• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.213-220
• /
• 2011

This paper proposes an effective, four-stage smoke detection method based on video that provides emergency response in the event of unexpected hazards in early fire-alarming systems. In the first phase, an approximate median method is used to segment moving regions in the present frame of video. In the second phase, a color segmentation of smoke is performed to select candidate smoke regions from these moving regions. In the third phase, a feature extraction algorithm is used to extract five feature parameters of smoke by analyzing characteristics of the candidate smoke regions such as area randomness and motion of smoke. In the fourth phase, extracted five parameters of smoke are used as an input for a K-nearest neighbor (KNN) algorithm to identify whether the candidate smoke regions are smoke or non-smoke. Experimental results indicate that the proposed four-stage smoke detection method outperforms other algorithms in terms of smoke detection, providing a low false alarm rate and high reliability in open and large spaces.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.4
• /
• pp.785-796
• /
• 2012

In this paper, we propose an effective Behavior-based detection technique using the frequency of system calls to detect malicious code, when the number of training data is fewer than the number of properties on system calls. In this study, we collect the Native APIs which are Windows kernel data generated by running program code. Then we adopt the normalized freqeuncy of Native APIs as the basic properties. In addition, the basic properties are transformed to new properties by GLDA(Generalized Linear Discriminant Analysis) that is an effective method to discriminate between malicious code and normal code, although the number of training data is fewer than the number of properties. To detect the malicious code, kNN(k-Nearest Neighbor) classification, one of the bayesian classification technique, was used in this paper. We compared the proposed detection method with the other methods on collected Native APIs to verify efficiency of proposed method. It is presented that proposed detection method has a lower false positive rate than other methods on the threshold value when detection rate is 100%.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.105-112
• /
• 2006

In this study, we propose a simple preprocessing method for classification of basal cell carcinoma (BCC), which is one of the most common skin cancer. The preprocessing step consists of data clipping with a half Hanning window and dimension reduction with principal components analysis (PCA). The application of the half Hanning window deemphasizes the peak near $1650cm^{-1}$ and improves classification performance by lowering the false negative ratio. Classification results with various classifiers are presented to show the effectiveness of the proposed method. The classifiers include maximum a posteriori probability (MAP), k-nearest neighbor (KNN), probabilistic neural network (PNN), multilayer perceptron(MLP), support vector machine (SVM) and minimum squared error (MSE) classification. Classification results with KNN involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic BCC detection.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.173-190
• /
• 2015

The purpose of this study is to improve bankruptcy prediction models by using a novel hybrid under-sampling approach. Most prior studies have tried to enhance the accuracy of bankruptcy prediction models by improving the classification methods involved. In contrast, we focus on appropriate data preprocessing as a means of enhancing accuracy. In particular, we aim to develop an effective sampling approach for bankruptcy prediction, since most prediction models suffer from class imbalance problems. The approach proposed in this study is a hybrid under-sampling method that combines the k-Reverse Nearest Neighbor (k-RNN) and one-class support vector machine (OCSVM) approaches. k-RNN can effectively eliminate outliers, while OCSVM contributes to the selection of informative training samples from majority class data. To validate our proposed approach, we have applied it to data from H Bank's non-external auditing companies in Korea, and compared the performances of the classifiers with the proposed under-sampling and random sampling data. The empirical results show that the proposed under-sampling approach generally improves the accuracy of classifiers, such as logistic regression, discriminant analysis, decision tree, and support vector machines. They also show that the proposed under-sampling approach reduces the risk of false negative errors, which lead to higher misclassification costs.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.32 no.1
• /
• pp.92-99
• /
• 1996

2단계 접속 논리(two-stage cascaded logic)는 관측 지역 내에 새로이 출현한 표적에 대한 트랙을 만드는 대표적인 방법중의 하나이다. 2단계 접속 논리의 트랙 생성 (track formation)에 관한 성능 평가 방법 및 결과는 Bar-Schalom에 의해 발표된 바가 있으나, 그 연구 결과는 트랙 생성 성능을 도출할 때 클러터로 인한 오경보율(false alarm probability)을 무시한다는 가정에 기초한 것이기 때문에, 오경보율이 높은 경우에는 적용 할 수 없다는 단점을 지닌다. 이에 본 논문에서는 오경보율을 고려하여 2단계 접속 논리의 트랙 생성 성능을 평가 할 수 있는 개선된 방법을 제시하고자 한다. 그리고 2단계 접속 논리에서 사용하는 데이터 연관(data association)기법으로 트랙 분리(track splitting)기법과 최 근접 데이터 선택 기법(nearest neighbor rule)을 사용하는 경우에 대하여 각각의 성능 평가 결과를 몇 가지 예시하고자 한다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.979-984
• /
• 2004

The ball bearing having faults generally shows, nonlinear vibration characteristics. For the effective method of fault diagnosis on bail bearing, non-linear diagnostic methods can be used. In this paper, the correlation dimension analysis based on nonlinear timeseries was applied to diagnose the faults of ball bearing. The correlation dimension analysis shows some Intrinsic information of underlying dynamical systems, and clear the classification of the fault of ball bearing.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.116-123
• /
• 2009

Feature point matching, which is finding the corresponding points from two images with different viewpoint, has been used in various vision-based applications and the demand for the real-time operation of the matching is increasing these days. This paper presents a real-time feature point matching method by using a local descriptor derived by Zernike moments. From an input image, we find a set of feature points by using an existing fast corner detection algorithm and compute a local descriptor derived by Zernike moments at each feature point. The local descriptor based on Zernike moments represents the properties of the image patch around the feature points efficiently and is robust to rotation and illumination changes. In order to speed up the computation of Zernike moments, we compute the Zernike basis functions with fixed size in advance and store them in lookup tables. The initial matching results are acquired by an Approximate Nearest Neighbor (ANN) method and false matchings are eliminated by a RANSAC algorithm. In the experiments we confirmed that the proposed method matches the feature points in images with various transformations in real-time and outperforms existing methods.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.111-118
• /
• 2024

In general network-based intrusion detection system is designed to detect malicious behavior directed at a network or its resources. The key goal of this paper is to look at network data and identify whether it is normal traffic data or anomaly traffic data specifically for accounting information systems. In today's world, there are a variety of principles for detecting various forms of network-based intrusion. In this paper, we are using supervised machine learning techniques. Classification models are used to train and validate data. Using these algorithms we are training the system using a training dataset then we use this trained system to detect intrusion from the testing dataset. In our proposed method, we will detect whether the network data is normal or an anomaly. Using this method we can avoid unauthorized activity on the network and systems under that network. The Decision Tree and K-Nearest Neighbor are applied to the proposed model to classify abnormal to normal behaviors of network traffic data. In addition to that, Logistic Regression Classifier and Support Vector Classification algorithms are used in our model to support proposed concepts. Furthermore, a feature selection method is used to collect valuable information from the dataset to enhance the efficiency of the proposed approach. Random Forest machine learning algorithm is used, which assists the system to identify crucial aspects and focus on them rather than all the features them. The experimental findings revealed that the suggested method for network intrusion detection has a neglected false alarm rate, with the accuracy of the result expected to be between 95% and 100%. As a result of the high precision rate, this concept can be used to detect network data intrusion and prevent vulnerabilities on the network.