• ETRI Journal
• /
• v.45 no.1
• /
• pp.75-92
• /
• 2023

Level 3 autonomous vehicles require conditional autonomous driving in which autonomous and manual driving are alternately performed; whether the driver can resume manual driving within a limited time should be examined. This study investigates whether the demographics and subjective driving tendencies of drivers affect the take-over performance. We measured and analyzed the reengagement and stabilization time after a take-over request from the autonomous driving system to manual driving using a vehicle simulator that supports the driver's take-over mechanism. We discovered that the driver's reengagement and stabilization time correlated with the speeding and wild driving tendency as well as driving workload questionnaires. To verify the efficiency of subjective questionnaire information, we tested whether the driver with slow or fast reengagement and stabilization time can be detected based on machine learning techniques and obtained results. We expect to apply these results to training programs for autonomous vehicles' users and personalized human-vehicle interfaces for future autonomous vehicles.

• Journal of Sensor Science and Technology
• /
• v.31 no.2
• /
• pp.96-101
• /
• 2022

As the elderly population gradually increases, the risk of fatal fall accidents among the elderly is increasing. One way to cope with a fall accident is to determine the fall direction before impact using a wearable inertial measurement unit (IMU). In this context, a previous study proposed a method of classifying fall directions using a support vector machine with sensor velocity, acceleration, and tilt angle as input parameters. However, in this method, the IMU signals are processed through several processes, including a Kalman filter and the integration of acceleration, which involves a large amount of computation and error factors. Therefore, this paper proposes a machine learning-based method that classifies the fall direction before impact using IMU raw signals rather than processed data. In this study, we investigated the effects of the following two factors on the classification performance: (1) the usage of processed/raw signals and (2) the selection of machine learning techniques. First, as a result of comparing the processed/raw signals, the difference in sensitivities between the two methods was within 5%, indicating an equivalent level of classification performance. Second, as a result of comparing six machine learning techniques, K-nearest neighbor and naive Bayes exhibited excellent performance with a sensitivity of 86.0% and 84.1%, respectively.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.131-140
• /
• 2024

The outbreak of Covid-19 has forced teachers of special education in Saudi Arabia to keep to themselves to live in a technology-infused society throughout the virtual teaching and learning process. This study set out to explore the competence, self-efficacy, and autonomy in using information communication technology (ICT) of special education teachers in Saudi Arabia. A total of 244 special education teachers in Saudi Arabia participated in this study. This study adopted the New General Self-Efficacy Scale developed and validated by Chen, Gully, and Eden (2001), as well as the Basic Psychological Needs in Exercise Scale (BPNES) developed and validated by Vlachopoulos and Michailidou (2006). Confirmatory factor analysis (CFA) and multivariate analysis of variance (MANOVA) were used as the main data analysis in this study. The findings showed that special education teachers in Saudi Arabia possessed competence, self-efficacy, and autonomy in using ICT in their teaching and learning process. All the factor loadings in each factor were.75 or higher, indicating good factor loadings. The results of the MANOVA indicated that special education teachers in Saudi Arabia do not report different perceptions of their competence, self-efficacy, and autonomy despite their different gender, age group, academic background, and teaching experiences.

• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.34-40
• /
• 2018

Currently, artificial neural networks perform well for a single task, but NN have the problem of forgetting previous learning by learning other kinds of tasks. This is called catastrophic forgetting. To use of artificial neural networks in general purpose this should be solved. There are many efforts to overcome catastrophic forgetting. However, even though there was a lot of effort, it did not completely overcome the catastrophic forgetting. In this paper, we propose sequential iterative learning using core concepts used in elastic weight consolidation (EWC). The experiment was performed to reproduce catastrophic forgetting phenomenon using EMNIST data set which extended MNIST, which is widely used for artificial neural network learning, and overcome it through sequential iterative learning.

• Journal of The Korean Association of Information Education
• /
• v.12 no.2
• /
• pp.223-234
• /
• 2008

Educating qualified elementary school teachers depends on excellent pre-service education. The high quality of education is accomplished by various interactions between teachers and learners, as well as active participation by students. In the present study, online problem-based learning and an e-portfolio were used to examine the effect on the computer-curriculum education to reflect social and individual needs, and to enhance the quality of instruction at universities. Students (n=105) participated in six different problem-based learning sessions. At the same time, they developed Blog e-portfolios as individual and group products, and wrote reflective journals that focused on their learning processes and results. A qualitative analysis method was employed to analyze the reflective journals. The results of the analyses showed the following: 1) Increasing the understanding of the computer-curriculum education, 2) enhancing students' competence in using ICT potentially, 3) cultivating student-centered teaching and learning strategies on ICT, and 4) enhancing competence of future teaching activities through experiencing e-portfolio as a performance-assessment tool.

• Smart Structures and Systems
• /
• v.29 no.2
• /
• pp.375-387
• /
• 2022

One of the latest teaching strategies is smart classroom teaching. Teaching is carried out with the assistance of smart teaching technologies to improve teacher-student contact, increase students' learning autonomy, and give fresh ideas for the fulfillment of students' deep learning. Computer-based technology has improved students' language learning and significantly motivating them to continue learning while also stimulating their creativity and enthusiasm. However, the difficulties and barriers that many EFL instructors are faced on seeking to integrate information and communication technology (ICT) into their instruction have raised discussions and concerns regarding ICT's real worth in the language classroom. This is a case study that includes observations in the classroom, field notes, interviews, and written materials. In EFL classrooms, both computer-based and non-computer-based activities were recorded and analyzed. The main instrument in this study was a survey questionnaire comprising 43 items, which was used to examine the efficiency of ICT integration in teaching and learning in public schools in Kuala Lumpur. A total of 101 questionnaires were delivered, while each responder being requested to read the statements provided. The total number of respondents for this study was 101 teachers from Kuala Lumpur's public secondary schools. The questionnaire was randomly distributed to respondents with a teaching background. This study indicated the accuracy of utilizing Teaching-Learning-Based Optimization (TLBO) in analyzing the survey results and potential for students to learn English as a foreign language using computers. Also, the usage of foreign language may be improved if real computer-based activities are introduced into the lesson.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.588-596
• /
• 2019

The purpose of this study is to propose an ICT-oriented teacher curriculum in order to improve early childhood teacher's competency using ICT instructional media. To this end, a survey was conducted to investigate the importance and current level of early childhood teacher's competency. After identifying the necessity of ICT instructional media competency, the contents of an ICT-oriented teacher curriculum were designed. A survey of teacher competency among 207 teachers showed the highest educational need for ICT instructional media competency. In addition, ICT-based teacher curriculum was classified into ICT literacy education and ICT utilization education based on the analysis results of sub-indexes on ICT instructional media competency. Each part was hierarchized into three levels of awareness, application, and spread according to the teacher's competency level and the educational contents were suggested based on the goals set for each level. In this study, it consisted of ICT literacy education, including understanding educational policy related to ICT utilization, understanding the goals and assessment of the ICT curriculum and ICT utilization education, including the use of teaching and learning methods, application of digital technology, ICT learning environment building and management for developing teacher professionalism related to ICT instructional media.

• Journal of Platform Technology
• /
• v.10 no.3
• /
• pp.51-59
• /
• 2022

Machine learning, which has recently innovatively developed, has become an important technology that can solve various optimization problems. In this paper, we introduce the latest research papers that solve the problem of channel sharing in heterogeneous networks using machine learning, analyze the characteristics of mainstream approaches, and present a guide to future research directions. Existing studies have generally adopted Q-learning since it supports fast learning both on online and offline environment. On the contrary, conventional studies have either not considered various coexistence scenarios or lacked consideration for the location of machine learning controllers that can have a significant impact on network performance. One of the powerful ways to overcome these disadvantages is to selectively use a machine learning algorithm according to changes in network environment based on the logical network architecture for machine learning proposed by ITU.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.1
• /
• pp.31-46
• /
• 2023

This study classified and confirmed the learning modes about start-ups that are based on the accelerator's program which was focusing on the Korean accelerators in the ICT field targeting global market. Eight accelerator practitioners were interviewed who were in charge of operating programs for accelerators, qualitatively analyzing method of the interview was conducted. The interview results to identify various learning modes that accelerators provide to startups through programs. In order to identify and classify learning modes, the researcher reviewed various prior documents and using categories of experience accumulation, observation, experimentation, trial and error, and improvisation as a priori code for the qualitative analysis. The interview results were analyzed through a subject analysis. As the result of the study, the learning modes offered by the accelerator's programs to startups were confirmed, with two subcategories identified for each of the five categories: experiential, learning from others, experimental, trial and error, and improvisation. Given the limited research on accelerator programs and their main function, the main function of accelerators, this study identified the types of learning modes that offered by the accelerator's programs to startups from the perspective of learning. This study provides important insights into the types of learning modes that offered by the accelerator programs, which can help to improve our understanding of how accelerators support organizational learning for startups. Additionally, this information can be useful for startups considering in participating in the accelerator programs, as it can help them making informed decisions about their involvement.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.4
• /
• pp.355-361
• /
• 2018

Recently, there are efforts to improve my learning ability by using various learning tools based on ICT technology. The application such as games is used in conjunction with lecture class to induce interest in the class and to enhance the learning effect by using smartphone app as learning tool. In addition, we are trying to improve creative thinking ability, problem solving ability and logical thinking ability through early coding education. In this paper, we describe the learning and quiz app using the app inventor and conducted the related questionnaire. We developed a learning philosophy for preliminary early childhood teachers using the developed apps and taught them how to utilize them in early childhood education by explaining the apps and using the app inventor. Through questionnaires, we confirmed the learning effect and the willingness to use in early childhood education. Through this study, I hope to improve the ability of early childhood teacher learning and to utilize the coding in early childhood education with the app developed as the app inventor.