[home]   [news]   [pubs]   [resume]   [talks]   [service]
Recent news is listed below.


July '16 Our paper 'Sparsifying Deep Learning Layers for Constrained Resource Inference on Wearables' has been (conditionally) accepted to SenSys 2016.
June '16 Our paper 'LEO: Scheduling Sensor Inference Algorithms across Heterogeneous Mobile Processors and Network Resources' has been accepted to MobiCom 2016; a collaboration with the University of Cambridge and Samsung Research.
Our paper 'Engagement-Aware Computing: Modelling User Engagement with Mobile Contexts' has been accepted at UbiComp 2016!
April '16 Our work on deep activity models for smartwatches wins best paper at WristSense 2016!
Mar '16 BodyScan is provisionally accepted at MobiSys! This is part of our new initiative into forms of radio-based sensing for wearables. A sister system (HeadScan) will appear at IPSN in April; pre-print of the HeadScan paper is available here.
Honored to be serving as the PC Chair of HotMobile 2017. I will be working with Elizabeth Belding who will be the General Chair. Stay tuned for more details.
Feb '16 I have accepted a Senior Lecturer (Associate Professor) position at UCL, but will be also maintaining my current role at Bell Labs. At UCL, I will be part of the Digital Health Institute and the UCL Interaction Center.
Pre-prints of two of our recent papers on enabling deep learning for mobile and wearables are now available. "DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices" will appear at IPSN 2016; while "From Smart to Deep: Robust Activity Recognition on Smartwatches using Deep Learning" is to be presented at WristSense 2016.
Jan '16 Two papers provisionally accepted to IPSN '16. The first details unobtrusive monitoring of internal body states (such as, eating and drinking) using a wearable that exploits PHY-level radio transmissions; a first-of-its kind device developed with collaborators at MSU. The second presents DeepX -- a software-based accelerator for deep learning models that enables wearable-class hardware to cope with the deepest forms of this important direction in machine learning.

Oct '15 Initial results of a measurement study examining the system resource overhead of deep learning inference phases on wearables, phones and embedded devices will appear at the IoT-App workshop at SenSys.
Sept '15 DeepEar wins best paper at UbiComp '15! Congrats to all my co-authors.
Aug '15 I am joining the editorial board of ACM SIGMOBILE Mobile Computing and Communications Review, “GetMobile Magazine”; there I will be working with Robin Kravets on a column covering the latest and greatest in mobile computing research.
DeepEar, and our broader work into deep learning for wearable and mobile platforms, is featured in the New Scientist -- 'Eavesdropping app will turn your smartphone into a virtual PA'.
Jul '15 Three papers accepted at UbiComp '15 -- DeepEar, Compressive CrowdSensing and Prime! Very excited about the new ground we are breaking in deep learning for wearables/mobiles, low burden crowdsensing and the bootstrapping collaborative apps. Congrats to my co-authors at Microsoft Research, University of Cambridge, UC Davis, Tsinghua University, UC Santa Barbara, and University of Bologna.
Mar '15 ZOE accepted at MobiSys -- 'ZOE: A Cloud-less Dialog-enabled Continuous Sensing Wearable Exploiting Heterogeneous Computation', collaboration with University of Cambridge and Intel Research.
Happy to be serving on the PC for SenSys 2015. Looking forward to seeing the best in sensing systems in Seoul later in the year. Also Fernando and I (co-PC chairs) want to remind everyone that there are only a few days remaining to submit to Mobiquitous 2015! (Due Date: March 13th.)
Feb '15 'Deep Learning Squeezed Onto a Phone' -- MIT Technology Review has featured our on-going work into deep learning for mobile sensing using wearables and smartphones. Article references our preliminary HotMobile paper; I can't wait to share our latest work once it is public.
I am serving on the PC for two exciting workshops at MobiSys this year: 2nd Workshop on Physical Analytics and Future Mobile User Interfaces. Please consider submitting!
Jan '15 New changes for the new year: I am delighted to be joining Bell Labs as a Principal Scientist. I will be reporting to Fahim Kawsar and shaping the mobile sensing directions of the on-going IoT research activity within the lab.
Two papers accepted into IPSN 2015, the outcome of some of my final projects at MSR: 'Cost-Aware Compressive Sensing for Networked Sensing Systems' and 'SIFT: Building an Internet of Safe Things'. Really love the direction of both these pieces of work.

Dec '14 Our early exploration into applications of deep learning within the mobile sensing domain -- 'Can Deep Learning Revolutionize Mobile Sensing?' -- has been accepted to HotMobile '15.
I'm serving on the PCs of ICWSM '15, UbiComp '15 and DCOSS '15 (mobile sensing track chair). Looking forward to seeing the latest and greatest from the community.
Sept '14 Our UbiComp '14 paper on the Networked Community Behavior framework was nominated for best paper. The conference talk is available on Vimeo here.
I'm serving on the PCs of SECON '15 (group leader), WristSense and WoWMom '15. Please consider these upcoming meetings for latest work!
Aug '14 Our paper 'DSP.Ear: Leveraging Co-Processor Support for Continuous Audio Sensing on Smartphones' has been accepted to SenSys '14 -- joint work with University of Cambridge and Samsung Research.
July '14 Our paper 'Connecting Personal-scale Sensing and Networked Community Behavior to Infer Human Activities' has been accepted to UbiComp '14.
Visited the Intel China Research Center (ICRC) in Beijing. Very impressed by the systems work going on there towards exciting IoT and wearable platforms.
Less than one month until the deadline for MobiCASE 2014. November is a great time to visit Austin, Texas!
June '14 Our paper 'Caiipa: Automated Large-scale Mobile App Testing through Contextual Fuzzing' has been accepted to MobiCom '14.
May '14 I am serving on the TPC for CIKM 2014 and PerCom 2015, please consider submitting!
Gave keynote at PAKDD workshop -- Mobile Sensing, Mining and Visualization for Human Behavior Inference; also managed to visit the great folks at NCTU. Happy to visit Taiwan again.
Feb '14 I am serving on the TPC for Multimedia 2014, please consider submitting!
Jan '14 MoodScope project featured in CACM article -- 'How Do You Feel? Your Computer Knows' -- along with a range of recent advances in affective computing.

Dec '13 Serving as co-TPC chair of MobiCASE '14 (working together with Shivakant Mishra) and on the PC for Mobiquitous '14; please keep both of these upcoming mobile conferences in mind later in the new year!
Nov '13 Attended SenSys '13 in Rome and a brief visit to the University of Cambridge while in England.
Oct '13 I am serving on the TPC for UbiComp 2014 and WoWMoM 2014. Looking forward to seeing the latest breakthroughs from both academica and industry.
Sept '13 Our paper 'Piggyback CrowdSensing (PCS): Energy Efficient Crowdsourcing of Mobile Sensor Data by Exploiting Smartphone App Opportunities' has been accepted to SenSys '13.
I am serving on the TPC for HotMobile 2014 -- please consider submitting your best early stage ideas.
Aug '13 Gave keynote -- "Smartphones, Crowds and the Cloud: Population Guided Sensing Systems" at HotPlanet '13, co-located with SIGCOMM 2013. I love Hong Kong!
July '13 Our paper 'Understanding the Coverage and Scalability of Place-centric CrowdSensing' has been accepted to UbiComp '13.
I co-organized, together with Andrew Campbell, a one-day tutorial on smartphone-based methods for social science as part of the 2013 Summer Institute in Social and Personality Psychology (SISPP '13) at UC Davis.
June '13 Gave invited talk -- "Towards Symbiotic CrowdSensing Systems" at the Third International Workshop on M2M Technology organized by the Intel-NTU Connected Context Computing Center. My first time in Taipei!
May '13 Our paper 'Preference, Context and Communities: A Multi-faceted Approach to Predicting Smartphone App Usage Patterns' has been accepted to ISWC 2013.
Apr '13 I am serving on the TPC for RTSS 2013 and MobiCASE 2013, please consider submitting!
I am co-organizing, together with Mirco Musolesi, the 2nd ACM Workshop on Mobile Systems for Computational Social Science co-located with UbiComp '13. Please consider submitting your recent work in this exciting new field.
Mar '13 Our paper 'Unobtrusive Sleep Monitoring using Smartphones' was accepted to Pervasive Health '13.
Two papers accepted to MobiSys 2013! 'MoodScope: Building a Mood Sensor from Smartphone Usage Patterns' -- joint work with Rice University; and, 'CarSafe App: Alerting Drowsy and Distracted Drivers using Dual Cameras on Smartphones' -- joint work with Dartmouth College.
Jan '13 I will be serving on the TPC for SenSys 2013 and UbiComp 2013, please consider submitting!
I am co-organizing the 3rd International Workshop on Mobile Sensing, this year the focus will be on the intersection of Big Data and Mobile Sensing. Both position papers and technical papers are welcome!


Nov '12 Our paper 'On the Feasibility of User De-Anonymization from Shared Mobile Sensor Data' was presented at PhoneSense '12
Our paper 'The Visage Face Interpretation Engine for Mobile Phone Applications' won best paper at MobiCASE '12.
Sept '12 Our paper 'Automatically Characterizing Places with Opportunistic CrowdSensing using Smartphones' won best paper at UbiComp '12.
I will be serving on the TPC for Mobisys 2013, please consider submitting!
I gave talks at FIT ’12 and Aoyama Gakuin University. My first time to Japan!
Aug '12 I will be serving on the TPC for Pervasive Health 2013, please consider submitting!


Mar '11 Excited to be joining the Mobile and Sensing Systems group at Microsoft Research Asia.