VU Logo
Go to the homepage of the Vrije Universiteit. Goto the homepage of the Faculty of Sciences. Goto the homepage of the Department of Computer Science.

My photo

Claudio Martella

(Former) Ph.D. student, Large-scale Distributed Systems Group

Dept. of Computer Science
VU University Amsterdam
De Boelelaan 1081A, Room W&N-P430
1081 HV Amsterdam
The Netherlands

E-mail: claudio [dot] martella [at] vu [dot] nl

Short bio | Research Interests | Publications | Presentations | Teaching | Projects

Short bio

In December 2011, I joined the Large-scale Distributed Systems Group , Dept. of Computer Science at VU University Amsterdam as a PhD student, under the supervision of Prof. Maarten van Steen.
Previously, I was Analyst at TIS Innovation Park where I worked on scaling Enterprise 2.0 solutions to big intranet datasets with Hadoop. For my M.Sc., I visited the Laboratory of Autonomous Robotics and Artificial Life at the National Research Council in Rome, where I worked on Adaptation in Embodied and Situated Agents.
I hold a B.Sc. in Computer Science and a M.Sc. in Intelligent Systems, both obtained at the Universita degli Studi di Milano.
In February 2017, I have succesfully defended my Ph.D. dissertation "Crowd Textures: from Sensing Proximity to Understanding Crowd Behavior". Since then, I have joined the Geo/Location team at Google as a Software Engineer.

Research Interests

My research interests span from modeling social behavior to large-scale processing of data. The work related to my Ph.D. research is within the Extreme Wireless Distributed Systems project. The EWiDS project focuses on devising (decentralized) solutions for the construction and deployment of large-scale wireless (sensor) systems.
Our central research question is how to devise a large-scale collaborative network of highly mobile, miniaturized, wireless devices collecting, disseminating, aggregating, and processing information to provide instant feedback to its users for the purpose of maintaining their safety and comfort.
In particular, my main area of interest within the project relates to how we can model crowd behavior throgh spatio-temporal proximity information. In particular, I follow the approach of measuring spatio-temporal proximity data through radio-based proximity sensors (not too unlike BLE transcievers in modern smartphones and beacons), and representing it through so-called proximity graphs. Once the data is collected and represented through a spatio-temporal graph, crowd behavioral analysis boils down to data/graph mining algorithms to identify, quantify, and qualify the crowd behavior of interest.



  • "Apache Giraph: Distributed Graph Processing on Hadoop." C. Martella (2014) Presentation at Hadoop Summit 2014.

  • "Apache Giraph: Distributed Graph Processing in the Cloud." C. Martella (2012) Presentation at FOSDEM 2012.

  • "Hadoop: A Hands-on Introduction." E. Bruni and C. Martella (2011) Presentation at CLIC-CIMEC, University of Trento 2011.

  • "NoSQL with Graphs: mining graphs for fun and profit." C. Martella (2011) Tech Talk at NoSQLDay 2011.

  • "TCP/IP Implementation: an overview of the implementation of the TCP/IP stack in the Linux kernel and the subsystem architecture." C. Martella (2002) Tech Talk at Hackmeeting02.

Program Commitee

  • 11th IEEE International Conference on Services Computing (SCC) 2014

  • 5th IEEE International Conference on Cloud Computing Technology and Science (CloudCom) 2013


In my night-life, I'm member of the Apache Giraph project as PPMC member and committer. Giraph is an open source implementation of the distributed graph processing framework Pregel by Google.
You can find my code on my github.
If you're interested, you can follow me on twitter: @claudiomartella.
If you care, I also write about my work, but not only, on my blog.

I am also co-author of the book Practical Graph Analytics with Apache Giraph, which is published by Apress. The book teaches you how to apply the Apache Giraph programming model to real-world graph data examples. The book starts by showing you how to mine graph data using the most straightforward algorithms. Then, you'll dive into the Giraph architecture and the main APIs as you discover how to model and process more complex scenarios. Along the way, you'll pick up techniques for handling data from disparate sources, swapping data in and out of memory, and running Giraph in the cloud.


  • Introduction to Computer Science 2012/13 - Instructor