• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.797-799
• /
• 2000

Most neural network learning schemes are derived from learning systems which are generally iterative in nature. But, when the given input-output training vector pairs satisfy a PLI condition, the training and the application of a hard-limited neural network can be achieved non-iteratively with very short training time and very robust recognition when it is applied to recognize any untrained patterns. In this paper, a method of expanding the dimension of training pattern data is suggested. The proposed method demonstrates better performance and robustness.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.5-12
• /
• 1995

In the case where the set of training vectors constitute clusters, the codevectors of the codebook which is used to compression for speech and images in the vector quantization are regarded as the central vectors of the clusters constituted by given training vectors. In this work, we consider the distribution of Euclidean distance obtaining in the process of searching for the minimum distance between vectors, and propose the method searching for the proper number of and the central vectors of clusters. And then, the proposed method shows more than the about 4[dB] SNR than the LBG algorithm and the competitive learning algorithm

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.4
• /
• pp.965-974
• /
• 2003

In this paper we propose an incremental classification of multi-class data set by LS-SVM. By encoding the output variable in the training data set appropriately, we obtain a new specific output vectors for the training data sets. Then, online LS-SVM is applied on each newly encoded output vectors. Proposed method will enable the computation cost to be reduced and the training to be performed incrementally. With the incremental formulation of an inverse matrix, the current information and new input data are used for building another new inverse matrix for the estimation of the optimal bias and lagrange multipliers. Computational difficulties of large scale matrix inversion can be avoided. Performance of proposed method are shown via numerical studies and compared with artificial neural network.

• The Journal of Information Technology and Database
• /
• v.8 no.1
• /
• pp.95-104
• /
• 2001

In the text classification domain, labeling the training documents is an expensive process because it requires human expertise and is a tedious, time-consuming task. Therefore, it is important to reduce the manual labeling of training documents while improving the text classifier. Selective sampling, a form of active learning, reduces the number of training documents that needs to be labeled by examining the unlabeled documents and selecting the most informative ones for manual labeling. We apply this methodology to Naive Bayes, a text classifier renowned as a successful method in text classification. One of the most important issues in selective sampling is to determine the criterion when selecting the training documents from the large pool of unlabeled documents. In this paper, we propose two measures that would determine this criterion : the Mean Absolute Deviation (MAD) and the entropy measure. The experimental results, using Renters 21578 corpus, show that this proposed learning method improves Naive Bayes text classifier more than the existing ones.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.429-431
• /
• 2003

The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.473-481
• /
• 2008

This paper presents an approach to Back-propagation and Radial Basis Function neural network method with various training set for automatic vehicle detection from aerial images. The initial extraction of candidate object is based on Mean-shift algorithm with symmetric property of a vehicle structure. By fusing the density and the symmetry, the method can remove the ambiguous objects and reduce the cost of processing in the next stage. To extract features from the detected object, we describe the object as a log-polar shape histogram using edge strengths of object and represent the orientation and distance from its center. The spatial histogram is used for calculating the momentum of object and compensating the direction of object. BPNN and RBFNN are applied to verify the object as a vehicle using a variety of non-car training sets. The proposed algorithm shows the results which are according to the training data. By comparing the training sets, advantages and disadvantages of them have been discussed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3515-3524
• /
• 2023

A reinforcement learning framework is proposed for the control problem of outlet steam pressure of the once-through steam generator(OTSG) in this paper. The double-layer controller using Proximal Policy Optimization(PPO) algorithm is applied in the control structure of the OTSG. The PPO algorithm can train the neural networks continuously according to the process of interaction with the environment and then the trained controller can realize better control for the OTSG. Meanwhile, reinforcement learning has the characteristic of difficult application in real-world objects, this paper proposes an innovative pretraining method to solve this problem. The difficulty in the application of reinforcement learning lies in training. The optimal strategy of each step is summed up through trial and error, and the training cost is very high. In this paper, the LSTM model is adopted as the training environment for pretraining, which saves training time and improves efficiency. The experimental results show that this method can realize the self-adjustment of control parameters under various working conditions, and the control effect has the advantages of small overshoot, fast stabilization speed, and strong adaptive ability.

• Physical Therapy Korea
• /
• v.10 no.3
• /
• pp.81-90
• /
• 2003

This study was conducted to assess the effects of the gait training method in incomplete spinal cord injured persons using an auto-walking machine. Persons with incomplete spinal cord injury level C or D on the American Spinal Injury Association impairment scale participated for eight weeks in an auto-walking training program. The gait training program was carried out for 15 minutes, three times per day for 8 weeks with an auto-walking machine. The foot rests of the auto-walking machine can be moved forward, downward, backward and upward to make the gait pattern with fixed on crank. The patient's body weight is supported by a harness during waking training. We evaluated the gait speed, physiologic cost index, motor score of lower extremities and the WISCI (walking index for spinal cord injury) level before the training and after the forth and eighth week of walking training. 1. The mean gait speed was significantly increased from .22 m/s at pre-training to .28 m/s after 4 weeks of training and .31 m/s after 8 weeks of training (p=.004). 2. The mean physiologic cost index was decreased from 4.6 beats/min at pre-training to 3.0 beats/min after 4 weeks and 2.0 beats/min after 8 weeks of training, but it was not statistically significant (p=.140). 3. The mean motor score of lower extrernities was significantly increased from 29.8 to 35.8 after 8 weeks of training (p=.043). 4. The mean WISCI level was significantly increased from level 10 to level 19 after 8 weeks of training (p=.007). The results of this study suggest that the gait training program using the auto-walking machine increased the gait speed, muscle strength and galt pattern (WISCI level) in persons with incomplete spinal cord injury. A large, controlled study of this technique is warranted.

• The Korean Journal of Emergency Medical Services
• /
• v.16 no.1
• /
• pp.91-101
• /
• 2012

Purpose: This study aims to assess the influencing factors on the level of satisfaction with clinical training and to provide basic data for more efficient clinical training. Method: The study was conducted on 402 paramedic students who have experienced clinical training from September 6 until October 12 in 2011. The questionnaires consisted of 40 questions. We used SPSS 18.0 frequency analysis, technical statistics, t-test, ANOVA, Pearson's correlation coefficients and multiple regression analysis. Result: 1. The level of satisfaction with clinical training showed significant difference between the frequency (F=8.837, p=.000) and clinical training managers (F=5.418, p=.001). 2. The level of satisfaction with clinical training showed the strongest positive correlation with the satisfaction of clinical training hospitals (r=.694, p=.000). 3. Multiple regression analysis revealed the most powerful predictor for satisfaction with clinical training was the satisfaction level of clinical training hospitals(48.2%) and the frequency of clinical training experiences(.8%), the preparation before the clinical training(5.4%), the total duration of clinical training(.7%), and the satisfaction of emergency department education(1.0%). These five variables accounted for 56.1% of the satisfaction of clinical training among paramedic students. Conclusion: As student's satisfaction of the clinical training increases, the quality of paramedics is expected to improve in the future. As a result, the future paramedics can be nurtured to be highly skilled in on-the-scene emergency situations after graduation.