• 대한화학회지
• /
• 제58권6호
• /
• pp.543-552
• /
• 2014

A quantitative structure activity relationship (QSAR) study is performed for modeling and prediction of oral bioavailabilities of 216 diverse set of drugs. After calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regression (MLR), artificial neural network (ANN), support vector machine (SVM) and random forest (RF) techniques. Comparison between statistical parameters of these models indicates the suitability of SVM over other models. The root mean square errors of SVM model were 5.933 and 4.934 for training and test sets, respectively. Robustness and reliability of the developed SVM model was evaluated by performing of leave many out cross validation test, which produces the statistic of $Q^2_{SVM}=0.603$ and SPRESS = 7.902. Moreover, the chemical applicability domains of model were determined via leverage approach. The results of this study revealed the applicability of QSAR approach by using SVM in prediction of oral bioavailability of drugs.

• 한국자동차공학회논문집
• /
• 제22권3호
• /
• pp.68-74
• /
• 2014

As the number of ECUs (Electronic control units) are increasing, reliability and functional stability of a software in an ECU is getting more important. Therefore the application of functional safety standards ISO 26262 is making the software more reliable. Software fault injection test (SFIT) is required as a verification technique for the application of ISO 26262. In case of applying SFIT, an artificial error is injected to inspect the vulnerability of the system which is not easily detected during normal operation. In this paper, the basic concept of SFIT will be examined and the application of SIFT based on ISO26262 will be described.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.1
• /
• pp.265-270
• /
• 2006

Recently, inertial sensors like gyros and accelerometers have been quite miniaturized by Micro Electro-Mechanical Systems (MEMS) technology. JAXA is developing a MEM-based GPS/INS hybrid navigation system named Micro-GAIA. The navigation performance of Micro-GAIA was evaluated through off-line analysis by using flight test data. The estimation errors of the roll, pitch, and azimuth were $0.03^{\circ}$, $0.05^{\circ}$, $0.05^{\circ}$ $(1{\sigma})$, respectively. he horizontal position errors after 60-second GPS outages were reduced to 25 m CEP. The attitude errors and position errors are nearly half of ones reported previously[2]. Furthermore, using the adaptive Kalman filters, the robustness against the uncertainty of the measurement noise was improved. Comparing the innovation-based and residual-based adaptive Kalman filters, it was confirmed that the latter is robuster than the former.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.953-955
• /
• 1993

In this paper we propose a new stability theorem and a robust stability condition for linguistic fuzzy model systems in state space. First we define a stability in linear sense. After representing the fuzzy model by a system with disturbances, A necessary and sufficient condition for the stability is derived. This condition is proved to be a sufficient condition of the fuzzy model. The Q in the Lyapunov equation is iteratively adjusted by an gradient-based algorithm to improve its stability test. Finally, stability robustness bounds of a system having modeling error is derived. An example is also included to show that the stability test is powerful.

• 분석과학
• /
• 제22권5호
• /
• pp.355-359
• /
• 2009

An enzyme electrode bound by rubber solution was newly constructed and the test of its practicability were carried out. The binder of carbon powder was styrene-butadiene rubber dissolved in toluene and enzyme source was ground tissue of cabbage root. Volatilization of the solvent made the electrode material possess a mechanical robustness and a fast signal appearance. The electrode showed electrochemically irreversible characteristics and a powerful catalytic power (detection limit=$5.0{\times}10^{-5}M$, S/N=2). The double reciprocal plot of signal current and substrate concentration was ideally linear and the symmetry factor and exchange current density of the electrode used in this work were 0.35 and $4.93{\times}10^{-5}Acm^{-2}$ respectively.

• 무역학회지
• /
• 제47권2호
• /
• pp.1-18
• /
• 2022

This paper examines the effects of export subsidies on agricultural food exports, focusing on a case of Gyeongsangbuk-do. Using monthly data of agricultural food exports during 2007-2020 and the GLS regression analysis, we test the hypothesis whether the export subsidies would increase the exports of four major agri-food categories with three digit codes of HS such as fruits, vegetables, flowers, and mushrooms. Evidence shows that the export subsidies had statistically significant impacts on the agri-food exports except flowers. In order to test the robustness of the analysis, the agri-food export subsidies are reclassified into four sub-subsidy policies, and the analysis re-examines the effects of the sub-subsidies on agri-food exports. It shows that export policies for production stabilization, logistics, and overseas marketing promote the exports of agri-foods significantly. Alternative export policies are drawn in this study since the existing subsidies conflict with the WTO agricultural agreement.

• Bulletin of the Korean Chemical Society
• /
• 제32권7호
• /
• pp.2397-2404
• /
• 2011

Variable selection k nearest neighbor QSAR modeling approach was applied to a data set of 80 3-arylisoquinolines exhibiting cytotoxicity against human lung tumor cell line (A-549). All compounds were characterized with molecular topology descriptors calculated with the MolconnZ program. Seven compounds were randomly selected from the original dataset and used as an external validation set. The remaining subset of 73 compounds was divided into multiple training (56 to 61 compounds) and test (17 to 12 compounds) sets using a chemical diversity sampling method developed in this group. Highly predictive models characterized by the leave-one out cross-validated $R^2$ ($q^2$) values greater than 0.8 for the training sets and $R^2$ values greater than 0.7 for the test sets have been obtained. The robustness of models was confirmed by the Y-randomization test: all models built using training sets with randomly shuffled activities were characterized by low $q^2{\leq}0.26$ and $R^2{\leq}0.22$ for training and test sets, respectively. Twelve best models (with the highest values of both $q^2$ and $R^2$) predicted the activities of the external validation set of seven compounds with $R^2$ ranging from 0.71 to 0.93.

• 대한원격탐사학회지
• /
• 제39권3호
• /
• pp.297-309
• /
• 2023

최근 조식동물로 인한 갯녹음 현상으로 인해 연안 생태계 및 어장환경의 황폐화가 가속화되고 있다. 이러한 갯녹음 현상을 모니터링하고 방지대책을 세우기 위해서는 광범위한 해역에 대한 원격탐사 기반의 모니터링 기술 도입이 필요하다. 본 연구에서는 수중에서 촬영된 동영상으로부터 조식동물을 탐지하고 모니터링하기 위한 딥러닝 기반 객체 탐지 모델의 강인성(robustness)을 비교 분석하였다. 우리나라 연안의 대표적인 조식동물 7종을 대상으로 이미지 데이터셋을 구축하였으며, 이를 활용하여 딥러닝 기반 객체 탐지 모델인 You Only Look Once (YOLO)v7과 YOLOv8을 훈련시켰다. 총 6개의 YOLO 모델(YOLOv7, YOLOv7x, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x)에 대해 탐지 성능과 탐지 속도를 평가하였으며, 수중환경에서 촬영 시 발생할 수 있는 다양한 이미지 왜곡에 대해서 강인성 평가를 실시하였다. 평가결과 YOLOv8 계열 모델이 파라미터(parameter) 수 대비 더 높은 탐지 속도(약 71-141 FPS [frame per second])를 보였다. 탐지 성능에 있어서도 YOLOv8 계열 모델(mean average precision [mAP] 0.848-0.882)이 YOLOv7 계열 모델(mAP 0.847-0.850)에 비해 더 높은 성능을 보이는 것을 확인하였다. 모델의 강인함에 있어서 형태 왜곡에 대해서는 YOLOv7 계열 모델이 YOLOv8 계열 모델에 비해 강인한 것을 확인하였으며, 색상 왜곡에 대해서는 YOLOv8 계열 모델이 상대적으로 강인한 것을 확인 하였다. 따라서 실해역에서 수중 영상 촬영 시, 형태 왜곡은 발생 빈도가 낮으며 색상 왜곡은 연안에서 빈번하게 발생한다는 점을 고려했을 때, 연안해역에서 조식동물 탐지와 모니터링을 위해서는 YOLOv8 계열 모델을 활용하는 것이 타당한 것으로 판단된다.

• 한국정밀공학회지
• /
• 제33권2호
• /
• pp.129-138
• /
• 2016

This paper presents a natural corners-based SLAM (Simultaneous Localization and Mapping) with a robust data association algorithm in a real unknown environment. Corners are extracted from raw laser sensor data, which are chosen as landmarks for correcting the pose of mobile robot and building the map. In the proposed data association method, the extracted corners in every step are separated into several groups with small numbers of corners. In each group, local best matching vector between new corners and stored ones is found by joint compatibility, while nearest feature for every new corner is checked by individual compatibility. All these groups with local best matching vector and nearest feature candidate of each new corner are combined by partial compatibility with linear matching time. Finally, SLAM experiment results in an indoor environment based on the extracted corners show good robustness and low computation complexity of the proposed algorithms in comparison with existing methods.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.255-265
• /
• 2020

This study aims to test the interrelationship among perceived value, tourist satisfaction, quality of life, and tourist loyalty in an Indonesian tourist adventure destination. The respondents were recruited from Bromo Mountain, East-Java Province, Indonesia. For this study, 250 questionnaires were distributed, of which 240 could be used for analysis, yielding a response rate of 96%. Data was analyzed using Partial Least Squares with smartPLS 3 software. Both outer model and inner model evaluation were conducted to ensure the robustness of the proposed model. The findings showed that perceived value does not have a direct significant effect on tourist loyalty. However, tourist satisfaction and quality of life have significant effects on tourist loyalty. The mediating effect test indicated that tourist satisfaction and quality of life significantly mediated the effect of perceived value on tourist loyalty. The multi-group analysis test found that the demographic factor does not have any influence. By accomplishing its research objectives, this study provides both theoretical and practical contributions. From a theoretical standpoint, this study provides a comprehensive conceptual model in explaining Indonesia adventure tourist loyalty. From a practical standpoint, this study offers recommendations to adventure tourism management to enhance the sustainability of the tourism destination, especially the adventure tourism destination.