• 인터넷정보학회논문지
• /
• 제23권5호
• /
• pp.79-85
• /
• 2022

이상 탐지는 일반적인 사용자들의 데이터 집합 속에서 비정상적인 데이터 흐름을 파악하여 미리 차단하는 방법이다. 기존에 알려진 방식은 이미 알려진 공격의 시그니처를 활용하여 시그니처 기반으로 공격을 탐지 및 방어하는 방식인데, 이는 오탐율이 낮다는 장점이 있지만 제로 데이 취약점 공격이나 변형된 공격에 대해서는 매우 취약하다는 점이 문제점이다. 하지만 이상 탐지의 경우엔 오탐율이 높다는 단점이 존재하지만 제로 데이 취약점 공격이나 변형된 공격에 대해서도 식별하여 탐지 및 차단할 수 있다는 장점이 있어 관련 연구들이 활발해지고 있는 중이다. 본 연구에서는 이 중 이상 탐지 메커니즘에 대해 다뤘다. 앞서 말한 단점인 높은 오탐율을 보완하며 그와 더불어 이상 탐지와 분류를 동시에 수행하는 새로운 메커니즘을 제안한다. 본 연구에서는 여러 알고리즘의 특성을 고려하여 5가지의 구성으로 실험을 진행하였다. 그 결과로 가장 우수한 정확도를 보이는 모델을 본 연구의 결과로 제안하였다. Extra Tree와 Three layer ANN을 동시에 적용하여 공격 여부를 탐지한 후 공격을 분류된 데이터에 대해서는 Extra Tree를 활용하여 공격 유형을 분류하게 된다. 본 연구에서는 NSL-KDD 데이터 세트에 대해서 검증을 진행하였으며, Accuracy는 Normal, Dos, Probe, U2R, R2L에 대하여 각각 99.8%, 99.1%, 98.9%, 98.7%, 97.9%의 결과를 보였다. 본 구성은 다른 모델에 비해 우수한 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.782-787
• /
• 2004

Internet Engineering Task Force (IETF) has been considering the deployment of the Random Early Detection (RED) in order to avoid the increasing of packet loss rates which caused by an exponential increase in network traffic and buffer overflow. Although RED mechanism can prevent buffer overflow and hence reduce an average values of packet loss rates, but this technique is ineffective in preventing the consecutive drop in the high traffic condition. Moreover, it increases a probability and average number of consecutive dropped packet in the low traffic condition (named as "uncritical condition"). RED mechanism effects to TCP congestion control that build up the consecutive of the unnecessary transmission rate reducing; lead to low utilization on the link and consequently degrade the network performance. To overcome these problems, we have proposed a new mechanism, named as Extended Drop slope RED (ExRED) mechanism, by modifying the traditional RED. The numerical and simulation results show that our proposed mechanism reduces a drop probability in the uncritical condition.

• 정보보호학회논문지
• /
• 제22권6호
• /
• pp.1219-1230
• /
• 2012

최근 들어 많은 사용자들은 WEP, WPA와 같은 보호 메커니즘을 이용하여 인증 및 기밀성이 제공되는 무선 랜을 이용하고 있다. 하지만 각 보호 메커니즘의 취약성이 발견되고 이를 이용하여 사용자의 정보가 제 3자에게 노출되거나 변조되어 악용하는 공격 기법들이 제안되었다. 본 논문에서는 무선 랜 보안 메커니즘을 분석하고 알려진 취약성을 이용하여 PSK(Pre-Shared Key) 크래킹 및 쿠키 세션 하이재킹 공격을 수행하고, PSK 크래킹 공격에 대응할 수 있는 개선된 4-way handshake 메커니즘과 쿠키 세션 하이재킹 공격을 방어할 수 있는 쿠키 재전송 탐지 메커니즘을 제안한다. 제안하는 메커니즘은 기존 방식의 취약성에 대응하여 보다 안전한 무선 랜 환경을 구축하는데 활용할 수 있을 것으로 기대한다.

• 한국인터넷방송통신학회논문지
• /
• 제21권3호
• /
• pp.81-89
• /
• 2021

자연 조건에서 Apple 감지에는 가림 문제와 작은 대상 감지 어려움이 있다. 본 논문은 SSD 기반의 개선 된 모델을 제안한다. SSD 백본 네트워크 VGG16은 ResNet50 네트워크 모델로 대체되고 수용 필드 구조 RFB 구조가 도입되었다. RFB 모델은 작은 표적의 특징 정보를 증폭하고 작은 표적의 탐지 정확도를 향상시킨다. 유지해야 하는 정보를 필터링하기 위해 주의 메커니즘 (SE)과 결합하면 감지 대상의 의미 정보가 향상된다. 향상된 SSD 알고리즘은 VOC2007 데이터 세트에 대해 학습된다. SSD에 비해 개선 된 알고리즘은 폐색 및 작은 표적 탐지의 정확도를 3.4 % 및 3.9 % 향상 시켰다. 이 알고리즘은 오 탐지율과 누락된 감지율을 향상 시켰다. 본 논문에서 제안한 개선 된 알고리즘은 더 높은 효율성을 갖는다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권5호
• /
• pp.2001-2006
• /
• 2014

The objective of this study was to investigate the diagnostic significance of EBV antibody combined detection for nasopharyngeal carcinoma (NPC) in a high incidence region of southern China. Two hundred and eleven untreated NPC patients, 203 non-NPC ENT patients, and 210 healthy controls were recruited for the study. The titers of VCA/IgA and EA/IgA were assessed by immunoenzyme assay, and the levels of Rta/IgG and EBNA1/IgA were determined by enzyme-linked immunosorbent assay. The levels of VCA/IgA, EA/IgA, Rta/IgG and EBNA1/IgA demonstrated no association with gender or age (p>0.05). The receiver operating characteristic curve and the area under the curve were used to evaluate the diagnostic value. The sensitivity of VCA/IgA (98.1%) and the specificity of EA/IgA (98.5%) were the highest. When a logistic regression model was used to combine the results from multiple antibodies to increase the accuracy, the combination of VCA/IgA+Rta/IgG, whose area under the curve was 0.99, had the highest diagnostic efficiency, and its sensitivity, specificity and Youden index were 94.8%, 98.0% and 0.93 respectively. The data suggest that the combination of VCA/IgA+Rta/IgG may be most suitable for NPC serodiagnosis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3797-3822
• /
• 2020

The inspection of cracks on the surface of tunnel linings is a common method of evaluate the condition of the tunnel. In particular, determining the thickness and shape of a crack is important because it indicates the external forces applied to the tunnel and the current condition of the concrete structure. Recently, several automatic crack detection methods have been proposed to identify cracks using captured tunnel lining images. These methods apply an image-segmentation mechanism with well-annotated datasets. However, generating the ground truths requires many resources, and the small proportion of cracks in the images cause a class-imbalance problem. A weakly annotated dataset is generated to reduce resource consumption and avoid the class-imbalance problem. However, the use of the dataset results in a large number of false positives and requires post-processing for accurate crack detection. To overcome these issues, we propose a crack detection method using a ternary classifier. The proposed method significantly reduces the false positive rate, and the performance (as measured by the F1 score) is improved by 0.33 compared to previous methods. These results demonstrate the effectiveness of the proposed method.

• Journal of Information Processing Systems
• /
• 제12권2호
• /
• pp.183-195
• /
• 2016

This paper presents a complete method for vehicle detection and tracking in a fixed setting based on computer vision. Vehicle detection is performed based on Scale Invariant Feature Transform (SIFT) feature matching. With SIFT feature detection and matching, the geometrical relations between the two images is estimated. Then, the previous image is aligned with the current image so that moving vehicles can be detected by analyzing the difference image of the two aligned images. Vehicle tracking is also performed based on SIFT feature matching. For the decreasing of time consumption and maintaining higher tracking accuracy, the detected candidate vehicle in the current image is matched with the vehicle sample in the tracking sample set, which contains all of the detected vehicles in previous images. Most remarkably, the management of vehicle entries and exits is realized based on SIFT feature matching with an efficient update mechanism of the tracking sample set. This entire method is proposed for highway traffic environment where there are no non-automotive vehicles or pedestrians, as these would interfere with the results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.238-245
• /
• 2016

Inverters are considered the basic building blocks of industrial electrical drive systems that are widely used for various applications; however, the failure of electronic switches mainly affects the constancy of these inverters. For safe and reliable operation of an electrical drive system, faults in power electronic switches must be detected by an efficient system that is capable of identifying the type of faults. In this paper, an open switch fault identification technique for a three-phase inverter is presented. Single, double, and triple switching faults can be diagnosed using this method. The detection mechanism is based on stator current analysis. Discrete wavelet transform (DWT) using Daubechies is performed on the Clarke transformed (-) stator current and features are extracted from the wavelets. An artificial neural network is then used for the detection and identification of faults. To prove the feasibility of this method, a Simulink model of the DWT-based feature extraction scheme using a neural network for the proposed fault detection system in a three-phase inverter with an induction motor is briefly discussed with simulation results. The simulation results show that the designed system can detect faults quite efficiently, with the ability to differentiate between single and multiple switching faults.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권8호
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.