Pengfei Zhou (周鹏飞)
Office: N4-B2a-02h, 50 Nanyang Avenue, PDCC, NTU, Singapore, 639798
Phone: +65 93592907
Email: pfzhou AT ntu.edu.sg

 

Biography

I am now a Ph.D. student in School of Computer Science Engineering, Nanyang Technological University, working in the Wireless And Networked Distributed Sensing (WANDS) group with Prof. Mo Li. I received my B.E. degree in Department of Automation from Tsinghua University in 2009.

Research Interests

My research topics include sensor characterization and fusion in mobile computing and systems, innovative mobile applications and human-centric computing. Additionally, the problems in cellular network communications also fascinate me and I am trying to tackle them with mobile sensing.

Publications

[TOSN] Mo Li, Pengfei Zhou, Yuanqing Zheng, Zhenjiang Li, and Guobin (Jacky) Shen. "IODetector: A Generic Service for Indoor Outdoor Detection", In ACM Transactions on Sensor Networks, accepted to appear. Exteneded version of the Sensys'12 paper.
[TMC] Pengfei Zhou, Yuanqing Zheng, Mo Li. "How Long to Wait?: Predicting Bus Arrival Time with Mobile Phone based Participatory Sensing", In IEEE Transactions on Mobile Computing, Vol. 13, Issue 6, Pages 1228-1241, June 2014. (PDF). Exteneded version of the Mobisys'12 paper.

[ICDCS'15] Pengfei Zhou, Shiqi Jiang, Mo Li. "Urban Traffic Monitoring with the Help of Bus Riders", In IEEE ICDCS, Columbus, Ohio, USA, June-July, 2015, (PDF)(Slides)
[MobiCom'14] Pengfei Zhou, Mo Li, and Guobin (Jacky) Shen. "Use It Free: Instantly Knowing Your Phone Attitude", In ACM MobiCom, Maui, Hawaii, USA, September 2014, (PDF)(Slides)(Demo video: Car App, Comparison).
[SenSys'12] Pengfei Zhou, Yuanqing Zheng, Zhenjiang Li, Mo Li, and Guobin (Jacky) Shen. "IODetector: A Generic Service for Indoor Outdoor Detection", In ACM SenSys, Toronto, Canada, November 2012, (PDF)(Slides)(Demo app).
[MobiSys'12] Pengfei Zhou, Yuanqing Zheng, Mo Li. "How Long to Wait?: Predicting Bus Arrival Time with Mobile Phone based Participatory Sensing", In ACM MobiSys, Low Wood Bay, United Kingdom, June 2012, (PDF)(Slides) (Demo video).

Posters and Demos

[MobiCom'14] Pengfei Zhou, Weiming Chan, Shiqi Jiang, Jiajue Ou, Mo Li, and Guobin (Jacky) Shen. "Demo: Instant Phone Attitude Estimation and Its Applications", In ACM MobiCom, Maui, Hawaii, USA, September 2014. (PDF)
[VLCS'14] Pengfei Zhou, Zhenjiang Li, Yuanqing Zheng, and Mo Li. "Harnessing Visible Light: Characterization and Applications", In 1st ACM Workshop on Visible Light Communication Systems, Maui, Hawaii, USA, September 2014.
[SenSys'13] Pengfei Zhou, Zhiyuan Chen, and Mo Li. "Poster Abstract: Smart Traffic Monitoring with Participatory Sensing", In ACM SenSys, Rome, Italy, November 2013.
[APSYS'13] Pengfei Zhou and Mo Li. "Building Smart Transportation with Participatory Sensing", In APSYS, Singapore, July 2013.
[SenSys'12] Pengfei Zhou, Yuanqing Zheng, Zhenjiang Li, Mo Li, and Guobin (Jacky) Shen. "Demo - IODetector: A Generic Service for Indoor Outdoor Detection", In ACM SenSys, Toronto, Canada, November 2012.
[MobiSys'12] Pengfei Zhou, Yuanqing Zheng, Mo Li. "Demo - How Long to Wait?: Predicting Bus Arrival Time with Mobile Phone based Participatory Sensing", In ACM MobiSys, Low Wood Bay, United Kingdom, June 2012.

Research Projects

  • Smart Transportation with Mobile Phone based Participatory Sensing
  • People: Pengfei Zhou, Yuanqing Zheng, Mo Li.

    This project monitors real time transportation information and predicts future traffic fluctuation for travellers. It solely relies on the collaborative effort of the participating users and is independent from the commercial transportation operating companies. The significant independence functionality ensures that the systems developed in this project can be easily adopted to support universal transportation service systems without requesting support from particular transportation operating companies or authorities.

    [Bus Arrival Time Prediction] We present a bus arrival time prediction system based on bus passengers' participatory sensing. With commodity mobile phones, the bus passengers' surrounding environmental context is effectively collected and utilized to estimate the bus traveling routes and predict bus arrival time at various bus stops. Instead of referring to GPS enabled location information, we resort to more generally available and energy ecient sensing resources, including cell tower signals, movement statuses, audio recordings, etc., which bring less burden to the participatory party and encourage their participation.
    Try our data collection app on Google Play (Jurong Bus Traffic).


    You can watch the video on youku as well.
    We are currently developing a traffic monitoring system based on the urban bus route systems, where the bus stops are used as landmarks to segment the entire road systems for traffic estimation. The system turns buses into dummy probes, monitors their travel statuses, and derives the instant traffic map of the city. It takes lightweight sensor hints and collects minimum set of cellular data from the bus riders’ mobile phones. Unlike previous works that rely on intrusive detection or full cooperation from “probe vehicles”, our approach resorts to the crowd-participation of ordinary bus riders, who are the information source providers and major consumers of the final traffic output. baner

  • Ambient Environment Sensing for Mobile Applications
  • People: Pengfei Zhou, Yuanqing Zheng, Zhenjiang Li, Mo Li, Microsoft Research.

    Nowadays, location-based and context-ware mobile applications and services have been well developed in many areas. They greatly benefit our lives. This project studies the essential and primitive information, which was assumed to be known in advance before, for upper layer applications and services.

    [Indoor/outdoor Detection] The indoor/outdoor switching provides essential and primitive information for upper layer mobile applications. We present IODetector: a lightweight sensing service which runs on the mobile phone and detects the indoor/outdoor environment in a fast, accurate, and efficient manner. Constrained by the energy budget, IODetector leverages primarily lightweight sensing resources including light sensors, magnetism sensors, celltower signals, etc. For universal applicability, IODetector assumes no prior knowledge (e.g., fingerprints) of the environment and uses only on-board sensors common to mainstream mobile phones.
    Try our demo app for Android phones on Google Play (Indoor/outdoor detection).

    baner

    [Phone Attitude Estimation] The phone attitude gives the 3D orientation of the phone with respect to the earth coordinate system. It is determined by three degrees of freedom, namely Roll, Yaw and Pitch (a.k.a Azimuth). The gyroscope sensor directly measures 3-axis angular velocities and thus removes the 3 degrees of freedom; whereas these 3 degrees of freedom can also be independently eliminated by jointly using the compass (for estimating the geographical north) and the accelerometer (for estimating the gravity direction). Modern smartphones typically integrate all the three sensors, which allows us to choose the best estimates of the 3 degrees of freedom at different moments.

    baner

    Professional Activities

  • Reviewer
  • IEEE/ACM Transactions on Networking
    IEEE Transactions on Parallel and Distributed Systems
    Journal of Pervasive and Mobile Computing
    IEEE INFOCOM 2013, 2014, 2015
    IEEE PerCom 2012
    ACM MobiHoc 2014
    ACM MobiSys 2015

     

    Drupal 6 Appliance - Powered by TurnKey Linux