• 한국정보처리학회논문지
• /
• 제6권12호
• /
• pp.3514-3522
• /
• 1999

대량의 정보를 대상으로 하는 웹 정보 검색 기술은 정보를 수집하는 방법과 브라우징의 시각화 인터페이스 기법에 대해 활발히 연구가 진행된 반면에, 수집된 정보를 효율적으로 분류하는 구조적 모델링에 관한 연구는 미흡한 실정이다. 이 논문에서는 정보의 구조적 모델을 기반으로 하여 정보의 특성을 시각적인 기법으로 제공함으로써 사용자의 검색 환경을 효율적으로 운용하는데 목적이 있다. 이를 위해 정보가 갖는 특성을 기반으로 하여 정보를 Facet 단위로 분류하는 구조적 방법을 제안하고, 정보간의 관련성을 정의한다. 또한, 각 Facet 단위의 정보가 갖는 특성에 대한 분석 결과를 다중 뷰를 통해 시각화한다. 따라서, 사용자는 검색 대상 범위의 정보에 대한 체계적인 구조 및 시각화된 정보를 인지한 후, 좀 더 쉽게 검색을 수행할 수 있다. 중심어 매칭 방식에 의한 검색 결과 목록을 제시하는 기존의 검색 기법이 정보를 찾는데 중점을 둔 반면에, 이 논문은 저장된 정보가 무엇이 있는지를 구조적으로 표현하여 사용자의 이해도를 향상시킴으로써 사용자의 관점에 중점을 둔다.

• Korean Journal of Radiology
• /
• 제21권7호
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.

• 한국산업보건학회지
• /
• 제24권2호
• /
• pp.208-218
• /
• 2014

Objectives: The major objective of this study was to develop and validate a tier 1 exposure model utilizing worker exposure monitoring data and characteristics of worker activities routinely performed at construction sites, in order to estimate worker exposures without sampling. Methods: The Registration, Evaluation, Authorization and Restriction of Chemicals(REACH) system of the European Union(EU) allows the usage of exposure models for anticipating chemical exposure of manufacturing workers and consumers. Several exposure models have been developed such as Advanced REACH Tools(ART). The ART model is based on structured subjective assessment model. Using the same framework, a tier 1 exposure model has been developed. Worker activities at construction sites have been analyzed and modifying factors have been assigned for each activity. Korean Occupational Safety and Health Agency(KOSHA) accrued work exposure monitoring data for the last 10 years, which were retrieved and converted into exposure scores. A separate set of sampling data were collected to validate the developed exposure model. These algorithm have been realized on Excel spreadsheet for convenience and easy access. Results: The correlation coefficient of the developed model between exposure scores and monitoring data was 0.36, which is smaller than those of EU models(0.6~0.7). One of the main reasons explaining the discrepancy is poor description on worker activities in KOSHA database. Conclusions: The developed tier 1 exposure model can help industrial hygienists judge whether or not air sampling is required or not.

• 재활복지공학회논문지
• /
• 제4권1호
• /
• pp.71-80
• /
• 2010

본 연구의 목적은 병원에서 기밀한 환자의료정보를 다루는 물리치료사와 작업치료사 행동의 예측모형을 개발하고자 하는 것이다. 계획된 행동 모델이론과 계획된 행동 모델에 습관, 사회적 압력, 업무 편리성의 변수를 추가하여 확장 모델 1, 2로 환자의료기록을 보장하는 물리치료사와 작업치료사의 행동에 영향을 미치는 전치 요소들을 설명하는 타당성을 검증하고자 하였다. A 시의 120명의 물리치료사와 작업치료사를 대상으로 설문조사를 실시하였다. 120부의 설문지가 배포되었으며, 110부가 회수되어 91.6%의 응답률을 보였다. Independent t test와 one-way ANOVA를 사용하여, 나이 임상 경력, 성별, 직장 내 구성원과 교육 수준에 따른 각 군 간의 차이를 검증하였으나, 통계적인 유의미한 차이는 없었다. 모델에서 제안된 개념들 간의 관계는 구조모형방정식을 사용하여 분석하였다. 구조모형방정식을 사용하여 분석한 결과 확장 모델 2가 TpB 모델과 확장된 모델 1보다 효과적인 모델로 나타났다.

• 환경영향평가
• /
• 제6권2호
• /
• pp.113-121
• /
• 1997

LHR(Landfill Hazard Ranking Model) was developed for assessing the relative hazard of landfills by using the method of value-structured approach. LHR consists of combining a multiattribute decision-making method with a qualitative risk assessment approach. A pairwise comparision method was applied to determine weights of landfill factors related. To prove the validity of weights allocation of landfill hazard evaluation factors, sensitivity analysis was applied. Firstly, the impact on landfill hazard score according to variations of weights of landfill hazard factors was analyzed. Secondly, the impact on landfill hazard score according to conditions change of landfill hazard factors was analyzed. As a result of sensitivity analysis, LHR composite scores are largely influenced by some factors following sequential order such as waste volume, proximity to sensitive environments, containment facilities, distance from drinking water supplies, and waste toxicity. The relative order of landfill hazard evaluated by LHR is not influenced by the weights change of individual factors. Therefore, LHR seems to be a credible model to determine priorities of landfill remediation based on the vulnerability of water resources.

• 한국생산제조학회지
• /
• 제22권1호
• /
• pp.168-172
• /
• 2013

In 3D wafer-stacking technology, one of the major issues is wafer warpage. Especially, The important reason of warpage has been known due to CTE(Coefficient of Thermal Expansion) mismatch between materials. It was too hard to choose how to make the FE model for blanket structured wafer level 3D packaging, because the thickness of each layer in wafer level 3D packaging was too small (micro meter or nano meter scale) comparing with diameter of wafer (6 or 8 inches). In this study, the FE model using the shell element was selected and simulated by the ANSYS WorkBench to investigate effects of the CTE on the warpage. To verify the FE model, it was compared by experimental results.

• Journal of Mechanical Science and Technology
• /
• 제17권12호
• /
• pp.1844-1854
• /
• 2003

This paper discusses details of modeling and robust control of an AMB (active magnetic bearing) spindle, and part I presents a modeling and validation process of the AMB spindle. There are many components in AMB spindle : electromagnetic actuator, sensor, rotor, power amplifier and digital controller. If each component is carefully modeled and evaluated, the components have tight structured uncertainty bounds and achievable performance of the system increases. However, since some unknown dynamics may exist and the augmented plant could show some discrepancy with the real plant, the validation of the augmented plant is needed through measuring overall frequency responses of the actual plant. In addition, it is necessary to combine several components and identify them with a reduced order model. First, all components of the AMB spindle are carefully modeled and identified based on experimental data, which also render valuable information in quantifying structured uncertainties. Since sensors, power amplifiers and discretization dynamics can be considered as time delay components, such dynamics are combined and identified with a reduced order. Then, frequency responses of the open-loop plant are measured through closed-loop experiments to validate the augmented plant. The whole modeling process gives an accurate nominal model of a low order for the robust control design.

• 제어로봇시스템학회논문지
• /
• 제21권1호
• /
• pp.34-39
• /
• 2015

In this paper, a finite impulse response (FIR) filter is proposed for discrete-time nonlinear systems. The proposed filter is designed by combining the estimate of the perturbation state and nominal state. The perturbation state is estimated by adapting the optimal time-varying FIR filter for the linearized perturbation model and the nominal state is directly obtained from the nonlinear nominal trajectory model. Since the FIR structured estimators use the finite horizon information on the most recent time interval, the proposed extended FIR filter satisfies the bounded input/bounded output (BIBO) stability, which can't be obtained from infinite impulse response (IIR) estimators. Thus, it can be expected that the proposed extended FIR filter is more robust than IIR structured estimators such as an extended Kalman filter for the round-of errors and the uncertainties from unknown initial states and uncertain system model parameters. The simulation results show that the proposed filter has better performance than the extended Kalman filter (EKF) in both robustness and fast convergency.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.113-119
• /
• 2019

It has been reported that large amounts of information on agri-foods were delivered to consumers through television and social networks, and the information may influence consumers' behavior. The purpose of this paper was first to analyze relations of social network service and broadcasting program on paprika consumption in the aspect of amounts to purchase and identify potential factors that can promote paprika consumption; second, to develop prediction models of paprika consumption by using structured and unstructured big data. By using data 2010-2017, cross-correlation and time-series prediction algorithms (autoregressive exogenous model and vector error correction model), statistically significant correlations between paprika consumption and television programs/shows and blogs mentioning paprika and diet were identified with lagged times. When paprika and diet related data were added for prediction, these data improved the model predictability. This is the first report to predict paprika consumption by using structured and unstructured data.

• Asia pacific journal of information systems
• /
• 제10권2호
• /
• pp.1-22
• /
• 2000

This paper presents an exploratory research on the application of the Technology Acceptance Model(TAM) to the domain of object orientation to investigate the validity of TAM in the perspective of its causal relationships. In the Management Information Systems(MIS) area, TAM has been applied to computer usage behavior as a specific technology adoption model. This paper also suggests the factors that affect the technology acceptance of object orientation in U.S. organizations through a modified TAM. Two major research questions are addressed. First, this research investigates the effect of these external variables on the dependent variable, the actual usage of object orientation in the viewpoint of knowledge interaction between structured methods and object orientation. Second, is TAM valid for the technology acceptance of object orientation in terms of its causal relationships? This study empirically explores the impact of the external variables on the level of actual usage of object orientation via the mediating variables in TAM. A structured questionnaire is administered to Data Processing Management Association(DPMA) professionals in US. The result of this study reveals one important contradictory finding that is not consistent with expectations based on related theory. TAM does not accommodate the technology acceptance of object orientation perhaps because object orientation is a complex and organization-level adoptive technology or the measures for the mediating constructs in TAM may not be appropriate in industry settings.