Johan Dahlin Passionate about finding hidden patterns and trends in data.

  • 2016

    PhD Automatic Control

    Linköping University, Sweden.
    Includes two years of coursework in Engineering, Machine Learning and Statistics.

  • 2011

    MSc Engineering Physics

    Umeå University, Sweden.
    Majors in Risk Management and Industrial Statistics.

  • 2011

    B.Sc. Economics

    Umeå University, Sweden.
    Includes coursework in Marketing, Project Management and Law.

Who am I?

I began life in Enköping, Sweden in 1986. As a young boy, I quickly found an interest in Mathematics and Computer Science, which led me to study Engineering and then to pursue a PhD based on research and coursework. 

I received my PhD in Automatic Control in May 2016 after successfully defending my thesis which contained a total of 17 peer-reviewed papers (13 conference papers and 3 journal papers) published at top conferences and journals in the fields of Computational Statistics and System Identification.

Currently, I am developing automated data-driven algorithms for building dynamical models as a PostDoc at the School of Engineering at the University of Newcastle, Australia.

During my research career, I have worked at a number of different companies and universities. I visited Prof. Robert Kohn at he University of New South Wales,  Australia during the autumn of 2014 as part of his PhD studies. I have also worked as a Research Scientist at Sectra AB and as a PostDoc at the division of Statistics and Machine Learning at Linköping University.

What are my objectives and passions?

The Economist has described data as the new oil which can result in the next industrial revolution. Everyday, more and more information is gathered from sensors and the Internet. As a result, Big Data, Statistics and Machine Learning (in short Data Analytics) have become essential tools to generate insights from this data.

 

Objectives in Data Science

  • To condense data into a model.
  • To gain understanding, to make decisions or to forecast future behaviours using this model.
  • However, many models and the algorithms that fit them to data cannot yet cope with the complex, dirty and large data materials
  • I work on how to build algorithms that better scale with the amount of information and to accelerate current methods for model building. 

My Passion

  • Bayesian data analysis employed to finding hidden patterns and trends in data.
  • I work with numbers, images, text documents and other forms of data.
  • I want to make use of my expertise to improve the world in terms of health-care/medicine, economics and the environment.
  • I believe that learning from data is essential in this quest by enabling improved data-driven decision making and forecasting.

What kind of research interests me?

My interests in research are rather broad and spans employing methods from Statistics, Machine Learning, Artificial Intelligence, Engineering, etc. to solve real-world problems. You can see some examples of practical applications of my research on the next page and here I discuss some more academic interests.

Accelerating Monte Carlo algorithms for Bayesian inference, such as particle filtering and Markov chain Monte Carlo.

Efficient inference in longitudinal data, i.e., short data records for many individuals.

Approximate Bayesian inference by modifying the model to simplify inference, e.g., using Gaussian process optimisation.

Developing methods for applying Machine/Deep Learning for applications in Climate Science, Medicine and Finance.

What can my research be used for?

Teaching computers to detect cancer

Applying recent advances in deep learning to train computers to detect and classify cancers in mammograms.

Breast cancer is one of the most common forms of cancers in women with about two million new cases every year. In 2015, about half a million women died from the disease despite extensive screenings of the population and much research into better treatments. Deep learning and AI can potentially help doctors to analyze mammograms to detect the cancer at an early state.

A first step towards this goal is to teach the computer to recognize different types of structures and landmarks in images, which then can be used to classification (per pixel) of tissues to find tumors. The use of AI can in this case help medical doctors by decreasing their workload via marking and sorting images that require further analysis by an expert.

Image credits to Nevit Dilmen.

mammography

What can my research be used for?

rubble

Finding survivors in disaster areas

Fusing information from many different sources to be able to estimate where it is likely to find survivors and to guide first responders.

It is often difficult to coordinate and plan the rescue work after a disaster such as an earthquake or a Tsunami. In this project, we aim to develop statistical models that can combine information from cameras mounted on UAVs, maps, cell tower information, etc. to create a probability map over an area. This map would tell the first responders and other emergency personnel where it is most likely to find survivors after a disaster.

Image credits to Mark Dixon on FlickR.

What can my research be used for?

Finding alternative medical diagnoses

Leveraging methods from Machine Learning to mine information found in electronic health records.

Electronic health records (EHRs) of patients are usually stored on a central server at hospitals. These are a possible gold-mine of information that is currently large under-utilised. In this project, we aim to make use of modern Machine Learning, Deep Learning and Natural Language Processing methods to extract useful information from these records, which can help medical doctors to make better diagnoses. These is done by presenting a list of possible diagnoses, which can be useful in helping medical doctors in their work or for planning and resource allocation.

Image credits to NEC Corporation of America at FlickR.

ehr

Would you like to know more?

I love to connect with new people for networking and to share experiences and idea. Therefore, do not hesitate to get in touch with me if you have any questions connected to my research, the source code on GitHub or if you would like to discuss a business idea or hire me for a job.