Tony T. Luo

Research Scientist, Programme Lead
Institute for Infocomm Research (I2R)
Agency for Science, Technology and Research (A*STAR)

Mailing Address: 1 Fusionopolis Way, #21-01, Connexis (South Tower), Singapore 138632
Tel: (+65) 6408 2257    Fax: (+65) 6776 1378
Email: luot <at> i2r.a-star.edu.sg


I am a Research Scientist from the Infrastructure, Energy and Environment (IEE) Department, as well as the Programme Lead of the "Sensor & Network Analytics" programme, both at the Institute for Infocomm Research (I2R), A*STAR, Singapore. I received my PhD degree in Electrical and Computer Engineering from the National University of Singapore.


Research Interests

  • Internet of Things: IoT analytics with machine learning; trust management in IoT
  • Mobile crowdsensing / crowdsourcing: incentives, trust, and privacy
Earlier:
  • Wireless networks (sensor / ad hoc / cognitive radio)
  • Software-defined networking (SDN)

    PAPERS    SOFTWARE    TALKS    SERVICES

Selected Recent Publications

[Complete list of publications]

  • [FUSION'18] MASA: Multi-agent Subjectivity Alignment for Trustworthy Internet of Things
    L. Zeynalvand, J. Zhang, T. Luo, and S. Chen
    21st International Conference on Information Fusion (FUSION), July 2018. To appear.
  • [ICC'18] Distributed anomaly detection using autoencoder neural networks in WSN for IoT
    T. Luo and S. Nagarajan
    IEEE International Conference on Communications (ICC), May 2018.
  • [Globecom'17] Reshaping mobile crowd sensing using cross validation to improve data credibility [pdf] [slides] [DOI: 10.1109/GLOCOM.2017.8255050]
    T. Luo and L. Zeynalvand
    IEEE Global Communications Conference (GLOBECOM), December 2017.
    With the idea of "crowd validating crowd", this paper proposes a cross validation approach in which a validating crowd is strategically selected to validate the quality of data contributed by the contributing crowd. A five-component cross validation mechanism is designed to reshape the original crowdsensed data into a more credible posterior belief of the ground truth.
  • [ComMag'17] Sustainable incentives for mobile crowdsensing: Auctions, lotteries, and trust and reputation systems [pdf] [DOI: 10.1109/MCOM.2017.1600746CM]
    T. Luo, S. S. Kanhere, J. Huang, S. K. Das, and F. Wu
    IEEE Communications Magazine, vol. 55, no. 3, pp. 68-74, March 2017.

    This survey paper provides a technical overview and analysis of six incentive mechanism design frameworks, namely auction, lottery, trust and reputation system, as well as bargaining game, contract theory, and market-driven mechanism.
  • [TIST'16] Incentive mechanism design for crowdsourcing: an all-pay auction approach [ACM Lib] [pdf] [DOI: 10.1145/2837029]
    T. Luo, S. K. Das, H-P. Tan, and L. Xia
    ACM Transactions on Intelligent Systems and Technology, vol. 7, no. 3, pp. 35:1-26, February 2016.

    The most commonly used auctions for incentive mechanism design are winner-pay auctions, where only winners (highest bidders) need to pay (money or effort) for their bids (and be rewarded). On the contrary, all-pay auctions require every worker to pay regardless of who will win, while still rewarding the winners only. This appears to be rather unreasonable, but we show in this paper that all-pay auctions not only have several advantages over winner-pay auctions, but can also generate higher profit by using an adaptive prize.
  • [TMC'16] Incentive mechanism design for heterogeneous crowdsourcing using all-pay contests [pdf] [DOI: 10.1109/TMC.2015.2485978]
    T. Luo, S. S. Kanhere, S. K. Das, and H-P. Tan
    IEEE Transactions on Mobile Computing, vol. 15, no. 9, pp. 2234-2246, September 2016.

    We all know that crowdworkers are heterogeneous, but it is hard to model and analyze. Therefore, existing work usually assumes the same distribution (e.g., uniform or normal) for all the workers, without considering the "deeper" heterogeneity where each individual worker has her own distribution (associated with her "type"). This paper deals with this model and designs an incentive mechanism based on asymmetric all-pay auctions.
  • [INFOCOM'15] Crowdsourcing with Tullock contests: A new perspective [pdf] [DOI: 10.1109/INFOCOM.2015.7218641]
    T. Luo, S. S. Kanhere, H-P. Tan, F. Wu, and H. Wu
    The 34th IEEE International Conference on Computer Communications (INFOCOM), April 2015, pp. 2515-2523.

    Acceptance rate: 19%
    Best Paper Award nominee
    What is a Tullock contest? Think it as a lucky draw! While auctions have dominated the realm of mechanism design for decades, this paper suggests Tullock contests as an alternative mechanism that is more appealing to "ordinary" participants. Tullock contests distinguish themselves from auctions in being imperfectly discriminating: "You always have a chance to win, no matter how 'weak' you are." This feature is particularly desirable for, e.g., large-scale crowdsensing.
  • [TMC'15] Quality of contributed service and market equilibrium for participatory sensing [pdf] [DOI: 10.1109/TMC.2014.2330302]
    C-K. Tham and T. Luo
    IEEE Transactions on Mobile Computing, vol. 14, no. 4, pp. 829-842, April 2015.
    In order to characterize QoS for crowdsensing, this work proposes a metric called Quality of Contributed Service (QCS) which aggregates individual quality of contributions and takes into account information quality and time sensitivity. QCS is then analyzed using a market based supply-and-demand model.
  • [COMNET'14] Fairness and social welfare in service allocation schemes for participatory sensing [pdf] [DOI: 10.1016/j.comnet.2014.07.013]
    C-K. Tham and T. Luo
    Computer Networks, Elsevier, vol. 73, pp. 58-71, November 2014.

    Instead of using monetary or reputation-based reward, this paper proposes a resource-allocation approach to incentivize crowdsensing. Specifically, it allocates each user some "service quota" based on the amount of contribution the user makes. A typical applicable scenario is a platform that uses crowdsensed data to provide some information service (transport, air quality, healthcare, etc.).
  • [MASS'14] Optimal prizes for all-pay contests in heterogeneous crowdsourcing [pdf] [DOI: 10.1109/MASS.2014.66] [Extended work: TMC'16]
    T. Luo, S. Kanhere, S. Das, and H-P. Tan
    The 11th IEEE International Conference on Mobile Ad-hoc and Sensor Systems (MASS), October 2014, pp. 136-144.

    Acceptance rate: 26.5% (48 out of 181)
    We all know that crowdworkers are heterogeneous, but it is hard to model and analyze. Therefore, existing work usually assumes the same distribution (e.g., uniform or normal) for all the workers, without considering the "deeper" heterogeneity where each individual worker has her own distribution (associated with her "type"). This paper deals with this model and designs an incentive mechanism based on asymmetric all-pay auctions.
  • [SECON'14] SEW-ing a Simple Endorsement Web to incentivize trustworthy participatory sensing [pdf] [DOI: 10.1109/SAHCN.2014.6990404]
    T. Luo, S. Kanhere, and H-P. Tan
    The 11th IEEE International Conference on Sensing, Communication, and Networking (SECON), July 2014, pp. 636-644.
    Acceptance rate: 28.6% (67 out of 234)
    This work takes a social-network perspective to connect participants into an endorsement-based social network. It proposes and explores "nepotism"---a tradeoff between selfishness and altruism---to both incentivize participation and improve trustworthiness for crowdsensing.
    [SEW has been implemented in two mobile crowdsensing smartphone apps called imReporter and FoodPriceSG. Find the links below in "Systems Work".]
  • [INFOCOM'14] Profit-maximizing incentive for participatory sensing [pdf] [Much enhanced version: ACM TIST'16]
    T. Luo, H-P. Tan, and L. Xia
    The 33rd IEEE International Conference on Computer Communications (INFOCOM), April 2014, pp. 127-135.

    Acceptance rate: 19% (319 out of 1650)

[Complete list of publications]


Systems Work

Besides theory, I also have keen interest in the actual development of real systems. The below are three mobile crowdsourcing/crowdsening systems developed by my team, all available for download at Apple Store and Google Play:

Related Publications:

  • VoteNet. I2R-A*STAR Technology Disclosure, filed in 2017.
  • T. Luo, S. Kanhere, and H-P. Tan, "SEW-ing a Simple Endorsement Web to incentivize trustworthy participatory sensing," IEEE 11th International Conference on Sensing, Communication, and Networking (SECON), July 2014. [pdf] (This paper describes an incentive engine used by imReporter & FoodPriceSG.)
  • F-J. Wu and T. Luo, "WiFiScout: A crowdsensing WiFi advisory system with gamification-based incentive," IEEE 11th International Conference on Mobile Ad Hoc and Sensor Systems (MASS), October 2014. [pdf] (This paper summarizes the WiFi-Scout system and its incentive scheme.)

Invited Talks & Tutorial

  • Shanghai Jiao Tong University, "Smart Factories: Augmenting intelligence for Industrial IoT with machine learning", May 2018.
  • IEEE ICC 2016 Tutorial, "Mobile crowdsourcing: Incentives, Trust, and Privacy", May 2016. [slides]
  • Sun Yat-sen University, "Building Internet of Things and smart cities via mobile crowd sensing", December 2016.
  • Xiamen University, "Empowering smart cities and the Internet of Things: A mobile crowdsensing perspective", December 2016.
  • Chinese University of Hong Kong, "Incentive mechanism design and trust systems for crowdsourcing", May 2015.
  • Singapore University of Technology and Design, "Incentives and trustworthiness in crowdsourcing", December 2014.
  • University of Electronic Science and Technology of China, "Incentivizing trustworthy human-centric systems", April 2014.
  • University of Melbourne, Australia, "Incentives and QoS in participatory sensing", March 2012.

Professional Activities


Miscellaneous

[Copyright Notice] Papers downloaded from this site are restricted to personal or classroom use only and not for profit or commercial advantage; any commercial usage must obtain written permission from the authors. Users shall refrain from any copyright infringements and adhere to relevant policies stipulated by corresponding organizations such as IEEE, ACM, or Elsevier.

© Tony T. Luo 2007-2018