• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2024

Recently, mobile manipulators have been utilized in agriculture industry for weed removal and harvest automation. This paper proposes a domain adaptive fruit detection method for harvest automation, by utilizing OWL-ViT model which is an open-vocabulary object detection model. The vision-language model can detect objects based on text prompt, and therefore, it can be extended to detect objects of undefined categories. In the development of deep learning models for real-world problems, constructing a large-scale labeled dataset is a time-consuming task and heavily relies on human effort. To reduce the labor-intensive workload, we utilized a large-scale public dataset as a source domain data and employed a domain adaptation method. Adversarial learning was conducted between a domain discriminator and feature extractor to reduce the gap between the distribution of feature vectors from the source domain and our target domain data. We collected a target domain dataset in a real-like environment and conducted experiments to demonstrate the effectiveness of the proposed method. In experiments, the domain adaptation method improved the AP50 metric from 38.88% to 78.59% for detecting objects within the range of 2m, and we achieved 81.7% of manipulation success rate.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.143-148
• /
• 2024

Traffic congestion has caused issues in various forms such as the environment and economy. Recently, an intelligent transport system (ITS) using artificial intelligence (AI) has been focused so as to alleviate the traffic congestion problem. In this paper, we propose a reinforcement learning-based traffic signal control algorithm that can smooth the flow of traffic while reducing discomfort levels of drivers and pedestrians. By applying the proposed algorithm, it was confirmed that the discomfort levels of drivers and pedestrians can be significantly reduced compared to the existing fixed signal control system, and that the performance gap increases as the number of roads at the intersection increases.

• Earthquakes and Structures
• /
• v.17 no.1
• /
• pp.17-29
• /
• 2019

The present study aims to present a comprehensive understanding of the performance of neighboring multi-story buildings with different dynamic characteristics under blast loads. Two different scenarios are simulated in terms of explosion locations with respect to both buildings. To investigate the effect of interaction between the neighboring buildings in terms of the induced responses, the separation gap is set to be sufficiently small to ensure collisions between stories. An adequately large separation gap is set between the buildings to explore responses without collisions under the applied blast loads. Several blast loads with different peak pressure intensities are employed to perform the dynamic analysis. The finite-element toolbox Computer Aided Learning of the Finite-Element Method (CALFEM) is used to develop a MATLAB code to perform the simulation analysis. The dynamic responses obtained in the scenarios considered herein are presented comparatively. It is found that the obtained stories' responses are governed mainly by the location and intensity of the applied blast loads, separation distances, and flexibility of the attacked structures. Moreover, explosions near a light and flexible building may lead to a significant decrease in blast resistance because explosions severely influence the dynamic responses of the building's stories.

• Journal of The Korean Association of Information Education
• /
• v.21 no.5
• /
• pp.497-507
• /
• 2017

Research on software education and linking and convergence of other subjects has been mainly focused on mathematics and science subjects. The dissatisfaction of various preferences and types of learning personality cause to learning gap. In addition, it is not desirable considering the solution of various fusion problems that can apply the computational thinking. In this way, it is possible to embrace the diverse tendencies and preferences of students through the linkage with the English subject, which is a linguistic approach that deviates from the existing mathematical and scientific approach. By combining similarities in the process of learning a new language of English education and software education. For this purpose, based on the analysis of teaching - learning model of elementary English subject and software education, we developed a class model by modifying existing English subject and software teaching - learning model to be suitable for linkage. Then, the learning elements applicable to software education were extracted from the contents of elementary school English curriculum, and a program applied to the developed classroom model was designed and the practical application method of learning was searched.

• The Korean Journal of Emergency Medical Services
• /
• v.15 no.2
• /
• pp.43-54
• /
• 2011

Purpose: The purpose of this study was to explore EMT-paramedic students' experience of simulation education and analyze the confidence before and after education, learning attitude and course evaluation. Method: Research survey was conducted on 38 EMT-paramedic students during November, 2011 and EMT-paramedic students' experience of simulation education was analyzed after applying head, spinal, and chest injury scenario. The confidence before and after education, learning attitude and course evaluation in gender were analyzed by Mann-Whitny U test and the difference of confidence before and after education was analyzed by Wilcoxon signed rank test and learning attitude & course evaluation were analyzed by evaluating frequency, percentage, mean, standard deviation by using SPSS WIN 17.0 program. Results: 1. Students experienced various advantages such as increasing interest and self-reflection on learning, critical thinking ability, and EMT-paramedic-role experience and recognition of importance of teamwork. Students also pointed out disadvantages such as gap between real situation and simulation, limit of time and equipments, and burden of demonstration. 2. The confidence between before and after education, learning attitude and course evaluation in gender were not significant different statistically. 3. Confidence mean score elevated from 5.53(before education) to 5.87(after education), but the difference in their confidence did not show significant difference statistically. 4. Total mean score in learning attitude after simulation education was 3.70 out of 5.00, which is considerably very high. 5. Total mean score in course evaluation was 3.89 with score of 3.83 in evaluation in learning environment and 3.99 in evaluation of debriefing. Conclusion: The finding of this study demonstrate that the simulation education can provide a safe and repetitive practice environment, improve problem-solving ability and critical thinking, and increase the confidence in prehospital emergency care; therefore, simulation may be the new effective EMT-paramedic education strategy.

• Smart Media Journal
• /
• v.8 no.1
• /
• pp.67-73
• /
• 2019

This study investigates Active Learning and Facilitation Convergence Education Program which can improve core competency to cope with vocational education in the fourth industrial revolution era. I applied the integrated advantages of Active Learning which enhances 'problem solving skill' and those of Facilitation for creative thinking idea to application design process coursework and verified the effectiveness of such education method through student satisfaction survey. I also designed application contents for the students who are familiar with the mobile environments and UI contents for data visualization which can help those students to improve their skills in software. Every coursework was conducted as a team project. As a result, Active Learning and Facilitation Convergence Education Program is found to be helpful in improving the basic skills and competencies required in college education. I hope this work helps to reduce the educational gap between industry and professional colleges.

• Journal of Engineering Education Research
• /
• v.25 no.1
• /
• pp.3-11
• /
• 2022

The purpose of this study is to empirically analyze the learning experiences of high school mathematics and science subjects of new students in science and engineering, and to provide basic data and respond to strengthen basic knowledge of science and engineering students in the future. The subjects of the survey were 481 freshmen in science and engineering at S University. First, as a result of analyzing the learning experiences of freshmen, the geometric subjects were significantly lower, which is the result of students' sensitive responses to transitional changes in the curriculum and SAT system after revision. In science, general elective subjects were higher than career elective subjects, and there was a deviation between science subjects, which is a result of reflecting the diversity and hierarchy of science subjects. Next, as a result of analyzing the difference in learning experience after revision compared to before the revision of the curriculum, the learning experience of Mathematics II increased significantly and the geometry decreased significantly. Both Chemistry I and II increased significantly compared to before the revision, and Earth Science I decreased significantly. This can be seen as a result of strategic choices based on obtaining grades in the CSAT and disadvantages in college entrance exams. As a result of the study, students' sensitive reactions to changes in the high school education environment were confirmed, basic mathematics and science-related courses were opened to alleviate variations in the academic ability due to elective courses, and countermeasures tailored to each university's situation.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.4
• /
• pp.415-435
• /
• 2007

A transition from elementary to secondary school, and among grades, among learning contents is a essential problem in education. A connectivity between learning contents is important in student's growth and development. A gap between lower grades and higher grades in elementary school is no less extensive than a gap between elementary mathematics and secondary mathematics. In this paper, we start with a critical mind about a transition and connectivity between lower grades and higher grades in elementary school. In order to compare between elementary grades, we firstly focus 4th grade mathematics which finish lower grades and start higher grades at the same time. First, we make up a questionnaire to 4th grade students and teachers in charge 4th grade. A questionnaire is composed of questions about the degree of difficulty in the learning(and teaching) of 4th grade mathematics comparing with 3rd grade mathematics. Second, we compare to lower grades lessons(1st grade) and 4th grade lessons using a qualitative method. we analyze the lesson contents, activities and time through 'analysis of the learning course'. And we compare the pattern of eliciting questions, question patterns, nomination patterns and feedback patterns between 1st grade and 4th grade lessons. We hope that this paper is a fundamental sources in investigating a connectivity between lower grades and higher grades in elementary mathematics in the future.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.3
• /
• pp.284-288
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.347-350
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.