SIGMOBILE Research Highlights

SIGMOBILE has established a new research highlights selection process. Papers of high quality and broad appeal will be selected from SIGMOBILE sponsored conferences by a committee including SIGMOBILE's major conferences representatives and elected officials. These papers will be recommended for consideration for the Communications of the ACM Research Highlights section and published in ACM GetMobile (if they did not already appear) and on the web.

Current Awardees

  • ACM MobiCom 2016

    Emotion recognition using wireless signals

    Zhao, Mingmin and Adib, Fadel and Katabi, Dina

    This paper demonstrates a new technology that can infer a person's emotions from RF signals reflected off his body. EQ-Radio transmits an RF signal and analyzes its reflections off a person's body to recognize his emotional state (happy, sad, etc.). The key enabler underlying EQ-Radio is a new algorithm for extracting the individual heartbeats from the wireless signal at an accuracy comparable to on-body ECG monitors. The resulting beats are then used to compute emotion-dependent features which feed a machine-learning emotion classifier. We describe the design and implementation of EQ-Radio, and demonstrate through a user study that its emotion recognition accuracy is on par with state-of-the-art emotion recognition systems that require a person to be hooked to an ECG monitor.

  • ACM SenSys 2016

    A Lightweight and Inexpensive In-ear Sensing System For Automatic Whole-night Sleep Stage Monitoring

    Nguyen, Anh and Alqurashi, Raghda and Raghebi, Zohreh and Banaei-Kashani, Farnoush and Halbower, Ann. C and Vu, Tam.

    This paper introduces LIBS, a light-weight and inexpensive wearable sensing system, that can capture electrical activities of human brain, eyes, and facial muscles with two pairs of custom-built flexible electrodes each of which is embedded on an off-the-shelf foam earplug. A supervised non-negative matrix factorization algorithm to adaptively analyze and extract these bioelectrical signals from a single mixed in-ear channel collected by the sensor is also proposed. While LIBS can enable a wide class of low-cost self-care, human computer interaction, and health monitoring applications, we demonstrate its medical potential by developing an autonomous whole-night sleep staging system utilizing LIBS's outputs. We constructed a hardware prototype from off-the-shelf electronic components and used it to conduct 38 hours of sleep studies on 8 participants over a period of 30 days. Our evaluation results show that LIBS can monitor biosignals representing brain activities, eye movements, and muscle contractions with excellent fidelity such that it can be used for sleep stage classification with an average of more than 95% accuracy.

  • ACM MobiSys 2016

    Reactive Control of Autonomous Drones

    Bregu, Endri and Casamassima, Nicola and Cantoni, Daniel and Mottola, Luca and Whitehouse, Kamin

    Aerial drones, ground robots, and aquatic rovers enable mobile applications that no other technology can realize with comparable flexibility and costs. In existing platforms, the low-level control enabling a drone's autonomous movement is currently realized in a time-triggered fashion, which simplifies implementations. In contrast, we conceive a notion of reactive control that supersedes the time-triggered approach by leveraging the characteristics of existing control logic and of the hardware it runs on. Using reactive control, control decisions are taken only upon recognizing the need to, based on observed changes in the navigation sensors. As a result, the rate of execution dynamically adapts to the circumstances. Compared to time-triggered control, this allows us to: i) attain more timely control decisions, ii) improve hardware utilization, iii) lessen the need to over-provision control rates. Based on 260+ hours of real-world experiments using three aerial drones, three different control logic, and three hardware platforms, we demonstrate, for example, up to 41% improvements in control accuracy and up to 22% improvements in flight time.

  • ACM MobiSys 2016

    Practical Human Sensing in the Light

    Li, Tianxing and Liu, Qiang and Zhou, Xia

    We present StarLight, an infrastructure-based sensing system that reuses light emitted from ceiling LED panels to reconstruct fine-grained user skeleton postures continuously in real time. It relies on only a few (e.g., 20) photodiodes placed at optimized locations to passively capture low-level visual clues (light blockage information), with neither cameras capturing sensitive images, nor on-body devices, nor electromagnetic interference. It then aggregates the blockage information of a large number of light rays from LED panels and identifies best-fit 3D skeleton postures. StarLight greatly advances the prior light-based sensing design by dramatically reducing the number of intrusive sensors, overcoming furniture blockage, and supporting user mobility. We build and deploy StarLight in a 3.6 m x 4.8 m office room, with customized 20 LED panels and 20 photodiodes. Experiments show that StarLight achieves 13.6 degree mean angular error for five body joints and reconstructs a mobile skeleton at a high frame rate (40 FPS). StarLight enables a new unobtrusive sensing paradigm to augment today's mobile sensing for continuous and accurate behavioral monitoring.

Committee Members and SIGMOBILE Conferences (2 year term)

  • Chair: Cecilia Mascolo, University of Cambridge
  • Ex Chair (empty)
  • SIGMOBILE EC Chair Suman Banerjee, University of Wisconsin-Madison
  • HotMobile: Romit Roy Choudhury, University of Illinois Urbana-Champaign
  • MobiCom: Heather Zheng, University of California at Santa Barbara
  • MobiHoc: Theodoros Salonidis, IBM Research
  • MobiSys: Landon Cox, Duke University
  • SenSys: Kay Römer, Graz University of Technology
  • UbiComp: Junehwa Song, Korea Advanced Institute of Science and Technology
  • Industry Member: Monisha Ghosh, University of Chicago and Consultant at Cablevision
  • Industry Member: Lama Nachman, Intel Research

Nomination Process and Paper Eligibility

Nominations come from three sources:

  • The SIGMOBILE Research Highlights Committee, working closely with the program chairs from the conferences they represent, will review and nominate papers from the SIGMOBILE conferences for consideration by the full committee.
  • Best paper nominees are nominated by default.
  • Any SIGMOBILE member may nominate a paper appearing in a SIGMOBILE conference. Authors may not nominate their own papers. Nominations can be made by emailing title, authors, conference and year of publication to the contact at the bottom of this page.

All papers published in the covered conference within the previous half year will be considered by the committee. Papers published in conferences not in the above list are also eligible for consideration, but the committee does not take responsibility for proactively considering these venues. Community members may ask the committee to consider papers from such venues through the community nomination process, described below.

Community Candidates

Community members not on the committee may ask for papers to be considered by submitting to the committee chair a nominating proposal. Such a proposal must summarize the contribution of the paper and explain why the paper is suitable for inclusion in the SIGMOBILE Highlights series. Such a nominating proposal should be no more than a page in length. Periodic reminders of nominating deadlines will be sent to the SIGMOBILE mailing list.

Deadlines for Nomination

  • First Deadline: 31st August each year for papers published in HotMobile, Mobihoc, and Mobisys.
  • Second Deadline: 28th February each year for papers published in Mobicom, Sensys, Ubicomp.

Committee Candidates

Each of the members of the committee covering a particular conference will be responsible for reviewing the papers for that it in consultation with others from that community. We anticipate that this committee member will at least contact the program chair for the relevant conference and ask the chair to suggest one or two papers for consideration. We encourage the program chair to solicit input from members of the program committee. The committee member will then bring potential papers to the committee for a discussion.

Best Paper Candidates

All best papers at conferences in that half year will automatically be considered candidates.

Selection Process

The full committee (minus people with conflicts of interest) will discuss via email the candidate papers, both those arising from the committee, best paper candidates and from any community candidates. The committee will meet electronically twice a year in early September and in early March.

The committee may solicit input from outside experts on the merits of any candidate papers. The committee will select for nomination papers taking into consideration technical quality, the ability to summarize the results in an 8 page paper, and the likely interest from computer scientists in other areas. For each paper nominated, the committee will send to the CACM:

  • a copy of the paper
  • a description of why the paper merits publication in SIGMOBILE Highlights (1/2 page)
  • a list of possible people to write the Technical Perspective
  • consent to the nomination from the authors and prospective technical perspective writers

Conflicts of interest

Committee members may not nominate their own papers for consideration. Committee members may not participate in the discussion of whether one of their papers may be nominated to SIGMOBILE Highlights. Other conflicts of interest should be disclosed to the committee chair, who will decide how to handle such conflicts. A committee member may decide to recuse him or herself from the discussion of any paper for reasons of conflict of interest. Papers by committee members may be nominated by the community nomination process.