• Proceedings of the KIEE Conference
• /
• 2004.07c
• /
• pp.1784-1786
• /
• 2004

PD(Partial Discharge) signal emitted from PD sources has their intrinsic features in the region of time and frequency. STFT(Short Time Fourier Transform) shows time-frequency distribution at the same time. 2-Dimensional matrices(33${\times}$77) from STFT for PD pulse signals are a good feature vectors and can be decreased in dimension by wavelet 2D data compression technique. Decreased feature vectors(13${\times}$24) were used as inputs of Back-propagation ANN(Artificial Neural Network) for discrimination of Multi-PD sources(air discharge sources(3), surface discharge(1)). They are a good feature vectors for discriminating Multi-PD sources.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.409-415
• /
• 2003

Recently, the modular learning are very popular and receive much attention for pattern classification. The modular learning method based on the "divide and conquer" strategy can not only solve the complex problems, but also reach a better result than a single classifier′s on the learning quality and speed. In the neural network area, some researches that take the modular learning approach also have been made to improve classification performance. In this paper, we propose a simple modular neural network for characters recognition of vehicle number plate and evaluate its performance on the clustering methods of feature vectors used in constructing subnetworks. We implement two clustering method, one is grouping similar feature vectors by K-means clustering algorithm, the other grouping unsimilar feature vectors by our proposed algorithm. The experiment result shows that our algorithm achieves much better performance.

• Journal of Korea Multimedia Society
• /
• v.13 no.6
• /
• pp.817-824
• /
• 2010

Linear Discriminant Analysis (LDA) has been successfully applied for dimension reduction in face recognition. However, LDA requires the transformation of a face image to a one-dimensional vector and this process can cause the correlation information among neighboring pixels to be disregarded. On the other hand, 2D-LDA uses 2D images directly without a transformation process and it has been shown to be superior to the traditional LDA. Nevertheless, there are some problems in 2D-LDA. First, it is difficult to determine the optimal number of feature vectors in a reduced dimensional space. Second, the size of rectangular windows used in 2D-LDA makes strong impacts on classification accuracies but there is no reliable way to determine an optimal window size. In this paper, we propose a new algorithm to overcome those problems in 2D-LDA. We adopt an ensemble approach which combines several classifiers obtained by utilizing various window sizes. And a practical method to determine the number of feature vectors is also presented. Experimental results demonstrate that the proposed method can overcome the difficulties with choosing an optimal window size and the number of feature vectors.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.54 no.7
• /
• pp.332-338
• /
• 2005

PD(Partial Discharge) signal emitted from PD sources has their intrinsic features in the region of time and frequency STFT(Short Time Fourier Transform) shows time-frequency distribution at the same time. 2-Dimensional matrices(33$\times$77) from STFT for PD pulse signals are a good feature vectors and can be decreased in dimension by wavelet 2D data compression technique. Decreased feature vectors(13$\times$24) were used as inputs of Back-propagation ANN(Artificial Neural Network) for discrimination of Multi-PD sources(air discharge sources(3), surface discharge(1)). They are a good feature vectors for discriminating Multi-PD sources in the air.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.45-48
• /
• 2007

This paper proposes a flexible selection method of feature vectors for speaker identification. In speaker identification, overlapped region between speaker models lowers the accuracy. Recently, a method was proposed which discards overlapped feature vectors without regard to the source causing the overlap. We suggest a new method using both overlapped features among speakers and non-overlapped features to mitigate the overlap effects.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.3
• /
• pp.149-157
• /
• 2001

In the video retrieval system, visual clues of still images and motion information of video are employed as feature vectors. We generate the temporal textures to express the motion information whose properties are simple expression, easy to compute. We make those temporal textures of wavelet coefficients to express motion information, M components. Then, temporal texture feature vectors are extracted using spatial texture feature vectors, i.e. spatial gray-level dependence. Also, motion amount and motion centroid are computed from temporal textures. Motion trajectories provide the most important information for expressing the motion property. In our modeling system, we can extract the main motion trajectory from the temporal textures.

• Speech Sciences
• /
• v.14 no.2
• /
• pp.127-135
• /
• 2007

Feature vectors of speech are generally extracted from whole frequency domain. The inherent character of a speaker is located in the low band or high band frequency. However, if the speech is corrupted by narrowband noise with concentrated energy, speaker verification performance is reduced as the individual characteristic is removed. In this paper, we propose a PCA Covariance Model based on the multiband to extract the robust feature vectors against the narrowband noise. First, we divide the overall frequency band into several subbands. Second, the correlation of feature vectors extracted independently from each subband is removed by PCA. The distance obtained from each subband has different distribution. To normalize against the different distribution, we moved the value into the normalized distribution through the mapping function. Finally, the represented value applying the weighting function is used for speaker verification. In the experiments, the proposed method shows better performance of the speaker verification and reduces the computation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.754-759
• /
• 2007

In this paper, we proposed the Bi-Modal Sensor Fusion Algorithm which is the emotional recognition method that be able to classify 4 emotions (Happy, Sad, Angry, Surprise) by using facial image and speech signal together. We extract the feature vectors from speech signal using acoustic feature without language feature and classify emotional pattern using Neural-Network. We also make the feature selection of mouth, eyes and eyebrows from facial image. and extracted feature vectors that apply to Principal Component Analysis(PCA) remakes low dimension feature vector. So we proposed method to fused into result value of emotion recognition by using facial image and speech.

• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.67-78
• /
• 2018

This article proposes the modified KNN (K Nearest Neighbor) algorithm which considers the feature similarity and is applied to the word categorization. The texts which are given as features for encoding words into numerical vectors are semantic related entities, rather than independent ones, and the synergy effect between the word categorization and the text categorization is expected by combining both of them with each other. In this research, we define the similarity metric between two vectors, including the feature similarity, modify the KNN algorithm by replacing the exiting similarity metric by the proposed one, and apply it to the word categorization. The proposed KNN is empirically validated as the better approach in categorizing words in news articles and opinions. The significance of this research is to improve the classification performance by utilizing the feature similarities.

• The KIPS Transactions:PartD
• /
• v.8D no.5
• /
• pp.507-512
• /
• 2001

Feature-based similarity has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects. the performance of conventional multidimensional data structures tends to deteriorate as the number of dimensions of feature vectors increase. The $R^{*}-Tree$ is the most successful variant of the R-Tree. In this paper, we propose a SOM-based $R^{*}-Tree$ as a new indexing method for high-dimensional feature vectors. The SOM-based $R^{*}-Tree$ combines SOM and $R^{*}-Tree$ to achieve search performance more scalable to high-dimensionalties. Self-Organizingf Maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. Each node of the topological feature map holds a codebook vector. We experimentally compare the retrieval time cost of a SOM-based $R^{*}-Tree$ with of an SOM and $R^{*}-Tree$ using color feature vectors extracted from 40,000 images. The results show that the SOM-based $R^{*}-Tree$ outperform both the SOM and $R^{*}-Tree$ due to reduction of the number of nodes to build $R^{*}-Tree$ and retrieval time cost.