• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.592-599
• /
• 2020

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.61-70
• /
• 2004

The operation mode of neural network is divided into learning and recognition process. Learning is updating process of weight until neural network archives target result from input pattern. Recognition is arithmetic process of input pattern and weight. Traditional inner product process is focused to improve processing speed and hardware complexity. There is no hardware architecture to distinguish between loaming and recognition mode of neural network. In this paper we propose the new architecture of low power inner product processor for reconfigurable neural network. The proposed architecture is similar with bit-serial inner product processor on learning mode. It have several advantages which are fast processing base on bit-level, suitability of hardware implementation and pipeline architecture to compute data. And proposed architecture minimizes active units and reduces consumption power on recognition mode. Result of simulation shows that active units is depend on bit representation of weight, but we can reduce active units about 50 precent.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.105-108
• /
• 1997

Previous studies in stock market predictions using artificial intelligence techniques such as artificial neural networks and case-based reasoning, have focused mainly on spot market prediction. Korea launched trading in index futures market (KOSPI 200) on May 3, 1996, then more people became attracted to this market. Thus, this research intends to predict the daily up/down fluctuant direction of the price for KOSPI 200 index futures to meet this recent surge of interest. The forecasting methodologies employed in this research are the integration of genetic algorithm and artificial neural network (GAANN) and the integration of genetic algorithm and case-based reasoning (GACBR). Genetic algorithm was mainly used to select relevant input variables. This study adopts the categorical data preprocessing based on expert's knowledge as well as traditional data preprocessing. The experimental results of each forecasting method with each data preprocessing method are compared and statistically tested. Artificial neural network and case-based reasoning methods with best performance are integrated. Out-of-the Model Integration and In-Model Integration are presented as the integration methodology. The research outcomes are as follows; First, genetic algorithms are useful and effective method to select input variables for Al techniques. Second, the results of the experiment with categorical data preprocessing significantly outperform that with traditional data preprocessing in forecasting up/down fluctuant direction of index futures price. Third, the integration of genetic algorithm and case-based reasoning (GACBR) outperforms the integration of genetic algorithm and artificial neural network (GAANN). Forth, the integration of genetic algorithm, case-based reasoning and artificial neural network (GAANN-GACBR, GACBRNN and GANNCBR) provide worse results than GACBR.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.350-357
• /
• 1991

A speech recognition system based on a neural network, which can be used for telephon number services was tested. Because in Korea two different cardinal number systems, a koreanic one and a sinokoreanic one, are in use, it is necessary that the used systems is able to recognize 22 discret words. The structure of the neural network used had two layers, also a structure with 3 layers, one hidden layreformed of each 11, 22 and 44 hidden units was tested. During the learning phase of the system the so called BP-algorithm (back propagation) was applied. The process of learning can e influenced by using a different learning factor and also by the method of learning(for instance random or cycle). The optimal rate of speaker independent recognition by using a 2 layer neural network was 96%. A drop of recognition was observed by overtraining. This phenomen appeared more clearly if a 3 layer neural network was used. These phenomens are described in this paper in more detail. Especially the influence of the construction of the neural network and the several states during the learning phase are examined.

• Journal of Korean Society of Transportation
• /
• v.24 no.7 s.93
• /
• pp.81-90
• /
• 2006

It is important to clarify the relationship between traffic accidents and various influencing factors in order to reduce the number of traffic accidents. This study developed a traffic accident frequency prediction model using by multi-linear regression and qualification theories which are commonly applied in the field of traffic safety to verify the influences of various factors into the traffic accident frequency The data were collected on the Korean National Highway 17 which shows the highest accident frequencies and fatality rates in Chonbuk province. In order to minimize the uncertainty of the data, the fuzzy theory and neural network theory were applied. The neural network theory can provide fair learning performance by modeling the human neural system mathematically. Tn conclusion, this study focused on the practicability of the fuzzy reasoning theory and the neural network theory for traffic safety analysis.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.3
• /
• pp.684-689
• /
• 2005

In this paper, we propose car license plate recognition using morphological information and an enhanced neural network. Morphological information on horizontal and vertical edges was used to extract the license plate from a car image. We used a contour tracking algorithm combined with the method of histogram and location information to extract individual characters in the extracted plate. The enhanced neural network is proposed for recognizing them, which has the method of combining the ART-1 and the supervised teaming method. The proposed method has applied to real world car images. The experimental results show that the proposed method has better the extraction rates than the methods with information of the thresholding, the RGB and the HSI, respectively. And the proposed neural network has better recognition performance than the conventional neural networks.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.77-82
• /
• 2007

In this paper, we proposed the image processing techniques for extracting the cracks in a concrete surface crack image and the enhanced Max-Min neural network for recognizing the directions of the extracted cracks. The image processing techniques used are the closing operation or morphological techniques, the Sobel masking for extracting for edges of the cracks, and the iterated binarization for acquiring the binarized image from the crack image. The cracks are extracted from the concrete surface image after applying two times of noise reduction to the binarized image. We proposed the method for automatically recognizing the directions of the cracks with the enhanced Max-Min neural network. Also, we propose an enhanced Max-Min neural network by auto-tuning of learning rate using delta-bar-delta algorithm. The experiments using real concrete crack images showed that the cracks in the concrete crack images were effectively extracted and the enhanced Max-Min neural network was effective in the recognition of direction of the extracted cracks.

• Journal of the Korean GEO-environmental Society
• /
• v.14 no.5
• /
• pp.15-22
• /
• 2013

The submarine pipe, which is one of the most important coastal structures, is widely used in the development of coastal and ocean engineering. The scour of the submarine pipe occurs due to the wave and the current according to the state of the sea bed. The scour affects the submarine pipe and causes it to undergo settlement and fatigue. It is difficult to predict the local scour under complicated and various conditions of the coastal environment, even though many researches on the scour of the submarine pipe have been studied in recent years. This study analyzed the scour depth around a submarine pipe by using the Neural Network technique. The back-propagation algorithms was used to train the Neural Network. The 58 simulating experimental data for the performance and validation of the Neural Network technique were analyzed in this study. Then, the regression analysis for the same data was performed in this study to predict and compare with the Neural Network technique for the scour depth.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.40-48
• /
• 2018

This paper proposes a license-plate recognition algorithm for automobile black-box image which is obtained from the camera moving with the automobile. The algorithm intends to increase the overall recognition-rate of the license-plate by increasing the Korean character recognition-rate using multi-stage neural network for automobile black-box image where there are many movements of the camera and variations of light intensity. The proposed algorithm separately recognizes the vowel and consonant of Korean characters of automobile license-plate. First, the first-stage neural network recognizes the vowels, and the recognized vowels are classified as vertical-vowels('ㅏ','ㅓ') and horizontal-vowels('ㅗ','ㅜ'). Then the consonant is classified by the second-stage neural networks for each vowel group. The simulation for automobile license-plate recognition is performed for the image obtained by a real black-box system, and the simulation results show the proposed algorithm provides the higher recognition-rate than the existing algorithms using a neural network.