Quantifying User Reputation Scores, Data Trustworthiness, and User Incentives in Mobile Crowd-Sensing

Pouryazdan, Maryam; Kantarcı, Burak; Soyata, Tolga; Foschini, Luca; Song, Houbing

doi:10.1109/access.2017.2660461

Cited by 130 publications

(66 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reputation values of workers are obtained and updated according to their historical contributions. Pouryazdan et al [11] proposed a collaborative reputation scoring method based on statistical and vote-based user reputation scores to quantify the data trustworthiness, which improves platform utility and data trustworthiness in mobile crowdsensing.…”

Section: A Overview Of Reputation Management In Crowdsensingmentioning

confidence: 99%

Reliable Federated Learning for Mobile Networks

Kang

Xiong

Niyato

et al. 2020

IEEE Wireless Commun.

402

157

View full text Add to dashboard Cite

Federated learning, as a promising machine learning approach, has emerged to leverage a distributed personalized dataset from a number of nodes, e.g., mobile devices, to improve performance while simultaneously providing privacy preservation for mobile users. In the federated learning, training data is widely distributed and maintained on the mobile devices as workers. A central aggregator updates a global model by collecting local updates from mobile devices using their local training data to train the global model in each iteration. However, unreliable data may be uploaded by the mobile devices (i.e., workers), leading to frauds in tasks of federated learning. The workers may perform unreliable updates intentionally, e.g., the data poisoning attack, or unintentionally, e.g., low-quality data caused by energy constraints or high-speed mobility. Therefore, finding out trusted and reliable workers in federated learning tasks becomes critical. In this article, the concept of reputation is introduced as a metric. Based on this metric, a reliable worker selection scheme is proposed for federated learning tasks. Consortium blockchain is leveraged as a decentralized approach for achieving efficient reputation management of the workers without repudiation and tampering. By numerical analysis, the proposed approach is demonstrated to improve the reliability of federated learning tasks in mobile networks.

show abstract

Section: A Overview Of Reputation Management In Crowdsensingmentioning

confidence: 99%

Reliable Federated Learning for Mobile Networks

Kang

Xiong

Niyato

et al. 2020

IEEE Wireless Commun.

402

157

View full text Add to dashboard Cite

show abstract

“…Users can have a passive role, e.g., in many crowd-sensing applications such as [37], [39]- [41] users only provide their data. For instance, incentives are offered to users to improve crowd-sensing data quality in [37]. In [64], user perception is utilized to fine-tune QoS, which in turn provides energy savings.…”

Section: B User Involvement In Network Operationmentioning

confidence: 99%

“…The studies on incentive methods either rely on hypothetical assumptions (e.g., [37], [43], [72], [73]), or field studies (e.g., [48], [49], [71], [74]). Both methods suffer from reliability, as the statistical assumptions are hard to justify and many field studies are limited to a small group of participants with similar demographics, e.g., university students.…”

Section: B User Involvement In Network Operationmentioning

confidence: 99%

Spatial Configuration of Agile Wireless Networks With Drone-BSs and User-in-the-loop

Bor-Yaliniz

El-Keyi

Yanıkömeroğlu

2019

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Agile networking can reduce over-engineering, costs, and energy waste. Towards that end, it is vital to exploit all degrees of freedom of wireless networks efficiently, so that service quality is not sacrificed. In order to reap the benefits of flexible networking, we propose a spatial network configuration scheme (SNC), which can result in efficient networking; both from the perspective of network capacity, and profitability. First, SNC utilizes the drone-base-stations (drone-BSs) to configure access points. Drone-BSs are shifting paradigms of heterogeneous wireless networks by providing radically flexible deployment opportunities. On the other hand, their limited endurance and potential high cost increase the importance of utilizing drone-BSs efficiently. Therefore, secondly, user mobility is exploited via user-in-the-loop (UIL), which aims at influencing users' mobility by offering incentives. The proposed uncoordinated SNC is a computationally efficient method, yet, it may be insufficient to exploit the synergy between drone-BSs and UIL. Hence, we propose joint SNC, which increases the performance gain along with the computational cost. Finally, semi-joint SNC combines benefits of joint SNC, with computational efficiency. Numerical results show that semi-joint SNC is two orders of magnitude times faster than joint SNC, and more than 15% profit can be obtained compared to conventional systems.Index Terms-Unmanned aerial vehicle, user-in-the-loop, agile network, drone-BS. arXiv:1809.05315v1 [cs.NI]

show abstract

“…Vehicular systems [10] have access to numerous hundred sensors embedded in cars, and latest vehicles come equipped with new types of sensors, for example, radar and camera. It has been believing that researchers in a number of fields of science and engineering as well as local state, and federal agencies can significantly benefit from this new sensing infrastructure as they will have access to valued data from the physical world.…”

Section: Related Workmentioning

confidence: 99%

“…In this algorithm, user pool is divided into two segments such as for (u in 1:2) // inner for loop is running from 1 to 2 times used for locations 10 …”

Section: A Pseudo Codementioning

confidence: 99%

An Efficient Participant’s Selection Algorithm for Crowdsensing

Ali¹,

Draz²,

Yasin³

et al. 2018

ijacsa

View full text Add to dashboard Cite

Abstract-With the advancement of mobile technology the use of Smartphone is greatly increased. Everyone has the mobile phones and it becomes the necessity of life. Today, smart devices are flooding the internet data at every time and in any form that cause the mobile crowdsensing (MCS). One of the key challenges in mobile crowd sensing system is how to effectively identify and select the well-suited participants in recruitments from a large user pool. This research work presents the concept of crowdsensing along with the selection process of participants from a large user pool. MCS provides the efficient selection process for participants that how well suited participant's selects/recruit from a large user pool. For this, the proposed selection algorithm plays our role in which the recruitment of participants takes place with the availability status from the large user pool. At the end, the graphical result presented with the suitable location of the participants and their time slot.

show abstract

Quantifying User Reputation Scores, Data Trustworthiness, and User Incentives in Mobile Crowd-Sensing

Cited by 130 publications

References 68 publications

Reliable Federated Learning for Mobile Networks

Reliable Federated Learning for Mobile Networks

Spatial Configuration of Agile Wireless Networks With Drone-BSs and User-in-the-loop

An Efficient Participant’s Selection Algorithm for Crowdsensing

Contact Info

Product

Resources

About