Deep-Learning Approach for Uncertainty Error Evaluation of Crowdsourced Trajectories and Navigation Database Generation
0
Citation
23
Reference
10
Related Paper
Abstract:
Ubiquitous indoor positioning technology plays an important role in providing indoor location-based services (iLBS) for the public. At this stage, crowdsourced multi-modal data fusion is regarded as an effective way to realize ubiquitous indoor positioning, especially for large-scale indoor spaces based on public daily-life trajectories and local positioning stations. Therefore, an effective uncertainty error evaluation method for daily-life trajectories is the key to generating a high-quality crowdsourced navigation database and further improving the performance of the final multi-source fusion system. To solve this problem, this paper proposes a deep-learning approach for autonomously evaluating the uncertainty error of crowdsourced daily-life trajectories, by learning and analyzing motion features extracted from pedestrian trajectories comprehensively from spatial and temporal perspectives. A novel deep-learning structure taking into account the spatiotemporal characteristics of the trajectory is modeled and related spatiotemporal features are extracted and modeled as the input vector of the proposed deep-learning structure. Real-world experimental results under generated trajectory datasets from large-scale indoor scenarios indicate that the proposed deep-learning structure can autonomously evaluate the uncertainty error of crowdsourced trajectories and realize much more accurate navigation database generation performance compared with existing state-of-the-art algorithms.Keywords:
Crowdsourcing
Despite its successes in various machine learning and data science tasks, crowdsourcing can be susceptible to attacks from dedicated adversaries. This work investigates the effects of adversaries on crowdsourced classification, under the popular Dawid and Skene model. The adversaries are allowed to deviate arbitrarily from the considered crowdsourcing model, and may potentially cooperate. To address this scenario, we develop an approach that leverages the structure of second-order moments of annotator responses, to identify large numbers of adversaries, and mitigate their impact on the crowdsourcing task. The potential of the proposed approach is empirically demonstrated on synthetic and real crowdsourcing datasets.
Crowdsourcing
Citizen Science
Cite
Citations (0)
The term “crowdsourcing” was initially introduced by Howe in his article “The Rise of Crowdsourcing” [1]. During the last few years, crowdsourcing has become popular among companies, institutions and universities, as a crowd-centered modern “tool” for problem solving. Crowdsourcing is mainly based on the idea of an open-call publication of a problem, requesting the response of the crowd for reaching the most appropriate solution. The focus of this paper is on the role of crowdsourcing in knowledge acquisition for planning applications. The first part provides an introduction to the origins of crowdsourcing in knowledge generation. The second part elaborates on the concept of crowdsourcing, while some indicative platforms supporting the development of crowdsourcing applications are also described. The third part focuses on the integration of crowdsourcing with certain web technologies and GIS (Geographic Information Systems), for spatial planning applications, while in the fourth part, a general framework of the rationale behind crowdsourcing applications is presented. Finally, the fifth part focuses on a range of case studies that adopted several crowdsourcing techniques.
Crowdsourcing
Crowdsourcing software development
Cite
Citations (36)
สำนกหอสมด มหาวทยาลยขอนแกน ใชเครองมอ Crowdsourcing ในการรบฟงเสยงผใชบรการ หลกการของ Crowdsourcing คอแทนทจะมอบใหบคคลหรอฝายใดฝายหนงทำการพฒนาอะไรใหมขนมา หรอทำการตดสนใจ แกไขปญหาเรองใดเรองหนง กลบเปดโอกาสใหฝงชนหรอสาธารณชนทวไปไดมโอกาสในการคดการตดสนใจแทน สำนกหอสมดจงนำแนวคดนมาเพอใหผใชบรการมสวนรวมสรางสรรค Content หรอทเรยกวา Co-Creation เปนกลยทธทางการตลาดทเนนการปฏสมพนธ (Interaction) เนนการตดตอสอสารเพอแลกเปลยนความคด ความตองการ ความคดเหนระหวางกน เพอทำใหเกดคณคาเพมในรปแบบของสนคา บรการ หรอประสบการณรวม ดวยการนำแนวคด Framework for Building a Co-creation Capability มาดำเนนการไดแก 1. การรบฟง (Listen) ดวยการใช Crowdsourcing 2. ความผกพน (Engage) ดวยการใหผใชมสวนรวมในการออกแบบบรการ 3. การตอบสนอง (Respond) เพอสรางสรรคบรการใหตรงกบความตองการของผใชบรการและเกดการมสวนรวมของผใชบรการอยางแทจรง สำนกหอสมดเปนหนวยงานแรกทนำเครองมอ Crowdsourcing มาใชในการรบฟงเสยงผใชบรการหองสมดมาอยางตอเนองตงแตป 2558 จนถงปจจบน จากการสอบถามจำนวน 9 ครง มผมารวมตอบจำนวน 7505 ครง ไดแนวคดหรอไอเดยตางๆกวา 206 ไอเดย ไอเดยทผใชบรการมสวนรวมในการเสนอถกนำมาออกแบบบรการหรอแกไขปญหาทเกดขนภายในหองสมดจรง และตรงกบความตองการของ ภายใตบรบทของการดำเนนงานหองสมดทเปนไปไดจรง ซงเปนทสนใจของคณะผศกษาดงานจากหลายแหงทใหความสนใจในรปแบบของการนำ Crowdsourcing มาใชงานทสามารถนำไปปรบใชในงานหองสมดไดงายดาย โดยไมมคาใชจาย และยงเพมภาพลกษณในงานหองสมดใหดทนสมยในมมมองของผใชบรการ
Crowdsourcing
Co-Creation
Crowdsourcing software development
Cite
Citations (0)
Mobile Crowdsourcing is now a highly compelling topic for research. Using crowdsourcing, a user can request for a solution to any problem he or she is facing to the mass people. In today's world, crowdsourcing can be applied to solve industrial, academical, business, and other problems. The utility of the crowdsourcing system depends on the involvement of the people in the task. However, due to several reasons, people become unwilling to participate in crowdsourcing tasks. In this paper, we have identified the reasons that prevent users from engaging in the crowdsourcing task. The obstacles are later classified according to the types of participants of a crowdsourcing task. Each of the participants has several obstacles that demotivate them from participating in the crowdsourcing. This survey paper will support us to understand the challenges that should be faced when designing a crowdsourced framework. If we can address these challenges, it will be easier to build a crowdsourcing framework to solve any problem.
Crowdsourcing
Crowdsourcing software development
Cite
Citations (7)
Crowdsourcing
Crowdsourcing software development
Cite
Citations (1)
Crowdsourcing
Crowdsourcing software development
Cite
Citations (37)
Crowdsourcing
Crowdsourcing software development
Cite
Citations (0)
Behavior change technologies are ubiquitous. The design of behavior change technologies requires familiarity of users and exploration of proper technologies, supported by the vast information and ideas collected through crowdsourcing. This article thus applies crowdsourcing to the design of behavior change technologies. A three-week design project was conducted, whereby designers' use of the information and ideas collected was recorded. Results validated the support of crowdsourcing, and revealed the features of crowdsourcing and traditional design methods. Designers selected higher- quality information from crowdsourcing than from traditional methods. Crowdsourcing and traditional methods collected different behavior changes, and induced different developments of behavior change technologies. Some suggestions on the application of crowdsourcing are also provided.
Crowdsourcing
Emerging Technologies
Crowdsourcing software development
Cite
Citations (0)
Crowdsourcing is a new approach to performing tasks, with a group of volunteers rather than experts. For example, the Geo-Wiki project [1] aims to improve the global land-cover map by crowdsourcing for image recognition. Though crowdsourcing gives a simple way to perform tasks that are hard to automate, analysis of data received from non-experts is a challenging problem that requires a holistic approach. Here we study in detail the dataset of the Cropland Capture game (part of Geo-Wiki project) to increase the accuracy of campaign’s results. Using this analysis, we developed a methodology for a generic type of crowdsourcing campaign similar to the Cropland Capture game. The proposed methodology relies on computer vision and machine learning techniques. Using the Cropland Capture dataset we showed that our methodology increases agreement between aggregated volunteers’ votes and experts’ decisions from 77% to 86%.
[1] Fritz, Steffen, et al. “Geo-Wiki. Org: The use of crowdsourcing to improve global land cover.” Remote Sensing 1.3 (2009): 345-354.
Crowdsourcing
Citizen Science
Land Cover
Cite
Citations (0)
Despite its successes in various machine learning and data science tasks, crowdsourcing can be susceptible to attacks from dedicated adversaries. This work investigates the effects of adversaries on crowdsourced classification, under the popular Dawid and Skene model. The adversaries are allowed to deviate arbitrarily from the considered crowdsourcing model, and may potentially cooperate. To address this scenario, we develop an approach that leverages the structure of second-order moments of annotator responses, to identify large numbers of adversaries, and mitigate their impact on the crowdsourcing task. The potential of the proposed approach is empirically demonstrated on synthetic and real crowdsourcing datasets.
Crowdsourcing
Citizen Science
Cite
Citations (0)