General
Academic interests
- Machine learning
- Image analysis
- Reinforcement learning
- Natural language processing
- Explainable Artificial Intelligence
- Computer graphics and virtual environments
Courses taught
Background
Master thesis from Østfold University College. PhD from University of Oslo.
Tags:
The Digital Society,
DigiTech
Publications
-
Tran, Thi Thuy Chau; Nguyen, Hoa Thi; Magnusson, Lars Vidar & Olsson, Roland
(2026).
How Well Do Automatically Evolved Neurons Perform? A Comparative Study in Human Activity Recognition.
ESREL 2026.
doi:
https:/cmsweb.com.sg/rps2prod/esrel2026/epro/pdf/esrel26-p26301.pdf.
Full text in Research Archive
Show summary
Neuroevolution, a subfield of AI leveraging evolutionary algorithms, offers an effective method for automatically generating data-adaptive equations that optimize fit for specific datasets while minimizing human design bias. This study investigates the efficacy of the WISDM-ARN, a specialized Adaptive Recurrent Neuron (ARN) synthesized via the Automatic Design of Algorithms through Evolution (ADATE) system, for Human Activity Recognition (HAR). In safety-critical applications, such as healthcare monitoring and industrial safety, the reliability of locomotion classification is paramount to prevent system failures and ensure user protection. We benchmark the evolved WISDM-ARN against three established architectures: Simple RNN, Long Short-Term Memory (LSTM), and Transformers. Experimental results demonstrate that the WISDM-ARN successfully adapts to the unique temporal characteristics of gyroscope data, achieving a testing accuracy of 97\%, which is comparable to the baseline models with resulting 70\%, 95\%, and 92\%, respectively. These findings highlight the potential of neuroevolutionary synthesis as a dependable alternative to manually engineered architectures. By integrating neuroevolution with modern deep learning, the ADATE-generated neuron represents a significant step toward automated reliable neural modeling for human activity recognition tasks and safety-enhanced time-series analysis.
-
Sorano, Ruslan; Ripon, Kazi Shah Nawaz & Magnusson, Lars Vidar
(2024).
Evolutionary Optimization of Artificial Neural Networks and Tree-Based Ensemble Models for Diagnosing Deep Vein Thrombosis.
In Westphal, Florian; Peretz-Andersson, Einav; Riveiro, Maria; Bach, Kerstin & Heintz, Fredrik (Ed.),
14th Scandinavian Conference on Artificial Intelligence SCAI 2024, June 10-11, 2024, Jönköping, Sweden.
Swedish Artificial Intelligence Society.
ISSN 9789180757096.
p. 178–187.
doi:
10.3384/ecp208020.
Full text in Research Archive
Show summary
Machine learning algorithms, particularly artificial neural networks, have shown promise in healthcare for disease classification, including diagnosing conditions like deep vein thrombosis. However, the performance of artificial neural networks in medical diagnosis heavily depends on their architecture and hyperparameter configuration, which presents virtually unlimited variations. This work employs evolutionary algorithms to optimize hyperparameters for three classic feed-forward artificial neural networks of pre-determined depths. The objective is to enhance the diagnostic accuracy of the classic neural networks in classifying deep vein thrombosis using electronic health records sourced from a Norwegian hospital. The work compares the predictive performance of conventional feed-forward artificial neural networks with standard tree-based ensemble methods previously successful in disease prediction on the same dataset. Results indicate that while classic neural networks perform comparably to tree-based methods, they do not surpass them in diagnosing thrombosis on this specific dataset. The efficacy of evolutionary algorithms in tuning hyperparameters is highlighted, emphasizing the importance of choosing the optimization technique to maximize machine learning models' diagnostic accuracy.
-
Sorano, Ruslan; Ripon, Kazi Shah Nawaz; Magnusson, Lars Vidar; Halstensen, Thor-David & Ghanima, Waleed
(2024).
Enhancing Deep Vein Thrombosis Diagnosis with Multi-Objective Evolutionary Algorithm and Machine Learning.
In Ogul, Hasan; Aamodt, Jonas Moræus; Misra, Sanjay & Kjølerbakken, Kai Morgan (Ed.),
2024 4th International Conference on Applied Artificial Intelligence (ICAPAI).
IEEE (Institute of Electrical and Electronics Engineers).
ISSN 9798350349764.
p. 1–1.
doi:
10.1109/ICAPAI61893.2024.10541216.
Full text in Research Archive
-
-
Magnusson, Lars Vidar; Olsson, Roland & Tran, Thi Thuy Chau
(2023).
Recurrent Neural Networks for Oil Well Event Prediction.
IEEE Intelligent Systems.
ISSN 1541-1672.
38(2),
p. 73–80.
doi:
10.1109/MIS.2023.3252446.
Full text in Research Archive
Show summary
We have conducted a comparison between three types of recurrent neural networks and their ability to predict anomalies occurring in oil wells using a publicly available dataset. We have included two types of well-known state-of-the-art recurrent neural networks and a new type with neurons evolved specifically for the dataset using automatic programming. We show that the new type of recurrent neuron offers a massive improvement over the state of the art. The overall test accuracy of the new network type is 94.6%, which is an improvement by 18.3%, or 14.6 percentage points. We also show that a network with the new neuron performs better than any other solution proposed for the dataset.
-
-
Sorano, Ruslan; Magnusson, Lars Vidar & Abbas, Khurshid
(2022).
Comparing Effectiveness of Machine Learning Methods for Diagnosis of Deep Vein Thrombosis.
Lecture Notes in Computer Science (LNCS).
ISSN 0302-9743.
p. 279–293.
doi:
10.1007/978-3-031-10548-7_21.
Full text in Research Archive
-
-
-
Magnusson, Lars Vidar & Olsson, Roland
(2016).
Improving the Canny Edge Detector Using Automatic Programming: Improving Hysteresis Thresholding.
NIKT: Norsk IKT-konferanse for forskning og utdanning.
ISSN 1892-0713.
doi:
10.1109/icivc.2016.7571270.
Full text in Research Archive
-
Larsen, Kristin; Magnusson, Lars Vidar & Olsson, Roland
(2014).
Edge Pixel Classification Using Automatic Programming.
NIKT: Norsk IKT-konferanse for forskning og utdanning.
ISSN 1892-0713.
Full text in Research Archive
-
Magnusson, Lars Vidar & Olsson, Roland
(2014).
Improving Graph-Based Image Segmentation Using Automatic Programming.
In Esparcia-Alcázar, Anna I. & Mora, Antonio (Ed.),
Applications of Evolutionary Computation. 17th European Conference, EvoApplications 2014, Granada, Spain, April 23-25, 2014.
Springer.
ISSN 9783662455234.
p. 464–475.
doi:
10.1007/978-3-662-45523-4_38.
Full text in Research Archive
View all works in NVA
-
Leonardsen, Ann-Chatrin Linqvist; Hardeland, Camilla & Magnusson, Lars Vidar
(2024).
Kunstig intelligens og beslutningsstøtte i helsetjenesten.
dagensmedisin.no.
Full text in Research Archive
-
-
-
-
-
-
-
Magnusson, Lars Vidar
(2016).
Improving the Canny edge detector using automatic programming: Improving non-max suppression.
Full text in Research Archive
-
Magnusson, Lars Vidar
(2016).
Improving the Canny Edge Detector Using Automatic Programming: Improving Hysteresis Thresholding.
Full text in Research Archive
-
-
-
Aliyari, Mostafa; Ayele, Yonas Zewdu; Markeset, Tore; Barabady, Javad & Magnusson, Lars Vidar
(2025).
Machine Learning-Driven Approaches for Performance Assessment of Critical Infrastructure: UAV-assisted Bridge Inspections, Hazard Identification, Failure Detection, Power Load Forecasting.
Universitetet i Stavanger.
ISSN 9788284393544.
Full text in Research Archive
Show summary
This PhD research explores application of emerging technologies like remotely operated vehicles (ROVs), specifically unmanned aerial vehicles (UAVs) and machine learning (ML), focusing on deep learning (DL) for data collection and data analysis of critical infrastructure systems (CIs), particularly in bridge inspections and power load forecasting. As technological and demographic changes heighten the complexity and vulnerability of CIs, innovative methods for data collection and analysis are essential. One part of this research investigates hazard identification and risk assessment in bridge inspections utilizing UAVs. The images captured during these inspections are used to develop DL methods, such as mask region-based convolutional neural networks (Mask R-CNNs) and transfer learning techniques for failure detection, specifically crack detection. Empirical validation through case studies of the Grimsøy and Håkenby bridges in Norway illustrates the practical application of UAVassisted bridge inspections. The results indicate that integrating UAVs with advanced DL techniques significantly improves structural failure detection, enhancing prediction accuracy and overall safety. The second part of the study focuses on time series data related to power load forecasting. This section includes a comparative analysis of the effectiveness of various time series prediction DL models, such as Long Short-Term Memory (LSTM) and Transformers. Additionally, a novel ant colony optimization (ACO) algorithm is developed to optimize the parameters of the multi-head attention layer (MHAL), a main component of Transformers, for power load forecasting. The findings demonstrate notable improvements in power load prediction accuracy and optimized resource allocation within power systems. Overall, this research highlights how critical infrastructures can benefit from the integration of new technologies and advanced machine learning predictive techniques for effective risk and performance assessment, ultimately enhancing asset management strategies.
-
View all works in NVA
Published June 12, 2018 4:14 PM
- Last modified June 24, 2026 10:05 AM
