Adjunct Professor - Department of Strategy and Entrepreneurship
Publications
Stensrud, Erik & Myrtveit, Ingunn (2019)
The Problem of High Confidence Mistakes of Deep Learning in Safety-critical Functions
Yurish, Sergey Y (red.). Advances in Signal Processing and Artificial Intelligence: Proceedings of the 1st International Conference on Advances in Signal Processing and Artificial Intelligence
Automating Inspections of Cargo and Ballast Tanks using Drones
Bertram, Volker (red.). 18th International Conference on Computer and IT Applications in the Maritime Industries - COMPIT’19
DNV GL has performed production surveys in enclosed spaces using drones since 2016, demonstrating cost savings and increased personnel safety. It is a vision to develop autonomous inspection drones to reduce the need to enter tanks. We expect that this will reduce survey duration and survey preparation costs for the clients and be a major safety improvement for surveyors. A number of drone capabilities are required to enable visual close-up inspection and non-destructive testing in enclosed, GPS-denied, and poorly lit environments. We describe current and possible future survey scenarios and the desired capabilities of an autonomous inspection drone for enclosed compartments. Then, we report status from an ongoing research project managed by DNV GL and including several industry partners. We highlight technical challenges and results on drone navigation functionalities, computer vision, hyperspectral imaging, and ultrasonic steel thickness measurements.
Agrell, Christian; Eldevik, Simen, Hafver, Andreas, Pedersen, Frank Børre, Stensrud, Erik & Huseby, Arne (2018)
Pitfalls of machine learning for tail events in high risk environments
Haugen, Stein; Barros, Anne, van Gulijk, Coen, Kongsvik, Trond & Vinnem, Jan Erik (red.). Safety and Reliability – Safe Societies in a Changing World. Proceedings of ESREL 2018, June 17-21, 2018, Trondheim, Norway
Most of today’s Machine Learning (ML) methods and implementations are based on correlations, in the sense of a statistical relationship between a set of inputs and the output(s) under inves- tigation. The relationship might be obscure to the human mind, but through the use of ML, mathematics and statistics makes it seemingly apparent. However, to base safety critical decisions on such methods suffer from the same pitfalls as decisions based on any other correlation metric that disregards causality. Causality is key to ensure that applied mitigation tactics will actually affect the outcome in the desired way. This paper reviews the current situation and challenges of applying ML in high risk environments. It further outlines how phenomenological knowledge, together with an uncertainty-based risk perspective can be incorporated to alleviate the missing causality considerations in current practice.
Stensrud, Erik & Myrtveit, Ingunn (2012)
Validity and reliability of evaluation procedures in comparative studies of effort prediction models
Towards goal-based software safety certification based on prescriptive standards
[Academic lecture]. IEEE 22nd International Symposium on Software Reliability Engineering, 1st International Workshop on Software Certification (ISSRE WoCoCER).
Myrtveit, Ingunn & Stensrud, Erik (2009)
User Satisfaction with Search-driven Enterprise portals
[Academic lecture]. ICSOFT conference.
Foss, Tron; Stensrud, Erik, Kitchenham, B. & Myrtveit, Ingunn (2002)
A Simulation Study of the Model Evaluation Criterion MMRE
[Report]. Handelshøyskolen BI.
Stensrud, Erik & Myrtveit, Ingunn (2002)
Identifying High Performance ERP Projects
[Report]. Handelshøyskolen BI.
Stensrud, Erik & Myrtveit, Ingunn (2002)
SW Cost Estimation: Measuring Model Performance of Arbitrary Function Approximators
[Report]. Handelshøyskolen BI.
Myrtveit, Ingunn; Stensrud, Erik & Olsson, Ulf Henning (2001)
Assessing the Benefits of Imputing ERP Projects with Missing Data
[Academic lecture]. 7th International Software Metrics Symposium.
Foss, Tron; Myrtveit, Ingunn & Stensrud, Erik (2001)
A Comparison of LAD and OLS Regression for Effort Prediction of Software Projects
[Academic lecture]. 12th European Software Control and Metrics Conference (ESCOM 2001).
Foss, Tron; Myrtveit, Ingunn & Stensrud, Erik (2001)
MRE and Heteroscedasticity: An Empirical Validation of the Assumption of Homoscedasticity of the Magnitude of Relative Error
[Academic lecture]. 12th European Software Control and Metrics conference.