FYS302 Mining of biospectroscopy data

The course is taught in June and is a part of the BioSpec Summer School. Pre-courses need to be delivered before the start of the summer school. See https://www.nmbu.no/en/faculty/realtek/research/groups/biospectroscopy/summerschool for teaching period.

For the BioSpec Summer School, lectures and tutorials will be evenly spread throughout the teaching period. The course covers the principles of spectroscopy and data science for analysis of data from biophotonics. It gives an introduction to biological data obtained with analytical methods, with a special focus on spectroscopy. The course contains training in data analysis through tutorials and working as an expert in a multidisciplinary team. Furthermore, special focus will be given on the development of personal presentation skills.

The course covers:

• Spectroscopic techniques
• Analytical methods in biology
• Principal Component Analysis

• Basic methods of pre-processing for spectroscopic data
• Advanced pre-processing methods such as Mie correction and fringes correction
• Multivariate methods for clustering
• Basic regression
• Machine learning methods for regression and classification

• Deep learning methods
• Data analysis of hyperspectral images
• Introduction to the machine learning software platform Orange/Quasar

• Gain multidisciplinary knowledge in biology, spectroscopy and data analysis.
• Improve theoretical and practical knowledge in data analysis of high-dimensional biological data including hyperspectral imaging data.
• Acquire skills for working in an international and multidisciplinary team.
• Acquire presentation skills through presenting the results of the course project.
• Improve theoretical and practical knowledge within biophotonics and gain an overview of the analytical methods used in the field.
• Improve theoretical knowledge in the interaction between light and biological matter.
• Get insight into how the discipline has evolved and impacted society through invited lectures about applications of biophotoncis and data science.
• Be able to carry out interdisciplinary analyses with colleagues from other academic fields.
• Acquire skills to analyze and critically evaluate various sources of information and use them to structure and formulate scholarly arguments.
• Improve communication skills about academic issues, analyses and conclusions in the field, both with specialists and the general public.