• 한국인터넷방송통신학회논문지
• /
• 제19권1호
• /
• pp.29-35
• /
• 2019

4차 산업 혁명이 진행되며 많은 회사들의 스마트 팩토리에 대한 관심이 커지고 있으며 센서의 중요성 또한 대두되고 있다. 정보를 수집하기 위한 센서에서 고장이 발생하면 공장을 최적화하여 운영할 수 없기 때문에 이에 따른 손해가 발생할 수 있다. 이를 위해 센서의 상태를 진단하여 센서의 고장을 진단하는 일이 필요하다. 본 논문에서는 디지털 센서의 고장유형 중 Rising time과 Falling time 고장을 딥러닝 알고리즘 RNN의 LSTM을 통해 신호를 분석하여 고장을 진단하는 모델을 제안한다. 제안한 방식의 실험 결과를 정확도와 ROC 곡선 그래프의 AUC(Area under the curve)를 이용하여 Rule 기반 고장진단 알고리즘과 비교하였다. 실험 결과, 제안한 시스템은 Rule 기반 고장진단 알고리즘 보다 향상되고 안정된 성능을 보였다.

• 한국환경보건학회지
• /
• 제47권4호
• /
• pp.320-329
• /
• 2021

Background: Smoking exposure may be objectively assessed through specific biomarkers. The most common biomarker for smoking is cotinine concentration in urine, and setting an optimal cut-off point can accurately classify smoking status. Such a cut-off point for Korean adolescents has never been studied. Objectives: The aim of this study was to determine a cut-off point for urinary cotinine concentration for the discrimination of smoking in adolescents. Methods: Participants were adolescents aged 13~18 years who participated in the third cycle of the Korean National Environmental Health Survey. We used urine samples to confirm the level of cotinine concentrations. Smoking status was determined by self-reported questionnaire. We identified the optimal cotinine cut-off point for discriminating smoking status using receiver operating characteristic curve analysis. Results: Of the 904 participants, 28 (3.1%) were smokers, among whom 20 (71.4%) were male. The median urinary cotinine concentrations in smokers was 218 ㎍/L (male: 215 ㎍/L, female: 303 ㎍/L), and that in non-smokers was 1.31 ㎍/L (male: 1.46 ㎍/L, female: 1.18 ㎍/L). We found significant differences in urinary cotinine concentration according to smoking status and sex (p<0.001). Urinary cotinine concentrations performed well for identifying smoking adolescents [area under the curve: 0.954 (male: 0.963, female: 0.908)]. The cut-off that optimally distinguished smokers from non-smokers was 39.85 ㎍/L (sensitivity: 89.3%, specificity: 97.4%). Male [39.85 ㎍/L (sensitivity: 90.0%, specificity: 94.9%)] had a different optimal cut-off point than female [26.26 ㎍/L (sensitivity: 87.5%, specificity: 99.6%)]. Conclusions: This study determined a cut-off point for urinary cotinine of 39.85 ㎍/L (male: 39.85 ㎍/L, female: 26.26 ㎍/L) to distinguish smokers from non-smokers in adolescents.

• 한국지형학회지
• /
• 제27권3호
• /
• pp.87-103
• /
• 2020

The purpose of this study is to evaluate the risk of cropland and man-made infrastructures in a landslide-prone area using a GIS-based method. To achieve this goal, a landslide inventory map was prepared based on aerial photograph analysis as well as field observations. A total of 550 landslides have been counted in the entire study area. For model analysis and validation, extracted landslides were randomly selected and divided into two groups. The landslide causative factors such as slope, aspect, curvature, topographic wetness index, elevation, forest type, forest crown density, geology, land-use, soil drainage, and soil texture were used in the analysis. Moreover, to identify the correlation between landslides and causative factors, pixels were divided into several classes and frequency ratio was also extracted. A landslide susceptibility map was constructed using a bayesian predictive model (BPM) based on the entire events. In the cross validation process, the landslide susceptibility map as well as observation data were plotted with a receiver operating characteristic (ROC) curve then the area under the curve (AUC) was calculated and tried to extract a success rate curve. The results showed that, the BPM produced 85.8% accuracy. We believed that the model was acceptable for the landslide susceptibility analysis of the study area. In addition, for risk assessment, monetary value (local) and vulnerability scale were added for each social thematic data layers, which were then converted into US dollar considering landslide occurrence time. Moreover, the total number of the study area pixels and predictive landslide affected pixels were considered for making a probability table. Matching with the affected number, 5,000 landslide pixels were assumed to run for final calculation. Based on the result, cropland showed the estimated total risk as US $ 35.4 million and man-made infrastructure risk amounted to US $ 39.3 million.

• 한국지형학회지
• /
• 제26권3호
• /
• pp.53-67
• /
• 2019

The purpose of this study is to identify the quality of landslide susceptibility in a landslide-prone area (Jinbu-myeon, Gangwon-do, South Korea) by spatial prediction modeling approach and compare the results obtained. For this goal, a landslide inventory map was prepared mainly based on past historical information and aerial photographs analysis (Daum Map, 2008), as well as some field observation. Altogether, 550 landslides were counted at the whole study area. Among them, 182 landslides are debris flow and each group of landslides was constructed in the inventory map separately. Then, the landslide inventory was randomly selected through Excel; 50% landslide was used for model analysis and the remaining 50% was used for validation purpose. Total 12 contributing factors, such as slope, aspect, curvature, topographic wetness index (TWI), elevation, forest type, forest timber diameter, forest crown density, geology, landuse, soil depth, and soil drainage were used in the analysis. Moreover, to find out the co-relation between landslide causative factors and incidents landslide, pixels were divided into several classes and frequency ratio for individual class was extracted. Eventually, six landslide susceptibility maps were constructed using the Bayesian Predictive Discriminant (BPD), Empirical Likelihood Ratio (ELR), and Linear Regression Method (LRM) models based on different category dada. Finally, in the cross validation process, landslide susceptibility map was plotted with a receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) and tried to extract success rate curve. The result showed that Bayesian, likelihood and linear models were of 85.52%, 85.23%, and 83.49% accuracy respectively for total data. Subsequently, in the category of debris flow landslide, results are little better compare with total data and its contained 86.33%, 85.53% and 84.17% accuracy. It means all three models were reasonable methods for landslide susceptibility analysis. The models have proved to produce reliable predictions for regional spatial planning or land-use planning.

• Korean Journal of Radiology
• /
• 제23권1호
• /
• pp.139-149
• /
• 2022

Objective: To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists' performance for pulmonary nodule detection on chest radiographs (CXRs). Materials and Methods: A total of 111 adults, including 49 patients with 83 pulmonary nodules, who underwent both CXR using the dual energy technique and chest CT, were enrolled. Using CT as a reference, two independent radiologists evaluated CXR images for the presence or absence of pulmonary nodules in three reading sessions (standard CXR, BSt-DE CXR, and BSp-DL CXR). Person-wise and nodule-wise performances were assessed using receiver-operating characteristic (ROC) and alternative free-response ROC (AFROC) curve analyses, respectively. Subgroup analyses based on nodule size, location, and the presence of overlapping bones were performed. Results: BSt-DE with an area under the AFROC curve (AUAFROC) of 0.996 and 0.976 for readers 1 and 2, respectively, and BSp-DL with AUAFROC of 0.981 and 0.958, respectively, showed better nodule-wise performance than standard CXR (AUAFROC of 0.907 and 0.808, respectively; p ≤ 0.005). In the person-wise analysis, BSp-DL with an area under the ROC curve (AUROC) of 0.984 and 0.931 for readers 1 and 2, respectively, showed better performance than standard CXR (AUROC of 0.915 and 0.798, respectively; p ≤ 0.011) and comparable performance to BSt-DE (AUROC of 0.988 and 0.974; p ≥ 0.064). BSt-DE and BSp-DL were superior to standard CXR for detecting nodules overlapping with bones (p < 0.017) or in the upper/middle lung zone (p < 0.017). BSt-DE was superior (p < 0.017) to BSp-DL in detecting peripheral and sub-centimeter nodules. Conclusion: BSp-DL (GAN-based bone suppression) showed comparable performance to BSt-DE and can improve radiologists' performance in detecting pulmonary nodules on CXRs. Nevertheless, for better delineation of small and peripheral nodules, further technical improvements are required.

• 대한치과교정학회지
• /
• 제25권2호
• /
• pp.153-163
• /
• 1995

본 연구는 III급 부정 교합을 판별하는데 있어, 수평 부조화의 진단에 이용되는 여러 진단 항목들의 진단학적 효율과 타당성을 ROC analysis로 비교하는데 그 목적이 있다. ROC(Receiver Operating Characteristic) analysis는 연속적으로 변하는 cut-off value에서의 sensitivity와 1-specificity에 의해 그려지는 곡선으로서 진단 방법의 타당성을 결정하고, 여러 진단 방법들을 비교하는 분석법으로 알려져 있다. 부정교합자 496명을 대상으로 측모 두부 X-선 계측사진과 진단모형을 이용하여, 진단모형 계측을 통해 부정교합군을 분류하였으며, 이중 III급 부정 교합자는 245명이었다. 측모 두부 X-선계측사진에서 16개의 계측항목을 선정하였으며, 이 계측항목들과 III급 부정교합의 관계를 알아보고자 각도 계측항목에서는 $1^{\circ}$ 간격으로, 선계측항목에서는 1mm의 간격으로 sensitivity와 specificity를 구해 ROC curve를 그렸다. 그리고, 이 계측항목들의 직접적인 비교를 위해 ROC curve 아래의 면적을 계산해냈다. 결과는 다음과 같다. 1. III급 부정교합을 판별하는데 있어, "Wits" appraisal이 다른 계측 항목에 비해 더 나은 진단 효율을 보였다. 2. AB plane angle, ANB angle, App-Bpp distance, AF-BF distance, APDI, N perpendicular to A 와 Pog to N perpendicular의 차이, maxillomandibular differential도 높은 진단 가치를 보였다. 3. 하악골의 위치를 평가하는 계측항목은 중정도의 진단 효율을 보였다. 4. 상악골에 대한 계측항목은 III급 부정교합의 판별에 대한 진단 가치가 낮았다.

• 문화기술의 융합
• /
• 제6권3호
• /
• pp.457-462
• /
• 2020

골다공증은 주로 노인에서 나타나는 질병으로써 뼈 질량 및 조직의 구조적 악화에 따라 골절의 위험을 증가시킨다. 본 연구의 목적은 영양소 성분과 골다공증과의 연관성을 파악하고, 영양소 성분을 기반으로 골다공증을 예측하는 모델을 생성 및 평가하는 것이다. 실험방법으로 binary logistic regression을 이용하여 연관성분석을 수행하였고, naive Bayes 알고리즘과 variable subset selection 메소드를 이용하여 예측 모델을 생성하였다. 단일 변수들에 대한 분석결과는 남성에서 식품섭취량과 비타민 B2가 골다공증을 예측하는데 가장 높은 the area under the receiver operating characteristic curve (AUC)값을 나타내었다. 여성에서는 단일불포화지방산이 가장 높은 AUC값을 나타내었다. 여성 골다공증 예측모델에서는 Correlation based feature subset 및 wrapper 기반 feature subset 메소드를 이용하여 생성된 모델이 0.662의 AUC 값을 얻었다. 남성에서 전체변수를 이용한 모델은 0.626의 AUC를 얻었고, 그외 남성 모델들에서는 민감도와 1-특이도에서 예측 성능이 매우 낮았다. 이러한 연구결과는 향후 골다공증 치료 및 예방을 위한 기반정보로 활용할수 있을 것으로 기대된다.

• 전자공학회논문지
• /
• 제52권8호
• /
• pp.67-73
• /
• 2015

디지털 영상의 배포에서, 위 변조자에 의해 영상이 변조되는 심각한 문제가 있다. 이러한 문제를 해결하기 위하여, 본 논문에서는 영상의 Fourier 변환 변이계수를 이용한 미디언 필터링 (Median Filtering: MF) 영상의 포렌식 판정 알고리즘을 제안한다. 제안된 알고리즘에서, 영상의 각 수평, 수직라인의 Fourier 변환 (Fourier Transform: FT)을 하고, 이웃 라인과의 변이계수를 기반으로 하여 MF 검출 (Median Filtering Detection: MFD)을 위한 10 Dim. 특징벡터를 정의한다. 이는 MF 검출기의 SVM (Support Vector Machine) 학습에 사용된다. 제안된 미디언 필터링 검출 스킴은 동일 10 Dim. 특징벡터의 MFR (Median Filter Residual)과 Rhee의 MF 검출 스킴과 비교하여 원영상, JPEG (QF=90), Down 스케일링 (0.9) 그리고 Up 스케일링 (1.1) 영상에서는 성능이 우수하며, Gaussian 필터링($3{\times}3$) 영상에서는 성능이 일부 높았다. 제안된 알고리즘은 성능평가 전체항목에서 민감도 (Sensitivity; TP: True Positive rate)와 1-특이도 (1-Specificity; FP: False Positive rate)에 의한 AUC (Area Under ROC (Receiver Operating Characteristic) Curve)가 모두 1에 수렴하여 'Excellent (A)' 등급임을 확인하였다.

• 대한산업공학회지
• /
• 제40권3호
• /
• pp.325-332
• /
• 2014

High cognitive workload decreases a driver's ability of judgement and response in traffic situation and could result in a traffic accident. Electrocardiography (ECG) has been used for evaluation of drivers' cognitive workload; however, individual differences in ECG response corresponding to cognitive workload have not been fully considered. The present study developed an evaluation method of individual driver's cognitive workload based on ECG data, and evaluated its usefulness through an experiment in a driving simulator. The evaluation method developed by the present study determined the optimal ECG evaluation condition for individual participant by analysis of area under the receiver operating characteristic curve (AUC) for various conditions (total number of conditions = 144) in terms of four aspects (ECG measure, window span, update rate, and workload level). AUC analysis on the various conditions showed that the optimal ECG evaluation condition for each participant was significantly different. In addition, the optimal ECG evaluation condition could accurately detect changes in cognitive workload for 47% of the total participants (n = 15). The evaluation method proposed in the present study can be utilized in the evaluation of individual driver's cognitive workload for an intelligent vehicle.

• 한국방사선학회논문지
• /
• 제11권3호
• /
• pp.131-137
• /
• 2017

본 연구는 부산 경남지역의 담낭담석의 위험인자를 알아보고자 하였다. 실험대상은 2016년 6월~12월까지 2016년 12월까지 부산 P병원을 내원하여 복부초음파를 실시한 대상으로 하였다. 그 중 복부초음파와 혈청학적 검사를 동시에 실시한 353명을 대상으로 위험인자를 분석하였다. 초음파 검사 상 담낭담석과 관련있는 위험인자들의 통계분석은 독립표본 t검정(independent t-test)과 카이제곱 검정(chi-square test)을 시행하였다. 차이검정 결과를 고려하여 독립변수에 대한 상대 위험비(odds ratio, OR) 산출을 위해 다중 로지스틱 회귀분석(multiple logistic regression analysis)을 시행하여 변수들로부터 예측모형을 산정하여 타당성을 검정하였다. 그 결과 담낭담석 위험인자로 확인된 연령, ${\gamma}GTP$로 예측모형 및 예측 확률값을 산출하였다. 연령에서 민감도 49.7%, 특이도 82.2%를 보였으며, ROC 곡선하면적이 0.724를 나타내었다. ${\gamma}GTP$에서는 민감도 69.3%, 특이도 62.4%를 보였으며, ROC 곡선하면적이 0.699를 나타내어 예측모형의 타당성을 확인할 수 있었다.