• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.1085-1096
• /
• 2009

Population stratification can cause spurious associations between genetic markers and disease locus. In order to handle this population stratification in haplotype-based case-control association studies, we added population indicators as covariates to the haplotype trend regression model proposed by Zaykin et al. (2002). We investigated through simulations how both population stratification and measurement error in the estimation of true population of each individual affect type I error probabilities of the association tests based on both Zaykin et al.'s (2002) model and the proposed model. Based on those results, in the situation that there exists population stratification but there is no error in population classification of each individual, our proposed model does satisfy a type I error probability whereas Zaykin et al.'s (2002) model does not. However, as the measurement error increases, a type I error probability of our model correspondingly becomes larger than a nominal significance level. It implies that as long as uncertainty in the estimation of true population of each individual still remains, it is nearly impossible to avoid false positive in case-control association studies based on haplotypes.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• The KIPS Transactions:PartC
• /
• v.10C no.7
• /
• pp.843-850
• /
• 2003

Script viruses are easy to make a variation because they can be built easily and be spread in text format. Thus signature-based method has a limitation in detecting script viruses. In a consequence, many researches suggest simple heuristic methods, but high false-positive error is always being an obstacle. In order to overcome this problem, our previous study concentrated on analyzing data flow of codes and has low-false positive error, but still could not detect a polymorphic virus because polymorphic virus loads self body and changes it before make a descendent. We suggest a heuristic detection method which expands the detection range of previous method to include polymorphic script viruses. Expanded data flow analysis heuristic has an expanded grammar to detect Polymorphic copy Propagation. Finally, we will show the experimental result for the effectiveness of suggested method.

• The Korean Journal of Cytopathology
• /
• v.8 no.2
• /
• pp.120-128
• /
• 1997

Fine needle aspiration cytology of breast lesion is well known as a simple, economic and effective diagnostic modality. For the evaluation of cytohistologic correlation, 256 cases of cytologic smears and subsequent histologic sections during 2-year period from Jan. 1995 to Dec. 1996 were reviewed. 1. Fifteen cases(5.9%) were proven as insufficient for evaluation, and 13 of them were fibrocystic change histologically. One case of carcinoma exhibiting sufficient amount of aspirates with no malignant cells on smear was regarded as inadequate. 2. Cytohistologic correlation of 240 cases revealed sensitivity 87.0%, specificity 100.0%, positive predictive value 100.0%, negative predictive value 97.0%, false positive rate 0.0% and false negative rate 13.0%. Total diagnostic accuracy is 95.7%. 3. Total 6 cases of negative were due to small amount of aspirates containing scantiness of malignant cells in two and underestimation in four. 4. Diagnostic concordance rates of fibrocystic change and fibroadenoma were 95.5% and 80.0%, respectively. Diagnostic discrepancies were noted in 7 cases of fibrocystic change and 6 cases of fibroadenoma, however, cytologic discrimination of two entities was not easy in seven of them. 5. In a case of phyllodes tumor and a case of duct ectasia, the discrepancy was due to targeting error. Other three cases(lymphoma, adenomyoepithelioma and granulomatous mastitis) were misinterpreted because of poor acquaintance with those entities. Diagnostic accuracy of fine needle aspiration cytology of breast lesions are relatively high. However, good technique on aspiration and adequate interpretation are necessary to reduce the false negative rate and the discrepancy between cytologic and histologic diagnoses.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.661-663
• /
• 2001

침입탐지 시스템은 내부자의 불법적인 사용, 오용 또는 외부 침입자에 의한 중요 정보 유출 및 변경을 알아내는 것으로서 각 운영체제에서 사용자가 발생시킨 키워드, 시스템 호출, 시스템 로그, 사용시간, 네트워크 패킷 등의 분석을 통하여 침입여부를 결정한다. 본 논문에서 제안하는 침입탐지시스템은 권한 이동 관련 이벤트 추출 기법을 이용하여 사용자의 권한이 바뀌는 일정한 시점만큼 기록을 한 후 HMM모델에 적용시켜 평가한다. 기존 실험에서 보여주었던 데이터의 신뢰에 대한 단점을 보완하기 위해 다량의 정상행위 데이터와 많은 종류의 침입유형을 적용해 보았고, 그 밖에 몇 가지 단점들을 수정하여 기존 모델에 비해 향상된 성능을 보이는지를 평가하였다 실험 결과 호스트기반의 침입에 대해서 매우 좋은 탐지율을 보여 주었고 F-P error(false positive error) 또한 매우 낮은 수치를 보여 주었다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.210-215
• /
• 2009

In this study event-related optical signals were extracted from the prefrontal cortexes using functional near infrared spectroscopy while subjects were carrying out 2-back working memory tasks. Four events such as start, yes, no, and error were considered based on the onsets of the stimulus, positive true responses, positive false responses, and negative responses in the 2-back working memory task, respectively. The optical signals recorded were analyzed by peri-event histograms and power spectrum distributions. The results showed specific characteristics of the event-related optical neuronal signals and an opened possibility of an application to control a non-invasive brain-computer interface system or an object of a virtual reality.

• Journal of Biomedical Engineering Research
• /
• v.11 no.2
• /
• pp.209-216
• /
• 1990

Pulmonary nodules in chest X-Ray images were detected using the symmetric property of human lung and its performance was evaluated. Thls algorithm reduced the effect of background components and enhanced the nodule signals relatively. The image was divided and processed separately, the half with matched filter only, and the other half with warping and matched filter. This algorithm increased the entire detection rate by reducing False-Positive error and improving True-Positive detectability. Result shows 10-25 % improvement in detection rate compared with the conventional alsorithm for nodules size of 10mm.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.759-770
• /
• 2009

A problem of separating signals from noises is considered, when they are randomly mixed in the observation. It is assumed that the noise follows a Gaussian distribution and the signal follows a Gamma distribution, thus the underlying distribution of an observation will be a mixture of Gaussian and Gamma distributions. The parameters of the mixture model will be estimated from the EM algorithm. Then the signals and noises will be classified by a fixed threshold approach based on multiple testing using positive false discovery rate and Bayes error. The proposed method is applied to a real optical emission spectroscopy data for the quantitative analysis of inclusions. A simulation is carried out to compare the performance with the existing method using 3 sigma rule.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.3
• /
• pp.19-25
• /
• 2017

Nowadays, networked computer systems play an increasingly important role in our society and its economy. They have become the targets of a wide array of malicious attacks that invariably turn into actual intrusions. This is the reason computer security has become an essential concern for network administrators. Recently, a number of Detection/Prevention System schemes have been proposed based on various technologies. However, the techniques, which have been applied in many systems, are useful only for the existing patterns of intrusion. Therefore, probe detection has become a major security protection technology to detection potential attacks. Probe detection needs to take into account a variety of factors ant the relationship between the various factors to reduce false negative & positive error. It is necessary to develop new technology of probe detection that can find new pattern of probe. In this paper, we propose an hybrid probe detection using Fuzzy Cognitive Map(FCM) and Self Adaptive Module(SAM) in dynamic environment such as Cloud and IoT. Also, in order to verify the proposed method, experiments about measuring detection rate in dynamic environments and possibility of countermeasure against intrusion were performed. From experimental results, decrease of false detection and the possibilities of countermeasures against intrusions were confirmed.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.