• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.319-324
• /
• 2005

An integrated approach for prostate cancer detection using proteomic data is presented. Due to the high-dimensional feature of proteomic data, the discrete wavelet transform (DWT) is used in the first-stage for data reduction as well as noise removal. After the process of DWT, the dimensionality is reduced from 43,556 to 1,599. Thus, each sample of proteomic data can be represented by 1599 wavelet coefficients. In the second stage, a voting method is used to select a common set of wavelet coefficients for all samples together. This produces a 987-dimension subspace of wavelet coefficients. In the third stage, the Autoassociator algorithm reduces the dimensionality from 987 to 400. Finally, the artificial neural network (ANN) is applied on the 400-dimension space for prostate cancer detection. The integrated approach is examined on 9 categories of 2-class experiments, and also 3- and 4-class experiments. All of the experiments were run 10 times of ten-fold cross-validation (i. e. 10 partitions with 100 runs). For 9 categories of 2-class experiments, the average testing accuracies are between 81% and 96%, and the average testing accuracies of 3- and 4-way classifications are 85% and 84%, respectively. The integrated approach achieves exciting results for the early detection and diagnosis of prostate cancer.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.94-98
• /
• 2009

A video caption recognition system has been developed for broadcasting sport events such as major league baseball. The purpose of the system is to translate the information expressed in English units such as miles per hour (MPH) to the international system of units (SI) such as km/h. The system detects the ball speed displayed in the video and recognizes the numerals. The ball speed is then converted to km/h and displayed by the following character generator (CG) system. Although neural-network based methods are widely used for character and numeral recognition, we use template matching to avoid the training process required before the broadcasting. With the proposed template matching method, the operator can cope with the situation when the caption’s appearance changed without any notification. Templates are configured by the operator with a captured screenshot of the first pitch with ball speed. Templates are updated with following correct recognition results. The accuracy of the recognition module is over 97%, which is still not enough for live broadcasting. When the recognition confidence is low, the system asks the operator for the correct recognition result. The operator chooses the right one using hot keys.

• Korean Journal of Cognitive Science
• /
• v.10 no.4
• /
• pp.71-83
• /
• 1999

Conventional symbolic inference systems lack flexibility because they do not well reflect flexible semantic structure of knowledge and use symbolic logic for their basic inference mechanism. For solving this problem. we have recently proposed the 'Connectionist Semantic Network(CSN)' as a model for flexible knowledge representation and inference based on neural networks. The CSN is capable of carrying out both approximate reasoning and commonsense reasoning based on similarity and association. However. we have difficulties in representing general and structured high-level knowledge and variable binding using the connectionist framework of the CSN. In this paper. we propose a hybrid system called SymCSN(Symbolic CSN) that combines a symbolic module for representing general and structured high-level knowledge and a connectionist module for representing and learning low-level semantic structure Simulation results show that the SymCSN is a plausible model for human-like flexible knowledge representation and inference.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.337-340
• /
• 2004

The exactly reproduced prosody of a TTS system is one of the key factors that affect the naturalness of synthesized speech. In general, rules about prosody had been gathered either from linguistic knowledge or by analyzing the prosodic information from natural speech. But these could not be perfect and some of them could be incorrect. So we proposed artificial neural network(ANN)s that can be trained to team the prosody of natural speech and generate it. In learning phase, let ANNs learn the pitch and energy contour of center phoneme by applying a string of phonemes in a sentence to ANNs and comparing the output pattern with target pattern and making adjustment in weighting values to get the least mean square error between them. In test phase, the estimation rates were computed. We saw that ANNs could generate the prosody of a sentence.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1207-1214
• /
• 2019

Technologies of the 4th industrial revolution have been unknowingly seeping into our lives. Many IoT based home security systems are using the convolutional neural network(CNN) as good biometrics to recognize a face and protect home and family from intruders since CNN has demonstrated its excellent ability in image recognition. In this paper, three layouts of CNN for 2D and 2.5D image of small dataset with various input image size and filter size are explored. The simulation results show that the layout of CNN with 50*50 input size of 2.5D image, 2 convolution and max pooling layer, and 3*3 filter size for small dataset of 2.5D image is optimal for a home security system with recognition accuracy of 0.966. In addition, the longest CPU time consumption for one input image is 0.057S. The proposed layout of CNN for a face recognition is suitable to control the actuators in the home security system because a home security system requires good face recognition and short recognition time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1153-1160
• /
• 2019

In this paper, we experimented to find out how the number of convolution layers, the size, and the number of kernels affect the CNN. In addition, the general CNN was also tested for analysis and compared with the CNN used in the experiment. The neural networks used for the analysis are based on CNN, and each experimental model is experimented with the number of layers, the size, and the number of kernels at a constant value. All experiments were conducted using two layers of fully connected layers as a fixed. All other variables were tested with the same value. As the result of the analysis, when the number of layers is small, the data variance value is small regardless of the size and number of kernels, showing a solid accuracy. As the number of layers increases, the accuracy increases, but from above a certain number, the accuracy decreases, and the variance value also increases, resulting in a large accuracy deviation. The number of kernels had a greater effect on learning speed than other variables.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.429-438
• /
• 2006

Neural Networks(NNs) are applied for solving a wide variety of nonlinear problems in several areas, such as image processing, pattern recognition etc. Although NN can be simulated by using software, many potential NN applications required real-time processing. Thus they need to be implemented as hardware. The hardware implementation of multi-layer perceptrons(MLPs) in several kind of NNs usually uses a fixed-point arithmetic due to a simple logic operation and a shorter processing time compared to the floating-point arithmetic. However, the fixed-point arithmetic-based MLP has a drawback which is not able to apply the MLP software that use floating-point arithmetic. We propose a design method for MLPs which has the floating-point arithmetic-based fully-pipelining architecture. It has a processing speed that is proportional to the number of the hidden nodes. The number of input and output nodes of MLPs are generally constrained by given problems, but the number of hidden nodes can be optimized by user experiences. Thus our design method is using optimized number of hidden nodes in order to improve the processing speed, especially in field of a repeated processing such as image processing, pattern recognition, etc.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.91-98
• /
• 2018

Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. In particular, porcine respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this paper, we propose a noise-robust system for the early detection and recognition of pig wasting diseases using sound data. In this method, first we convert one-dimensional sound signals to two-dimensional gray-level images by normalization, and extract texture images by means of dominant neighborhood structure technique. Lastly, the texture features are then used as inputs of convolutional neural networks as an early anomaly detector and a respiratory disease classifier. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (low-cost sound sensor) and accurately (over 96% accuracy) even under noise-environmental conditions, either as a standalone solution or to complement known methods to obtain a more accurate solution.

• The Journal of Korean Physical Therapy
• /
• v.15 no.3
• /
• pp.295-345
• /
• 2003

This study investigated activation of cerebral cortex in patients with hemiplegia that was caused by neural damage. Key-point control movement therapy of Bobath was performed for 9 weeks in 3 subjects with hemiplegia and fMRI was used to compare and analyze activated degree of cerebral cortex in these subjects. fMRI was conducted using the blood oxygen level-dependent(BOLD) technique at 3.0T MR scanner with a standard head coil. The motor activation task consisted of finger flexion-extension exercise in six cycles(one half-cycles = 8 scans = $3\;sec{\times}\;8\;=\;24\;sec$). Subjects performed this task according to visual stimulus that sign of right hand or left hand twinkled(500ms on, 500ms off). After mapping activation of cerebral motor cortex on hand motor function, below results were obtained. 1. Activation decreased in primary motor area, whereas it increased in supplementary motor area and visual association area(p<.001). 2. Activation was observed in bilateral medial frontal gyrus, middle frontal gyrus of left cerebrum, inferior frontal gyrus, inter-hemispheric, fusiform gyrus of right cerebrum, superior parietal lobule of parietal lobe and precuneus in subjedt 1, parahippocampal gyrus of limbic lobe and cingulate gyrus in subject 2, and inferior frontal gyrus of right frontal lobe, middle frontal gyrus, and inferior parietal lobule of left cerebrum in subject 3 (p<.001). 3. Activation cluster extended in declive of right cellebellum posterior lobe in subject 1, culmen of anterior lobe and declive of posterior lobe in subject 2, and dentate gyrus of anterior lobe, culmen and tuber of posterior lobe in subject 3 (p<.001). In conclusion, these data showed that Key-point control movement therapy of Bobath after stroke affect cerebral cortex activation by increasing efficiency of cortical networks. Therefore mapping of brain neural network activation is useful for plasticity and reorganization of cerebral cortex and cortico-spinal tract of motor recovery mechanisms after stroke.