• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.277-278
• /
• 2022

최근 전동킥보드 보급이 이루어지면서 이와 관련된 교통사고가 증가하고 있다. 이에 따라 전동킥보드 주행 시 헬멧 착용을 의무화하는 도로교통법 개정안이 시행되고 있지만, 물리적으로 대부분 현장에서 단속이 어렵다. 본 논문에서는 딥러닝 영상인식 기술을 활용한 객체검출(object detection) 모델인 YOLOv4를 기반으로 전동킥보드 사용자의 헬멧 미착용 검출시스템을 제안하였다. 이를 통해 전동킥보드 주행 시 헬멧 착용 여부를 효율적으로 단속하는데 활용 할 수 있을 것으로 기대한다.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.425-431
• /
• 2021

The purpose of this study is to compare and analyze leading brands of the scooter-sharing system market of Korea, KICKGOING and Lime, in terms of user experience, and to suggest the improvement direction of the applications and scooters of those two services. The assessment was conducted in such a way that the experimental group using scooter-sharing system over a certain frequency would choose the specific service they use most frequently, and complete a questionnaire: based on the reorganized version of the Peter Morville's Honeycomb Model. Based on the results of the experiment, We drew a conclusion that the services need to add navigation features in the application, to provide more simple procedures for reporting breakdown or accident and browsing insurance information, and to improve the user and pedestrian safety levels by gamification, et cetera. We expect this study to help the fast-growing smart mobility market and scooter-sharing systems that represent the market develop into a user-centered way.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.233-237
• /
• 2020

In this study, the thermal analysis on the brake disc of electric kickboard was analyzed. The different heat is transmitted depending on the pad contact surface of brake disc. The trend that the temperature decreases at the part away from the contact surface was almost constant. And model A showed a slightly lower temperature distribution than model B. Model A has a maximum equivalent stress of 7% higher than model B. By being applied with the higher heat transfer above the contact surface, it is thought that model B has a greater strength than model A if the design takes into account the corner of the brake disc. If this study result is utilized to the design of electric kickboard, the design of brake disc with better strength is considered to be established. The durability of brake against the heat can be evaluated by applying this study result to the brake disc of electric kickboard. And it is seen that the result can be the design of brake with strength and the aesthetic convergence.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.22-39
• /
• 2021

This study estimated mode choice models for access travel and neighborhood travel from an SP survey in metropolitan areas where shared e-scooter services are offered. Model results show that travel time and travel cost have negative effects on mode utility. It is also revealed that people are more sensitive to travel time in access travel, whereas they are more influenced by travel cost in neighborhood travel. Looking at individual and household attributes, it has a positive effect when under 40 yerars of age, owning bikes, being a public transportation user, while it has been shown a negative effect in less than 3 million won in monthly household income and owning individual cars.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1228-1229
• /
• 2023

현대 도시 모빌리티의 중요한 구성 요소로 자리 잡은 전동킥보드는 편리한 이동 수단으로 인기를 얻고 있으나, 이에 따른 안전사고 증가로 운전자와 보행자의 안전이 심각하게 위협받고 있다. 본 논문에서는 전동킥보드 운전 중에 발생한 사고의 원인을 객관적으로 분석하고, 사고가 운전자의 부주의로 인한 것인지를 판별하며, 이로 인한 배상 책임을 정확하게 결정하기 위한 모델을 제안한다. 운전 중 수집된 센서 데이터를 활용하여 Deep SVDD (Deep Support Vector Data Description) 모델을 구축하고, 이상치 탐지를 통해 운전 패턴을 분류하며 운전자의 부주의로 인한 사고를 파악한다. 이를 통해, 정확하고 공정한 배상 책임 판단을 지원하며, 도시 모빌리티 분야에서 안전사고 감소에 기여할 것으로 기대된다.

• The Journal of the Korea Contents Association
• /
• v.21 no.9
• /
• pp.471-476
• /
• 2021

Personal mobility (PM) is a new concept of transportation used by one or two people using electricity. Personal transportation aims to move quickly and conveniently over an ambiguous distance that is too close to the destination and too far to walk. In particular, as electric kickboard sharing services have become more common in recent years, they are receiving great popularity from citizens. However, it is necessary to come up with an alternative solution as it is acting as a risk not only to users but also to pedestrians and road drivers. Therefore, in order to present measures to establish and improve a safe personal mobility utilization environment, this research was conducted as follows. First, based on GPS data from shared electric kickboards, the usage status in everyday life was examined and analyzed in detail. Second, it is convenient to rent and return shared electric kickboards directly to applications regardless of time, and it is highly accessible to rent them from their location and reach their destination. Based on these findings, this study suggests that careful access to rental and return could have a more positive effect on users and pedestrians by installing a cradle in a place where there is more use than disorderly device placement and expansion.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.860-862
• /
• 2022

4차 산업 혁명 시대의 각 분야에서 딥러닝, IoT 기술이 접목되면서 최신 기술이 빠르게 발전을 하는 추세이다. 동시에 최근 몇 년간 전동 킥보드 사용자가 급증하면서 사고 수는 배로 늘어나 교통 분야에서는 전동 킥보드에 많은 관심이 쏠리고 있다. 본 연구는 이 두 가지 분야를 접목하여 안전한 전동 킥보드 이용 문화 확립을 통해 스마트 도시에 이바지하고자 한다. 이를 위해서는 사용자들을 단속하는 것이 아닌 자율적으로 올바른 교통 문화에 이바지할 수 있도록 유도하는 것이 효과적이며 이 점이 기존 시스템과의 주요한 차이점이다. 본 논문에서는 영상인식과 IoT를 통한 안전 주행 장려 시스템을 제안하고 이를 앱에서 구현한 모습을 소개한다. 이를 통해 안전한 도로교통 문화뿐만 아니라 친환경 교통수단 이용 장려로 인한 탄소 저감 효과까지 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.643-646
• /
• 2021

경찰청에 따르면 도로교통법이 개정된 이후 3개월단 개인형 이동장치(PM)를 단속한 결과 무면허 운전이 3199건에 달하는 것으로 나타났다. 공유 킥보드 서비스의 경우 회원가입을 할 때 운전면허증 취득 여부를 확인하긴 하지만 서비스를 이용할 때는 별도의 확인 절차 없이 대여할 수 있기 때문에 운전면허증을 취득하지 않았어도 대여하는 경우가 발생한다. 본 논문에서는 공유 킥보드 서비스의 보안 취약점을 보완하기 위해 오토인코더와 변이형 오토인코더를 사용한 딥러닝 기반의 공유 킥보드 대리 대여 방지 시스템을 제안한다. 오토인코더는 지문 데이터로부터 특징만을 추출할 수 있어, 사용자의 지문 원본을 서버에게 노출시키지 않을 수 있다. 변이형 오토인코더는 생성형 모델로써, 사용자의 지문 데이터를 증폭 시켜 합성곱 신경망의 성능을 높이는데 도움을 준다. 이러한 오토인코더와 변이형 오토인코더의 특징을 이용해 사용자의 지문을 서버에 노출시키지 않으면서 적은 데이터로 신뢰성 높은 사용자 인증이 가능한 전동 킥보드 대여 시스템을 제안한다.

• Journal of the Korean Society of Systems Engineering
• /
• v.20 no.spc1
• /
• pp.108-118
• /
• 2024

As shared electric kick scooters spread to cities worldwide as a result of the proliferation of personal mobility, they have emerged as a significant social issue, impacting pedestrian and user safety, as well as urban aesthetics. In this study, we propose solutions to the unique problems associated with shared electric kick scooters, such as illegal parking, charging, and redistribution. Furthermore, we present research on supplementary services utilizing electric kick scooters in urban areas to enhance citizen safety and user satisfaction through the development of an autonomous electric kick scooter system structure and operational strategies. We suggest a low-cost autonomous electric kick scooter structure and propose AI processing, sensor fusion, and system operation methods to add autonomous capabilities to affordable electric kick scooters. Additionally, we propose operational systems and related technologies for offering various supplementary services.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.54-69
• /
• 2021

Policy improvement such as the revision of the Road Traffic Act are proposed for personal mobility(especially e-scooter) usage. However, there is not enough discussion to solve the problem of using shared e-scooter. In this study, we analyze the influencing factors that amount of pick-up and drop-off of shared e-scooter by dividing the Seoul into a 200m grid. we develop spatial auotcorrelation model such as spatial lag model, spatial error model, spatial durbin model, and spatial durbin error model in order to consider the characteristics of the aggregated data based on a specific space, and the spatial durbin error model is selected as the final model. As a result, demographic factor, land use factor, and transport facility factors have statistically significant impacts on usage of shared e-scooter. The result of this study will be used as basic data for suggesting efficient operation strategies considering the characteristics of weekday and weekend.