• 터널과지하공간
• /
• 제17권2호
• /
• pp.102-108
• /
• 2007

일반적으로 암판정을 수행하기 인해 가장 널리 사용되는 방법은 암석의 강도와 절리의 발달빈도를 고려하는 것이다. 하지만 미세균열과 연장성이 긴 절리들이 암반에 존재하고 있는 경우에는 이러한 방법이 합리적이지 않다. 그러므로 복잡한 지질조건을 가지고 있는 암반에서의 굴착난이도 결정은 절리빈도와 실내시험(일축압축강도, 점하중강도, 실내탄성파속도 등)과 현장탄성파속도와의 상관관계를 종합하여 암판정을 수행하는 것이 더욱 더 합리적이라고 판단된다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.394-396
• /
• 2021

특정 질병 진단을 위한 병리 검사는 필수적이며, 최근 이러한 분야의 시간적, 인적 자원의 필요성을 줄이기 위해 인공 지능을 활용한 암세포의 자동분류가 가능한 시스템 구축에 관련된 연구가 활발하게 진행되고 있다. 하지만, 이전 연구에서는 제한적인 심층학습 알고리즘에 기인한 비교적 낮은 정확도로 데이터 처리에 한계가 존재하였다. 본 연구에서는 심층 학습의 일종인 Convolution Neral Network를 통해 4종류의 암세포를 4 Class Classifciation을 시행하는 방법을 제안한다. EfficientNet, ResNet, Inception을 사용하였으며 여러 하이퍼 파라미터 튜닝을 통해 얻은 모델을 앙상블 하여 최종적으로 97.26의 정확도를 얻을 수 있었다.

• 한국농공학회논문집
• /
• 제65권6호
• /
• pp.15-22
• /
• 2023

In this study, We conduct a comparative study of deep learning-based classification of agricultural field attributes using Tagged Image File (TIF) and Enhanced Compression Wavelet (ECW) images. The goal is to interpret and classify the attributes of agricultural fields by analyzing the differences between these two image formats. "FarmMap," initiated by the Ministry of Agriculture, Food and Rural Affairs in 2014, serves as the first digital map of agricultural land in South Korea. It comprises attributes such as paddy, field, orchard, agricultural facility and ginseng cultivation areas. For the purpose of comparing deep learning-based agricultural attribute classification, we consider the location and class information of objects, as well as the attribute information of FarmMap. We utilize the ResNet-50 instance segmentation model, which is suitable for this task, to conduct simulated experiments. The comparison of agricultural attribute classification between the two images is measured in terms of accuracy. The experimental results indicate that the accuracy of TIF images is 90.44%, while that of ECW images is 91.72%. The ECW image model demonstrates approximately 1.28% higher accuracy. However, statistical validation, specifically Wilcoxon rank-sum tests, did not reveal a significant difference in accuracy between the two images.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.

• 터널과지하공간
• /
• 제3권2호
• /
• pp.167-174
• /
• 1993

Index tests are useful because they are rapid and cheap-and if bias is known the fundamental property can be estimated, as when estimating the compressive strength or the tensile sterngth from the rock test hammer value. Index tests which have proved to be very useful are the rock test hammer, the point load test and sonic velocity test. These can provide index values in their owing right or be used to estimate the compressive strength, the tensile strength and elastic modulus. Because of the heterogeneous and fractured nature of rock, many index tests have been developed for a variety of purposes, e.g.for use in rock mass classification schemes.

• 한국공간구조학회논문집
• /
• 제16권2호
• /
• pp.55-60
• /
• 2016

The Membrane structure has a number of problems in the application of a fireproof code based on general buildings codes. Thus, the fireproof code of membrane structure is necessary to activate the construction of the membrane structure. Because it requires a systematic classification of fire retardant and flame proof performance of membrane material. Fire retardant and flame proof tests are conducted on membrane materials mostly used in current construction to propose the fire and flame retardant performance criteria of membrane materials. Fire and flame retardant tests results, PTFE membrane material with the glass fiber fabric have a limit-combustible performance. PVDF membrane material with the polyester fabric does not ensure the fire retardant performance, but this membrane material has the flame retardant performance of a thick fabric. Also, ETFE does not ensure the fire retardant performance, but this membrane material has the flame retardant of a thin fabric.

• East Asian Economic Review
• /
• 제20권4호
• /
• pp.493-517
• /
• 2016

This paper examines the persistent properties of 12 sectoral relative prices between Korea and Japan obtained following the Classification of Individual Consumption according to Purpose (COICOP) over the period of 1985-2016. Applying a new econometric method developed by Pesaran which controls for the cross-section dependence in a panel, we are not able to reject the hypothesis that the sectoral real exchange rates contain a common stochastic trend. On the other hand, the well-known panel unit root tests such as the IPS and LLC tests widely used by previous studies strongly reject the unit root hypothesis. Since the error term of the regression for our panel exhibits significant cross-section dependence, these opposite results justify that the use of the new econometric method is appropriate.

• 한국지반환경공학회 논문집
• /
• 제23권1호
• /
• pp.15-23
• /
• 2022

This paper presents the results of full-scale load tests performed frictional anchors to various lengths at several sites in Korea. Various rock types were tested, ranging from highly weathered shale to sound gneiss. In many tests, rock failure was reached and the ultimate loads were recorded along with observations of the shape and extent of the failure surface. Laboratory tests were also conducted to investigate the influence of the corrosion protection sheath on the bond strength. Based on test results, the main parameters governing the uplift capacity of the rock anchor system were determined. By evaluation of the ultimate uplift capacity of anchor foundations in a wide range of in situ rock masses, rock classification suitable for structural foundation was developed. Finally, a very simple and economical design procedure is proposed for rock anchor foundations subjected to uplift tensile loads.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제36권3호
• /
• pp.355-372
• /
• 2022

본 연구에서는 그릿 검사가 초등수학영재를 판별하는 도구로서 타당성에 대하여 검증하고자 하였다. 이를 위하여 문헌 연구를 통하여 선행 연구들에서 그릿 검사의 측정 도구들에 대한 자료를 수집하였고, 전문가 검토를 통하여 영재판별을 위한 판별 문항을 개발하였다. 본 연구를 위해 서울특별시 초등학교 일반학생 39명과 영재교육원 수학영재 20명을 대상으로 그릿 검사, 수학 문제해결력 검사, 수학 창의성 검사, 수학 행동 특성 검사를 실시하여 상관관계를 분석하였다. 상관관계 분석 결과 그릿 검사는 수학 문제해결력 검사와 0.521, 수학 창의성 검사와 .440, 수학 행동 특성 검사와 .601의 상관을 갖는 것으로 나타났으며, 모두 유의확률 p<.01 유의도를 보였다. 또한 판별 분석을 통하여 집단 판별의 유의성을 검증한 결과에서 그릿 검사는 집단 내 분산을 총 분산으로 나눈 Wilk's λ가 .799로 나타났으며 유의확률은 p<.001로 그릿 검사가 수학영재와 일반학생을 판별하는데 유의함을 확인하였다. 연구 결과, 그릿 검사가 초등수학영재를 판별하기 위한 대안적인 도구로 타당성이 검증되어 수학영재 판별 도구로 활용 가능할 수 있음을 나타낸다.

• 한국의학물리학회지:의학물리
• /
• 제28권4호
• /
• pp.197-206
• /
• 2017

We develop guidelines for the quality assurance of radiation treatment planning systems (TPS) by comparing and reviewing recommendations from major countries and organizations, as well as by analyzing the AAPM, ESTRO, and IAEA TPS quality assurance guidelines. We establish quality assurance items for acceptance testing, commissioning, periodic testing, system management, and security, and propose methods to perform each item within acceptable standards. Acceptance includes tests of hardware and network environments, data transmission, software, and benchmarking as specified by the system supplier, and apply the IAEA classification criteria. Commissioning includes dosimetric and non-dosimetric items for assessing TPS performance by applying the AAPM classification criteria and the latest technical items from the IAEA. Periodic quality assurance tests include daily, weekly, monthly, yearly, and occasional items by applying the AAPM classification criteria. System management and security items include the state and network connectivity of TPS, periodic data backup, and data access security. The guidelines for TPS quality assurance proposed in this study will help to improve the safety and quality of radiotherapy by preventing incidents related to radiotherapy.