• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.242-263
• /
• 2021

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.5
• /
• pp.349-357
• /
• 2022

Since the flight control computer of unmanned aerial vehicle (UAV) is a flight critical equipment, it is necessary to ensure reliability and safety from the development step, and a redundancy-based fault management design is required in order to operate normally even a failure occurs. To reduce cost, weight and power consumption, the dual-redundant flight control system design is considered in UAV. However, there are various restrictions on the fault management design. In this paper, we propose the fault detection and isolation designs for the dual-redundant flight control computer to satisfy the safety requirements of an UAV. In addition, the flight control computer developed by applying the fault management design performed functional tests in the integrated test environment, and after performing FMET in the HILS, its reliability was verified through flight tests.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.762-765
• /
• 2021

In this paper, an automotive ECU (electronic control unit) with Kalman filter accelerator is designed and implemented. RISC-V is exploited as a processor core. Accelerator for Kalman filter matrix operation, CAN (controller area network) controller for in-vehicle network, and LIN (local interconnect network) controller are designed and embedded. Kalman filter operation consists of time update process and measurement update process. Current state variable and its error covariance are estimated in time update process. Final values are corrected from input measurement data and Kalman gain in measurement update process. Usually floating-point multiplication is exploited in software implementation, but fixed-point multiplier considering accuracy analysis is exploited in this paper to reduce hardware area. In 28nm silicon fabrication, its operating frequency, area, and gate counts are 100MHz, 0.37mm², and 760k gates, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.283-290
• /
• 2022

Blockchain is a technology that secures integrity and transparency by distributing and storing transaction details within multiple node networks. Recently, research is being conducted to secure integrity by applying blockchain to Bill of Lading (B/L documents) of monetary value. In this paper, we study a blockchain-based bill of lading system to improve usability. The shippers register the issued bill of lading on the blockchain, and banks in each country read it to conduct L/C transactions. The consignees receive the goods after completing certification with a quick response code (QR) containing the bill of lading information. Through this, shippers enjoy merits in that they can shorten the time and cost of sending shipping documents by mail and prove the integrity of the documents. The consignees have the advantage of being able to check the documents at the same time as they are registered and trust the transaction. Finally, on the bank side, the security of shipping documents is ensured and verification can be done quickly.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.67-76
• /
• 2022

Power and signal transmission using electromagnetic waves are essential in modern times, and a guided structure is needed to transmit electromagnetic waves efficiently through the desired path. This paper performed an electromagnetic simulation using the in-house code for the 2-D/3-D waveguide using the finite element method. The accuracy of the analysis was verified by comparing it with the results of HFSS, a representative electromagnetic wave simulation software. In addition, the performance of the Absorbing Boundary Condition (ABC), which is essential to truncate the infinite computational domain for computational electromagnetics, was analyzed. Finally, the parallelization technique was applied to accelerate the simulation speed, demonstrating performance improvement.

• Journal of Creative Information Culture
• /
• v.6 no.3
• /
• pp.179-187
• /
• 2020

This study was conducted to verify the effect of convergence education applying computing thinking ability of elementary school students on problem solving ability and interest. The subjects of this study were 23 students in 3rd grade elementary school and 15 students in 6th grade, totaling 38 subjects. As a research method, problem-solving ability and interest were measured through questionnaires, and data were analyzed through T-test to see the pre-post differences of the experimental group. As a result of the study, first, it was found that convergence education applying computing thinking ability had a positive effect on problem solving ability. Second, it was found that convergence education applying computational thinking has a partial effect on the degree of interest by subject. Looking at the details, interest in software education and physical activity was high, but interest in eating habits was relatively low. From the above results, it can be seen that convergence education based on computational thinking contributes to drawing students' problem solving ability, and interest.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.758-765
• /
• 2021

Recently, various research on the application of deep learning to video encoding for enhancing coding efficiency are being actively studied. This paper proposes a deep learning based intra prediction which uses multiple models by extending Matrix-based Intra Prediction(MIP) that is a neural network-based technology adopted in VVC. It also presents an efficient learning method for the multi-model intra prediction. To evaluate the performance of the proposed method, we integrated the VVC MIP and the proposed fully connected layer based multi-model intra prediction into HEVC reference software, HM16.19 as an additional intra prediction mode. As a result of the experiments, the proposed method can obtain bit-saving coding gain up to 0.47% and 0.19% BD-rate, respectively, compared to HM16.19 and VVC MIP.

• Journal of The Korean Association of Information Education
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2022

With the development of artificial intelligence, society is moving toward another world that has never existed before. As a result, interest in artificial intelligence education is also increasing, and research on artificial intelligence education is being conducted more actively in Korea. However, many studies have been conducted focusing on the upper grades of elementary school, and curriculum and programs for the lower grades are still insufficient. Therefore, in this study, a total of 6 sessions of artificial intelligence programs were developed to understand image recognition for the lower grades of elementary school. The validity was secured by conducting expert validity for 8 experts, and the effectiveness was verified through the pre-post-response sample t-test by applying it to the experimental group. As a result, both artificial intelligence understanding and artificial intelligence attitude showed statistically significant results, and both the interest and difficulty of educational programs were found to be suitable for lower grade students. Based on the contents of this study, it is necessary to review its application and effectiveness in various environments through follow-up studies in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.735-743
• /
• 2021

The mobile electronic notice service (MENS) is a service that delivers a mobile electronic notice to a smartphone in the person's name through an authorized electronic document intermediary instead of a bill that was delivered by mail using paper. In order to provide the MENS, information is needed to identify the same user between the sending agency and the authorized electronic document relay. In this paper, we propose a standard for safe conversion and utilization of Connecting Information (CI) used as user identification information for MENS. In the proposed method, it is necessary for the requesting institution to send the electronic notice to provide the resident registration number to the identity verification institution and convert it into the CI. In this case, a safe and efficient MENS will be possible by proposing a review standard and processing method to verify the appropriateness of the conversion of CI. By applying the proposed method to the MENS, it can contribute to service activation and reinforcement of user privacy protection.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.75-86
• /
• 2022

This study aims to solve the problem of class imbalance in numerical data by using a deep learning-based Variational AutoEncoder and to improve the performance of the learning model by augmenting the learning data. We propose 'D-VAE' to artificially increase the number of records for a given table data. The main features of the proposed technique go through discretization and feature selection in the preprocessing process to optimize the data. In the discretization process, K-means are applied and grouped, and then converted into one-hot vectors by one-hot encoding technique. Subsequently, for memory efficiency, sample data are generated with Variational AutoEncoder using only features that help predict with RFECV among feature selection techniques. To verify the performance of the proposed model, we demonstrate its validity by conducting experiments by data augmentation ratio.