• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.668-673
• /
• 2021

As the fourth industrial revolution begins in earnest, related technologies are becoming a hot topic. Hardware development is accelerating to make the most of technologies such as high-speed wireless communication, and related companies are growing rapidly. Artificial intelligence often uses desktops in general for related research, but it is mainly used for the learning process of deep learning and often transplants the generated models into devices to be used by including them in programs, etc. However, it is difficult to produce results for devices that do not have sufficient power or performance due to excessive learning or lack of power due to the use of models built to the desktop's performance. In this paper, we analyze efficiency using boards with several Neural Process Units on sale before developing the performance of deep learning to match embedded boards, and deep learning accelerators that can increase deep learning performance with USB, and present a simple development direction possible using embedded boards.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4268-4289
• /
• 2020

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

• Journal of Information Technology Applications and Management
• /
• v.9 no.2
• /
• pp.17-32
• /
• 2002

Even though the distance education via web has a great advantage to overcome time and space, its problem is that the management of trainees is not efficient compared with classroom and group education. This problem is a great obstacle to the objects and achievement standards of distance education, giving controversial arguments to the advocators of distance education. Distance educators need to monitor the trainees'participation and responses continuously and offer appropriate feedback to the trainees. However, the existing distance education system only focuses on teaching and learning activities, and as a result, the efficient management function of distance education is not available. Accordingly, the study attempts to find out the appropriate managing elements of distance teacher training in order to effectively achieve the goals of teacher training and the efficient management of distance education. Also, it proposes distance teacher training management system that offers appropriate feedback to trainees, applying the derived elements of distance teacher training to the training processes. To verify the efficiency of the system, hypotheses on related items of distance teacher education and learning types are suggested, and the achievement degree of learning and its relations are investigated through questionnaire of learning types. In addition, a system using UML which is the standard of object-oriented modeling language is devised, so. that mutual management, language independence and convenient development environment as well as reusability can be offered, and so the design standardization and efficient system realization could be achieved, while flexible change of system according to education process and computing environment is possible.

• Steel and Composite Structures
• /
• v.37 no.2
• /
• pp.193-209
• /
• 2020

In this paper, the efficiency of five Machine Learning (ML) methods consisting of Deep Learning (DL), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Gradient Tree Booting (GTB) for regression and classification of the Ultimate Load Factor (ULF) of nonlinear inelastic steel frames is compared. For this purpose, a two-story, a six-story, and a twenty-story space frame are considered. An advanced nonlinear inelastic analysis is carried out for the steel frames to generate datasets for the training of the considered ML methods. In each dataset, the input variables are the geometric features of W-sections and the output variable is the ULF of the frame. The comparison between the five ML methods is made in terms of the mean-squared-error (MSE) for the regression models and the accuracy for the classification models, respectively. Moreover, the ULF distribution curve is calculated for each frame and the strength failure probability is estimated. It is found that the GTB method has the best efficiency in both regression and classification of ULF regardless of the number of training samples and the space frames considered.

• Journal of Fisheries and Marine Sciences Education
• /
• v.11 no.1
• /
• pp.43-58
• /
• 1999

To instruct in accordance with learner's trait & preceding knowledge, letting the learner control the learning activities is the important task of educator & major goal of the Education Department this year. This article intends to provide useful Instructional Model for the teachers in fisheries marine high school, when they design the individualized teaching model using motivation. One of the major reason for the fisheries marine high school students' low learning achievement is due to the neglecting motivation elements in teaching - learning processes. Recently, with assistance of the information communication technology development, various teaching methods such as Individualized Multimedia Mediated Instruction, Internet Instruction, have come to the major method in activating motivation and computer-mediated instruction considering the learner's individual difference is the useful tools for the instructional efficiency. Because current navigation text book of fisheries marine high school have special characteristic considering the spacial context & time series from departing port to entering port, Teachers can maximize learner's learning accomplishment by using individualized multimedia & providing similar situation like a real navigation(simulating), representing this text characteristics. Thus this paper searches for the specifications of Keller's Motivation Model & Sweeter's Tutorial Model to solve instructional efficiency problems in fisheries marine high school & developed an efficient instructional design by integrating two models.

• Journal of Radiation Protection and Research
• /
• v.48 no.1
• /
• pp.20-27
• /
• 2023

Background: As the number of nuclear facilities nearing their pre-determined design life increases, demand is increasing for technology and infrastructure related to the decommissioning and decontamination (D&D) process. It is necessary to consider the nature of the dismantling environment constantly changing and the worker doing new tasks. A method was studied that can calculate the effect of learning and the change in work time on the work process, according to the learning-forgetting curve model (LFCM). Materials and Methods: The LFCM was analyzed, and input values and scenarios were analyzed for substitution into the D&D process of a nuclear facility. Results and Discussion: The effectiveness and efficiency of the training were analyzed. It was calculated that skilled workers can receive a 16.9% less collective radiation dose than workers with only basic training. Conclusion: Using these research methods and models, it was possible to calculate the change in the efficiency of workers performing new tasks in the D&D process and the corresponding reduction in the work time and collective dose.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.426-432
• /
• 2022

HVAC systems play a critical role in reducing energy consumption in buildings. Integrating occupants' thermal comfort evaluation into HVAC control strategies is believed to reduce building energy consumption while minimizing their thermal discomfort. Advanced technologies, such as visual sensors and deep learning, enable the recognition of occupants' discomfort-related actions, thus making it possible to estimate their thermal discomfort. Unfortunately, it remains unclear how accurate a deep learning-based classifier is to recognize occupants' discomfort-related actions in a working environment. Therefore, this research evaluates the classification performance of occupants' discomfort-related actions while sitting at a computer desk. To achieve this objective, this study collected RGB video data on nine college students' cold discomfort-related actions and then trained a deep learning-based classifier using the collected data. The classification results are threefold. First, the trained classifier has an average accuracy of 93.9% for classifying six cold discomfort-related actions. Second, each discomfort-related action is recognized with more than 85% accuracy. Third, classification errors are mostly observed among similar discomfort-related actions. These results indicate that using human action data will enable facility managers to estimate occupants' thermal discomfort and, in turn, adjust the operational settings of HVAC systems to improve the energy efficiency of buildings in conjunction with their thermal comfort levels.

• Structural Engineering and Mechanics
• /
• v.47 no.4
• /
• pp.495-511
• /
• 2013

In this paper, a new efficient optimization algorithm called Teaching-Learning-Based Optimization (TLBO) is used for the least weight design of trusses with continuous design variables. The TLBO algorithm is based on the effect of the influence of a teacher on the output of learners in a class. Several truss structures are analyzed to show the efficiency of the TLBO algorithm and the results are compared with those reported in the literature. It is concluded that the TLBO algorithm presented in this study can be effectively used in the weight minimization of truss structures.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.259-260
• /
• 2013

본 논문에서는 1년 과정의 컴퓨터 프로그래밍 수업에 참여한 상위 수준 학습자들을 대상으로 맞춤형 학습을 위한 다양한 학습공동체를 운영하였을때 어떤 유형이 상위 학습자들에게 효과적인지를 분석하였다. 분석 결과, 동일한 상위 학습자가 튜터로 참여했을 때와 그렇지 않았을 때 성적 변화가 눈에 띄게 나타났으며 이것은 가르치는 활동이 본인의 학습 이해도를 높이는데 얼마나 영향을 미치는지를 보여주고 있다.

• Journal of Engineering Education Research
• /
• v.10 no.3
• /
• pp.79-92
• /
• 2007

To enhance the excellence, effectiveness and economical efficiency in the learning process, we implement a hybrid educational system for engineering experiments where web-based virtual laboratory systems and distance education systems are properly integrated. In the first stage, we designed client/server distributed environment and developed web-based virtual laboratory systems for digital systems and electrical/electronic circuit experiments. The proposed virtual laboratory systems are composed of four important sessions and their management system: concept learning session, virtual experiment session, assessment session. With the aid of the management system every session is organically tied up together to achieve maximum learning efficiency. In the second stage, we have implemented efficient and cost-effective distant laboratory systems for practicing electric/electronic circuits, which can be used to eliminate the lack of reality occurred during virtual laboratory session. The use of simple and user-friendly design allows a large number of people to access our distant laboratory systems easily. Thus, self-guided advanced training is available even if a lot of expensive equipment will not be provided in the on-campus laboratories. The proposed virtual/distant laboratory systems can be used in stand-alone fashion, but to enhance learning efficiency we integrated them and developed a hybrid educational system for engineering experiments. Our hybrid education system provides the learners with interactive learning environment and a new approach for the delivery of engineering experiments.