• Electronics and Telecommunications Trends
• /
• v.38 no.4
• /
• pp.95-103
• /
• 2023

The importance of the decentralized training with decentralized execution (DTDE) framework is well-known in the study of multiagent reinforcement learning. In many real-world environments, agents cannot share information. Hence, they must be trained in a decentralized manner. However, the DTDE framework has been less studied than the centralized training with decentralized execution framework. One of the main reasons is that many problems arise when training agents in a decentralized manner. For example, DTDE algorithms are often computationally demanding or can encounter problems with non-stationarity. Another reason is the lack of simulation environments that can properly handle the DTDE framework. We discuss current research trends in the DTDE framework.

• Journal of The Korean Association of Information Education
• /
• v.23 no.2
• /
• pp.107-116
• /
• 2019

The purpose of this study is to develop a Python sorting algorithm training program based on execution time as an educational method for enhancing the logical thinking power of elementary students and then to verify the effect. The education program was developed based on the results of the pre-demand analysis conducted on 100 elementary school teachers. In order to verify the effectiveness of the developed educational program, I teached 25 students of the volunteer sample of the elementary school education donation program conducted at ${\bigcirc}{\bigcirc}$ University conducted 42 hours, 7 days. The results of the pre-test and post-test were analyzed using the 'Group Assessment of Logical Thinking(GALT)' developed by the Korea Educational Development Institute. The results showed that the Python sorting algorithm training centered on execution time was effective in improving the logical thinking ability of elementary school students.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.615-624
• /
• 2006

The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data layer, node, md weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.655-673
• /
• 2004

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA ), Logit Analysis, Neural Network. The after-crisis bankrupted companies were limited to the research data and the listed companies belonging to manufacturing industry was limited to the research data so as to improve prediction accuracy and validity of the model. In order to assure meaningful bankruptcy prediction, training data and testing data were not extracted within the corresponding period. The result is that prediction accuracy of neural network model is more excellent than that of logit analysis and MDA model when considering that execution of testing data was followed by execution of training data.

• Journal of the Korean Society of Physical Medicine
• /
• v.7 no.4
• /
• pp.401-409
• /
• 2012

PURPOSE: The purpose of this study is to assess the difference in the effect of provision of feedback on knowledge of performance and knowledge of result in the training using somesthetic video game aimed at enhancement of balance of hemiparalysis patients due to stroke. METHODS: 20 stroke patients participated in the study. The participants were randomly divided into 2 groups, namely, the knowledge of performance feedback group (KP group, n=10) and the knowledge of result feedback group (KR group, n=10). Both groups received somesthetic video game training 5 times (30 minutes each) a week for total of 4 weeks. The KP group received feedback on the patterns of movement in execution of somesthetic video game. The KR group received feedback on the scores acquired following execution of somesthetic video game. Verification of the significance of the data was performed through paired t-test and independent t-test. RESULTS: Both groups displayed significant reduction in the movement of center of pressure (COP) and Timed up and Go (TUG), and significant increase in the Berg Balance Scale (BBS) following the training. Although the movement of COP was reduced for the KP group in comparison to the KR group, it was not statistically significant, and there was significant reduction in TUG and significant increase in BBS. CONCLUSION: The above results illustrate that provision of feedback on knowledge of performance is more effective than feedback on knowledge of result in somesthetic video game training for the purpose of enhancement of balance in stroke patients. Therefore, provision of feedback on knowledge of performance is necessary in somesthetic video game training for stroke patients.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.161-169
• /
• 2011

Recent intelligent video surveillance system asks for development of more advanced technology for analysis and recognition of video data. Especially, machine learning algorithm such as Support Vector Machine (SVM) is used in order to recognize objects in video. Because SVM training demands massive amount of computation, parallel processing technique is necessary to reduce the execution time effectively. In this paper, we propose a parallel processing method of SVM training with a multi-core processor. The results of parallel SVM on a 4-core processor show that our proposed method can reduce the execution time of the sequential training by a factor of 2.5.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.2014-2020
• /
• 2008

The considerable numbers of accidents have been occurred in railway industrials due to human errors by the railway operators, and we recognised that the design of work and the working environment influence the way people behavior. Human factors are a significant contribute to the occurrence of incidents, and that safety education and training guideline need to be designed to railway safety. In order to develop the education and training program guideline for railway operators, we performed investigation not only existing internal training programs and external railway and other industrial's training programs but also education engineering theory and expert interview. As a result we make up guideline to education and training program. The guideline are composed 10 section.

• Physical Therapy Korea
• /
• v.18 no.2
• /
• pp.27-34
• /
• 2011

The aim of this study was to determine the effect of action-observation training on arm function in people with stroke. Fourteen chronic stroke patients participated in action-observation training. Initially, they were asked to watch video that illustrated arm actions used in daily activities; this was followed by repetitive practice of the observed actions for 3 times a week for 3 weeks. Each training session lasted 30 min. All subject participated 12 training session on 9 consecutive training days. For the evaluation of the clinical status of standard functional scales, Wolf motor function test was carried out at before and after the training and at 2 weeks after the training. Friedman test and Wilcoxon signed rank test was used to analyze the results of the clinical test. There was a significant improvement in the upper arm functions after the 3-week action-observation training, as compared to that before training. The improvement was sustained even at two weeks after the training. This result suggest that action observation training has a positive additional impact on recovery of stroke-induced motor dysfunctions through the action observation-action execution matching system, which includes in the mirror neuron system.

• Journal of the Society of Disaster Information
• /
• v.15 no.3
• /
• pp.347-357
• /
• 2019

Purpose: The purpose of this paper is to present a method for effectively conducting discussion-based training in disaster response safety training. Method: To this end, we analyzed the disaster response training of developed countries and suggested the training scenarios by applying the war-game process that is currently applied in the operation planning of our military. Result: In one disaster situation, several contingencies could be identified, and supplementary requirements for the manual could be derived. Conclusion: Therefore, in conclusion, if the military war-game process is applied to the discussion-based training in disaster response safety training, effective training can be carried out.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.849-854
• /
• 2004

This paper proposes an algorithm to enhance the execution time of kNN in the document classification. The proposed algorithm is to enhance the execution time by minimizing the computing cost of the similarity between two documents by using the list of pairs, while the conventional kNN uses the iist of pairs. The 1ist of pairs can be obtained by applying the matrix transposition to the list of pairs at the training phase of the document classification. This paper analyzed the proposed algorithm in the time complexity and compared it with the conventional kNN. And it compared the proposed algorithm with the conventional kNN by using routers-21578 data experimentally. The experimental results show that the proposed algorithm outperforms kNN about $90{\%}$ in terms of the ex-ecution time.