• Korean Journal of Radiology
• /
• 제23권4호
• /
• pp.466-478
• /
• 2022

Objective: ¹⁸F-fluorodeoxyglucose (FDG) PET/CT is often used for detecting malignancy in patients with newly diagnosed hemophagocytic lymphohistiocytosis (HLH), with acceptable sensitivity but relatively low specificity. The aim of this study was to improve the diagnostic ability of ¹⁸F-FDG PET/CT in identifying malignancy in patients with HLH by combining ¹⁸F-FDG PET/CT and clinical parameters. Materials and Methods: Ninety-seven patients (age ≥ 14 years) with secondary HLH were retrospectively reviewed and divided into the derivation (n = 71) and validation (n = 26) cohorts according to admission time. In the derivation cohort, 22 patients had malignancy-associated HLH (M-HLH) and 49 patients had non-malignancy-associated HLH (NM-HLH). Data on pretreatment ¹⁸F-FDG PET/CT and laboratory results were collected. The variables were analyzed using the Mann-Whitney U test or Pearson's chi-square test, and a nomogram for predicting M-HLH was constructed using multivariable binary logistic regression. The predictors were also ranked using decision-tree analysis. The nomogram and decision tree were validated in the validation cohort (10 patients with M-HLH and 16 patients with NM-HLH). Results: The ratio of the maximal standardized uptake value (SUVmax) of the lymph nodes to that of the mediastinum, the ratio of the SUVmax of bone lesions or bone marrow to that of the mediastinum, and age were selected for constructing the model. The nomogram showed good performance in predicting M-HLH in the validation cohort, with an area under the receiver operating characteristic curve of 0.875 (95% confidence interval, 0.686-0.971). At an appropriate cutoff value, the sensitivity and specificity for identifying M-HLH were 90% (9/10) and 68.8% (11/16), respectively. The decision tree integrating the same variables showed 70% (7/10) sensitivity and 93.8% (15/16) specificity for identifying M-HLH. In comparison, visual analysis of ¹⁸F-FDG PET/CT images demonstrated 100% (10/10) sensitivity and 12.5% (2/16) specificity. Conclusion: ¹⁸F-FDG PET/CT may be a practical technique for identifying M-HLH. The model constructed using ¹⁸F-FDG PET/CT features and age was able to detect malignancy with better accuracy than visual analysis of ¹⁸F-FDG PET/CT images.

• 한국측량학회지
• /
• 제30권1호
• /
• pp.49-58
• /
• 2012

도심지의 빌딩들은 시간이 갈수록 형태가 다양해지고, 식생이나 도로와 같은 객체들과 유사한 분광 특성을 나타냄으로써 광학 영상만을 이용하여 추출하기가 어려워지고 있다. 본 연구에서는 이러한 문제를 해결하기 위해 항공 Light Detection and Ranging(LiDAR) 자료와 항공 사진의 융합을 통해 항공 사진상에서의 빌딩과 그 경계를 추출하는 방법을 제안한다. 먼저 항공 사진에 Adaptive dynamic range linear stretching 방사 강조 기법을 적용하고, 에디슨 에지 디텍터를 이용하여 이진 경계 지도를 생성하였다. 동시에 항공 LiDAR 자료로부터 normalized Digital Surface Model을 생성하고, 빌딩 영역을 추출하여 이진 경계 지도와의 중첩을 통해 임시 빌딩 영역을 추출하였다. 마지막으로 항공 LiDAR 자료와 항공 사진 간의 위치 오차를 고려하여 경계 강화 과정을 수행함으로써 최종 빌딩 경계를 추출하였다. 제안 방법의 검증을 위해 두 개의 실험 지역을 선정하여 제안 방법을 적용하였고, 정량적인 정확도평가에서 F-measure, Jaccard coefficient, Yule coefficient, Overall accuracy의 값이 모두 0.85 이상의 정확도를 보여주었다.

• Journal of Animal Science and Technology
• /
• 제57권3호
• /
• pp.9.1-9.5
• /
• 2015

Background: A simple binary scoring system (SBSS) was developed and used to assess the welfare measures of commercial broiler chickens in South Korea. We also correlated welfare measures with environmental parameters of broiler house. Our measures of welfare included lameness, hock burn (HB) and foot pad dermatitis (FPD), whilst environmental parameters included air temperature, relative humidity, air speed, light intensity, air quality (in particular carbon dioxide ($CO_2$) and ammonia ($NH_3$) concentrations) and airborne microbes. Results: The effect of environmental parameters on welfare measures was apparent even on 10-day-old broilers. A non-parametric correlation analysis revealed significant correlations between environmental parameters and welfare measures. The key environmental parameters were relative humidity and light intensity. The results indicate that there is a need for proper control of environmental conditions on poultry farms, which could reduce health problems and subsequently reduce disease and mortality. Conclusions: In conclusion, the simplicity of SBSS makes it preferable over more complex scoring systems and allows a farmer to more easily assess the welfare measures on their own farm.

• 정보보호학회논문지
• /
• 제29권2호
• /
• pp.275-285
• /
• 2019

웹 어셈블리는 웹 브라우저 자바스크립트의 성능 향상을 위해 설계된 새로운 바이너리 표준이다. 웹 어셈블리는 효율적인 실행 및 간결한 표현과 여러 언어를 바탕으로 작성된 코드를 네이티브에 가까운 속도로 구동될 수 있는 새로운 웹 표준으로 자리 잡고 있다. 하지만 현재 웹 어셈블리 취약성 검증은 웹 어셈블리 인터프리터 언어에 제한되어 있으며, 웹 어셈블리 바이너리 자체에 대한 취약성 검증은 부족한 상황이다. 따라서 웹 어셈블리의 자체적인 안전성 검증이 필요한 실정이다. 본 논문에서는 먼저 웹 어셈블리의 구동 방식과 현재 웹 어셈블리의 안전성 검증 방법에 대해서 분석한다. 또한 기존에 발생하였던 웹 어셈블리 안전성 검증 방식에 대해 살펴보고, 이에 따른 기존 안전성 검증 방식의 한계점을 분석한다. 최종적으로 기존 안전성 검증 방법의 한계점을 극복하기 위한 웹 어셈블리 API 기반 퍼징 방법을 소개한다. 이는 기존 안전성 검증 도구로 탐지할 수 없었던 크래시를 탐지함으로써 제안하는 퍼징의 효용성을 검증한다.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.

• Journal of Forest and Environmental Science
• /
• 제28권3호
• /
• pp.170-178
• /
• 2012

Dipterocarps or Dipterocarpaceae is a commercially important timber producing and dominant keystone tree family in the rain forests of Borneo. Borneo's landscape is changing at an unprecedented rate in recent years which affects this important biodiversity. This paper attempts to model the natural occurrence (distribution including those areas with natural forests before being converted to other land uses as opposed to current distribution) of dipterocarp species in Sarawak which is important for forest biodiversity conservation and management. Local modeling method of Inverse Distance Weighting was compared with commonly used statistical method (Binary Logistic Regression) to build the best natural distribution models for three genera (12 species) of dipterocarps. Database of species occurrence data and pseudoabsence data were constructed and divided into two halves for model building and validation. For logistic regression modeling, climatic, topographical and edaphic parameters were used. Proxy variables were used to represent the parameters which were highly (p>0.75) correlated to avoid over-fitting. The results show that Inverse Distance Weighting produced the best and consistent prediction with an average accuracy of over 80%. This study demonstrates that local interpolation method can be used for the modeling of natural distribution of dipterocarp species. The Inverse Distance Weighted was proven a better method and the possible reasons are discussed.

• 한국인터넷방송통신학회논문지
• /
• 제10권5호
• /
• pp.57-62
• /
• 2010

최근 의료분야에서는 대규모의 데이터를 빠르게 검색 및 추출이 가능하게 의사결정트리 기법에 대한 연구들이 진행되고 있다. 현재 CART, C4.5, CHAID 등 여러 기법이 개발되었는데, 이러한 클레시파이 기법들은 몇몇 의사결정 나무 알고리즘이 이진분리로 분류를 하는데, 나머지 데이터의 결과가 손실될 우려가 있다. 그중 C4.5는 엔트로피의 측정값에 높고 낮음으로 트리 모양을 구성해 가는 방식이고, CART 알고리즘은 엔트로피 매트릭스를 사용하여 범주형 자료나 연속형 자료에 적용할수가 있다. 이에 본 논문에서는 클래시파이 기법 중 C4.5와 CART를 유방암 환자 데이터에 대해 적용하여 실험하여, 그 결과 분석을 통한 성능 평가를 수행하였다. 실험에서는 교차검증을 통해 그 결과에 대한 정확성을 측정하였다.

• ETRI Journal
• /
• 제42권3호
• /
• pp.324-332
• /
• 2020

In this paper, a blind symbol timing offset (STO) estimation method is proposed for offset quadrature phase-shift keying (OQPSK) modulated signals, which also works for other linearly modulated signals (LMS) such as binary-PSK, QPSK, 𝜋/4-QPSK, and minimum-shift keying. There are various methods available for blind STO estimation of LMS; however, none work in the case of OQPSK modulated signals. The popular cyclic correlation method fails to estimate STO for OQPSK signals, as the offset present between the in-phase (I) and quadrature (Q) components causes the cyclic peak to disappear at the symbol rate frequency. In the proposed method, a set of close and approximate offsets is used to compensate the offset between the I and Q components of the received OQPSK signal. The STO in the time domain is represented as a phase in the cyclic frequency domain. The STO is therefore calculated by obtaining the phase of the cyclic peak at the symbol rate frequency. The method is validated through extensive theoretical study, simulation, and testbed implementation. The proposed estimation method exhibits robust performance in the presence of unknown carrier phase offset and frequency offset.

• 한국정보처리학회논문지
• /
• 제6권4호
• /
• pp.977-987
• /
• 1999

현행 교통 신호 제어기는 사전에 계획된 신호 시간 체계 또는 시간대별로 선택되는 방법을 취하고 있다. 이와 같은 신호 체계는 교통 상황 변화에 적절하게 대응하기 어려운 문제점을 갖고 있다. 특히, 혼잡 상황과 같은 문제들은 이진 논리로써 해결하기 어렵다. 따라서, 본 논문에서는 교통 혼잡 상황에 신속하게 대처할 수 있는 신호기 제어 시스템을 제안하였다. 본 논문에서 제안한 제어기는 불확실성 및 퍼지환경에서 작동한다. 따라서, 도로의 혼잡 상황을 퍼지 논리를 사용하여 표현하고 퍼지 추론기에 의해 신호 시간을 결정하도록 하였다. 본 논문에서 제안한 신호기 제어 시스템의 타당성을 검증하고자 페트리네트를 이용하여 모델링 하였다.

• 수산해양교육연구
• /
• 제28권4호
• /
• pp.1076-1088
• /
• 2016

This study was to validate the WSBS_PECT (Workplace Spirituality Belief Scale for Prospective Early Childhood Teacher) using discriminant analysis on prospective early childhood teachers' happiness and career maturity. The data from 523 prospective early childhood teachers were analyzed statistically through t-test and binary logistic regression model. The results indicated that 1) the higher group in workplace spirituality belief significantly gets more scores of happiness and career maturity than the lower group, 2) 1 factors of the WSBS_PECT has discriminant power on prospective early childhood teachers' happiness, and 3) 2 factors ('meaning for life' and 'belief on calling for ECE teacher job') of the WSBS_PECT are effective to discriminate prospective early childhood teachers' career maturity. Further statistical works are supplementary needed to validate the WSBS_PECT and to increase its' feasibility.