• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.175-179
• /
• 2021

With the recent increase in the proportion of single-person households, the demand for reasonable personal mobility has increased, and the "Personal Mobility" industry that can be used conveniently and concisely has grown rapidly. In fact, according to data from the Korea Transport Institute, the scale of the electric kickboards rental industry, one of the personal mobility industry sectors, is expected to expand to 200,000 units in 2022. Due to the characteristics of electric kickboards that are powered by electricity, stable and efficient battery supply is the most basic and important issue. According to recent reviews from users who have used the electric kickboard, there were cases where the use of the electric kickboard is attempted, but the battery is in a discharged state or the battery charge level is low and thus cannot be used. Therefore, this paper proposes a solar charging system for stable battery use of electric kickboards. When this system is applied, it is expected that it will not only be an eco-friendly charging method for electric kickboards, but also stably supply and demand batteries while driving.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.40-53
• /
• 2021

Recently, shared dockless e-scooter usage has rapidly increased, rather than the station-based shared mobility service, because of convenience. This transition leads to new social problems in urban areas such as increased traffic accidents and hindrance of pedestrian environments. In this study, we analyze the usage characteristics of shared e-scooters in Seoul, and identify factors influencing demand for shared e-scooters by developing a negative binomial regression model. As a result, the usage characteristics show that the average trip distance, the average trip duration, and the average trip speed were 1.5km, 9.4min, and 10.3km/h, respectively. Demographic factor, transport facility factors, land use factors, and weather factors have statistically significant impacts on demand for shared e-scooters. The results of this study will be used as basic data for suggesting effective operation strategies for areas with higher shared e-scooter demand and for establishing transport policies for facilitating shared e-scooter usage.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.131-142
• /
• 2023

In this paper, we propose a new station selection algorithm to solve the illegal parking problem of shared electric scooters and improve the service quality. Recently, as a solution to the urban transportation problem, shared electric scooters are attracting attention as the first and last mile means between public transportation and final destinations. As a result, the shared electric scooter market grew rapidly, problems caused by electric scooters are becoming serious. Therefore, in this study, text data are collected to understand the nature of the problem, and the problems related to shared scooters are viewed from the perspective of pedestrians and users in 'LDA Topic Modeling', and a station extension algorithm is based on this. Some parking lots have already been installed, but the existing parking lot location is different from the actual area of tow. Therefore, in this study, we propose an algorithm that can install stations at high actual tow density using mixed clustering technology using K-means after primary clustering by DBSCAN, reflecting the 'current state of electric scooter tow in Seoul'.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.173-186
• /
• 2022

The purpose of this study is to investigate the influence of gamification strategies on improving participation and motivation of shared electric scooter users. To this end, this study derived the user type through the first research question of how the shared electric scooter usage behavior and pulse are, and derived user tasks and scenarios. The second research question, a shared electric kickboard app with gamification, was tested by users to see if it helps increase user participation and form motivation. As a result of the analysis, it was found that users were induced to be considerate of other users by using a combination of the motivational, relational, and self-expression strategies of gamification. Second, it was found that the use of motivation, achievement and reward, and reward visualization strategy elements promotes user's voluntary behavior. Third, through relationship, achievement, and reward strategies, users participated to create a positive culture of shared electric scooters, drawing immediate feedback, indicating that convenience has increased. In conclusion, it was found that the user helped to play a positive role in voluntary participation and motivation through the use of the shared electric kickboard service with gamification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.326-328
• /
• 2021

The use of shared electric kickboards that can move quickly within a short distance at a relatively low price is increasing significantly. In this paper, we propose a system for recognizing incorrect parking of an abandoned shared kickboard by applying deep learning-based object recognition technology. In this paper, a model similar to CNN was created separately considering the characteristics of the experimental data, and it was shown that a recognition rate of 60% was obtained through the experiment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.260-261
• /
• 2023

공유 전동킥보드의 사용이 증가함에 따라, 불법 주차와 같은 문제점이 발생하고 있다. 시민들의 안전을 위협하는 문제를 해결하기 위해 CNN 모델 기반의 공유 전동킥보드 주차 판단 시스템을 구현하였다. 공유 전동킥보드에 탑재된 카메라, 기울기 센서를 통해 주차 상태를 판단하고, solidity와 python의 web3.py를 이용하여 컨소시엄 블록체인을 설계하였다. 주차 판단 기준이 되는 요소를 추가하고 가중치를 부여함으로써 신뢰 점수 식을 개선하였다. 본 논문에서 제안하는 모델을 통해 이용자의 자발적인 반납과 회사들의 효율적인 관리를 유도할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.986-987
• /
• 2023

본 논문은 신경근육질환 환자의 이동 문제를 해결하고, 기존 전동킥보드 시스템의 한계와 문제점도 해결하는 '신경근육질환 환자를 위한 전동킥보드 안전 환경 시스템'을 제안한다. 주요 특징은 다음과 같다. 첫째, 헬멧 착용 검사를 통과해야만전동킥보드를 이용할 수 있다. 휴대폰 전면 카메라를 통해 사용자의 모습을 촬영하면 딥러닝 모델을 통해 헬멧 착용 여부를 판단한다. 둘째, 주행 금지구역에서는 이용자 추적 모드를 활성화하여 OpenCV를 통해 이용자를 검출및 추적하고이에 따라 모터 PWM을 조절해서 방향 및 속력을 조절함으로써 이용자를 추적한다. 셋째, 헬멧 내 자이로 센서와 쇼크 센서를 통해 주행 사고를 감지하고 SMS를 이용해 해당 보호자에게 자동으로 사고 정보를 전달한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.201-204
• /
• 2021

최근 전동 킥보드 사용량이 크게 늘었으나, 다른 이동수단 대비 낮은 안정성과 사용자들의 헬멧 착용에 대한 인식 부족으로 인해 사고의 위험성이 큰 상황이다. 이에 대하여 정부는 헬멧 착용을 강제하는 법률을 제정하였으나, 경찰력의 한계에 따른 단속 미비로 여전히 헬멧 착용율은 낮다. 본 연구는 YOLO v3 알고리즘을 통해 학습시킨 딥러닝 모델을 활용하여 도로 상황을 촬영한 동영상 내에서 헬멧 착용자와 미착용자를 구분하고 미착용자 탐지 시 알람을 제공하는 시스템을 제시한다. 기존 YOLO 알고리즘 및 신경망을 적용하되, 전동 킥보드 데이터를 새로 수집하고 클래스를 구분하여 학습시켰다. 소수의 탐지 및 분류 오류를 보정하기 위해, 히스토그램 간 유사도를 측정해 최종적으로 객체를 추적 및 확정하고, 객체에 대한 헬멧 착용 여부를 통계적으로 확인한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.1-16
• /
• 2022

Recently, e-scooters have been attracting attention as eco-friendly modes of transportation in cities due to an increasing interest in the environment. Accordingly, various studies on usage behavior are being conducted, but studies that reflect individual travel attitudes are insufficient. Therefore, this study surveyed commuters in Seoul and analyzed respondents' traveling attitudes through factor analysis. It also built a binary logistic regression model for the intention to use shared e-scooters to determine how individual travel behaviors are affected. In particular, the model results showed that age, the main mode of transportation (car), walking time to the bus stop, and four travel attitude variables (disutility of travel, preference to self-drive, internet/smartphone friendliness, and willingness to pay extra money for services) significantly affected the intention to use shared e-scooters. This study is expected to be used as basic data, with aspect to travel behavior, for the efficient operation and use of shared e-scooters in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.124-140
• /
• 2023

The rapid growth in shared E-scooters worldwide has led to many studies on the topic. The results of these studies are still in the early stages, and the main factors affecting trips are being identified. In particular, the development of trip-generation models is very important for transportation planning, and a new transportation mode for developing the models for shared E-scooters is lacking both domestically and internationally. This study aims to develop a trip generation model for shared E-scooters using significant variables by thoroughly reviewing previous studies. The trip characteristics of major service areas and other areas may differ owing to the trip characteristics of the mode. The trip generation models were developed based on the service trip density by dividing the areas by service level. The factors affecting shared E-scooter trips in major service areas included the presence of universities, closeness centrality, and cultural areas, while factors affecting the trips in minor service areas included the presence of universities, betweenness centrality, and trip distance. The developed models provide basic information that can be used to establish transport policies for introducing shared E-scooters in cities in the future.