Academic interests
- Machine learning and Data Science
- Explainable Artificial Intelligence
- Applications within risk and safety
Background
I did my Master of Science at the Norwegian University of Life Sciences (NMBU), in Environmental Physics. In my thesis, I combined machine learning with image analysis of PET/CT-images of cancer tumors, to predict the treatment outcome. After that, I worked with technology consulting for Accenture, working with new technologies like machine learning and extended reality. Since August 2019, I have been a PhD Student at the Department of Mathematics at the University of Oslo. Here I am working on modelling and analysis of multidimensional high-resolution environmental data with application to airport runway condition management.
Tags:
Risk,
Statistics,
Machine Learning,
data science
Publications
-
Midtfjord, Alise Danielle & Huseby, Arne (2020). Estimating Runway Friction Using Flight Data, In Piero Baraldi; Francesco P. Di Maio & Enrico Zio (ed.),
e-proceedings of the 30th European Safety and Reliability Conference and 15th Probabilistic Safety Assessment and Management Conference (ESREL2020 PSAM15).
Research Publishing Services.
ISBN 9789811485930.
Artikkel.
Show summary
During the winter season, contamination of runway surfaces with snow, ice, or slush causes potential economic and safety threats for the aviation industry. The presence of these materials reduces the available tire-pavement friction needed for retardation and directional control. Therefore, pilots operating on contaminated runways need accurate and timely information on the actual runway surface conditions. Avinor, the company that operates most civil airports in Norway, have developed an integrated runway information system, called IRIS, currently used on 16 Norwegian airports. The system uses a scenario approach to identify slippery conditions. In order to validate the scenario model, it is necessary to estimate runway friction. The present paper outlines how this can be done using flight data from the Quick Access Recorder (QAR) of Boeing 737-600/700/800 NG airplanes. Data such as longitudinal acceleration, airspeed, ground speed, flap settings, engine speed, brake pressures are sampled at least each second during landings. The paper discusses some of the challenges with this. In particular, issues related to calibration of data are considered, and two different regression methods are compared.
View all works in Cristin
-
Midtfjord, Alise Danielle (2020). Estimating Runway Friction Using Flight Data.
Show summary
During the winter season, contamination of runway surfaces with snow, ice, or slush causes potential economic and safety threats for the aviation industry. The presence of these materials reduces the available tire-pavement friction needed for retardation and directional control. Therefore, pilots operating on contaminated runways need accurate and timely information on the actual runway surface conditions. Avinor, the company that operates most civil airports in Norway, have developed an integrated runway information system, called IRIS, currently used on 16 Norwegian airports. The system uses a scenario approach to identify slippery conditions. In order to validate the scenario model, it is necessary to estimate runway friction. The present paper outlines how this can be done using flight data from the Quick Access Recorder (QAR) of Boeing 737-600/700/800 NG airplanes. Data such as longitudinal acceleration, airspeed, ground speed, flap settings, engine speed, brake pressures are sampled at least each second during landings. The paper discusses some of the challenges with this. In particular, issues related to calibration of data are considered, and two different regression methods are compared.
-
Midtfjord, Alise Danielle (2020). Explainable Artificial Intelligence (XAI).
Show summary
As the use of “black box” algorithms such as deep learning increases rapidly, several challenges related to ethics and law arise. Explainable Artificial Intelligence (XAI) addresses these issues by creating understandable explanations of how and why AI systems arrive at their decisions, and we will try out some of these methods during this workshop.
-
Midtfjord, Alise Danielle (2020). Explainable Artificial Intelligence: How to make AI responsible.
Show summary
As the use of “black box” algorithms such as deep learning increases rapidly, several challenges related to ethics and law arise. These systems are not capable of explaining their decisions and actions to human users, making it difficult to make sure they follow the laws are morals of our society. Explainable Artificial Intelligence (XAI) addresses these issues by creating understandable explanations of how and why AI systems arrive at their decisions. In this presentation you will learn about some of the moral challenges rising with the use of artificial intelligence, what explainable artificial intelligence is and how it can address a lot of these challenges and contribute to creating trustworthy and responsible AI.
-
Grøndahl, Aurora Rosvoll; Midtfjord, Alise Danielle; Langberg, Geir Severin Rakh Elvatun; Tomic, Oliver; Indahl, Ulf Geir; Knudtsen, Ingerid Skjei; Malinen, Eirik; Dale, Einar & Futsæther, Cecilia Marie (2019). Prediction of treatment outcome for head and neck cancers using radiomics of PET/CT images. Radiotherapy and Oncology.
ISSN 0167-8140.
133, s 526- 526
-
Langberg, Geir Severin; Grøndahl, Aurora Rosvoll; Midtfjord, Alise Danielle; Tomic, Oliver; Liland, Kristian Hovde; Knudtsen, Ingerid Skjei; Dale, Einar; Malinen, Eirik & Futsæther, Cecilia Marie (2019). Establishing a complete radiomics framework for biomarker identification and outcome prediction using PET/CT images of head & neck cancers.
View all works in Cristin
Published Nov. 20, 2019 1:48 PM
- Last modified Jan. 17, 2020 11:00 AM