• The Korean Journal of Nuclear Medicine
• /
• v.32 no.4
• /
• pp.332-343
• /
• 1998

Purpose: The purpose of this study was to assess the diagnostic accuracy of various quantitation methods using F-18-fluorodeoxyglucose (FDG) in patients with malignant or benign lung lesion. Materials and Methods: 22 patients (13 malignant including 5 bronchoalverolar cell cancer; 9 benign lesions including 1 hamartoma and 8 active inflammation) were studied after overnight fasting. We performed dynamic PET imaging for 56 min after injection of 370 MBq (10 mCi) of FDG. Standardized uptake values normalized to patient's body weight and plasma glucose concentration (SUVglu) were calculated. The uptake rate constant of FDG and glucose metabolic rate were quantified using Patlak graphical analysis (Kpat and MRpat), three compartment-five parameter model (K5p, MR5p), and six parameter model taking into account heterogeneity of tumor tissue (K6p, MR6p). Areas under receiver operating characteristic curves (ROC) were calculated for each method. Results: There was no significant difference of rate constant or glucose metabolic rate measured by various quantitation methods between malignant and benign lesions. The area under ROC curve were 0.73 for SUVglu, 0.66 for Kpat, 0.77 for MRpat, 0.71 for K5p, 0.73 for MR5p, 0.70 for K6p, and 0.78 for MR6p. No significant difference of area under the ROC curve between these methods was observed except the area between Kpat vs. MRpat (p<0.05). Conclusion: Quantitative methods did not improve diagnostic accuracy in comparison with nonkinetic methods. However, the clinical utility of these methods needs to be evaluated further in patients with low pretest likelihood of active inflammation or bronchoalveolar cell carcinoma.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.186-189
• /
• 1993

능동 소나 체계에서 표적의 탐지거리 예측을 위하여 소나방정식이 이용되는데, 이는 음원 준위, 전달 손실, 표적 강도, 복반사 준위, 소음 준위, 방향성 이득, Detection threshold, Signal excess, 탐지 확률과 탐지거리의 요소로 구성된다. 본 연구에서는 능동 소나 체계에서 소나 깊이와 표적 깊이의 함수인 탐지거리를 계산하기 위한 알고리즘에 대해 살펴보았다. 소나의 각 요소와 환경이 주어졌을 때 SAFARI 모델을 이용하여 각 수신기의 깊이와 거리에서의 전달손실을 계산하였으며, 구하여진 전달 손실과 배경 소음 준위를 이용하여 Signal excess를 계산하였다. ROC(Receiver-operating-characteristic) 곡선을 이용하여 Signal excess를 탐지 확률로 계산한 후 두 항을 곱하여 각 깊이별 거리로 적분함으로서 탐지거리를 구하였다. 주파수 30Hz의 전방향 음원을 사용하여 여름의 일반적 음속 분포에서 계산한 결과 100m 음원 보다 300m 음원에서 상대적으로 큰 탐지거리를 얻었으며 각 음원 깊이별 평균 탐지거리는 100m 이하의 표면을 제외한 500m 까지는 거의 일정함을 알 수 있었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.148-151
• /
• 2006

본 논문에서 얼굴과 홍채 데이터를 사용하여 다중생체시스템에 기반한 스테가노그라피 구현을 제안한다. 이를 위해, 얼굴과 홍채 인식 기반의 다중생체인식을 구성하였다. 여기서, 홍채의 특징벡터는 디지털 워터마킹 기법을 이용하여 얼굴 이미지 안에 숨기게 된다. 얼굴과 홍채의 인식시스템은 퍼지집합 이론과 LDA 기법이 결합하여 확장한 Fuzzy-LDA(Fuzzy-Based Linear Discriminant Analysis)기법을 제안한다. 최종적으로 디지털 워터마킹 기법을 적용하여 얼굴이미지 안에 홍채 정보를 삽입하고 얼굴 데이터와 홍채 데이터를 통한 다중생체인식을 구성하였으며, 최종적으로 생체데이터 인식율의 ROC 곡선을 통해 제안된 워터마킹 기법의 좋은 성능을 확인하였고, 얼굴 인식율을 통해 워터마킹된 얼굴 영상과 원본 얼굴 영상을 비교하였다. 다양한 실험을 통해 제안된 기법이 다중생체시스템을 보호하고 효과적으로 사용 될 수 있음을 확인 할 수 있다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.133-136
• /
• 2000

에너지 차분 흥부 X선 화상으로부터 폐종류 음영을 검출하기 위한 필터를 예측해서 전문의의 진단보조 혹은 총합자동진단시스템의 구성 요소로서 필터가 발휘한 역할을 고려한 후, 구체적인 성능 평가 방법을 제안한다. 필터의 성능을 평가할 때 문턱값을 변화시킨 경우, 못보고 빠트린 비율과 잘못 본 비율의 변화를 ROC 곡선으로 나타내어 이것에 기초한 판단을 행하는 접근방법이 있다. 본 연구에서는 이와같은 평가에 대한 구체적인 예를 통하여 문제점을 명확히 하여 그 평가기준을 마련한다. 성능 평가를 행하기 위해 이용된 에너지 차분화상으로서, 임상 데이터 14개의 증예를 이용한다. 즉, 총 종류수 32개 한 개의 증예에 있어서 종류의 개수는 1~8개로 평균 2개, 1mm 당 샘플링 간격 5 픽셀, 비트 분해능 10 bit의 저압화상으로, 그 크기는 1760$\times$1760이다. 계산기 하드웨어의 제약으로부터 원화상을 가우스 함수로 평활화 해서 1/8로 축소한 화상으로 실험을 행한다. 상기 평가 절차에 따라, 이전에 개발된 다중해상도 ∇$^2$G 필터의 성능을 평가하고, 단일해상도 ∇$^2$G 필터와의 비교를 통해 그 성능이 우수함을 확인한다. 본 평가 방법은 화상진단 지원용 필터의 평가에 대해서 적용될 수 있을 것이다.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.247-252
• /
• 2015

As software has gotten bigger in magnitude and the complexity of software has been increased, the maintenance has gained in-creasing attention for its significant impact on the cost. Identifiers have an impact on more than 90 percent of the readability which accounts for a majority portion of the maintenance activities. For this reason, the existing works focus on domain-specific features based on identifiers. However, their approaches have a limitation when either a class name does not reflect the intention of its context or a class naming is incorrect. Therefore, this paper suggests a series of class name validation process by extracting properties of classes, building learning model by applying a decision tree technique of machine learning, and generating a validation report containing the list of recommendable postfixes of classes to be validated. To evaluate this, four open source projects are selected and indicators such as precision, recall, and ROC curve present the value of this work when it comes to five specific postfixes including functional information on class names.

• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.395-407
• /
• 2020

Most classification accuracy measures for optimal threshold are divided into two types: one is expressed with cumulative distribution functions and probability density functions, the other is based on ROC curve and AUC. Unal (2017) proposed the index of union (IU) as an accuracy measure that considers two types to get them. In this study, ten kinds of accuracy measures (including IU) are divided into six categories, and the advantages of the IU are studied by comparing the measures belonging to each category. The optimal thresholds of these measures are obtained by setting various normal mixture distributions; subsequently, the first and second type of errors as well as the error sums corresponding to each threshold are calculated. The properties and characteristics of the IU statistic are explored by comparing the discriminative power of other accuracy measures based on error values.The values of the first type error and error sum of IU statistic converge to those of the best accuracy measures of the second category as the mean difference between the two distributions increases. Therefore, IU could be an accuracy measure to evaluate the discriminant power of a model.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.746-755
• /
• 2013

This paper presents a three dimensional bilateral filter detecting target trajectory, extracting spatial target information using two dimensional bilateral filter and temporal target information using one dimensional bilateral filter. In order to discriminate edge pixel with flat background and target region spatially and temporally, spatial and temporal variance are used for an image and temporal profile. With this procedure, background and background profile are predicted without original target through two dimensional and one dimensional bilateral filter. Finally, using spatially predicted background and temporally predicted background profile, small target can be detected. For comparison of existing target detection methods and the proposed method, the receiver operating characteristics (ROC) is used in experimental results. Experimental results show that the proposed method has superior target detection rate and lower false alarm rate.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.4
• /
• pp.277-288
• /
• 2020

In this study, we performed algorithms to predict algae of Chlorophyll-a (Chl-a). Water quality and quantity data of the middle Nakdong River area were used. At first, the correlation analysis between Chl-a and water quality and quantity data was studied. We extracted ten factors of high importance for water quality and quantity data about the two weirs. Algorithms predicted how ten factors affected Chl-a occurrence. We performed algorithms about decision tree, random forest, elastic net, gradient boosting with Python. The root mean square error (RMSE) value was used to evaluate excellent algorithms. The gradient boosting showed 10.55 of RMSE value for the Gangjeonggoryeong (GG) site and 11.43 of RMSE value for the Dalsung (DS) site. The gradient boosting algorithm showed excellent results for GG and DS sites. Prediction value for the four algorithms was also evaluated through the Receiver operating characteristic (ROC) curve and Area under curve (AUC). As a result of the evaluation, the AUC value was 0.877 at GG site and the AUC value was 0.951 at DS site. So the algorithm's ability to interpret seemed to be excellent.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.3 s.106
• /
• pp.272-279
• /
• 2006

In this paper, we evaluate the performance of frame synchronization words of pilot bit patterns which are used for the channel estimation and frame synchronization confirmation in W-CDMA(Wide band Code Division Multiple Access) system. W-CDMA system also uses compressed mode to make measurements from another frequency without a full dual receiver terminal. It is confirmed by using computer simulation that the proposed frame synchronization words also maintain the frame synchronization property in the compressed mode by using the complementary mapping relationship of preferred pair ROC(Receiver Operating Characteristic) curves with probability of detection and false alarm are used to analized the performance of the proposed frame synchronization words by using the various detection metrics such as LLRT(Log Likelyhood Ratio Test), GLRT(Generalied Likelyhood Ratio Test), soft and hard correlation tests in AWGN and Rayleigh fading channels. It is expected that the research results fer the performance of pilot bit patterns of this paper can be useful reference for the design and implementation of frame synchronization in 3rd generation W-CDMA system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.1C
• /
• pp.8-16
• /
• 2010

This paper presents a new small target detection method using the cross product of the temporal pixels based on the temporal profile in infrared (IR) image sequences. The temporal characteristics of small targets and the various backgrounds are different. A new algorithm classifies target pixels and the background pixels through the hypothesis testing using the cross product of pixels on the temporal profile and predicts the temporal backgrounds based on the results. The small targets are detected by subtracting the predicted temporal background profile from the original temporal profile. For the performance comparison between the proposed algorithm and the conventional algorithms, the receiver operating characteristics (ROC) curves is computed in experiment. Experimental results show that the proposed algorithm has better discrimination and a lower false alarm rate than the conventional methods.