About me

I am a PhD Student in the Networks and Operating Systems Research Group, under the supervision of Professor Cecilia Mascolo. I am funded by Microsoft Research through their PhD Scholarship Programme. I am a member of Corpus Christi College.

My research lies at the intersection of mobile sensing, ubiquitous computing and machine learning. In particular, I am interested in how context monitoring and sensor-based applications can be made to co-exist on co-processor enabled mobile devices in an energy friendly manner. Recent mobile devices boast a range of heterogeneous processors such as the Qualcomm Hexagon DSP or Adreno GPU with the aim to lower the energy barrier for a variety of application domains including multimedia and sensor processing. In my research, I investigate how such heterogeneous computational elements can be fully leveraged to maximize the energy efficiency of multiple interacting microphone-based (e.g., speech recognition) or accelerometer-based (e.g, activity recognition) mobile applications. In addition, I explore ways to maximize the efficiency of sensor processing via deep learning techniques.

Highlights

MobiCom 2016 travel award

Best paper award at Ubicomp'15!

Best presentation award at MobiSys'15 PhD forum in Florence!

HotMobile'15 paper featured in MIT Tech Review!

ICWSM'14 paper @ MIT Technology Review!

LEO: Scheduling Sensor Inference Algorithms across Heterogeneous Mobile Processors and Network Resources.

Petko Georgiev, Nicholas D. Lane, Kiran K. Rachuri, Cecilia Mascolo.

In Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking (MobiCom16). New York, NY, USA. October 2016. [pdf]

DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices

Nicholas D. Lane, Sourav Bhattacharya, Petko Georgiev, Claudio Forlivesi, Lei Jiao, Lorena Qendro, Fahim Kawsar.

In Proceedings of the 15th International Conference on Information Processing in Sensor Networks (IPSN '16). April 2016. [pdf]

An Early Resource Characterization of Deep Learning on Wearables, Smartphones and Internet-of-Things Devices

Nicholas D. Lane, Sourav Bhattacharya, Petko Georgiev, Claudio Forlivesi, Fahim Kawsar.

In Proceedings of the 2015 International Workshop on Internet of Things towards Applications (IoT-App'15). November 2015. [pdf]

DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning

Nicholas D. Lane, Petko Georgiev, Lorena Qendro.

In Proceedings of the 17th International Conference on Ubiquitous Computing (UbiComp '15). Osaka, Japan. September 2015. [pdf]

Best Paper Award

ZOE: A Cloud-less Dialog-enabled Continuous Sensing Wearable Exploiting Heterogeneous Computation

Nicholas D. Lane, Petko Georgiev, Cecilia Mascolo, Ying Gao.

In Proceedings of the 13th ACM Conference on Mobile Systems, Applications, and Services (MobiSys '15). Florence, Italy. May 2015. [pdf]

Can Deep Learning Revolutionize Mobile Sensing?

Nicholas D. Lane and Petko Georgiev.

In Proceedings of the ACM International Workshop on Mobile Computing Systems and Applications (HotMobile 2015). Santa Fe, New Mexico, USA. February 2015. [pdf]

DSP.Ear: Leveraging Co-Processor Support for Continuous Audio Sensing on Smartphones.

Petko Georgiev, Nicholas D. Lane, Kiran K. Rachuri, Cecilia Mascolo.

In Proceedings of the ACM International Conference on Embedded Networked Sensor Systems (SenSys 2014). Memphis, Tennessee, USA. November 2014. [ArXiv]

Where Businesses Thrive: Predicting the Impact of the Olympic Games on Local Retailers through Location-based Services Data.

Petko Georgiev, Anastasios Noulas, Cecilia Mascolo.

In Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media (ICWSM 2014). Ann Arbor, Michigan, USA, June 2014. [ArXiv]

The Call of the Crowd: Event Participation in Location-based Social Services.

Petko Georgiev, Anastasios Noulas, Cecilia Mascolo.

In Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media (ICWSM 2014). Ann Arbor, Michigan, USA, June 2014. [ArXiv]

In the academic year 2014-2015 I was a ticker for the Part IA Java practical classes.

In the academic years 2014-2015, 2013-2014 I supervised the Part II course Mobile and Sensor Systems.

In the academic years 2014-2015, 2013-2014 I led the tutorial on social network analysis with Python for the Part III/MPhil course Social and Technological Network Analysis.

Address

Office FN01
Computer Laboratory, University of Cambridge
William Gates Building
15 JJ Thompson Avenue
Cambridge CB3 0FD

E-mail

petko.georgiev@cl.cam.ac.uk

Connect