• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.566-575
• /
• 2010

In recent, artificial immune system has become an important research direction in the anomaly detection of networks. The conventional artificial immune systems are usually based on the negative selection that is one of the computational models of self/nonself discrimination. A main problem with self and non-self discrimination is the determination of the frontier between self and non-self. It causes false positive and false negative which are wrong detections. Therefore, additional functions are needed in order to detect potential anomaly while identifying abnormal behavior from analogous symptoms. In this paper, we design novel network attack detection and response schemes based on artificial immune system, and evaluate the performance of the proposed schemes. We firstly generate detector set and design detection and response modules through adopting the interaction between dendritic cells and T-cells. With the sequence of buffer occupancy, a set of detectors is generated by negative selection. The detection module detects the network anomaly with a set of detectors and generates alarm signal to the response module. In order to reduce wrong detections, we also utilize the fuzzy number theory that infers the degree of threat. The degree of threat is calculated by monitoring the number of alarm signals and the intensity of alarm occurrence. The response module sends the control signal to attackers to limit the attack traffic.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.675-686
• /
• 2005

In this paper, we propose an efficient face region detection technique for the content-based video summarization. To segment video, shot changes are detected from a video sequence and key frames are selected from the shots. We select one frame that has the least difference between neighboring frames in each shot. The proposed face detection algorithm detects face region from selected key frames. And then, we provide user with summarized frames included face region that has an important meaning in dramas or movies. Using Bayes classification rule and statistical characteristic of the skin pixels, face regions are detected in the frames. After skin detection, we adopt the projection method to segment an image(frame) into face region and non-face region. The segmented regions are candidates of the face object and they include many false detected regions. So, we design a classifier to minimize false lesion using CART. From SGLD matrices, we extract the textual feature values such as Inertial, Inverse Difference, and Correlation. As a result of our experiment, proposed face detection algorithm shows a good performance for the key frames with a complex and variant background. And our system provides key frames included the face region for user as video summarized information.

• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.927-933
• /
• 2013

Face detection algorithm of OpenCV recognizes the faces by Haar matching between input image and Haar features which are learned through a set of training images consisting of many front faces. Therefore the face detection method by Haar matching yields a high face detection rate for the front faces but not in the case of the pan and deformed faces. On the assumption that distributional characteristics of color histogram is similar even if deformed or side faces, a face detection method using the histogram pattern matching is proposed in this paper. In the case of the missed detection and false detection caused by Haar matching, the proposed face detection algorithm applies the histogram pattern matching with the correct detected face area of the previous frame so that the face region with the most similar histogram distribution is determined. The experiment for evaluating the face detection performance reveals that the face detection rate was enhanced about 8% than the conventional method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• 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.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.635-638
• /
• 2001

본 논문에서는 수중 환경에서 분산 소나 시스템의 최적 정보 융합에 관한 알고리즘을 제시하였다. 기존의 방법은 Bayesian 법칙을 이용하여 local 소나와 퓨전 센터의 문턱치를 적절히 조절하여 분산 소나 시스템을 최적화했다. 그러나, 이러한 최적화 과정에서 소나의 개수를 늘려감에 따라 P/sub F/(false alarm probability)가 단조 증가하는 현상이 발생하였고 이러한 단점을 보완하기 위해 P/sub F/를 작은 간에 제한시키고 Bayesian 법칙과 Neyman-Pearson 법칙을 함께 적용하여 분산 소나 시스템을 최적화시킨다. 그러나, 이러한 조건 하에 시스템을 최적화시키는 것은 N-P hard 문제에 의해 계산 부하가 매우 크므로 unate 함수와 SQP(Sequential Quadratic Programming)을 이용하여 계산 부하를 감소시켰다.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.384-388
• /
• 2004

In this paper, we analyses transmission performance of synchronization pattern for over the air rekeying in aerial tactical link of LINK16, when it is given by symbol error rate, in respect of pattern detection probability and false alarm probability.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.97-103
• /
• 2003

Shewhart-type control charts have historically been used for attribute data, though they have ARL biased property and even are unable to detect the improvement of a process with some process parameters. So far most efforts have been made to improve the performance of attribute control charts in terms of faster detection of special causes without increasing the rates of false alarm. In this paper, control limits are proposed that yield an ARL (nearly) unbiased chart for attributes. Optimal design is also proposed for attribute control charts under a natural sense of criterion.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.607-609
• /
• 2002

본 논문은 흉부 전산화단층촬영 영상에서 폐 영역을 자동으로 분할하는 알고리즘과 폐결절을 자동으로 검출하는 알고리즘에 관한 연구 내용을 담고 있다. 폐 분할 알고리즘은 gray-level thresholding과 morphologic 영상 처리기법을 이용하였고, 폐결절 자동 검출 알고리즘은 추출된 결절 후보의 size, compactness, mean of gray level 값을 분석하여 혈관과 결절을 구분하였다. 개발한 폐결절 자동 검출 시스템은 실험한 영상에 포함된 폐결절 117개 중 55%인 64개를 검출하였고, 3.4 False Positive/section이었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.10 no.1
• /
• pp.11-16
• /
• 1985

The performance analysis of serial search spread spectrum synchronization system is carried out. To evaluate the synchronization probabilities, two chi-square densities for signal plus noise and noise only are derived. Then Neyman-Pearson scheme is applied to determine the threshold of the synchronization system. The synchronization probability curves are shown as a function of threshold and signal to noise ratios.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.49-52
• /
• 2002

This paper presents a fast algorithm for face detection from color images on internet. We use Mahalanobis distance between standard skin color and actual pixel color on IQ color space to segment skin color regions. The skin color regions are the candidate face region. Further, the locations of eyes and mouth regions are found by computing average pixel values on horizontal and vertical pixel lines. The geometry of mouth and eye locations is compared to the standard face geometry to eliminate false face regions. Our Method is simple and fast so that it can be applied to face search engine for internet.