Ole J. Mengshoel
YOU?
Author Swipe
View article: Artificial intelligence methods in gestational diabetes mellitus prediction: A systematic literature review
Artificial intelligence methods in gestational diabetes mellitus prediction: A systematic literature review Open
Gestational diabetes mellitus (GDM) is the most common metabolic disorder in pregnancy, posing risks to both maternal and neonatal health. Artificial intelligence (AI) and machine learning (ML)-based solutions hold the promise of improving…
View article: Visualizing Multimodality in Combinatorial Search Landscapes
Visualizing Multimodality in Combinatorial Search Landscapes Open
This work walks through different visualization techniques for combinatorial search landscapes, focusing on multimodality. We discuss different techniques from the landscape analysis literature, and how they can be combined to provide a mo…
View article: Implicit neural representation for fast 4D computed tomography of multiphase flow in porous media
Implicit neural representation for fast 4D computed tomography of multiphase flow in porous media Open
Time-resolved X-ray computed tomography (4D-CT) enables dynamic processes within objects to be tracked over time. A key application of 4D-CT is the scientifically and societally important study of multiphase flow in porous media. Obtaining…
View article: Detecting and Segmenting Solar Farms in Satellite Imagery: A Study of Deep Neural Network Architectures
Detecting and Segmenting Solar Farms in Satellite Imagery: A Study of Deep Neural Network Architectures Open
In line with global sustainability goals, such as the Paris Agreement, accurate mapping, monitoring, and management of solar farms are critical for achieving net zero emissions by 2050. However, many solar installations remain undocumented…
View article: Green Urban Mobility with Autonomous Electric Ferries: Studies of Simulated Maritime Collisions using Adaptive Stress Testing
Green Urban Mobility with Autonomous Electric Ferries: Studies of Simulated Maritime Collisions using Adaptive Stress Testing Open
With 90% of the world's goods transported by sea vessels, it is crucial to investigate their safety. This is increasingly important as autonomy is being introduced into sea vessels, which transport goods and people. To study the safety of …
View article: Creating Explainable Dynamic Checklists via Machine Learning to Ensure Decent Working Environment for All: A Field Study with Labour Inspections
Creating Explainable Dynamic Checklists via Machine Learning to Ensure Decent Working Environment for All: A Field Study with Labour Inspections Open
To address poor working conditions and promote United Nations’ sustainable development goal 8.8, “protect labour rights and promote safe working environments for all workers [...]”, government agencies around the world conduct labour inspe…
View article: Comparing Metaheuristic Optimization Algorithms for Ambulance Allocation: An Experimental Simulation Study
Comparing Metaheuristic Optimization Algorithms for Ambulance Allocation: An Experimental Simulation Study Open
The optimization of Emergency Medical Services is a central issue in modern healthcare systems. With this in focus, we study a data set containing medical emergencies for the years 2015--2019 from Oslo and Akershus, Norway. By developing a…
View article: Corrigendum: SemNet: Learning semantic attributes for human activity recognition with deep belief networks
Corrigendum: SemNet: Learning semantic attributes for human activity recognition with deep belief networks Open
[This corrects the article DOI: 10.3389/fdata.2022.879389.].
View article: SemNet: Learning semantic attributes for human activity recognition with deep belief networks
SemNet: Learning semantic attributes for human activity recognition with deep belief networks Open
Human Activity Recognition (HAR) is a prominent application in mobile computing and Internet of Things (IoT) that aims to detect human activities based on multimodal sensor signals generated as a result of diverse body movements. Human phy…
View article: Understanding the cost of fitness evaluation for subset selection
Understanding the cost of fitness evaluation for subset selection Open
With a focus on both the fitness and cost of subset selection, we study stochastic local search (SLS) heuristics in this paper. In particular, we consider subset selection problems where the cost of fitness function evaluation needs to be …
View article: Creating Dynamic Checklists via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All
Creating Dynamic Checklists via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All Open
Every year there are 1.9 million deaths world-wide attributed to occupational health and safety risk factors. To address poor working conditions and fulfill UN's SDG 8, "protect labour rights and promote safe working environments for all w…
View article: Identification of Failure Modes in the Collision Avoidance System of an Autonomous Ferry using Adaptive Stress Testing
Identification of Failure Modes in the Collision Avoidance System of an Autonomous Ferry using Adaptive Stress Testing Open
As complex autonomous systems emerge in the maritime sector, measures must be taken in order to ensure thorough safety assessment. Real-world testing can be costly and potentially dangerous, and therefore there is a need for suitable simul…
View article: A multi-objective genetic algorithm for jacket optimization
A multi-objective genetic algorithm for jacket optimization Open
Jackets are massive steel towers supporting offshore installations such as oil platforms and wind turbines. Due to the high costs of material, construction, and installation, there is an interest in optimizing such jacket designs. This is …
View article: Customizing Graph Neural Networks using Path Reweighting
Customizing Graph Neural Networks using Path Reweighting Open
Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them ar…
View article: FootprintID Dataset: Footstep-Induced Structural Vibration Data for Indoor Person Identification with Different Walking Speeds
FootprintID Dataset: Footstep-Induced Structural Vibration Data for Indoor Person Identification with Different Walking Speeds Open
The dataset consists of structural vibration data (vertical velocity of floor structure) induced by 10 people’s footsteps as they walk around with 8 different walking speeds, sensed by 5 geophone sensors. The footstep-induced structural vi…
View article: FootprintID Dataset: Footstep-Induced Structural Vibration Data for Indoor Person Identification with Different Walking Speeds
FootprintID Dataset: Footstep-Induced Structural Vibration Data for Indoor Person Identification with Different Walking Speeds Open
The dataset consists of structural vibration data (vertical velocity of floor structure) induced by 10 people’s footsteps as they walk around with 8 different walking speeds, sensed by 5 geophone sensors. The footstep-induced structural vi…
View article: Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning Open
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many app…
View article: Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems Open
We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many …
View article: Customized Graph Embedding: Tailoring Embedding Vectors to different Applications
Customized Graph Embedding: Tailoring Embedding Vectors to different Applications Open
Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides…
View article: AttriNet
AttriNet Open
Human activity recognition (HAR) is essential to many context-aware applications in mobile and ubiquitous computing. A human's physical activity can be decomposed into a sequence of simple actions or body movements, corresponding to what w…
View article: Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning Open
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many applicati…
View article: Adaptive Stress Testing: Finding Failure Events with Reinforcement Learning
Adaptive Stress Testing: Finding Failure Events with Reinforcement Learning Open
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many applicati…
View article: Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention Open
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, …
View article: Interpretable Categorization of Heterogeneous Time Series Data
Interpretable Categorization of Heterogeneous Time Series Data Open
Understanding heterogeneous multivariate time series data is important in many applications ranging from smart homes to aviation. Learning models of heterogeneous multivariate time series that are also human-interpretable is challenging an…
View article: Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models Open
Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response …