• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.54-59
• /
• 2006

Decision tree is one of the most effective and widely used methods for building classification model. Researchers from various disciplines such as statistics, machine learning, pattern recognition, and data mining have considered the decision tree method as an effective solution to their field problems. In this paper, an application of decision tree method to classify the faults of induction motors is proposed. The original data from experiment is dealt with feature calculation to get the useful information as attributes. These data are then assigned the classes which are based on our experience before becoming data inputs for decision tree. The total 9 classes are defined. An implementation of decision tree written in Matlab is used for these data.

• East Asian mathematical journal
• /
• v.36 no.4
• /
• pp.455-474
• /
• 2020

In this study, we investigate the latus rectum, one of the geometric measures of the conics, as one of the ways in which learners harmonize the geometric and algebraic approaches to conics from a pedagogical point of view. We also introduce the conical curve of Biot as presented in 'The Discourse on the Latus Rectum in conics(2013)' by Takeshi Sugimoto and reinterpret it for visualization and use as teaching material. Therefore, we expect that the importance of mathematical concepts will be recognized in conics and students can experience geometry learning that is explored in the school field and have a positive effect in developing the power to apply even in the context of applied problems.

• Journal of Biomedical Engineering Research
• /
• v.32 no.4
• /
• pp.289-294
• /
• 2011

Laboratory class is an integral part of biomedical engineering education. Current biomedical engineering curriculum in Korea mostly includes mandatory laboratory classes. Most of the Korean biomedical laboratory classes focus on electrical engineering aspects, while molecular/biological engineering aspects are neglected. Many leading universities in U.S.A. offer a more balanced laboratory class where both electrical engineering aspects and molecular/biological engineering aspects are considered. As a part of an effort to enhance undergraduate biomedical engineering education, a new biomedical engineering laboratory class is proposed to offer a more balanced laboratory learning experience.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.19-33
• /
• 2006

This study explores whether Russian, known to have a process of syllable-final devoicing, reveals differences in vowel duration as a function of the underlying voicing of the coda stop. This paper also examines whether non-native speakers of Russian and English learn typical L2 values in vowel duration. The results indicate that vowels in Russian have a slightly longer mean duration before a voiced stop than before a voiceless stop (a mean difference of 9.52 ms), but in most cases the differences did not exhibit statistical significance. In English the mean difference was 60.05 ms, and the differences were in most cases statistically significant. All native Russian speakers of English produced larger absolute differences in vowel duration for English than for Russian, and all native English speakers of Russian produced smaller absolute differences for Russian than for English. More experienced learners seemed to achieve more native-like values of vowel duration than less experienced learners did, suggesting that learning occurs gradually as the learners gain more experience with the L2.

• Journal of the Korean Institute of Rural Architecture
• /
• v.6 no.3
• /
• pp.96-105
• /
• 2004

The purpose of this study is to investigate and analyze the actual condition and utilization planning of rice mills in Korea. Especially there are 64 rice mills at Goesangun, Chungbuk. I had selected six among them and examined. They are comparatively good, worth preserving, and considered to be the historical and local values. The results of study are as follows; First, rice mills of agricultural villages are utilized as the place of learning that people can experience or the agricultural village museum. Second, it can be connected to the sightseeing resources. Therefore, they are utilized as a green tourism. Third, in order to activate small rice mills, it need a governmental support policy. Fourth, it is necessary of the multilateral plan that can be used as a place of village community.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.594-596
• /
• 2022

Over the last decades, deep neural networks have demonstrated significant success in various tasks. To address the special vision task, choosing a hot network as backbone to extract feature is a common way in both research and industry project. However, the choice of backbone usually requires the expert experience and affects the performance of the classification task. In this work, we propose a novel idea to support backbone decision-making by exploring the feature attribution and weights distribution of hidden layers from various backbones. We first analyze the visualization of feature maps on different size object and different depth layers to observe learning ability. Then, we compared the variance of weights and feature in last three layers. Based on analysis of the feature and wights, we summarize the traits and commonalities of existing networks.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.38-45
• /
• 2011

Studies have shown that infrastructure projects have continued to experience significant delays and cost overrun over an extended period of time and no evidence of learning ever have happened [1] [2]. Various causes contribute to the bias towards overrun [3]. This study contributes to literature by developing and subsequently validating a set of hypothesized relationships between project complexity and project performance. The results show that project complexity is associated with both the magnitude and variance of overrun. Further, the extent and magnitude of the positive bias towards overrun are moderated by project complexity.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.226-238
• /
• 2024

Recently, multi-access edge computing (MEC) has emerged as a promising technology to alleviate the computing burden of vehicular terminals and efficiently facilitate vehicular applications. The vehicle can improve the quality of experience of applications by offloading their tasks to MEC servers. However, channel conditions are time-varying due to channel interference among vehicles, and path loss is time-varying due to the mobility of vehicles. The task arrival of vehicles is also stochastic. Therefore, it is difficult to determine an optimal offloading with resource allocation decision in the dynamic MEC system because offloading is affected by wireless data transmission. In this paper, we study computation offloading with resource allocation in the dynamic MEC system. The objective is to minimize power consumption and maximize throughput while meeting the delay constraints of tasks. Therefore, it allocates resources for local execution and transmission power for offloading. We define the problem as a Markov decision process, and propose an offloading method using deep reinforcement learning named deep deterministic policy gradient. Simulation shows that, compared with existing methods, the proposed method outperforms in terms of throughput and satisfaction of delay constraints.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.54-61
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. By using the FCM, authors have proposed FCM-based fault diagnostic algorithm. However, it can offer multiple interpretations for a single fault. In process engineering, as experience accumulated, some form of quantitative process knowledge is available. If this information can be integrated into the FCM-based fault diagnosis, the diagnostic resolution can be further improved. The purpose of this paper is to propose an enhanced FCM-based fault diagnostic scheme. Firstly, the membership function of fuzzy set theory is used to integrate quantitative knowledge into the FCM-based diagnostic scheme. Secondly, modified TAM recall procedure is proposed. Considering that the integration of quantitative knowledge into FCM-based diagnosis requires a great deal of engineering efforts, thirdly, an automated procedure for fusing the quantitative knowledge into FCM-based diagnosis is proposed by utilizing self-learning feature of neural network. Finally, the proposed diagnostic scheme has been tested by simulation on the two-tank system.

• The Korean Journal of Community Living Science
• /
• v.27 no.1
• /
• pp.67-81
• /
• 2016

Responsible tourism has become an established area of the tourism industry. This study aims to identify the factors that influence re-participation in responsible tourism in rural Korea. On-site survey was conducted on 436 tourists by seven responsible tourism agencies in Korea. The motivation for responsible tourists was categorized into seven types: family togetherness, escape and relaxation, personal growth, social interaction, various experiences, learning, and natural experience. The estimation of a binary logistic regression model determined the characteristics of responsible tourists who are most likely to opt for re-participation in responsible tourism. Results indicated that important factors for re-participation in responsible tourism were 'age', 'educational level', 'accompany', 'length of stay', and 'motivation'. The results implied that tourists' internal and external factors are important for re-participation in responsible tourism. It is expected that this study will contribute to the market expansion of responsible tourism.