Hoppa till innehållet
Fredrik Sandin
Fredrik Sandin

Fredrik Sandin

Luleå tekniska universitet
Institutionen för system- och rymdteknik
A2304 Luleå


Machine learning and neuromorphic computing for embedded, decentralized and low-power AI in sensor systems, system of systems, IoT, autonomous machines etc. Interested in the physics of brains. More info: Scholar profilesemantic scholar profile.


Current PhD students

Graduated PhD students

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

Past Postdocs


Examiner of

  • Neural networks and learning machines (D7046E), link,
  • Neuromorphic computing, upcoming course in the Applied AI program,
  • Master thesis courses (X7010E, X7011E, X0003E). 

Since 2014, I am program director of the "Teknisk fysik och elektroteknik" program at LTU (Civilingenjör, 300Hp), co-directed with Andreas Almqvist.

Lectures in D0032 Introduction to AI and D0028E Programming and Digitalization. Was examiner for E0003E Electric circuit theory, D0011E Digital design, D0017E Introduction to programming for engineers. Before 2010 I taught courses in physics, in particular first-year courses in mechanics, thermodynamics, waves, optics etc, and also some 3rd cycle lectures in astrophysics, cosmology and quantum field theory.


MSc diploma work in ATLAS at CERN (2001). PhD in Physics (2007, LTU, Swedish Graduate School of Space Technology). First postdoc at IFPA in Belgium (2008-09), focusing on numerical simulations and modelling in theoretical physics. A growing interest for neuromorphic engineering and the physics of brains made me shift research focus. I did a second postdoc in brain-inspired machine learning (2010-11) at EISLAB, where I became assistant professor (until April 2016), associate professor (until March 2021) and presently work as professor. I served as a technical committee member of the SKF–LTU University Technology Center, as a research theme leader of the Intelligent Industrial Processes area of excellence, and as a member of the Applied AI Innovation Hub. I served in faculty workgroups focusing on improving education processes.


Some code and tools. Contact me if you are interested in code used in research articles that are not listed below.

  • 3FCS code, link. This code was developed and used for the quark matter calculations in the papers about neutron stars with quark matter cores and related phase diagrams, including the highly cited paper in Phys. Rev. D.
  • Femtolensing tool, link. Calculates the gravitational lensing signatures of low-mass (1014-1017 kg) compact interstellar objects. This code was developed when working on the preon star hypothesis, see highlights below.
  • N-dimensional random projection code, link. Result of early work on representation learning for cognitive computing.
  • CBVS code, link. Early work on cognitive computing, related publications here and here.
  • Dircheck, link. A useful tool for verification of file archives.
  • Python code for distributed computing over ssh, link.
  • ASOUND Matlab plugin, link.
  • Online collaborative writing in Latex, link. Developed before the time of Sharelatex/Overleaf etc.

Some highlights


Artikel i tidskrift

AI Concepts for System of Systems Dynamic Interoperability (2021)

Nilsson. J, Javed. S, Albertsson. K, Delsing. J, Liwicki. M, Sandin. F
Engineering applications of artificial intelligence
Artikel i tidskrift

Algorithmic performance constraints for wind turbine condition monitoring via convolutional sparse coding with dictionary learning (2021)

Martin-del-Campo. S, Sandin. F, Schnabel. S
Journal of Risk and Reliability, Vol. 235, nr. 4, s. 660-675
Artikel i tidskrift

Dictionary Learning Approach to Monitoring of Wind Turbine Drivetrain Bearings (2021)

Martin-del-Campo. S, Sandin. F, Strömbergsson. D
International Journal of Computational Intelligence Systems, Vol. 14, nr. 1, s. 106-121
Artikel i tidskrift

Impact of training and validation data on the performance of neural network potentials (2021)

A case study on carbon using the CA-9 dataset
Hedman. D, Rothe. T, Johansson. G, Sandin. F, Larsson. J, Miyamoto. Y
Carbon Trends, Vol. 3

Pretraining Image Encoders without Reconstruction via Feature Prediction Loss (2021)

Grund Pihlgren. G, Sandin. F, Liwicki. M
Ingår i: Proceedings of ICPR 2020, 25th International Conference on Pattern Recognition, s. 4105-4111, IEEE, 2021