• 대한전기학회논문지:전력기술부문A
• /
• 제48권11호
• /
• pp.1464-1471
• /
• 1999

This paper introduces complex-valued competitive learning neural network for spatio-temporal pattern recognition. There have been quite a few neural networks for spatio-temporal pattern recognition. Among them, recurrent neural network, TDNN, and avalanche model are acknowledged as standard neural network paradigms for spatio-temporal pattern recognition. Recurrent neural network has complicated learning rules and does not guarantee convergence to global minima. TDNN requires too many neurons, and can not be regarded to deal with spatio-temporal pattern basically. Grossberg's avalanche model is not able to distinguish long patterns, and has to be indicated which layer is to be used in learning. In order to remedy drawbacks of the above networks, unsupervised competitive learning using complex umber is proposed. Suggested neural network also features simultaneous recognition, time-shift invariant recognition, stable categorizing, and learning rate modulation. The network is evaluated by computer simulation with randomly generated patterns.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1996년도 추계학술대회논문집
• /
• pp.197-205
• /
• 1996

Unification of neural network with a hierarchical pattern recognition is presented for recognizing large set of objects. A two-step identification procedure is developed for pattern recognition: coarse and fine identification. The coarse identification is designed for finding a class of object while the fine identification procedure is to identify a specific object. During the training phase a course neural network is trained for clustering larger set of reference objects into a number of groups. For training a fine neural network, expert neural network is also trained to identify a specific object within a group. The presented idea can be interpreted as two step identification. Experimental results are given to verify the proposed methodology.

• 전기학회논문지
• /
• 제58권1호
• /
• pp.126-131
• /
• 2009

This study was carried out for the reliability of PD(Partial Discharge) pattern recognition. For the pattern recognition, the database for PD was established by use of self-designed insulation defects which occur and were mostly critical in GIS(Gas Insulated Switchgear). The acquired database was analyzed to distinguish patterns by means of PRPD(Phase Resolved Partial Discharge) method and stored to the form with to unite the average amplitude of PD pulse and the number of PD pulse as the input data of neural network. In order to prove the performance of genetic algorithm combined with neural network, the neural networks with trial-and-error method and the neural network with genetic algorithm were trained by same training data and compared to the results of their pattern recognition rate. As a result, the recognition success rate of defects was 93.2% and the neural network train process by use of trial-and-error method was very time consuming. The recognition success rate of defects, on the other hand, was 100% by applying the genetic algorithm at neural network and it took a relatively short time to find the best solution of parameters for optimization. Especially, it could be possible that the scrupulous parameters were obtained by genetic algorithm.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.345-350
• /
• 2002

In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.721-726
• /
• 2005

In this study, researchers classifying the artificial flaws in semiconductor. packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• 한국지능시스템학회논문지
• /
• 제14권2호
• /
• pp.216-221
• /
• 2004

This paper describes an optimal synthesis method of binary neural network for pattern recognition. Our objective is to minimize the number of connections and the number of neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm (NETLA) for the multilayered neural networks. The synthesis method in NETLA uses the Expanded Sum of Product (ESP) of the boolean expressions and is based on the multilayer perceptron. It has an ability to optimize a given binary neural network in the binary space without any iterative learning as the conventional Error Back Propagation (EBP) algorithm. Furthermore, NETLA can reduce the number of the required neurons in hidden layer and the number of connections. Therefore, this learning algorithm can speed up training for the pattern recognition problems. The superiority of NETLA to other learning algorithms is demonstrated by an practical application to the approximation problem of a circular region.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1422-1423
• /
• 2007

This study deals with various neural network algorithms for the on-site partial discharge pattern recognition. For the purpose, the pattern recognition has been carried out on partial discharge data for the typical artificial defect using 9 different neural network models. In order to enhance on-site applicability, artificial defects were installed in the insulation joint box of extra-high voltage xLPE cables and partial discharges were measured by use of the metal foil sensor and a HFCT as a sensor. As the result, it is found out that the accuracy of pattern recognition could be enhanced through the application of the Sigmoid function, the Momentum algorithm and the Genetic algorism on the artificial neural networks. Although Multilayer Perceptron (MLP) algorism showed the best result among 9 neural network algorisms, it is thought that more researches on others would be needed in consideration of on-site application.

• 대한기계학회논문집A
• /
• 제20권4호
• /
• pp.1309-1319
• /
• 1996

The research for the classification of the natural defects in welding zone is performd using the neuro-pattern recognition technology. The signal pattern recognition package including the user's defined function is developed to perform the digital signal processing, feature extraction, feature selection and classifier selection, The neural network classifier and the statistical classifiers such as the linear discriminant function classifier and the empirical Bayesian calssifier are compared and discussed. The neuro-pattern recognition technique is applied to the classificaiton of such natural defects as root crack, incomplete penetration, lack of fusion, slag inclusion, porosity, etc. If appropriately learned, the neural network classifier is concluded to be better than the statistical classifiers in the classification of the natural welding defects.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집A
• /
• pp.505-510
• /
• 2000

Vehicle performances such as fuel consumption and catalyst-out emissions are affected by a driving pattern, which is defined as a driving cycle with the grade in this study. We developed an algorithm to recognize a current driving pattern by using a neural network. And this algorithm can be used in adapting the driving control strategy to the recognized driving pattern. First, we classified the general driving patterns into 6 representative driving patterns, which are composed of 3 urban driving patterns, 2 suburban driving patterns and 1 expressway driving pattern. A total of 24 parameters such as average cycle velocity, positive acceleration kinetic energy, relative duration spent at stop, average acceleration and average grade are chosen to characterize the driving patterns. Second, we used a neural network (especially the Hamming network) to decide which representative driving pattern is closest to the current driving pattern by comparing the inner products between them. And before calculating inner product, each element of the current and representative driving patterns is transformed into 1 and -1 array as to 4 levels. In the end, we simulated the driving pattern recognition algorithm in a temporary pattern composed of 6 representative driving patterns and, verified the reliable recognition performance.