• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.11 no.17
• /
• pp.25-37
• /
• 1988

Joint inventory 방법을 다룬 기존의 연구는 생산비용이 일정하다는 조건만을 고려하였다. 본 논문은 기존의 연구에다 새로운 변수(learning curve ratio and learning retension)를 제조업자 측면에서 고려하여 보다 확장된 모델을 다룬다. Joint inventory 모델은 첫째 단일구매자와 둘째 학습곡선비율과 learning retention의 정도에 있어서 그 범위를 결합시키는데 이용되기 위해 개발되어 졌다. 구매자와 제조업자를 위한 로트 사이즈를 결정하기 위하여 증분비용접근방법 (Incremental Cost Approach, ICA)을 쓴다. 총결합비용은 기존모델보다 현저하게 적은데 그 이유는 학습과 learning retention 효과로 인한 제조업자의 생산비 절감과 재고유지 비용의 감소 때문이다. 학습과 learning retention이 현격한 경우, 총결합비용은 제조업자와 구매자의 개별적인 최적정책에서의 비용합(합)보다 적다. 소개된 모델의 효과를 보이기 위해 수치예제를 이용하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.208-217
• /
• 2021

3D-CNN is one of the deep learning techniques for learning time series data. However, these three-dimensional learning can generate many parameters, requiring high performance or having a significant impact on learning speed. We will use these 3D-CNNs to learn hand gesture and find the parameters that showed the highest accuracy, and then analyze how the accuracy of 3D-CNN varies through input data changes without any structural changes in 3D-CNN. First, choose the interval of the input data. This adjusts the ratio of the stop interval to the gesture interval. Secondly, the corresponding interframe mean value is obtained by measuring and normalizing the similarity of images through interclass 2D cross correlation analysis. This experiment demonstrates that changes in input data affect learning accuracy without structural changes in 3D-CNN. In this paper, we proposed two methods for changing input data. Experimental results show that input data can affect the accuracy of the model.

• 대한공업교육학회지
• /
• v.39 no.2
• /
• pp.1-18
• /
• 2014

This study took existing invention intellectual property related textbooks being utilized in secondary vocational education, analyzed the formation status of 'key learning elements' reflection ratio and drew optimum key learning elements formation ratio by invention intellectual property education content required in secondary vocational education in the future. For this, the study task was set up as 'what kind and how much of invention intellectual property key learning elements are in the invention intellectual property textbook education content now and what is the desirable ratio of each key learning elements in the future'. To resolve this task, 3 specialists analyzed the invention intellectual property education content reflection status and optimum reflection ratio by invention intellectual property education content required in the future is suggested by Delphi survey. The results of this study are as following. First, the result of analysis on invention intellectual property key learning elements included in the invention patent recognition books being utilized in secondary vocational education was that the books included all key learning elements; however, some textbooks have the trend of concentrating in D area (problem-solving activities). Second, the result of analysis on the reflection ratio by invention intellectual property education content area in the invention patent recognition books being utilized in secondary vocational education was that there was the trend in most textbooks that they concentrate in intellectual property creation area; while some textbooks deal with intellectual property protection area and intellectual property utilization area. Regarding by achievement type, knowledge area was main in all textbooks. Meanwhile, function area is dealt in invention patent basic, invention and problem-solving and design textbooks. Attitude area is not dealt or is dealt insufficiently in most textbooks. Third, the optimum reflection ratio of invention intellectual property education key learning elements required in secondary vocational education in the future as obtained by specialists' delphi survey was that it is necessary to decrease D (problem-solving activities) 17.7% area, E(invention fusion knowledge) 2.9% area, K(patent application) 6.9% and L(patent information investigation) area 9.6%. Regarding the optimum reflection ratio of invention intellectual property education content, it is suggested that the invention literacy area 3.1%, intellectual property creation area 4.5% and intellectual property protection area 10.6% would be decreased; while intellectual property utilization area 17.7% would be increased. Regarding optimum reflection ratio of achievement type, it is suggested that knowledge area 52% would be decreased; while function area 32.3% and attitude area 19.6% would be increased.

• 대한공업교육학회지
• /
• v.30 no.2
• /
• pp.23-32
• /
• 2005

The purpose of this study is to investigate and analyze the actual state of teaching and learning methods which are applied to the vocation inquiry section-related subjects of the College Scholastic Ability Test(CSAT) by the teachers who teach specialized subjects of vocational high schools. In order for us to get the background and feature of establishment in the area of vocation inquiry section of the CSAT, previous studies and literature was analyzed and sample survey on the 600 teachers who teach the vocation inquiry section-related subjects was made. The result of this survey is as shown below; First, the teachers who are in charge of vocation inquiry section-related subjects understand that theory and practice is in the ratio 60.76:39.24 and ratio of theory is higher than that of practice. Second, teaching and learning method which is the most relevant to the vocation inquiry section is in the order of lecture(83.9%), experiment & practice(50.4%), computerized learning(41.1%). Third, teaching and learning method which is the most used by the teachers who are in charge of vocation inquiry section-related subjects is in the order of lecture(85.8%), computerized learning(50.1%), experiment and practice(44.4%). Forth, the most desirable teaching and learning method which the teachers who are in charge of vocation inquiry section for this subject believe is in the order of lecture(62.7%) experience & practice(47.7%), computerized learning(44.4%). In light of this result, even though there were not so much difference among the teaching-learning methods which are the most consistent with the contents of the subject in relation to the vocation inquiry section, the most used teaching-learning method by the teachers who teach vocation inquiry section-related subjects and the most desirable teaching-learning method which the teachers who are in charge of vocation inquiry section believe, the most used teaching-learning method by the teachers who are in charge of the vocation inquiry section is lecture. Therefore, it is necessary for us to reinforce the contents in relation to the practice & experiment so that the experience and application can be accumulated and improved through practice which is the specialty of the course of the study in the vocational high school and various teaching and learning method should be developed in consideration of contents of the subject, capability & quality of the learners and status of a classroom.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.822-828
• /
• 2018

Recently, energy issues such as massive blackout due to increase in power consumption have been emerged, and it is necessary to improve the accuracy of prediction of power consumption as a solution for these problems. In this study, we investigate the difference between the actual power consumption and the predicted power consumption through the deep learning- based power consumption forecasting experiment, and the possibility of adjusting the power reserve ratio. In this paper, the prediction of the power consumption based on the deep learning can be used as a basis to reduce the power reserve ratio so as not to excessively produce extra power. The deep learning method used in this paper uses a learning model of long-short-term-memory (LSTM) structure that processes time series data. In the computer simulation, the generated power consumption data was learned, and the power consumption was predicted based on the learned model. We calculate the error between the actual and predicted power consumption amount, resulting in an error rate of 21.37%. Considering the recent power reserve ratio of 45.9%, it is possible to reduce the reserve ratio by 20% when applying the power consumption prediction algorithm proposed in this study.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.733-745
• /
• 2022

In software-defined wireless networking (SDWN), the optimal routing technique is one of the effective solutions to improve its performance. This routing technique is done by many different methods, with the most common using integer linear programming problem (ILP), building optimal routing metrics. These methods often only focus on one routing objective, such as minimizing the packet blocking probability, minimizing end-to-end delay (EED), and maximizing network throughput. It is difficult to consider multiple objectives concurrently in a routing algorithm. In this paper, we investigate the application of machine learning to control routing in the SDWN. An intelligent routing algorithm is then proposed based on the machine learning to improve the network performance. The proposed algorithm can optimize multiple routing objectives. Our idea is to combine supervised learning (SL) and reinforcement learning (RL) methods to discover new routes. The SL is used to predict the performance metrics of the links, including EED quality of transmission (QoT), and packet blocking probability (PBP). The routing is done by the RL method. We use the Q-value in the fundamental equation of the RL to store the PBP, which is used for the aim of route selection. Concurrently, the learning rate coefficient is flexibly changed to determine the constraints of routing during learning. These constraints include QoT and EED. Our performance evaluations based on OMNeT++ have shown that the proposed algorithm has significantly improved the network performance in terms of the QoT, EED, packet delivery ratio, and network throughput compared with other well-known routing algorithms.

• Journal of Gastric Cancer
• /
• v.18 no.2
• /
• pp.182-188
• /
• 2018

Purpose: Despite the fact that there are several reports of single-port laparoscopic distal gastrectomy (SPDG), no analysis of its learning curve has been described in the literature. The aim of this study was to investigate the favorable factors for SPDG and to analyze the learning curve of SPDG. Materials and Methods: A total of 125 cases of SPDG performed from November 2011 to December 2015 were enrolled. All operations were performed by 2 surgeons (surgeon A and surgeon B). The moving average method was used for defining the learning curve. All cases were divided into 10 cases in a sequence, and the mean operative time and estimated blood loss data were extracted from each group. Results: Surgeon A performed 68 cases (female-to-male sex ratio, 91.1%:8.82%), and surgeon B performed 57 cases (female-to-male sex ratio, 61.4%:38.5%). The operative time of surgeon B significantly decreased after 30 cases ($157.8{\pm}38.4$ minutes vs. $118.1{\pm}34.5$ minutes, P=0.003); that of surgeon A did not significantly decrease before and after around 30 cases ($160.8{\pm}51.6$ minutes vs. $173.3{\pm}35.2$ minutes, P=0.6). The subgroup analysis showed that the operative time significantly decreased in the patients with body mass index (BMI) of <$25kg/m^2$ (<$25kg/m^2$:${\geq}25kg/m^2$, $159.3{\pm}41.7$ minutes: $194.25{\pm}81.1$ minutes; P=0.001). Conclusions: Although there was no significant decrease in the operative time for surgeon A, surgeon B reached the learning curve upon conducting 30 cases of SPDG. BMI of <$25kg/m^2$ was found to be a favorable factor for SPDG.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.3
• /
• pp.327-336
• /
• 2022

Due to the COVID-19 pandemic, the ratio of online education in domestic universities has rapidly increased. This research has developed a curriculum that can be blended with online education-especaally for building construction. The realities of building construction education provided by domestic universities during the COVID-19 pandemic were analyzed. It was revealed that approximately 66.1% of the education was provided online, while approximately 33.9% of the education was provided in the form of face-to-face lectures. It was thus found that the ratio of online education had rapidly increased. We developed a blended learning curriculum of building construction subjects. The curriculum focused on weekly education procedures and the contents of education for each 15-week period. The curriculum proposed by this research could be applied flexibly according to the education goals of the instructor and the learning capabilities of the students.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.130-137
• /
• 2013

In this paper, we consider a two-agent scheduling with sequence-dependent exponential learning effects consideration, where two agents A and B have to share a single machine for processing their jobs. The objective function for agent A is to minimize the total completion time of jobs for agent A subject to a given upper bound on the objective function of agent B, representing the makespan of jobs for agent B. By assuming that the learning ratios for all jobs are the same, we suggest an enumeration-based backward allocation scheduling for finding an optimal solution and exemplify it by using a small numerical example. This problem has various applications in production systems as well as in operations management.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.910-917
• /
• 2020

In fire suppression, continuous delivery of water or foam to the fire source is essential. The present study concerns fire suppression in a ship under sea condition, by introducing reinforcement learning technique to aiming of fire extinguishing nozzle, which works in a ship compartment with six degrees of freedom movement by irregular waves. The physical modeling of the water jet and compartment motion was provided using Unity 3D engine. In the reinforcement learning, the change of the nozzle angle during the scenario was set as the action, while the reward is proportional to the ratio of the water particle delivered to the fire source area. The optimal control of nozzle aiming for continuous delivery of water jet could be derived. Various algorithms of reinforcement learning were tested to select the optimal one, the proximal policy optimization.