• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.1008-1011
• /
• 2018

크라우드센싱은 센서를 설치하는 대신 일반 대중들의 모바일 기기의 센서 정보를 이용하는 시스템이다. 본 논문에서는 오픈 소스 IoT 네트워크 플랫폼인 KaaIoT 플랫폼을 활용해 크라우드센싱 네트워크를 구축하는 방법을 제안한다. 제안된 시스템의 프로토타입을 구현하여 그 실현가능성과 성능을 보인다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.999-1007
• /
• 2018

To implement crowdsensing system in reality, trustiness between service provider server and user is necessary. Service provider server could manipulate the evaluation of sensing data to reduce incentive. Moreover, user could send a fake sensing data to get unjust incentive. In this paper, we adopt private blockchain on crowdsensing system, and thus paid incentives and sent data are unmodifiablely recorded. It makes server and users act as watcher of each others. Through adopting smart contract, our system automates sensing data evaluation and opens to users how it works. Finally, we show the feasibility of proposing system with performance evaluation and comparison with other systems.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.475-485
• /
• 2020

Recently, a crowdsensing system that provides a new sensing service with real-time sensing data provided from a user's device including a sensor without installing a separate sensor has attracted attention. In the crowdsensing system, meaningless data may be provided due to a user's operation error or communication problem, or false data may be provided to obtain compensation. Therefore, the detection and removal of the abnormal data determines the quality of the crowdsensing service. The proposed methods in the past to detect these anomalies are not efficient for the fast-changing environment of crowdsensing. This paper proposes an anomaly data detection method by extracting the characteristics of continuously and rapidly changing sensing data environment by using machine learning technology and modeling it with an appropriate algorithm. We show the performance and feasibility of the proposed system using deep learning binary classification model of supervised learning and autoencoder model of unsupervised learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.32-35
• /
• 2018

센서를 설치하는 대신 일반 대중들의 모바일 기기의 센서 정보를 이용하는 모바일 크라우드 센싱 기술을 활용해 적은 비용으로 주차장 포화도 정보를 제공하는 스마트 주차 시스템을 제안한다. 본 논문에서는 이러한 기술이 적용한 스마트 주차 시스템의 구조도를 제안하고, 특히 제공되는 정보에서 개인정보(장소, 시간, 차량번호 등의 연관관계)의 노출을 막기 위해 정보 제공에 사용되는 차량 이미지에서 번호판과 같은 개인정보를 효과적으로 제거하는 방법을 제시한다. 실험을 통해 그 가능성을 보인다.

• Journal of KIBIM
• /
• v.13 no.4
• /
• pp.106-114
• /
• 2023

In this study, we developed a method to quantify urban social costs using mobile sensing data, providing a novel approach to urban planning. By collecting and analyzing extensive mobile data over time, we transformed travel patterns into measurable social costs. Our findings highlight the effectiveness of big data in urban planning, revealing key correlations between transportation modes and their associated social costs. This research not only advances the use of mobile data in urban planning but also suggests new directions for future studies to enhance data collection and analysis methods.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.7
• /
• pp.119-126
• /
• 2019

The active living of the elderly leads to improve their lives and enhance social networks. In the view of the active living, the walkability is an essential factor for the elderly's daily life. To support the active living, making age-friendly environment is important. Considering that the elderly mainly carry out activities through walking, making the age-friendly walking environment is a preliminary action. The existing studies applied various methods such as surveys by experts. In spite of the benefits in theirs, there is still a limitation that current walkability measurement methods did not incorporate the actual elderly's walking activity. Thus, the purposes of this study is to measure the elderly's walking quantitatively using a wearable sensor, and to investigate the feasibility of comparing several walking environments based on the data collected from the actual elderly's walking. To do this, experiment was conducted in four types environments with 22 senior subjects. The walkability was measured by walking stability represented quantitatively as Maximum Lyapunov Exponent (MaxLE). Through the experiment results, it was confirmed that the stability of the elderly walking was different according to the walking environment, which also meant that bodily responses (walking stability) is highly related to walkability. The results will provide an opportunity for the continuous diagnosis of walking environments, thereby enhancing the active living of the elderly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.104-106
• /
• 2023

The mobile crowdsensing platform obtains sensing data from mobile users, and the involvement of the public increases the untrustworthy of collected data. In order to distinguish factual data from inaccurate data provided by untrustworthy users, the truth discovery method has been introduced for accurate data aggregation in mobile crowdsensing (MCS). To explore the application of truth discovery in mobile crowdsensing, we overview the general concepts of truth discovery algorithms. Finally, we summarize the main existing application prospects of truth discovery in mobile crowdsensing.