Alexei Pozdnoukhov

Photograph of Alexei Pozdnoukhov

Assistant Professor
Signatures Innovation Fellow
Director,
Smart Cities Research Center

115 McLaughlin Hall
CEE, Systems and Transportation
UC Berkeley, CA 94720

Phone: +1 510 984 8696
Email:
alexeip@berkeley.edu



Alexei holds a Ph.D. in computer science from EPFL, Switzerland, following his research in machine learning methods and computer vision that he carried out at IDIAP Research Institute in Martigny, Switzerland. He then worked on remote sensing and spatial data mining at the University of Lausanne (UNIL). Most recently, he held a position of a Science Foundation Ireland (SFI) Stokes Lecturer with the National Centre for Geocomputation (NCG).

Research areas:machine learning, spatial data mining, computational social science, urban mobility, smart cities



Fall 2016 CE88: Data Science for Smart Cities. M 12-2pm, Dwinelle 219. This is a 2 unit connector to the Foundations of Data Science, data8.org. There are no formal pre-requisites so you can also take it independently of Data8 (backgorund of junior/senior standing in any engineering major helps). Don't forget to enroll in all 3 components (Lecture, Lab, Discussion) in tele-bears.


Fall 2016 CE263N: Scalable Spatial Analytics. Here is a sample course syllabus.



Current Projects:

SmartBay SmartBay: Connected Mobility in the San Francisco Bay Area. Activity-based travel demand modelling from cellular data,
in collaboration with AT&T Research.

Demand forecasting and route inference, a.k.a. The MegaCell team of the Connected Corridors, with PI Prof Alexandre Bayen

NASA NextGen CTD Research. Similar Historical Days and Air Traffic Flow Management Response Strategies, with PI Prof Mark Hansen.

CITRIS seed project. Optimal Design of Smart Urban Crowd-Sensing, with Prof Shawn Newsam

NSF CRISP: Multi-scale Infrastructure Interactions with Intermittent Disruptions: Coastal Flood Protection, Transportation and Governance Networks, with PI Prof Mark Stacey and Prof Samer Madanat



2015

LBSN'15: ACM SIGSPATIAL Location-Based Social Networks workshop.

BayLearn'15: Bay Area Machine Learning Symposium is on 22nd of October 2015. Registration opens late September and closes October 9th.




Papers

Hegde V., Krnjajic M., Pozdnoukhov A., Unsupervised Event Detection with an Infinite Poisson Mixture Model. IEEE BigData Congress, 2015

Pozdnoukhov, A., Campbell, A., Feygin, S., Yin, M., and Mohanty, S., The SmartBay Project: Connected Mobility in the San Francisco Bay Area. In The Multi-Agent Transport Simulation: MATSim, edited by Horni, A., Nagel, K., and Axhausen, K., 2015, in press.

Wu C., Yadlowsky S., Thai J., Pozdnoukhov A., Bayen A., Cellpath: fusion of cellular and traffic sensor data for route flow estimation via convex optimization. Int Symp on Transportation and Traffic Theory (ISTTT) and Transportation Research: Part B, 2015, to appear. [PDF - route inference]

Yadlowsky S., Thai J., Wu C., Pozdnoukhov A., Bayen A., Link Density Inference from Cellular Infrastructure. Transportation Research Board (TRB) 94th Anuual Annual Meeting, Transportation Research Record (TRR), 2015 PDF [PDF - traffic density]



Recent papers, PDF - recommended to my students

Coffey C., Pozdnoukhov A., Temporal Decomposition and Semantic Enrichment of Mobility Flows, LBSN'13 at 21st ACM SIGSPATIAL GIS'2013, 2013 PDF  Bib [PDF - mobility analytics, trip purpose]

Tarasov A., Kling F., Pozdnoukhov A., Prediction of User Location Using the Radiation Model and Social Check-ins, UrbComp'13 at ACM SIGKDD, 2013 PDF  Bib

McArdle G., Furey E., Lawlor A., Pozdnoukhov A., Using Digital Footprints for a City-scale Traffic Simulation, ACM TIST. 2013 PDF

Kaiser C., Pozdnoukhov A., Enabling Real-time City Sensing with Kernel Stream Oracles and MapReduce, Pervasive and Mobile Computing, Volume 7, Issue 5, pp 708-721. 2013 PDF  Bib

M. Batty, K. W. Axhausen, F. Giannotti, A. Pozdnoukhov, A. Bazzani, M. Wachowicz, G. Ouzounis, Y. Portugali. Smart Cities of the Future. The European Physical Journal Special Topics, Volume 214, Issue 1, pp 481-518. 2012 PDF  Bib

Kling F., Pozdnoukhov A., When a City Tells a Story: Urban Topic Analysis, In proc of the 20th ACM SIGSPATIAL GIS, 2012 PDF (Best Poster Award runner up). [PDF - urban dynamics, functional areas]

Tuia, D., Pozdnoukhov, A., Foresti, L. and Kanevski, M. Active Learning for Monitoring Network Optimization, In Spatio-Temporal Design: Advances in Efficient Data Acquisition (eds J. Mateu and W. G. Mueller), John Wiley & Sons. 2012 PDF  Bib

McArdle G., Furey E., Lawlor A., Pozdnoukhov A., City-scale Traffic Simulation From Digital Footprints, UrbComp'12 at ACM SIGKDD, 2012 PDF  Bib [PDF - mobility, agent-based]

Coffey C., Nair R., Pinelli F., Pozdnoukhov A., Calabrese F. Missed Connections: Quantifying and Optimizing Multimodal Interconnectivity in Cities. IWCTS of the 20th ACM SIGSPATIAL GIS, 2012 PDF

McGrath R., Coffey C., Pozdnoukhov A., Habitualisation: localisation without location data, Nokia MDC challenge at PERVASIVE'2012, 2012 PDF

Lawlor A., Coffey C., McGrath R., Pozdnoukhov A., Stratification structure of urban habitats, Pervasive Urban Apps at PERVASIVE'2012, 2012 PDF

Foresti L., Kanevski M., Pozdnoukhov A. Kernel-based Mapping of Orographic Rainfall Enhancement in the Swiss Alps as Detected by Weather Radar. IEEE Transactions on Geoscience and Remote Sensing, Issue 99, pp 1-14 2012. PDF  Bib

Farmer C., Pozdnoukhov A., Building streaming GIScience from context, theory, and intelligence. Position paper, Big Data Age workshop at GIScience'2012 (our manifesto to GIScience), 2012 PDF

Tuia D., Joost S., Pozdnoukhov A. Active multiple kernel learning of wind power resources, Machine Learning for Sustainability at NIPS'11, 2011 PDF

Pozdnoukhov A., Kaiser C. Scalable Local Regression for Spatial Analytics, Proc of the 19th ACM SIGSPATIAL GIS'2011, 2011 Long paper: PDF  Bib [PDF - locally linear, streaming]

Pozdnoukhov A., Kaiser C. Space-Time Dynamics of Topics in Streaming Text, LBSN at 19th ACM SIGSPATIAL GIS'2011, 2011 PDF  Bib (Best Paper Award). [PDF - LDA and MMPP]

Pozdnoukhov A., Kaiser C. Area-to-point Kernel Regression on Streaming Data, Geostreaming at 19th ACM SIGSPATIAL GIS'2011, 2011 PDF  Bib

Coffey C., Pozdnoukhov A., Calabrese F. Time of Arrival Predictability Horizons for Public Bus Routes, Computational Transportation Science workshop at 19th ACM SIGSPATIAL GIS'2011, 2011 PDF  Bib

Walsh F., Pozdnoukhov A., Spatial structure and dynamics of urban communities, Pervasive Urban Applications at PERVASIVE'2011, 2011 PDF  Bib

Pozdnoukhov, A., Matasci, G., Kanevski, M., and Purves, R.S. Spatio-temporal avalanche forecasting with Support Vector Machines. Nat. Hazards Earth Syst. Sci., 11, 367-382, 2011. PDF  Bib

Foresti L., Pozdnoukhov A. Exploration of alpine orographic precipitation patterns with radar image processing and clustering techniques. Meteorological Applications, John Wiley & Sons, DOI 10.1002/met.272, 2011. PDF  Bib

Foresti L., Tuia D., Kanevski M. and Pozdnoukhov A. Learning wind fields with multiple kernels. Stochastic Environmental Research and Risk Assessment, Volume 25, Number 1, pp. 51-66, 2011 PDF Icon  Bib

Pozdnoukhov A., Spatial extensions to kernel methods, Proc. of the 18th ACM SIGSPATIAL GIS (short paper), 2010 PDF  Bib

Pozdnoukhov A., Walsh F., Exploratory Novelty Identification in Human Activity Data Streams, ACM SIGSPATIAL International Workshop on GeoStreaming at 18th ACM SIGSPATIAL GIS, 2010 PDF Icon  Bib

Pozdnoukhov A., Walsh F., Kaiser F., Statistical Machine Learning from VGI, Position paper at Role of Volunteered Geographic Information in Advancing Science Workshop at GIScience'10, 2010.

Kaiser C., Walsh F., Farmer C. and Pozdnoukhov A., User-centric time-distance representation of road networks. In Springer LNCS proc. of the GIScience'10 (full paper). 2010 PDF Icon  Bib

Tuia D., Ratle F., Pozdnoukhov A., Camps-Valls G. Multisource Composite Kernels for Urban-Image Classification. IEEE Geoscience and Remote Sensing Letters, Volume 7, Number 1, pp. 88-92, 2010. PDF Icon  Bib

Pozdnoukhov A., Dynamic network data exploration through semi-supervised functional embedding. In Proc of the 17th ACM SIGSPATIAL GIS, 2009 PDF Icon  Bib [PDF - deep learning]


Pozdnoukhov A., Bengio S. From Samples to Objects: Invariances in Kernel Methods. Pattern Recognition Letters Journal, Volume 27, Issue 10, pp. 1087-1097. 2006.






Previous projects:

RFP SFI Research Frontiers Programme: Learning Human Spatial Dynamics. Principle Investigator, (2011-2015).
Stokes and StratAG SRC SFI StratAG: Strategic Research Cluster in Advanced Geotechnologies. Co-PI, Scalable Statistical Learning project lead, Coordinator of the City-Scale Demonstrator (2011-2013).
GMorphs GMorphs: Contextual morphing of GMaps (Google Research Award 2010). Principle Investigator.
IBM Supervisor, an IBM PhD Fellowship Award to Cathal Coffey.
Data Analytics for Smarter Driving (Scalable Data Analytics Award 2010). Co-PI with PI Tim McCarthy.
COSMIC COSMIC: Complexity in Spatial Dynamics (ERA-NET on Complexity). Co-investigator with CASA-UCL (M. Batty), VU Amsterdam (P. Nijkamp), and University of St.Andrews (S. Fotheringham) (2010-2012).
Geocrowd Marie-Curie ITN Geocrowd: Creating Geospatial Knowledge World. Scientist in charge at NUIM (2011-2014).




Media:

A micro-simulation of road traffic in Greater Dublin region for a typical weekday. The model is calibrated from census travel surveys as well as social media data and takes into account the geography of community structure of the city. It is described in detail in an upcoming paper PDF Icon.

Dynamic mapping of GSM and 3G mobile phones usage reveal interesting patterns of user's activity. This heatmap is computed with a geographically weighted kernel density estimate with a temporal resolution of 15 minutes. So enjoy one week of Irish life as seen by a mobile phone network!

There are also methods both in spatial statistics and machine learning to downscale population densities to the street level from areal support data which is common to non-pervasive sensing infrastructures PDF Icon.


Book:

Machine Learning for Spatial Environmental Data Kanevski M., Pozdnoukhov A., Timonin V. Machine Learning Algorithms for Geospatial Data. Theory, Applications and Software. 377pp. EPFL press, 2009. Link