Background and activities
Harald Martens (1946) is Adjunct Professor at the Department of Engineering Cybernetics. He is a member of the research group for Cybernetics in Biomedicine. Martens has an MSc in industrial biochemistry and a Dr.techn in chemometrics and multivariate calibration from NTNU. He has written over two hundred research papers and several books on multivariate data modelling, which in total have been cited over 17 900 times (2017).
- Adjunct Professor, Dept. of Engineering Cybernetics, NTNU
- Research leader in IDLETechs AS (quantitative, interpretable analysis of Big Data)
Previous academic positions
- Guest researcher Makerere U, Uganda (3 months)
- Kyoto University, Japan (1 year)
- Lund University, Sweden (1 year)
- UC Davies, California, USA (1 year)
- Guest professor, Biocentrum DTU, Denmark (5 years)
- Adjunct professor, U-LIFE, Copenhagen (10 years)
- Professor II, Institute physical chemistry, NTNU (5 years)
- Professor II, IKBM, NMBU, Ås (5 years)
- Professor II, IMT, NMBU, Ås (5 years)
- Researcher, NOFIMA Ås (1973-86, 2003-2013)
- Member of Norwegian Academy of Technical Sciences (NTVA)
- Herman Wold gold medal from Swedish Chemical Society
- Honorary member of Norwegian Chemometric Society
- Chemometrics Prize/Eastern Analytical Symposium, USA
Current teaching in «real-world» data modelling:
- TTK19 - How to discover structures and relations in complex systems? http://www.itk.ntnu.no/emner/fordypning/ttk19
- TK8116 - Multivariate Data and Meta Modelling: Preparing for Big Data Cybernetics. http://www.ntnu.edu/studies/courses/TK8116#tab=omEmnet
These data analysis courses are of applied, cognitive and philosophical nature, intended to motivate students for later real-world R&D. Mathematical “soft modelling”, statistical cross-validation and graphical interpretation are combined generically to study Quantitative Big Data with the eyes of physics. Students perform one complete group research project, consisting of problem formulation, experimental design, actual measurements, data preprocessing, one-block multivariate data modelling (PCA) for overview and data clean-up, renewed measurements, two-block multivariate data modelling (PLSR) for overview and quantitative prediction, with cross-validation, graphical model interpretation and final reporting. Data tables from simple series of high-dimensional sound-spectra, or from students’ own projects, are used as a representative of the future’s multichannel measurements.
Current research activities:
- Easier use of «never-ending» megavariate data streams, e.g hyperspectral video
- New methods for model development in nonlinear dynamics
- New ways to reach the creative and the empathic student personality types wrt math and statistics, with a focus on discovery and meaning, rather than proofs and exactness
Scientific, academic and artistic work
A selection of recent journal publications, artistic productions, books, including book and report excerpts. See all publications in the database
- (2021) Metamodeling of the Electrical Conditions in Submerged Arc Furnaces. Metallurgical and Materials Transactions B.
- (2020) Multivariate Image Fusion: A Pipeline For Hyperspectral Data Enhancement. Chemometrics and Intelligent Laboratory Systems. vol. 205.
- (2017) Multivariate data modelling for de-shadowing of airborne hyperspectral imaging. Journal of Spectral Imaging. vol. 6 (a2).
- (2017) Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling. Frontiers in Robotics and AI. vol. 4.
- (2017) Genome-wide association mapping for milk fat composition and fine mapping of a QTL for de novo synthesis of milk fatty acids on bovine chromosome 13. Genetics Selection Evolution. vol. 49:20.
- (2017) On-The-Fly Processing of continuous high-dimensional data streams. Chemometrics and Intelligent Laboratory Systems. vol. 161.
- (2016) Frequency analysis and feature reduction method for prediction of cerebral palsy in young infants. IEEE transactions on neural systems and rehabilitation engineering. vol. 24 (11).
- (2015) High-Throughput Biochemical Fingerprinting of Saccharomyces cerevisiae by Fourier Transform Infrared Spectroscopy. PLOS ONE. vol. 10 (2).
- (2015) Quantitative Big Data: where chemometrics can contribute. Journal of Chemometrics. vol. 29 (11).
- (2015) 2D electrophoresis image segmentation within a pixel-based framework. Chemometrics and Intelligent Laboratory Systems. vol. 141.
- (2015) Frequency-based features for early cerebral palsy prediction. IEEE Engineering in Medicine and Biology Society. Conference Proceedings. vol. 2015-November.
- (2015) 150 Years of the Mass Action Law. PLoS Computational Biology. vol. 11 (1).
- (2014) A computational pipeline for quantification of mouse myocardial stiffness parameters. Computers in Biology and Medicine. vol. 53.
- (2014) Global structure of sloppiness in a nonlinear model. Journal of Chemometrics. vol. 28 (8).
- (2014) Analyzing complex mathematical model behavior by partial least squares regression-based multivariate metamodeling. Wiley Interdisciplinary Reviews: Computational Statistics. vol. 6 (6).
- (2014) Emulating facial biomechanics using multivariate partial least squares surrogate models. International Journal for Numerical Methods in Biomedical Engineering. vol. 30 (11).
- (2013) Fourier transform infrared spectroscopy for high-throughput phenotyping of Saccharomyces cereviseae. Yeast. vol. 30.
- (2013) Hierarchical multivariate regression-based sensitivity analysis reveals complex parameter interaction patterns in dynamic models. Chemometrics and Intelligent Laboratory Systems. vol. 120.
- (2013) Comparison of Sparse and Jack-knife partial least squares regression methods for variable selection. Chemometrics and Intelligent Laboratory Systems. vol. 122.
- (2013) Distribution based truncation for variable selection in subspace methods for multivariate regression. Chemometrics and Intelligent Laboratory Systems. vol. 122.