• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Journal of Fisheries and Marine Sciences Education
• /
• v.29 no.3
• /
• pp.767-777
• /
• 2017

The purpose of this paper is to develope a training model and to make a syllabus for electro-technical officers(ETOs) on ship. In order to complete the purpose, firstly we study on qualification for electro-technical officers and also examine the foreign, domestic cases. Secondly, through the STCW convention and the IMO Model Course 7.08, we have compared the standards of competence for officers in charge of an engineering watch and ETO, and analyze the additional standards of competence to acquire the ETO's licenses. Finally, based on the results of this, we will suggest the development of a training model that officers in charge of an engineering watch must complete in order to obtain an ETO's license. This paper is expected to be useful in the educational institution preparing for training course.

• Journal of Korean Elementary Science Education
• /
• v.29 no.4
• /
• pp.515-525
• /
• 2010

The purpose of this study was to analyze of how the elementary school teachers lead their classes of a science laboratory instruction and an engineering laboratory instruction in a science subject class. For this study, science laboratory and engineering laboratory lessons were selected and for each science and engineering laboratory lesson, five elementary school teachers were video-recorded of their lessons. The science and engineering laboratory lessons were analyzed by utilizing processes of the science model and the engineering model based on Schauble et al. (1991). The results of these studies are as follows: In science laboratory instruction, some participants didn't distinguish the difference between the science laboratory goal and the engineering laboratory goal. All of participants used search and end strategy of engineering laboratory for science laboratory lesson. In engineering laboratory instruction, all of participants guided to students engineering laboratory goal and used inferences and search strategy of engineering laboratory. However they didn't use the trial and error strategy or redesign which can be an essential element in engineering and design process. Educational implications are discussed.

• Journal of Practical Engineering Education
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2015

Learners acquire knowledge through many years of majors and educated classes. They convergence of engineering problem solving that combine a variety of subjects are difficult. In this paper, we suggest practical engineering problem solving model combined major educational courses for example optimization problem of heat sink temperature reduction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.543-547
• /
• 2012

The environmental education is more and more important according to increasing environmental problems, but university students don't receive it actively. Actually, environmental education in university is conducted and focused on environmental engineering. In order to have an effect on environmental education for all engineering college students, the course of environmental education consists of various fields of engineering study including environmental engineering. The environmental education categories for engineering college students are determined by using an AHP technique in this study. After educating engineering college students with the developed environmental education course, we evaluated the environmental education performance using the survey on perception level and purchasing data of environmentally consciously products by statistical and RFM analysis.

• Journal of Engineering Education Research
• /
• v.14 no.4
• /
• pp.39-47
• /
• 2011

This paper deals with nanoethics as a sort of extension of engineering ethics utilizing various books, articles, and reports concerning historical, social, and ethical aspects of nanotechnology. After a brief examination on the place and development process of nanotechnology, ethical issues on nanotechnology are analysed including safety problem, impact on environment, violating privacy, social inequity, military use, and human enhancement. The basic principles on nanoethics are proposed such as promotion of public understanding, construction of participatory governance, contribution to sustainable development, commitment to precautionary principle, and compliance with research integrity. Lastly, integrated method in nanoethics education is illustrated putting lecture model, investigation model and discussion model together. This paper can provide the contents available for nanoethics education, and make a basis for the sound development of nanotechnology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.771-788
• /
• 2020

Detection of abandoned objects for smart video surveillance should be robust and accurate in various situations with low computational costs. This paper presents a new algorithm for abandoned object detection based on the dual background model. Through the template registration of a candidate stationary object and presence authentication methods presented in this paper, we can handle some complex cases such as occlusions, illumination changes, long-term abandonment, and owner's re-attendance as well as general detection of abandoned objects. The proposed algorithm also analyzes video frames at specific intervals rather than consecutive video frames to reduce the computational overhead. For performance evaluation, we experimented with the algorithm using the well-known PETS2006, ABODA datasets, and our video dataset in a live streaming environment, which shows that the proposed algorithm works well in various situations.

• Journal of Engineering Education Research
• /
• v.11 no.3
• /
• pp.54-62
• /
• 2008

This paper presents the process of developing, applying and increasingly updating curriculums to reinforce education in IT field through cooperation of industry and academy by the invention of government. In particular, the curriculums are developed and refined in order to satisfy both industry as users and academy as suppliers, using a spiral model, which was originally proposed for software development by Boehm. The result and the assessment are described where the developed curriculums have been applied at the universities in a national-wide base through a project by government. The basic principles of this model are general enough to be applied to curriculum development in various areas of college education.

• Journal of Engineering Education Research
• /
• v.25 no.2
• /
• pp.3-12
• /
• 2022

The purpose of this study was to investigate the perceptions and educational needs of the university faculties in charge of capstone design courses. To achieve the purpose of this study, the 100 questionnaires collected from the faculties nationwide with teaching experience in capstone design courses were analyzed using descriptive statistics analysis, the Borich needs assessment model, and the Locus for focus model. The faculties perceived the importance of their roles in the following order: coaching students, providing opportunities for students to show their abilities, motivating and encouraging, and building trusting relationships with students. The biggest challenges that the faculties perceived in capstone design classes were the lack of university-industry collaboration and project execution time. In the analysis of the needs for the capstone design process, the research results showed that team-building, core task development and analysis, deriving problem-solving ideas, building prototypes, and comprehensive reflection ranked the top priorities. This study is expected to help the design of the courses and the development of customized faculty support programs by analyzing the faculties' perceptions and needs for capstone design classes.

• Journal of Practical Engineering Education
• /
• v.16 no.3_spc
• /
• pp.297-308
• /
• 2024

This study explored the application of the NFT-based Learn-and-Earn model in metaverse vocational education and training. Through expert interviews, Delphi analysis, and AHP analysis, the study evaluated considerations and importance of L&E model operation, NFT technology application, course history and certification management, teaching media copyright management, and platform-related issues. Based on the results, the study suggested the need for performance measurement, infrastructure establishment, institutional arrangement, and ethical issue response when utilizing the L&E model.