Fredrik Sandin
Fredrik Sandin

Fredrik Sandin

Associate Professor
Luleå University of Technology
Industrial Electronics
Embedded Internet Systems Lab
Department of Computer Science, Electrical and Space Engineering
+46 (0)920 493163
A2304 Luleå


I'm an Associate Professor performing research in the domain of applied machine learning and edge computing since 2010 at the Department of Computer Science, Electrical and Space Engineering. I currently work on projects related to:

  • Machine learning for condition monitoring.
  • Machine learning for automation of construction equipment.
  • Machine learning for system interoperability in IIoT and Industry 4.0.
  • Neuromorphic system for sub-milliwatt pattern recognition.
  • Machine learning for automation of edge datacenters.
  • Machine learning for fast approximation of carbon nanomaterial properties.
  • Machine learning for high-quality steel manufacturing.

Before 2010 I did my PhD in physics in the Swedish Graduate School of Space Technology and a two-year postdoc at IFPA in Belgium, both focusing on the physics and phenomenology of high-density states of matter in compact objects, link. My curiosity for the physics of the mind, the function of neural networks and neuromorphic engineering motivated me to shift research focus and contribute to the development of AI. Link to scholar profile.


I am the examiner of the following courses:

  • Electric circuit theory (E0003E), link.
  • Introduction to programming for engineers (D0017E), link.
  • Neural networks and learning machines (D7046E), link.

Since 2014, I coordinate the Engineering Physics and Electrical Engineering program at LTU (MSc / Civilingenjör, 300 credits). Before 2010 I taught several courses in physics.


Current PhD students

  • Jacob Nilsson, machine learning for M2M interoperability in the Arrowhead Framework.
  • Mattias Nilsson, architecture for low-power pattern recognition with DYNAP neuromorphic system.
  • Kim Albertsson (at CERN), machine learning in high-energy physics.
  • Rickard Brännvall (at RISE), machine learning for automation of datacenters, AutoDC.
  • Co-supervision of Gustav Grund Pihlgren and Muhammad Ahmer.

Current Postdocs

  • Sergio Martin del Campo Barraza, machine learning for automation of wind turbine condition monitoring system.

Graduated PhD students

  • Siddharth Dadhich, Automation of Wheel-Loaders, link.
  • Sergio Martin del Campo Barraza, Unsupervised feature learning applied to condition monitoring, link.
  • Blerim Emruli, Ubiquitous Cognitive Computing: A Vector Symbolic Approach, link.


Article in journal

Detection of particle contaminants in rolling element bearings with unsupervised acoustic emission feature learning (2019)

Martin del Campo Barraza. S, Schnabel. S, Sandin. F, Marklund. P
Tribology International, ISSN: 0301-679X, Vol. 132, s. 30-38
Article in journal

Field test of neural-network based automatic bucket-filling algorithm for wheel-loaders (2019)

Dadhich. S, Sandin. F, Bodin. U, Andersson. U, Martinsson. T
Automation in Construction, ISSN: 0926-5805, Vol. 97, s. 1-12
Data set

Dataset concerning the vibration signals from wind turbines in northern Sweden (2018)

Martin del Campo Barraza. S, Sandin. F, Strömbergsson. D
Article in journal

From Tele-remote Operation to Semi-automated Wheel-loader (2018)

Dadhich. S, Bodin. U, Sandin. F, Andersson. U
International Journal of Electrical and Electronic Engineering and Telecommunications, ISSN: 2319-2518, Vol. 7, nr. 4, s. 178-182
Conference paper

Predicting bucket-filling control actions of a wheel-loader operator using aneural network ensemble (2018)

Dadhich. S, Sandin. F, Bodin. U
Part of: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, 2018, 8489388