• 인터넷정보학회논문지
• /
• 제8권2호
• /
• pp.89-94
• /
• 2007

현재 새로운 스팸 메일 차단 시스템과 다양한 스팸 차단 기술에 대한 연구가 계속되고 있다. 그렇지만, 새로운 유형의 스팸 메일이 등장하면서 스팸 메일 차단률(Spam mail Filtering Rate)과 오인된 메일(False-positive mail) 발생률은 점차적으로 늘어나고 있다. 하지만 기존에 제안된 스팸 메일 필터링 알고리즘은 새로운 유형의 스팸 메일에 대응하기 위해 적용될 알고리즘 수의 증가와 효율적인 스팸 메일 필터링 알고리즘의 대응 관계에 대한 연구 부족으로 인하여 스팸 메일 차단 시스템의 처리 부하는 증가하고 이에 대한 신뢰성은 반감되고 있다. 본 논문에서는 스팸 메일 차단 시스템의 부하 처리 성능 및 신뢰성을 증가시키기 위해 Fit-FA Finder와 Privacy 기반의 오인된 메일을 복구시키는 SMBC플랫폼을 개발하고 성능을 분석하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2651-2673
• /
• 2019

In order to detect Denial of Service (DoS) attacks, victim-side detection methods are used popularly such as static threshold-based method and machine learning-based method. However, as DoS attacking methods become more sophisticated, these methods reveal some natural disadvantages such as the late detection and the difficulty of tracing back attackers. Recently, in order to mitigate these drawbacks, source-side DoS detection methods have been researched. But, the source-side DoS detection methods have limitations if the volume of attack traffic is relatively very small and it is blended into legitimate traffic. Especially, with the subtle attack traffic, DoS detection methods may suffer from high false positive, considering legitimate traffic as attack traffic. In this paper, we propose an effective source-side DoS detection method with traffic seasonality aware adaptive threshold. The threshold of detecting DoS attack is adjusted adaptively to the fluctuated legitimate traffic in order to detect subtle attack traffic. Moreover, by understanding the seasonality of legitimate traffic, the threshold can be updated more carefully even though subtle attack happens and it helps to achieve low false positive. The extensive evaluation with the real traffic logs presents that the proposed method achieves very high detection rate over 90% with low false positive rate down to 5%.

• 대한건축학회논문집:구조계
• /
• 제36권3호
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• 대한수학회보
• /
• 제48권3호
• /
• pp.523-537
• /
• 2011

A receiver operating characteristic (ROC) curve plots the true positive rate of a classier against its false positive rate, both of which are accuracy measures of the classier. The ROC curve has several interesting geometrical properties, including concavity which is a necessary condition for a classier to be optimal. In this paper, we study the nonparametric maximum likelihood estimator (NPMLE) of a concave ROC curve and its modification to reduce bias. We characterize the NPMLE as a solution to a geometric programming, a special type of a mathematical optimization problem. We find that the NPMLE is close to the convex hull of the empirical ROC curve and, thus, has smaller variance but positive bias at a given false positive rate. To reduce the bias, we propose a modification of the NPMLE which minimizes the $L_1$ distance from the empirical ROC curve. We numerically compare the finite sample performance of three estimators, the empirical ROC curve, the NMPLE, and the modified NPMLE. Finally, we apply the estimators to estimating the optimal ROC curve of the variance-threshold classier to segment a low depth of field image and to finding a diagnostic tool with multiple tests for detection of hemophilia A carrier.

• 융합보안논문지
• /
• 제22권5호
• /
• pp.145-154
• /
• 2022

최근 봇넷의 광범위한 확산과 고도의 정교함은 기업과 사용자뿐만 아니라 국가 간 사이버전에도 심각한 결과를 초래하고 있다. 이 때문에 봇넷을 탐지하고자 하는 연구는 꾸준히 되고 있다. 하지만, DGA 기반의 봇넷은 기존의 시그니처 및 통계 기반의 기술로는 탐지율은 높지만, 오탐율 또한 높은 한계가 있다. 이에 본 논문에서는 DGA 기반의 봇넷을 탐지하고자 문자 기반의 n-gram을 활용한 탐지모델을 제안한다. 제안한 모델을 통해 기존의 탐지 기술의 한계인 탐지율을 높이고 오탐율을 최소화할 수 있다. 다양한 DGA 봇넷에서 사용하는 대규모의 도메인 데이터셋과 정상 도메인에 대한 실험을 통해 기존의 모델보다 성능이 우수함을 확인하였다. 제안된 모델의 오탐율은 2~4% 미만이며 전체 탐지 정확도와 F1 점수는 모두 97.5%임을 확인하였다. 이처럼 본 논문에서 제안한 모델을 통해 DGA 기반의 봇넷에 대한 탐지 및 대응 능력이 향상될 것을 기대한다.

• 한국건강관리협회지
• /
• 제2권1호
• /
• pp.27-37
• /
• 2004

Background 'For many years, the Papanicolaou smear has been used to detect pre-malignant and malignant disease of the cervix. Although cervical cytology screening programmes have result in the reduction of cervical cancer incidence and mortality, Pap smear have been subjected to intense scrutiny and criticism in recent years. So cervicography is introduced. Cervicography is an adjunct method of cervical cancer screening intended to complement Papanicolaou smear. Cervicography involve obtaining and evaluating a photographic image of the cervix. The purpose of this investigation was to evaluate the efficacy of Papanicolaou smear and cervicography in cervical cancer screening. Materials & Methods : This study population was of 74 women, who visited department of obstetrics & Gynecology, Korea association of Health Promotion Chung-nam branch from January, 20O2 to October, 2003. All patients were taken Pap smear before cervicography, and then two cervicography was obtained with applying5% acetic acid. Those women in whom abnormalities were detected by either test subsequently obtained histologic specimen. Results : 1. The sensitivity and the specificity of Papanicolaou smear was 92.1% and 72.7%respectively.2. The sensitivity and the specificity of cervicography was 88.9% and 54.5% respectively. The false negative rate, and false positive rate of Papanicolaou smear were 7.9%, 27.2% respectively. The false negative rate, and false positive rate of cervicography were 11.1%,45.5% respectively. Conclusions . Papanicolaou smear is a useful method and an important tool for detecting cervical cancer. However when Papanicolaou smear and Cervicograpy is used together, the sensitivity is higher than for Papanicolaou smear used alone.

• 대한의용생체공학회:의공학회지
• /
• 제18권4호
• /
• pp.485-491
• /
• 1997

본 논문은 각성상태에 다른 생리신호와 행위신호 및 주관적 평가의 상관관계에 대하여 나타내었다. Nz와 반응시간은 mKSS level 의 변화와 동일한 경향을 나타내는데 반하여 1분당 눈 깜박임 수는 앞의 두 가지 변수와 다른 경향을 나타내었다. 1분당 눈깜박임 수는 mKSS level 1에서 5까지는 낮은 변화율 갖고 mKSS level 7에서는 높은 변화율을 갖는 반면에 mKSS level 9에서는 이와 반대로 변화율이 급격히 감소한다. 피검자들은 서로다른 1분당 눈깜박임 수(EBR)를 가지나 EBR의 변화율은 비슷하였다. 그러므로 EBR의 변화율을 각성판정지표로 사용할 수 있음을 알 수 있었다. 반응시간 실험 결과로부터mKSS level 5이상부터 작업수행능력이 낮아짐을 알 수 있었고 false positive 와 false negative 가 mKSS level3부터 관찰되었으므로 효과적으로 각성제어를 위하여 mKSS level 3과 5사이에 각성상태를 향상시키기 위한 소리나 향기 등의 자극을 주어야 함을 알 수 있었다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권5호
• /
• pp.2251-2255
• /
• 2014

Background: The aim of this study was to evaluate 10 years of false positive urine cytology records, along with follow-up histologic and cytologic data, to determine the significance of suspicious urine cytology findings. Materials and Methods: We retrospectively reviewed records of urine samples harvested between January 2002 and December 2012 from voided and catheterized urine from the bladder. Among the 21,283 urine samples obtained during this period, we located 1,090 eligible false positive findings for patients being evaluated for the purpose of confirming urothelial carcinoma (UC). These findings were divided into three categories: atypical, indeterminate, and suspicious of malignancy. Results: Of the 1,090 samples classified as false positive, 444 (40.7%) were categorized as atypical, 367 (33.7%) as indeterminate, and 279 (25.6%) as suspicious of malignancy. Patients with concomitant UC accounted for 105 (23.6%) of the atypical samples, 147 (40.1%) of the indeterminate samples, and 139 (49.8%) of the suspicious of malignancy samples (p<0.0001). The rate of subsequent diagnosis of UC during a 1-year follow-up period after harvesting of a sample with false positive urine cytology initially diagnosed as benign was significantly higher in the suspicious of malignancy category than in the other categories (p<0.001). The total numbers of UCs were 150 (33.8%) for atypical samples, 213 (58.0%) for indeterminate samples, and 199 (71.3%) for samples categorized as suspicious of malignancy. Conclusions: Urine cytology remains the most specific adjunctive method for the surveillance of UC. We demonstrated the clinical value of dividing false positive urine cytology findings into three categories, and our results may help clinicians better manage patients with suspicious findings.

• 대한세포병리학회지
• /
• 제6권2호
• /
• pp.140-147
• /
• 1995

In a six-year period (1988. 5-1994. 4), fine needle aspiration cytology(FNAC) of 322 pulmonary lesions from 296 patients were performed at Soonchunhyang University Hospital. Of these 322, malignancy was diagnosed cytologically in 139(43.2%), suspicious malignancy in 7(2.2%), negative in 164(50.8%), and insufficient material in 12(3.8%). Malignant lesions consisted of 54 cases of adenocarcinoma, 50 cases of squamous cell carcinoma, 18 cases of small cell carcinoma. They were verified by histologic examination in 70 cases. There were 2(0.6%) false positive cases due to florid bronchoalveolar hyperplasia and atypical bronchial epithelial cells associated with granulomatous lesion. The overall accuracy rate was 90%, the sensitivity 84.3% and the specificity 94.7%.

• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1265-1276
• /
• 2019

Data deduplication is a common method to improve cloud storage efficiency and save network communication bandwidth, but it also brings a series of problems such as privacy disclosure and dictionary attacks. This paper proposes a secure deduplication scheme for cloud storage based on Bloom filter, and dynamically extends the standard Bloom filter. A public dynamic Bloom filter array (PDBFA) is constructed, which improves the efficiency of ownership proof, realizes the fast detection of duplicate data blocks and reduces the false positive rate of the system. In addition, in the process of file encryption and upload, the convergent key is encrypted twice, which can effectively prevent violent dictionary attacks. The experimental results show that the PDBFA scheme has the characteristics of low computational overhead and low false positive rate.