• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.125-133
• /
• 2023

This paper proposes an AI model that determines parking and non-parking zones based on return authentication photos to address parking issues that may arise in shared electric scooter systems. In this study, we used a pre-trained Segformer_b0 model on ADE20K and fine-tuned it on tactile blocks and electric scooters to extract segmentation maps of objects related to parking and non-parking areas. We also presented a method to perform binary classification of parking and non-parking zones using the Swin model. Finally, after labeling a total of 1,689 images and fine-tuning the SegFomer model, it achieved an mAP of 81.26%, recognizing electric scooters and tactile blocks. The classification model, trained on a total of 2,817 images, achieved an accuracy of 92.11% and an F1-Score of 91.50% for classifying parking and non-parking areas.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.160-163
• /
• 2021

최근 국내 전동킥보드 공유서비스의 증가 추세에 따라 전동킥보드와 보행자 혹은 차량과의 충돌사고가 증가하고 있다. 이러한 충돌사고로 인한 사고를 예방하기 위해 본 논문에서는 영상처리 기술에 기반한 후방위험요소 감지 시스템을 제안한다. 제안 시스템은 전동킥보드 사용자의 안전 헬멧에 라즈베리파이와 파이캠을 장착하여 가까이 오는 보행자나 차량을 영상처리 기법을 활용하여 인식하도록 하여 이들과의 충돌을 사전에 방지하도록 해준다. 제안 시스템의 정확도를 파악하기 위해 입력영상의 해상도별 처리속도와 정확도를 비교한다. 아울러, 제안 시스템을 안전 헬멧에 장착하여 테스트필드 실험을 통해 실제 환경에서 사용가능 여부를 검증한다.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.65-70
• /
• 2021

Electric kickboards are inviting attention as next-generation transportation systems with their number of users increasing rapidly every year. However, the number of related accidents similarly increases with the increase in the number of users. The purpose of this study is to analyze the structural safety of electric kickboards according to the shape of the connection parts. For this purpose, four different shapes of the connection parts, i.e., cube, cylinder, toroid, and divided cube were selected. Subsequently, the safety was analyzed based on the finite element (FE) analysis under the front collision scenario. The results showed that the shape of the divided cube induced the lowest von Mises stress and the highest safety factor amongst the four models. Moreover, only the shape showed a safety factor higher than 1. However, the shape of the cylinder exhibited the lowest structural vulnerability. These results demonstrate the importance of the shape of the connection part in maintaining the overall safety of an electric kickboard.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.93-99
• /
• 2019

Small electric vehicles, such as electric bicycles or electric kickboards, operate with the power charged in a battery mounted in the vehicle, and some of these users use emergency power sockets installed in apartments or public facilities without getting permission. For this reason, the necessity for a simple method to approve the use of power with instant payment system rises for the building managers and small vehicle users as well. In this paper, we propose a technique to charge batteries for small electric vehicles with less than 1 [kW] through a power supply control device installed on the existing 15 [A]. sockets on the common residential properties or public buildings. It also describes the power user authorization algorithm and how to charge fees for the power used. As a result of this research, this paper shows how the user authentication power supply system with the effect of preventing power theft can be realized by creating an environment in which a battery in a small electric vehicle can be easily charged.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.2
• /
• pp.195-206
• /
• 2023

Most of the Micro-mobility parking in Korea use Dockless system. However, Dockless can result in cluttering, infrastructure deficiencies, and safety challenges as has been observed in cities. It is necessary to introduce a Station Parking system in order to solve the drawbacks of the dockless, but the introduction without engineering has low accessibility and induces side effects. In this study, to decide optimal location about number of the Micro-mobility Station, we has been applied the MCLP model about the coverage range, usage demand, usage time in order to classify the type of Micro-mobility Station. For the MCLP, User Date input to reflect realistic demand in Bundang new town, Korea. The result show that the optimal number of facilities in 400 m was 146, and the coverage ratio was 99.83 %, which was most suitable coverage for solving the parking problem. We also classified the demand into 4 levels and the usage time into 3 levels, and by crossing them, we were able to classify the Parking lot types into 12 types. It is possible to propose strategic policies in the installation and operation of Micro-mobility Parking System.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.307-309
• /
• 2023

본 논문에서는 LSTM Autoencoder를 활용한 전동기의 Anomaly Detection을 제안한다. 전동기의 Anomaly Detection를 통해 전동킥보드의 고장을 예방하여 이용자의 안전을 보장한다. 전동기로부터 얻은 시계열 진동 데이터와 시계열 데이터 분석에 유의미한 LSTM을 활용한 Autoencoder를 통해 Anomaly Detection을 구현했다. 그 결과 99.9%의 정확도를 기록하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.39-40
• /
• 2022

최근 전동 킥보드, 전동휠, 전기 자전거 등 개인형 이동수단(Personal Mobility)의 보급이 늘면서 관련 인명 교통사고가 급증하고 있다. 본 논문에서는 개인형 이동수단의 사용위험 및 사고 감소를 목적으로, 딥러닝 객체탐지 기술을 적용하여 다양한 위험요소를 증강현실 기술을 기반으로 한 HMD(Helmet mounted display)에 표시하는 '딥러닝 객체 인식과 증강현실을 적용한 개인 이동장치를 위한 HMD(Helmet Mounted Display) 어플리케이션'을 설계한다. 제시하는 방법은 실시간으로 수집된 전방의 실시간 영상 정보를 객체 탐지 알고리즘을 통해 위험요소 및 안전한 주행을 보조하는 객체를 감지하고 증강현실을 적용해 사용자에게 적절한 운전 보조장치 및 기능을 제공한다.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.211-218
• /
• 2021

A recent spread of personal mobility devices such as electric kickboards has brought about a rapid increase in accident cases. Such vehicles are susceptible to falling accidents due to their low dynamic stability and lack of outer protection chassis. This paper presents the development of an automatic emergency braking system and a safe starting system as driving assistance devices for electric kickboards. The braking system employed artificial intelligence to detect nearby threaening objects. The starting system was developed to disable powder to the motor until when the driver's boarding is confirmed. This study is meaningful in that it proposes the convergence technology of advanced driver assistance systems specialized for personal mobility devices.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.263-266
• /
• 2019

본 연구에서는 주행승차감 및 안정성을 고려한 전동킥보드의 문제점을 해결하기 위해 역공학 기법을 사용하여 주요 시스템의 품질요소, 제품특성 등을 분석하고 사용자 요구사항을 도출하기 위해 품질기능전개(QFD: Quality Function Deployment)방법론을 적용하였으며 그 결과로 사용자 요구사항은 6개의 범주에서 20개를 도출하였으며 품질특성 요구사항은 16개 도출하여 최종 12개를 시스템 품질특성(CTQ: Critical To Quality)으로 선정하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1206-1207
• /
• 2023

보행의 제한은 시각장애인의 자립적인 생활을 어렵게 하며 안전에도 큰 영향을 끼친다. 본 논문은 YOLOv5(You Only Look Once version 5)를 활용하여 안전한 보행을 돕는 방법을 제시한다. 제시하는 방법은 자동차나 자전거, 전동킥보드 등의 움직이는 사물과 사람을 실시간으로 인식하여 시각장애인에게 알림으로써 보행에 도움을 줄 수 있으며 시각장애인의 안전한 보행에 도움을 줄 것이라 기대한다.