• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.15-24
• /
• 2022

At present, there are few studies on signal control of pedestrian traffic flow and non-motor traffic flow at intersections. Research on the optimization scheme of mixed traffic flow signal control can coordinate and control the overall traffic flow of pedestrians, non-motor vehicles and motor vehicles, which is of great significance to improve the congestion at intersections. For the traffic optimization of intersections, this paper starts from two aspects: channelization optimization and phase design, and reduces the number of conflict points at intersections from spatial and temporal right-of-way allocation respectively. Taking the classical signal timing method as the theoretical basis, and aiming at ensuring the safety and time benefit of traffic travelers, a channelization optimization and signal control scheme of the intersection is proposed. The channelization and phase design methods of intersections with motor vehicles, non-motor vehicles and pedestrians as objects are discussed, and measures to improve the channelization optimization of intersections are proposed. A multi-objective optimization model of intersection signal control was established, and the model was solved based on NSGA-II algorithm.

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.365-373
• /
• 2023

Unmanned aerial vehicles are widely used in various fields, and real-time path replanning is a critical factor in enhancing the safety and efficiency of these devices. In this paper, we propose a real-time path replanning technique based on RRT* and LOSPO. The proposed technique first generates an initial path using the RRT* algorithm and then optimizes the path using LOSPO. Additionally, the optimized path can be converted into a trajectory that considers actual time and the dynamic limits of the aircraft. In this process, environmental changes and collision risks are detected in real-time, and the path is replanned as needed to maintain safe operation. This method has been verified through simulation-based experiments. The results of this paper make a significant contribution to the research on real-time path replanning for UAVs, and by applying this technique to various situations, the safety and efficiency of UAVs can be improved.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.257-258
• /
• 2020

기존의 드론 조작은 초보자에게 어려웠다. 초보자의 경우 드론을 조종하다가 드론이 추락하거나 장애물에 걸려 프로펠러 등의 부품들이 손상되는 경우를 빈번하게 마주한다. 본 연구에서는 초보자 또한 드론 파손의 걱정 없이 드론의 조작을 더욱 쉽게 개선시키는 것을 전제로 뇌파와 보조입력인 음성인식을 이용한 드론 컨트롤러 기술을 적용하고자 한다. 현재 대중적으로 출시되어 있는 드론의 경우 호버링 기능을 포함시켜 드론의 추락 위험을 줄여주는 기능을 탑재하고 있다. 하지만 속도가 빠른 드론의 조작에 있어 미숙한 초보자들은 장애물과의 충돌 그리고 드론 착륙 시 기체손상 등의 위험에 대비하기 힘들다. 본 논문은 이러한 문제점들을 개선하기 위해 기존의 드론 컨트롤러 대신 특정한 동작을 상상할 때 발현되는 동작상상뇌파와 음성입력을 적용한 '동작상상뇌파와 음성인식을 이용한 드론 컨트롤러' 기술을 제안한다. 기존의 드론 컨트롤러와는 다르게 빅 데이터 처리기술인 머신러닝을 이용하여 뇌파 데이터를 처리하고 그 데이터들과 입력되는 뇌파 값을 비교하여 드론을 제어한다. 또한 뇌파의 발현이 안정적이지 못하는 상황을 대비한 보조입력인 음성인식을 이용하여 드론의 기체손상을 최소화 시킬 수 있다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.265-265
• /
• 2019

Marine accidents continue to occur every year due to human errors. The purpose of this study is to promote navigational safety by preventing ship collision accidents caused by human errors of behavior of navigators. There are two ways to manage human error caused by navigator's behavior. It is divided in individual approach and system approach, which is applied to situational awareness theory and Rasmussen's behavioral theory. This study investigated past marine accidents caused by human error and conducted experiments using ship handling simulators to identify these two behavioral characteristics. After analyzing two human error characteristics, we will propose a countermeasure in next study.

• Korean Journal of Legislative Studies
• /
• v.15 no.1
• /
• pp.93-118
• /
• 2009

Why the National Assembly of Korea shows the serious disagreements or arguments in its operation? Regarding the question, this study pays attention to the perceptual differences among the parties for the structure of collective decision-making in the National Assembly of Korea. In addition, this study asserts that deepens the conflicts and the distrust in it. To be more specific, this study discusses about the optimal model for collective decision-making in legislative politics based on Buchanan and Tullock's opinion about it. And then, the trust in legislature forms the basis that makes it possible to respect the will of majority and protect the right of minority. The main reason that can't make the collective decision-making optimally in the National Assembly of Korea is to fight each other without the consensus about it. In this vein, making the collective decision-making optimally and recovering the trust among the parties are necessary to adopt a more consensual system. It will be helpful to prevent the use of noninstitutional means like the outside struggles or physical resistances in the National Assembly of Korea.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.275-276
• /
• 2022

VTS operators instruct ships to wait for entry and departure to sail in one-way to prevent ship collision accidents in ports with narrow routes. Currently, the instructions are not based on scientific and statistical data. As a result, there is a significant deviation depending on the individual capability of the VTS operators. Accordingly, this study built a 1d-convolutional neural network model by collecting ship and weather data to predict the exact travel time for ship entry/departure waiting for instructions in the port. It was confirmed that the proposed model was improved by more than 4.5% compared to other ensemble machine learning models. Through this study, it is possible to predict the time required to enter and depart a vessel in various situations, so it is expected that the VTS operators will help provide accurate information to the vessel and determine the waiting order.

• Convergence Security Journal
• /
• v.23 no.3
• /
• pp.65-71
• /
• 2023

The importance of combat drones has been highlighted through the recent outbreak of the Russia-Ukraine war. The combat drones play a significant role as a a game changer that alters the conventional wisdom of traditional warfare. Many pundits expect the role of combat swarm drones would be more crucial in the future warfare. In this regard, this paper aims to analyze the development of artificial intelligence-enabled combat swarm drones. To transform the human-operated swarm drones into fully autonomous weaponry system our suggestions are as follows. Developments of (1) AI algorithms for optimized swarm drone operations, (2) decentralized command and control system, (3) inter-drones' mission analysis and allocation technology, (4) enhanced drone communication security and (5) set up of ethical guideline for the autonomous system. Specifically, we suggest the development of AI algorithms for drone collision avoidance and moving target attacks. Also, in order to adjust rapidly changing military environment, decentralized command and control system and mission analysis allocation technology are necessary. Lastly, cutting-edging secure communication technology and concrete ethical guidelines are essential for future AI-enabled combat swarm drones.

• Journal of Aerospace System Engineering
• /
• v.18 no.3
• /
• pp.56-64
• /
• 2024

In this study, a drop impact tester was developed to comprehensively conduct basic testing and academic research on the drop impact characteristics of aerospace structures. A drop tester enables accurate assessment of the dynamic stresses and deformations that occur when an aircraft collides with the ground, thereby enabling the verification of important design factors, such as safety and mechanical strength. The drop tester consists of an electromagnet to attach and drop the test object, a crane to adjust the drop height of the test object, and a drop support structure for vertical drops. Numerical analysis of the drop test object for the test was performed, and basic tests were performed using the drop impact tester. Through the analysis and test results, the structural shape of the landing gear was analyzed, and the behavior of each part was evaluated.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.130-140
• /
• 2024

In this paper, we present a method of applying the kalman filter to control and correct errors in camera sensor recognition depending on the sea state environment. First, the specifications of the ship were described and the degree of error due to rolling was measured. After presenting the distance from the surface of the water to the sidelight required for simulation through PKMR-211, the ship selected as the model, error correction was performed using the camera error value as a variable in the feedback control system. In the experiment, the degree of rolling of the ship was expressed as variables 𝛼 and 𝛽, expressed in angles, and the angle change according to distance was compared. When comparing the error before and after applying the kalman filter in sea state 4, it decreased from +1.5556° to -1.1544° in red light regardless of distance, and the same result was confirmed in green light. Through this, calculations were performed considering the movement of the ship according to the maritime environment, and the future maneuverability of the ship was presented after error correction.