• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.31-36
• /
• 2011

In this paper, Mel-Frequency Cepstral Coefficient (MFCC), Decorrelated Filter Bank (DFB), Octave-based Spectral Contrast (OSC), Zero-Crossing Rate (ZCR), and Spectral Contract/Roll-Off are combined as a set of multiple feature-vectors for the music genre classification system based on the Support Vector Machine (SVM) classifier. In the conventional system, feature vectors for the entire genre classes are normalized for the SVM model training and classification. However, in this paper, selected feature vectors that are compared based on the One-Against-One (OAO) SVM classifier are only used for normalization. Using OSC as a single feature-vector and the multiple feature-vectors, we obtain the genre classification rates of 60.8% and 77.4%, respectively, with the conventional normalization method. Using the proposed normalization method, we obtain the increased classification rates by 8.2% and 3.3% for OSC and the multiple feature-vectors, respectively.

• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.593-601
• /
• 2022

We call "fruad" the cases that are not frequently occurring but cause significant losses. Fraud detection is commonly encountered in various applications, including wafer production in the semiconductor industry. It is not trivial to directly extend the standard binary classification methods to the fraud detection context because the misclassification cost is much higher than the normal class. In this article, we propose the functional fraud detection support vector machine (F²DSVM) that extends the fraud detection support vector machine (FDSVM) to handle functional covariates. The proposed method seeks a classifier for a function predictor that achieves optimal performance while achieving the desired sensitivity level. F²DSVM, like the conventional SVM, has piece-wise linear solution paths, allowing us to develop an efficient algorithm to recover entire solution paths, resulting in significantly improved computational efficiency. Finally, we apply the proposed F²DSVM to the defective wafer detection problem and assess its potential applicability.

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.9-13
• /
• 2005

Computer security has become a critical issue with the rapid development of business and other transaction systems over the Internet. The application of artificial intelligence, machine learning and data mining techniques to intrusion detection systems has been increasing recently. But most research is focused on improving the classification performance of a classifier. Selecting important features from input data leads to simplification of the problem, and faster and more accurate detection rates. Thus selecting important features is an important issue in intrusion detection. Another issue in intrusion detection is that most of the intrusion detection systems are performed by off-line and it is not a suitable method for a real-time intrusion detection system. In this paper, we develop the real-time intrusion detection system, which combines an on-line feature extraction method with the Least Squares Support Vector Machine classifier. Applying the proposed system to KDD CUP 99 data, experimental results show that it has a remarkable feature extraction and classification performance compared to existing off-line intrusion detection systems.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.43-53
• /
• 2014

Gunnery has been used to detect and classify artilleries. In this paper, we used electro-optical data to get the information of muzzle flash from the artilleries. Feature based approach was applied; we first defined features and sub-features. The number of sub-features was 38~40 generic sub-features, and 2 model-based sub-features. To classify multiclass data, we introduced tree structure with clustering the classes according to the similarity of them. SVM was used for each non-leaf nodes in the tree, as a sub-classifier. From the data, we extracted features and sub-features and classified them by the tree structure SVM classifier. The results showed that the performance of our classifier was good for our muzzle flash classification problem.

• Journal of Biomedical Engineering Research
• /
• v.28 no.1
• /
• pp.162-168
• /
• 2007

For the past decade, the full-field digital mammography has been widely used for early diagnosis of breast cancer, and computer aided diagnosis has been developed to assist physicians as a second opinion. In this study, we try to predict the breast cancer using both mediolateral oblique(MLO) view and craniocaudal(CC) view together. A skilled radiologist selected 35 pairs of ROIs from both MLO view and CC view of digital mammogram. We extracted textural features using Spatial Grey Level Dependence matrix from each mammogram and evaluated the generalization performance of the classifier using Support Vector Machine. We compared the multi-view based classifier to single-view based classifier that is built from each mammogram view. The results represent that the multi-view based computer aided diagnosis in digital mammogram could improve the diagnostic performance and have good possibility for clinical use to assist physicians as a second opinion.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.621-625
• /
• 2010

This paper presents a hand motion tracking method for hand gesture interface using a camera in mobile devices such as a smart phone and PDA. When a camera moves according to the hand gesture of the user, global optical flows are generated. Therefore, robust hand movement estimation is possible by considering dominant optical flow based on histogram analysis of the motion direction. A continuous hand gesture is segmented into unit gestures by motion state estimation using motion phase, which is determined by velocity and acceleration of the estimated hand motion. Feature vectors are extracted during movement states and hand gestures are recognized at the end state of each gesture. Support vector machine (SVM), k-nearest neighborhood classifier, and normal Bayes classifier are used for classification. SVM shows 82% recognition rate for 14 hand gestures.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.4
• /
• pp.22-30
• /
• 2008

In this paper, we deal with modulation classification method using WT capable of classifying incident digital signals without a priori information. These key features should have good properties of sensitive with modulation types and insensitive with SNR variation. The 4 key features for modulation recognition are selected using WT coefficients, which have the property of insentive to the changing of noise. The numerical simulations for classifying 8 digital modulation types using these features are peformed. The numerical simulations of the 3 types (i.e. DTC, MDC, and SVMC) of modulation classifiers are performed the investigation of classification accuracy and execution time to design the modulation classification module in software radio. The simulation result indicated that the execution time of MDC and DTC was best and MDC and SVMC showed good classification performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.7
• /
• pp.327-332
• /
• 2016

This study is a leading research project to develop an automatic grade decision making algorithm of a 6-years-old fresh ginseng. For this work, we developed a Ginseng image acquiring instrument which can take 4-direction's images of a Ginseng at the same time and obtained 245 jingen images using the instrument. The 12 parameters were extracted for each image by a manual way. Lastly, 4 parameters were selected depending on a Ginseng grade classification criteria of KGC Ginseng research institute and a survey result which a distribution of averaging 12 parameters. A pattern recognition classifier was used as a support vector machine, designed to "k-class classifier" using the OpenCV library which is a open-source platform. We had been surveyed the algorithm performance(Correct Matching Ratio, False Acceptance Ratio, False Reject Ratio) when the training data number was controlled 10 to 20. The result of the correct matching ratio is 94% of the $1^{st}$ ginseng grade, 98% of the $2^{nd}$ ginseng grade, 90% of the $3^{rd}$ ginseng grade, overall, showed high recognition performance with all grades when the number of training data are 10.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.397-402
• /
• 2007

In this paper, we apply a support vector machine(SVM) that incorporates an optimized nonlinear decision rule over different sets of feature vectors to improve the performance of statistical model-based voice activity detection(VAD). Conventional method performs VAD through setting up statistical models for each case of speech absence and presence assumption and comparing the geometric mean of the likelihood ratio (LR) for the individual frequency band extracted from input signal with the given threshold. We propose a novel VAD technique based on SVM by treating the LRs computed in each frequency bin as the elements of feature vector to minimize classification error probability instead of the conventional decision rule using geometric mean. As a result of experiments, the performance of SVM-based VAD using the proposed feature has shown better results compared with those of reported VADs in various noise environments.