• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.497-500
• /
• 2021

최근 모바일 기술이 실생활에 널리 활용하면서 점점 모바일 크라우드소싱 활용이 크게 기대되고 있다. 그래서 배달 인력이 아닌 일반인도 어플리케이션을 모바일 기기에 설치하면 배달 인력이 되어 작업을 수행할 수 있다. 본 연구에서는 일반인도 참여할 수 있는 모바일 크라우드소싱 기반 배달에서 딥러닝을 이용한 작업자 선정 기법을 소개한다. 그리고 실험을 통하여 합성곱 신경망(Convolutional Neural Network)을 적용한 본 기법이 효과적이라는 것을 보인다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.1-8
• /
• 2019

In this paper, we design a new mobile crowdsourcing control scheme based on the incentive mechanism. By using a novel incentive mechanism, mobile nodes can get the maximum payoff when they report their true private information. As mobile nodes participate in the overlapping coalition formation game, they can effectively invest their resource while getting the higher reward. Simulation results clearly indicate that the proposed scheme has a better performance than the other existing schemes under various mobile crowdsourcing environments.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.29-37
• /
• 2018

In recent years, there have been increasing interests in the mobile crowdsourcing that exploits multiple sensors, communication and user interfaces, and the computation power of widespread smartphones. In this paper, we present a novel mobile crowdsourcing-based driver assistance systems (MC-DAS) that crowdsource the sensor data of smartphone app having already passed a road segment, generate its profile information through a massive data processing, and forward this profile to the smartphone app of vehicle entering the road segment. Based on the MC-DAS platform, we also design and implement a new navigation system that advices the vehicle speed depending on the speedbump and on the road curvature profile. We expect that the proposed MC-DAS platform will be used as a platform for emerging new mobile crowdsourcing applications.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.1
• /
• pp.117-131
• /
• 2016

The development of LBS(location-based services) due to the widespread mobile environment highlights the importance of POI(point of interest) information. The accurate and up-to-date POI has to be ensured to reflect the information of rapidly changing places. For the efficient construction of POI, here we propose the novel construction system for t he place information. This system is based on crowd-sourcing in which a great number of users participate. In addition, we utilize the graph data model to build the new concept of the place information covering the wide areas extending from the specific point. Moreover, the implementation of the new system applying the graph data model and crowd-sourcing is realized in this paper. That is, this study suggests the whole new concept of the place information and shows the clustering and the renewal of the place information through crowd-sourcing.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.83-93
• /
• 2022

Research is underway to solve the traffic problem by using crowdsourcing, where drivers use their mobile devices to provide traffic information. If it is used for traffic event detection through crowdsourcing, the task of collecting related data is reduced, which lowers time cost and increases accuracy. In this paper, we propose a scheme to collect traffic-related data using crowdsourcing and to detect events affecting traffic through this. The proposed scheme uses machine learning algorithms for processing large amounts of data to determine the event type of the collected data. In addition, to find out the location where the event occurs, a keyword indicating the location is extracted from the collected data, and the administrative area of the keyword is returned. In this way, it is possible to resolve a location that is broadly defined in the existing location information or incorrect location information. Various performance evaluations are performed to prove the superiority and feasibility of the proposed scheme.

• Journal of Korea Game Society
• /
• v.17 no.2
• /
• pp.135-144
• /
• 2017

Sentiment analysis refers to a way of analyzing the writer's subjective opinions or feelings through text. For effective sentiment analysis, it is essential to build emotional word polarity lexicon. This paper introduces a crowdsourcing-based game that we have developed for efficiently building a polarity lexicon in Korean. First, we collected a corpus from the relating Internet communities using a crawler, and we classified them into words using the Twitter POS analyzer. These POS-tagged words are provided as a form of mobile platform based tagging game in which the players voluntarily tagged the polarities of the words, and then the result was collected into the database. So far we have tagged the polarities of about 1200 words. We expect that our research can contribute to the Korean sentiment analysis research especially in the game domain by collecting more emotional word data in the future.

• 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.

• The Journal of Society for e-Business Studies
• /
• v.16 no.1
• /
• pp.49-70
• /
• 2011

While new service development has become one of the most popular topics among practitioners and academics, methodologies development for new service development is only in its infancy. Especially, despite the growing interests in open innovations that effectively utilize external resources for R&D, existing research on new service development methodology designed to use external resources is scant. This article proposes a new methodology to generate new service business models that utilize massive external resources in combination with internal resources using ICT. The "Open Collaboration Innovation Methodology (OCIM)" is built based upon the theory of open innovation model and social psychology theories on behavioral motivation for cooperation. The model begins with the procedures to identify external resources that meet service objectives and requirements, and suggests motivation, control and monitoring mechanisms to implement a new service model. A business case is followed to demonstrate the use of the model. We expect that this model can be practically used by companies that are planning for developing new business models, and will provide a better understanding on open collaboration models, collective intelligence and crowd sourcing models.

• Korean Security Journal
• /
• no.62
• /
• pp.35-63
• /
• 2020

As the frequency and intensity of catastrophic disasters increase, there is widespread public sentiment that government capacity for disaster response and recovery is fundamentally limited, and that the involvement of civil society and the private sector is ever more vital. That is, in order to strengthen national disaster response capacity, governments need to build disaster systems that are more participatory and function through the channels of civil society, rather than continuing themselves to bear sole responsibility for these "wicked problems." With the advancement of smart mobile technology and social media, government and society as a whole have been called upon to apply these new information and communication technologies to address the current shortcomings of government-led disaster management. As illustrated in such catastrophic disasters as the 2011 Tohoku earthquake and tsunami in Japan, the 2010 Haitian earthquake, and Hurricane Katrina in the United States in 2005, the realization of participatory potential of smart technologies for better disaster response has enabled citizen participation via new smart technologies during disasters and resulted in positive impact on the management of such disasters. In this context, this study focuses on the South Korean context, and aims to analyze Korean government officials' readiness for public participation using smart technologies. On this basis, it aims to offer policy suggestions aimed at promoting smart technology-enabled citizen participation. For this purpose, it proposes a particular model, termed SMART (System, Motivation, Ability, Response, and Technology).