• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.4
• /
• pp.209-220
• /
• 2019

Even though the scale of hard structures for beach stabilization should carefully be determined such that these structures do not interrupt the great yearly circulation process of beach sediment in which the self-healing ability of natural beach takes places, massive hard structures such as the submerged breakwater of wide-width are frequently deployed as the beach stabilization measures. On this rationale, asymmetric ripple mat by Irie et al. (1994) can be the alternatives for beach stabilization due to its small scale to replace the preferred submerged breaker of wide-width. The effectiveness of asymmetric ripple mat is determined by how effectively the vortices enforced at the contraction part of flow area over the mat traps the sediment moving toward the offshore by the run-down. In order to verify this hypothesis, we carry out the numerical simulations based on the Navier-Stokes equation and the physically-based morphology model. Numerical results show that the asymmetric ripple mat effectively capture the sediment by forced vortex enforced at the apex of asymmetric ripple mat, and bring these trapped sediments back to the beach, which has been regarded to be the driving mechanism of beach stabilization effect of asymmetric ripple mat.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.2
• /
• pp.151-158
• /
• 2019

Wireless communication technology (WAVE) for vehicles, which is the core technology behind the next-generation intelligent transport system (C-ITS), is used to deliver information about vehicles to prevent traffic accidents and traffic situations that may arise between vehicles and infrastructure. Similar traffic issues often arise in marine scenarios. Currently, AIS is being used as a means of transmitting information such as the status of relative vessels, but research is being carried out to solve problems with AIS such as overloading by applying wireless communication technology for vehicles to the sea. In this study, a collision warning system suitable for small-sized vessels was developed based on the marine application of WAVE for vehicles verified through prior research, and the adequacy of this collision warning system was reviewed through a practical test. It is expected that this system will contribute greatly to future e-Navigation applications or self-driving ships as well as to preventing marine accidents.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.5
• /
• pp.49-58
• /
• 2019

In this paper, we propose an edge cloud platform architecture for implementing smart factory. The edge cloud platform is one of edge computing architecture which is mainly focusing on the efficient computing between IoT devices and central cloud. So far, edge computing has put emphasis on reducing latency, bandwidth and computing cost in areas like smart homes and self-driving cars. On the other hand, in this paper, we suggest not only common functional architecture of edge system but also light weight cloud based architecture to apply to the specialized requirements of smart factory. Cloud based edge architecture has many advantages in terms of scalability and reliability of resources and operation of various independent edge functions compare to typical edge system architecture. To make sure the availability of edge cloud platform in smart factory, we also analyze requirements of smart factory edge. We redefine requirements from a 4M1E(man, machine, material, method, element) perspective which are essentially needed to be digitalized and intelligent for physical operation of smart factory. Based on these requirements, we suggest layered(IoT Gateway, Edge Cloud, Central Cloud) application and data architecture. we also propose edge cloud platform architecture using lightweight container virtualization technology. Finally, we validate its implementation effects with case study. we apply proposed edge cloud architecture to the real manufacturing process and compare to existing equipment engineering system. As a result, we prove that the response performance of the proposed approach was improved by 84 to 92% better than existing method.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.673-681
• /
• 2021

This study is a case study of artificial intelligence education subjects in the graduate school of education. The main educational contents consisted of understanding and practice of machine learning, data analysis, actual artificial intelligence using Entries, artificial intelligence and physical computing. As a result of the survey on the educational effect after the application of the curriculum, it was found that the students preferred the use of the Entry AI block and the use of the Blacksmith board as a physical computing tool as the priority applied to the elementary education field. In addition, the data analysis area is effective in linking math data and graph education. As a physical computing tool, Husky Lens is useful for scalability by using image processing functions for self-driving car maker education. Suggestions for desirable AI education include training courses by level and reinforcement of data collection and analysis education.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.4
• /
• pp.105-114
• /
• 2009

Messages exchanged among vehicles must be authenticated in order to provide collision avoidance and cooperative driving services in VANET. However, digitally signing the messages can violate the privacy of users. Therefore, we require authentication systems that can provide conditional anonymity. Recently, Zhang et al. proposed conditionally anonymous authentication system for VANET using tamper-resistant hardware. In their system, vehicles can generate identity-based public keys by themselves and use them to sign messages. Moreover, they use batch verification to effectively verify signed messages. In this paper, we provide amelioration to Zhang et al.'s system in the following respects. First, we use a more efficient probabilistic signature scheme. Second, unlike Zhang et al., we use a security proven batch verification scheme. We also provide effective solutions for key revocation and anonymity revocation problems.

• 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.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.209-214
• /
• 2023

In the future, as autonomous vehicles become popular at home and abroad, the frequency of accidents involving autonomous vehicles is also expected to increase. In particular, when a fully autonomous vehicle is operated, various criminal/civil problems such as sexual violence, assault, and fraud between passengers may occur as well as the vehicle accident itself. In this case, forensics for accidents involving autonomous vehicles and accidents involving passengers in the vehicles are also about to change. This paper reviewed the types of security threats of autonomous vehicles, methods for maintaining the integrity of evidence data using blockchain technology, and research on digital forensics. Through this, it was possible to describe threats that would occur in autonomous vehicles using blockchain technology and forensic techniques for each type of accident in a scenario-type manner. Through this study, a block that helps forensics of self-driving vehicles before and after accidents by investigating forensic security technology of domestic and foreign websites to respond to vulnerabilities and attacks of autonomous vehicles, and research on block chain security of research institutes and information security companies. A chain method was proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.77-89
• /
• 2023

The purpose of this study is to empirically confirm what is an important variable of organizational change by intelligent technology acceptance and whether is a difference in important variables in the organization level of acceptance of intelligent technology. Recently, business models using intelligent technologies such as chat-bots, self-driving cars, credit-prevention fraud, face recognition, and health-care are emerging. External situation factors such as artificial intelligence, big data, COVID-19, and the ESG management are changing the direction of a company's management strategy. This research method established a structural equation model. As a result of the analysis, we found that the leadership, organizational culture, and organizational cooperation variables had a positive effect on human resource development variables. Human resource development found a positive effect on the performance of intelligent technology. In addition, we found the independent variables of leadership, organizational culture, and organizational cooperation had partial mediating effects on the performance of intelligent technology. Each group of levels of intelligent technology found performance differences. The organizational culture variables appeared as important variables in all groups. On the other hand, the leadership variable appeared as an important variable in the middle and lower groups of intelligent technology. The theoretical background of this study is that the business theory was updated through artificial intelligence and intelligent technology theory. As a practical implication, the organization adopting intelligent technology is necessary to prepare a systematic plan for organizational culture change.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.401-409
• /
• 2021

This study is a case study of artificial intelligence education subjects in the graduate school of education. The main educational contents consisted of understanding and practice of machine learning, data analysis, actual artificial intelligence using Entries, artificial intelligence and physical computing. As a result of the survey on the educational effect after the application of the curriculum, it was found that the students preferred the use of the Entry AI block and the use of the Blacksmith board as a physical computing tool as the priority applied to the elementary education field. In addition, the data analysis area is effective in linking math data and graph education. As a physical computing tool, Husky Lens is useful for scalability by using image processing functions for self-driving car maker education. Suggestions for desirable AI education include training courses by level and reinforcement of data collection and analysis education.