Vahid Moosavi

Post Doc. Researcher.

https://vahidmoosavi.com/

 

Research Agenda

Machine Learning and Big Data together offer a universal way of looking at the world phenomena, which is radically different than the classical expert based disciplinary research.

This new approach of computational modeling has inverted the classical notion of expertise from “having the answers to the known questions” to “learning to ask good questions”, where the answers can always be found with an appropriate level of modeling skills.

Short Biography

I finished my PhD thesis at the Chair for Computer Aided Architectural Design (CAAD), ETH Zurich by the end of April 2015. Here, you can take a look at my final PhD presentation. link
From November 2011-April 2015 I worked as a researcher in Singapore-ETH lab, Future Cities Laboratory.

Previously, I studied in Iran and received my B.S and M.S degrees in industrial and systems engineering from Isfahan University of Technology and Tehran Polytechnic respectively.

From May 2015, I am a senior researcher at the chair for Computer Aided Architectural Design (CAAD), ETH Zurich.

Research Interests

In general, I am fan of data driven modeling, but the main question is that what are the appropriate (new) methods for dealing with this new forms of data (usually unstructured and Big). In this regard, I am interested in the following research directions:

  • Representation and Encoding in the context of system modeling.
  • Unsupervised learning and specially Self Organizing Maps for dimensionality reduction and multivariate probability estimations.
  • Representation Learning with Deep Neural Networks
  • Invariances in random processes and Markov Chains
  • Function approximation and manifold learning methods

Further, as I am originally a systems engineer I have been always dreaming about finding unity through diversity of different application domains. Therefore, I have been always eager to be engaged in as diverse as possible fields of applied problems. So far I have experienced several specific problems in the following domains:

  • Spatio-Temporal Modeling:
    • Study of urban forms at the global scale: More than 1 million locations across the globe (link)
    • Data driven air pollution level estimation at the global scale
    • Fast and scalable urban flood risk emulation
    • Real estate market dynamics
    • Urban traffic modeling
    • Urban air pollution estimation
    • Urban economy and business activity level estimation
  •  Networked based economics and systemic risk
  • Applied Natural Language Modeling
    • Training financial time series models along with the news time series
    • Developing smart personalized news papers using news API data streams
  • Financial time series forecasting

Teaching

Data Driven Modeling: TECHNICAL SEMINAR SERIES ON THE MAIN CONCEPTS AND METHODS IN PROBABILITY THEORY, STATISTICS, OPTIMIZATION, LINEAR ALGEBRA AND MACHINE LEARNING THEORY TOWARD A FRAMEWORK FOR DATA LITERACY

Publications and Projects

  1. Vahid, Moosavi, Urban Morphology Meets Big Data And Representation Learning: An Investigation of Several Thousands of City Patterns Across the World, ISUF 2017 XXIV international conference: City and territory in the globalization age.
  2. Vahid Moosavi, Urban Data Streams and Machine Learning: A Case of Swiss Real Estate Market. arXiv preprint arXiv:1704.04979 (2017).
  3.  Vahid Moosavi,  “A Markovian Model of the Evolving World Input-Output Network.” arXiv preprint arXiv:1612.06186 (2016) (Under Review at PLOSONE).
  4. Diana Alvarez-Marin, Vahid Moosavi, Inverting Normative City Theories and Computational Urban Models: Towards a Coexistence With Urban Data Streams, (Under review at the journal of City)
  5. Vahid Moosavi, Contextual Mapping: Visualization of High Dimensional Spatial Patterns in a Single Geo-Map, (Computers, Environment and Urban Systems 61 (2017) 1–12). (link)
  6. Vahid Moosavi, Pre-Specific Modeling. Diss. Diss., Eidgenössische Technische Hochschule ETH Zürich, Nr. 22683, 2015. (link)
  7. (Edited Book) Ludger Hovestadt, Vera Buhlman, Vahid Moosavi, “Coding as Literacy: Self Organizing Maps”, Applied Virtuality Series, Birkhäuser: Vienna, 2015. (link)
  8. Vahid Moosavi, Gideon Aschwanden and Erik Velasco,” Finding candidate locations for aerosol pollution monitoring at street level using a data-driven methodology”, the journal of Atmospheric Measurement Techniques 8, 3563-3575, 2015. (link) and (link to poster)
  9. Vahid Moosavi, “Computational Urban Modeling: From Mainframes to Data Streams”, presented at AI for Cities Workshop in AAAI conference, Austin Texas 2015.
  10. Vahid, Moosavi, “Grand Technologies for Grand Energy Challenges: A Futuristic Scenario for Solar Energy in the Age of Information” (working paper) (link)
  11. Vahid, Moosavi, Computing With Contextual Numbers. arXiv preprint arXiv:1408.0889. (2014). (link)
  12. Vahid, Moosavi, “Beyond Rational Modeling”, 22nd Biennial European Meeting on Cybernetics and Systems Research, Vienna, 2014. (link)
  13. Vahid, Moosavi and Ludger Hovestadt. “Modeling urban traffic dynamics in coexistence with urban data streams.” Proceedings of the 2nd ACM SIGKDD International Workshop on Urban Computing. ACM, 2013. (link)
  14. Mathias Standfest and Vahid Moosavi, “Pre-Specific Modeling: Fuzzy Modeling and SOM”, Design Modeling Symposium, Berlin, Germany, 2013
  15. Vahid, Moosavi and Stephen Cairns, “Mapping Thematic Research Interests at Future Cities Laboratory (FCL), Singapore-ETH Centre (SEC): Self-Organizing Maps (SOMs)” (working paper) (link)
  16. Vahid Moosavi and Rongjun Qin, A New Automated Hierarchical Clustering Algorithm Based On Emergent Self Organizing Maps (ESOMs). iV2012- 16th International Conference Information Visualisation, LIRMM CNRS Univ. Montpellier II ,Montpellier, France, 10-13 July 2012. (link)
  17. Abbas Seifi,  Vahid Moosavi & Ehsan Ardestani : A Conceptual Framework for Evaluating New Business Opportunities for Corporate Diversification, Journal of Enterprise Transformation, 2:2, 105-129, 2012. (link)
  18. Mohammad Hossein Fazel Zarandi, Vahid Moosavi and Marzieh Zarinbal, ”A fuzzy reinforcement learning algorithm for inventory control in supply chains” , “The International Journal of Advanced Manufacturing Technology”, Vol.- , NO.0 , PP.0 _ 0 , 21 April 2012 (link)
  19. Mohamad Saraee,  Vahid Moosavi and Shabnam Rezapour, “Application Of Self Organizing Map (SOM) To Model A Machining Process”, Journal of Manufacturing Technology Management, Vol. 22 Iss: 6, pp.818 – 830, 2011. (link)
  20. Vahid Moosavi and Mahdi. Noorizadegan, Export Clusters in: Supply Chain And Logistics In International, National And Governmental Environments, Reza Zanjirani Farahani, Nasrin Asgari and Hoda Davarzani (Eds.), Springer-Verlag, Heidelberg 2009. link
  21. Morteza Zamanian, Vahid Moosavi and K. Kianfar, Multi Objective Facility Location, in: Facility location, R. Zanjirani Farahani (Ed.), AUT press, Tehran, Iran, winter 2007 (Persian)
  22. Vahid Moosavi, Enayatallah Moallemi, Abbas Seifi (2010) “Toward an alignment model between process maturity and business process management in the enterprise”, submitted to first international conference on business process management, Iran, Tehran, Spring 2010 (in Persian).
  23. Vahid Moosavi, Reza Jazemi and Abbas Seifi. (2010). “BPR in the physical resource management department of health ministry of Iran”, submitted to first international conference on business process management, Iran, Tehran, Spring 2010 (in Persian).

Presentations and Invited Talks

  1. Machine Intelligence Summit, Amsterdam, June 2017
  2. TU Vienna, March 2017
  3. PyData Zurich February 2017
  4. Pre-Specific Modeling – Computational Machines in Coexistence with Urban Data Streams, PhD Thesis Presentation at ETH Zurich 2015.
  5. Big Data and Urban Modeling Applications, SAP Singapore 2013
  6. Data Driven Modeling Beyond Idealization, Presented at METALITHICUM COLLOQUY #5 CODING AS LITERACY: SELF ORGANIZING MAPS
  7. Modeling in Coexistence with Data: Toward a Generic Notion of Space
    Presented at Future Cities Lab, ETH- Singapore Centre.
    Transition workshop 20150408
  8. Finding Candidate Locations for Aerosol Pollution Monitoring at Street Level Using a Data-Driven Methodology
    Presented at MIT CENSAM Workshop on June 2014 as a part of collaborative project between ETH and MIT in Singapore: Air pollution at street levelRelated publication
  9. Markovian Modeling of Urban Traffic Flows in Coexistence With Urban Data Streams,  Related Publication
  10. Toward of a Theory of Modeling
  11.  Toward of a Theory of Modeling
  12. System identification and Surrogate Modeling
  13. https://prezi.com/kvduedlai8dw/moving-singapore-maps/

Past and On Going Projects

An updated list can be found here

Github Repo

Email: svm@arch.ethz.ch