• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1999.05a
• /
• pp.169-172
• /
• 1999

Recently, the wavelet transform has been a new and powerful tool for signal processing. It is more suitable specially for the feature extraction and detection of non-stationary signals than traditional methods such as, the Fourier Transform(FT), the Fast Fourier Transform(FFT) and the Least Square Method etc. because of the characteristic of the multi-scale analysis and time-frequency domain localization. The wavelet transform has been developed for the analysis of PD pulse signal to raise in the progress of insulation degradation. In this paper, the wavelet transform was applied to one foundational method for feature extraction. For the obtain experimental data, a computer-aided partial discharge measurement system with a single acoustic sensor was used. If we are applying to the neural network method the accumulated data through the extracted feature, it is expected that we can detect the PD pulse signal in the insulation materials on the on-line.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1030-1032
• /
• 1998

In this paper, an efficient feature vector extraction method and MLP neural network are utilized to automatically detect and classify power quality disturbances, where the proposed classification procedure consists of the following three parts: i.e., (i) PQ disturbance detection using discrete wavelet transform. (ii) feature vector extraction from the detected disturbance. using several methods, such as FFT, DWT, Fisher's criterion. etc.. and (iii) classification of the corresponding type of each PQ disturbance by recognizing the pattern of the extracted feature vector. To demonstrate the performance and, applicability of the proposed classification algorithm. some test results obtained by analyzing 10-class PQ disturbances are also provided.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.6
• /
• pp.995-1001
• /
• 1995

The structure of a typical pattern recognition consists a pre-processing, a feature extraction(algorithm) and classification or recognition. In classification, when widely varying patterns exist in same category, we need the clustering which organize the similar patterns. Clustering algorithm is two approaches. Firs, statistical approaches which are k-means, ISODATA algorithm. Second, neural network approach which is T. Kohonen's LVQ(Learning Vector Quantization). Nikhil R. Palet al proposed the GLVQ(Generalized LVQ, 1993). This paper suggest the efficient feature extraction methods of handwritten numerals in GLVQ clustering network. We use the handwritten numeral data from 21's authors(ie, 200 patterns) and compare the proportion of misclassified patterns for each feature extraction methods. As results, when we use the projection combination method, the classification ratio is 98.5%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1431-1445
• /
• 2022

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.10
• /
• pp.95-104
• /
• 1993

IPA(interpattern association) model is a method of feature extraction using a neural network. Even in the case that the reference patterns are simuklar to one another, this model can recover the reference patterns effectively. However, when the pattern whose feature pixels are lost is used as input, this model can not guarantee perfect recovery of the reference pattern. It is proposed a improved interpattern association(IPA) model for the feature extraction using neural network. The improved IPA model that combines the first interconnection weight matrix of the IPA model with the second additional weight matrix is proposed here to overcome the recovery problem of the original IPA model. The results of computer simulation and optical experiment are advanced.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.4
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.95-108
• /
• 2010

In this paper, we present a hybrid neural network model for dynamic hand gesture recognition. The model consists of two modules, feature extraction module and pattern classification module. We first propose a modified CNN(convolutional Neural Network) a pattern recognition model for the feature extraction module. Then we introduce a weighted fuzzy min-max(WFMM) neural network for the pattern classification module. The data representation proposed in this research is a spatiotemporal template which is based on the motion information of the target object. To minimize the influence caused by the spatial and temporal variation of the feature points, we extend the receptive field of the CNN model to a three-dimensional structure. We discuss the learning capability of the WFMM neural networks in which the weight concept is added to represent the frequency factor in training pattern set. The model can overcome the performance degradation which may be caused by the hyperbox contraction process of conventional FMM neural networks. From the experimental results of human action recognition and dynamic hand gesture recognition for remote-control electric home appliances, the validity of the proposed models is discussed.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.26-31
• /
• 1994

A new feature extraction technique utilizing strange attractor and artificial neural network for speaker recognition is presented. Since many signals change their characteristics over long periods of time, simple time-domain processing techniques should e capable of providing useful information of signal features. In many cases, normal time series can be viewed as a dynamical system with a low-dimensional attractor that can be reconstructed from the time series using time delay. The reconstruction of strange attractor is described. In the technique, the raw signal will be reproduced into a geometric three dimensional attractor. Classification decision for speaker recognition is based upon the processing or sets of feature vectors that are derived from the attractor. Three different methods for feature extraction will be discussed. The methods include box-counting dimension, natural measure with regular hexahedron and plank-type box. An artificial neural network is designed for training the feature data generated by the method. The recognition rates are about 82%-96% depending on the extraction method.