• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.56-63
• /
• 2007

In this paper, an eye tracking method is presented using a neural network (NN) and mean-shift algorithm that can accurately detect and track user's eyes under the cluttered background. In the proposed method, to deal with the rigid head motion, the facial region is first obtained using skin-color model and con-nected-component analysis. Thereafter the eye regions are localized using neural network (NN)-based tex-ture classifier that discriminates the facial region into eye class and non-eye class, which enables our method to accurately detect users' eyes even if they put on glasses. Once the eye region is localized, they are continuously and correctly tracking by mean-shift algorithm. To assess the validity of the proposed method, it is applied to the interface system using eye movement and is tested with a group of 25 users through playing a 'aligns games.' The results show that the system process more than 30 frames/sec on PC for the $320{\times}240$ size input image and supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of Biomedical Engineering Research
• /
• v.31 no.1
• /
• pp.40-49
• /
• 2010

A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.175-184
• /
• 2008

To construct user profiles automatically, an extraction method for representative keywords from a set of documents is needed. In our previous works, we suggested such a method and showed its usefulness. Here, we apply it to the classification problem and observe how much it contributes to performance improvement. The method can be used as a linear document classifier with few modifications. So, we first evaluate its performance for that case. The method is also applicable to some non-linear classification methods such as GIS (Generalized Instance Set). In GIS algorithm, generalized instances are built from training documents by a generalization function and then the K-NN algorithm is applied to them, where the method can be used as a generalization function. For comparative works, two famous linear classification methods, Rocchio and Widrow-Hoff algorithms, are also used. Experimental results show that our method is better than the others for the case that only positive documents are considered, but not when negative documents are considered together.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2003.11a
• /
• pp.215-218
• /
• 2003

본 논문에서는 MPEG-7에 정의된 오디오 서술자를 이용한 오디오 특징을 기반으로 한 음악 검색 알고리즘을 제안한다. 특히 timbral 특징들은 음색 구분을 용이하게 할 수 있어 음악 검색뿐만 아니라 음악 장르 분류 또는 Query by humming에 이용 될 수 있다. 이러한 연구를 통하여 오디오 신호의 대표적인 특성을 표현 할 수 있는 특징벡터를 구성 할 수 있다면 추후에 멀티모달 시스템을 이용한 검색 알고리즘에도 오디오 특징으로 이용 될 수 있을 것이다 본 논문에서는 방송 시스템에 적용 할 수 있도록 검색 범위를 특정 컨텐츠의 O.S.T 앨범으로 제한하였다. 즉, 사용자가 임의로 선택한 부분적인 오디오 클립만을 이용하여 그 컨텐츠 전체의 O.S.T 앨범 내에서 음악을 검색할 수 있도록 하였다. 오디오 특징벡터를 구성하기 위한 MPEG-7 오디오 서술자의 조합 방법을 제안하고 distance 또는 ratio 계산 방식을 통해 성능 향상을 추구하였다. 또한 reference 음악의 템플릿 구성 방식의 변화를 통해 성능 향상을 추구하였다. Classifier로 k-NN 방식을 사용하여 성능 평가를 수행한 결과 timbral spectral feature들의 비율을 이용한 IFCR(Intra-Feature Component Ratio) 방식이 Euclidean distance 방식보다 우수한 성능을 보였다.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.283-294
• /
• 2015

A model that precisely forecasts how much wind power is generated is critical for making decisions on power generation and infrastructure updates. Existing studies have estimated wind power from wind speed using forecasting models such as ANFIS, SMO, k-NN, and ANN. This study applies a projected clustering technique to identify wind power patterns of wind turbines; profiles the resulting characteristics; and defines hourly and daily power patterns using wind power data collected over a year-long period. A wind power pattern prediction stage uses a time interval feature that is essential for producing representative patterns through a projected clustering technique along with the existing temperature and wind direction from the classifier input. During this stage, this feature is applied to the wind speed, which is the most significant input of a forecasting model. As the test results show, nine hourly power patterns and seven daily power patterns are produced with respect to the Korean wind turbines used in this study. As a result of forecasting the hourly and daily power patterns using the temperature, wind direction, and time interval features for the wind speed, the ANFIS and SMO models show an excellent performance.

• The Journal of Korea Robotics Society
• /
• v.8 no.4
• /
• pp.266-272
• /
• 2013

Facial feature extraction and tracking are essential steps in human-robot-interaction (HRI) field such as face recognition, gaze estimation, and emotion recognition. Active shape model (ASM) is one of the successful generative models that extract the facial features. However, applying only ASM is not adequate for modeling a face in actual applications, because positions of facial features are unstably extracted due to limitation of the number of iterations in the ASM fitting algorithm. The unaccurate positions of facial features decrease the performance of the emotion recognition. In this paper, we propose real-time facial feature extraction and tracking framework using ASM and LK optical flow for emotion recognition. LK optical flow is desirable to estimate time-varying geometric parameters in sequential face images. In addition, we introduce a straightforward method to avoid tracking failure caused by partial occlusions that can be a serious problem for tracking based algorithm. Emotion recognition experiments with k-NN and SVM classifier shows over 95% classification accuracy for three emotions: "joy", "anger", and "disgust".

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.2 s.173
• /
• pp.455-463
• /
• 2000

In order to develop nondestructive techniques for the quantitative estimation of creep damage a series of crept copper samples were prepared and their ultrasonic velocities were measured. Velocities measured in three directions with respect to the loading axis decreased nonlinearly and their anisotropy increased as a function of creep-induced porosity. A progressive damage model was described to explain the void-velocity relationship, including the anisotropy. The comparison of modeling study showed that the creep voids evolved from sphere toward flat oblate spheroid with its minor axis aligned along the stress direction. This model allowed us to determine the average aspect ratio of voids for a given porosity content. A novel technique, the back propagation neural network (BPNN), was applied for estimating the porosity content due to the creep damage. The measured velocities were used to train the BP classifier, and its accuracy was tested on another set of creep samples containing 0 to 0.7 % void content. When the void aspect ratio was used as input parameter together with the velocity data, the NN algorithm provided much better estimation of void content.

• Korean Journal of Remote Sensing
• /
• v.31 no.3
• /
• pp.205-214
• /
• 2015

In this study, a novel land-cover classification framework for multi-temporal SAR data is presented that can combine multiple features extracted through data transforms and multiple classifiers. At first, data transforms using principle component analysis (PCA) and 3D wavelet transform are applied to multi-temporal SAR dataset for extracting new features which were different from original dataset. Then, three different classifiers including maximum likelihood classifier (MLC), neural network (NN) and support vector machine (SVM) are applied to three different dataset including data transform based features and original backscattering coefficients, and as a result, the diverse preliminary classification results are generated. These results are combined via a majority voting rule to generate a final classification result. From an experiment with a multi-temporal ENVISAT ASAR dataset, every preliminary classification result showed very different classification accuracy according to the used feature and classifier. The final classification result combining nine preliminary classification results showed the best classification accuracy because each preliminary classification result provided complementary information on land-covers. The improvement of classification accuracy in this study was mainly attributed to the diversity from combining not only different features based on data transforms, but also different classifiers. Therefore, the land-cover classification framework presented in this study would be effectively applied to the classification of multi-temporal SAR data and also be extended to multi-sensor remote sensing data fusion.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.835-838
• /
• 2016

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology. Materials and Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient. Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set. Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.207-216
• /
• 2013

The aim of this study is to design a classifier for sleep stage analysis and select important feature set which shows sleep stage well based on physiological signals during sleep. Sleep has a significant effect on the quality of human life. When people undergo lack of sleep or sleep-related disease, they are likely to reduced concentration and cognitive impairment affects, etc. Therefore, there are a lot of research to analyze sleep stage. In this study, after acquisition physiological signals during sleep, we do pre-processing such as filtering for extracting features. The features are used input for the new combination algorithm using genetic algorithm(GA) and neural networks(NN). The algorithm selects features which have high weights to classify sleep stage. As the result of this study, accuracy of the algorithm is up to 90.26% with electroencephalography(EEG) signal and electrocardiography(ECG) signal, and selecting features are alpha and delta frequency band power of EEG signal and standard deviation of all normal RR intervals(SDNN) of ECG signal. We checked the selected features are well shown that they have important information to classify sleep stage as doing repeating the algorithm. This research could use for not only diagnose disease related to sleep but also make a guideline of sleep stage analysis.