• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.813-826
• /
• 2022

AI-based image processing technologies in various fields have been widely studied. However, the lighter the board, the more difficult it is to reduce the weight of image processing algorithm due to a lot of computation. In this paper, we propose a method using deep learning for object recognition algorithm in lightweight embedded boards. We can determine the area using a deep neural network architecture algorithm that processes semantic segmentation with a relatively small amount of computation. After masking the area, by using more accurate deep learning algorithm we could operate object detection with improved accuracy for efficient neural network (ENet) and You Only Look Once (YOLO) toward executing object recognition in real time for lightweighted embedded boards. This research is expected to be used for autonomous driving applications, which have to be much lighter and cheaper than the existing approaches used for object recognition.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.1
• /
• pp.1-25
• /
• 2022

This study aims to identify the current situation and core competencies of records managers and archivists through an in-depth interpretation of the perception and its meaning behind their experiences and, based on them, to seek the educational service directions of professional organizations. As a result of qualitative data analysis using interpretive phenomenological research method, this study identified three categories of field needs, core competencies, and educational service directions, as well as 10 super-topics, 30 sub-topics, and 82 semantic units. Based on this, this study has suggested the educational service directions of professional organizations, such as the provision of opportunities to secure external driving forces for work innovation, the provision of learning opportunities for communication and public discussion among institutions, and the provision of new partnerships and practical learning opportunities. This study is meaningful in having derived the main educational service directions that professional organizations should focus on and support by identifying the current situation and core competencies of records managers and archivists.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.74-84
• /
• 2022

Vehicle average speed information which measured at a point or a short section has a problem in that it cannot accurately provide the speed changes on an actual highway. In this study, segment separation method based on vehicle big data for accurate micro-speed estimation is proposed. In this study, to find the point where the speed deviation occurs using location-based individual vehicle big data, time and space mean speed functions were used. Next, points being changed micro-scale speed are classified through gradual segment separation based on geohash. By the comparative evaluation for the results, this study presents that the link-based speed is could not represent accurate speed for micro-scale segments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.110-115
• /
• 2021

With the era of the 4th Industrial Revolution, education on artificial intelligence is one of the important topics. However, since existing education is aimed at knowledge, it is not suitable for developing the active problem-solving ability and AI utilization ability required by artificial intelligence education. To solve this problem, we proposes PBL-based education method in which learners learn in the process of solving the presented problem. The problem presented to the learner is a completed project. This project consists of three types: a classification model, the training data of the classification model, and the block code to be executed according to the classified result. The project works, but each component is designed to perform a low level of operation. In order to solve this problem, the learners can expect to improve their computational thinking skills by finding problems in the project through testing, finding solutions through discussion, and improving to a higher level of operation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.17-32
• /
• 2022

This study explored an approach to estimate a flow-density diagram(FD) on a link in highway traffic environment by utilizing probe vehicles' time headway records. To study empirical flow-density diagram(EFD), the probe vehicles with vision sensors were recruited for collecting driving records for nine months and the vision sensor data pre-processing and GIS-based map matching were implemented. Then, we examined the new EFDs to evaluate validity with reference diagrams which is derived from loop detection traffic data. The probability distributions of time headway and distance headway as well as standard deviation of flow and density were utilized in examination. As a result, it turned out that the main factors for estimation errors are the limited number of probe vehicles and bias of flow status. We finally suggest a method to improve the accuracy of EFD model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.222-234
• /
• 2022

Background: Within the framework of the new Saudi Vision 2030, the education system is keen on developing Early Childhood (EC) curricula to meet the needs of children from diverse cultural and linguistic backgrounds, in addition to preparing teachers to be the main driving forces in this field. To achieve these strategic goals, the professional development of teachers has taken the lead in terms of their continuous professional achievements. Purpose: The recent study tended to explore the promotion of Cultural and Linguistic Competence (CLC) of teachers in preschool institutions in different sectors in the Kingdom of Saudi Arabia (KSA) include public, private and international. Method: In the current study, (n=300) of preschool female teachers, who had experience teaching children from diverse language and cultural backgrounds, participated voluntarily by filling out the exploratory questionnaire. It was designed on a five-point Likert scale. The credibility of the scale and the validity of the questionnaire were ascertained, and the content for which it was designed verified in terms of the purposes of the current investigation. Results: The results revealed that preschool female teachers in the private preschool settings have a higher level of CLC compared to those who were teaching in public and international preschools in KSA. In the private sector, preschool female teachers showed create abilities to provide culturally responsive environments for diverse students, applying various communication styles, and showing proper attitudes and values toward diversity. Implication: The current study provided key implications for policy makers regarding the promotion of CLC for all teachers, particularly preschool in government settings in KSA. It contributed to revealing the cultural awareness of preschool teachers' values and attitudes toward diversity.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.5
• /
• pp.139-146
• /
• 2022

With the recent development of the Internet of Things (IoT) and the convergence of vehicles and IT technologies, high-performance applications such as autonomous driving are emerging, and multi-access edge computing (MEC) has attracted lots of attentions as next-generation technologies. In order to provide service to these computation-intensive tasks in low latency, many methods have been proposed to partition tasks so that they can be performed through cooperation of multiple MEC servers(MECSs). Conventional methods related to task partitioning have proposed methods for partitioning tasks on vehicles as mobile devices and offloading them to multiple MECSs, and methods for offloading them from vehicles to MECSs and then partitioning and migrating them to other MECSs. In this paper, the performance of task partitioning methods using offloading and migration is compared and analyzed in terms of service delay, blocking rate and energy consumption according to the method of selecting partitioning targets and the number of partitioning. As the number of partitioning increases, the performance of the service delay improves, but the performance of the blocking rate and energy consumption decreases.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.10-16
• /
• 2021

This paper proposes a model that considers the parity-time symmetric structure as a state detection circuit for sensor applications using a stretchable inductor. In particular, to obtain a more practical computer simulation result, the stretchable inductor model was applied to this study model by referring to previously reported experimental results. The resistance component and phase component were controlled through the negative differential resistance circuit used in this study. In addition, the imbalance of the circuit caused by a change in the characteristics of the stretchable inductor could be compensated for using a negative differential resistance circuit. In particular, an analysis of the frequency characteristics of the sensor driving circuit of the parity-time symmetric structure proposed in this study confirmed that the Q-factor could be increased up to 20 times compared to the conventional resonant circuit.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.29-37
• /
• 2021

A 7 nm technology node using extreme ultraviolet lithography with a wavelength of 13.5 nm has been recently developed and applied to the semiconductor manufacturing process. Furthermore, the development of sub-3 nm technology nodes continues to be required. In this study, design factors of an electrostatic deflector for an ultra-miniaturized microcolumn system that can realize an electron wavelength of below 1.23 nm with an acceleration voltage of above 1 eV were investigated using a three-dimensional simulator. Particularly, the optimal design of the electrostatic octupole floating deflector was derived by optimizing the design elements and improving the driving method of the 1 keV low energy ultra-miniaturized microcolumn deflector. As a result, the entire wide field of view greater than 330 ㎛ at a working distance of 4 mm was realized with an ultra-high-resolution electron beam spot smaller than 10 nm. The results of this study are expected to be a basis technology for realizing a wafer-scale multi-array microcolumn system, which is expected to innovatively improve the throughput per unit time, which is the biggest drawback of electron beam lithography.