의 최적 안을 산출하면 시공공정을 정량화하여 효율적인 운영을 할 수 있다. 본 연구에서는 시공공정을 계획할 때 작업팀 운영의 변화에 따른 자원할당 변동치, 자원 손실비, 총공사비, 공사기간의 최적 안을 모의조작 할 수 있는 수식모형의 시안 식을 제안하였다. 제안된 수식모형을 검증하기 위하여 시공공정의 수평작업역과 수직작업 역이 각각 상이하게 구성된 공동주택 골조공사에 적용하여 시현하였다. 본 연구에서 제시된 수식모형을 적용하여 모의 조작을 실시한 결과가 실제 사례공사에서 적용된 작업팀의 운영실적보다 효율화를 달성하였다.

• 한국정보통신학회논문지
• /
• 제23권3호
• /
• pp.282-290
• /
• 2019

최근 어린이집이나 유치원 등 교육기관에서 아동학대가 빈번히 발생하고 있다. 정부는 CCTV 설치를 의무화하였지만 CCTV 영상을 열람하는 것이 쉽지 않다. 본 논문에서는 CCTV 영상을 이용하여 아동학대를 판단하는 모델을 제안한다. 먼저 아동학대란 성인이 물리적으로 아동에게 가해를 하는 것이므로 성인과 아동을 분류하는 모델이 필요하다. 기존의 Haar기법을 사용하여 성인과 아동을 분류하려면 정면 영상이 필요하지만 OpenPose를 사용하면 정면과 측면에 구애받지 않고 성인과 아동을 분류할 수 있다. 본 연구에서는 아동이 학대를 당할 때 성인과 아동의 자세의 특성을 적용하여 아동 학대 판단 모델을 설계 및 구현하였다. 구현한 시스템은 현재 설치되어있는 CCTV를 활용하므로 추가적인 설치가 필요하지 않고 실시간으로 아동학대가 발생하고 있는지 모니터링 할 수 있으므로 이에 따른 빠른 대처가 가능할 것으로 사료된다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.61-64
• /
• 2003

A band function model paired comparison method (BMPC method) is a kind of a paired comparison methods. Considering the human ambiguities, the BMPC method expressing the human judgment characteristics as a monotonous increase function with some width. Since function types are not specified in a BMPC method, the solution is obtained from inequalities, and the solution is given as a domain. To solve the simultaneous inequalities, the sequential renew method is used in the previous BMPC method. However, the sequential renew method requires much computational effort and memories. Generally, in BMPC method, it is able to solve only a paired comparison table which has less 12-13 samples. For that purpose, a new fast solution algorithm is required. In this paper, we proposed a new “search vector method” which renews the solution domain without creating new edge vectors. By using the method, it is able to decrease the necessary memory spaces and time to solve. The proposed method makes it able to solve more than 15 samples paired comparison inspections which are impossible to solve by previous method.