• Affect Recognition in Muscular Response Signals 

      Boeker, Matthias; Jakobsen, Petter; Riegler, Michael; Stabell, Lena Antonsen; Fasmer, Ole Bernt; Halvorsen, Pål; Hammer, Hugo Lewi (Peer reviewed; Journal article, 2023)
      This study investigated the potential of recognising arousal in motor activity collected by wrist- worn accelerometers. We hypothesise that emotional arousal emerges from the generalised central nervous system which ...
    • A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging 

      Jha, Debesh; Ali, Sharib; Hicks, Steven; Thambawita, Vajira L B; Borgli, Hanna; Smedsrud, Pia H.; de Lange, Thomas; Pogorelov, Konstantin; Wang, Xiaowei; Harzig, Philipp; Tran, Minh-Triet; Meng, Wenhua; Hoang, Trung-Hieu; Dias, Danielle; Ko, Tobey H.; Agrawal, Taruna; Ostroukhova, Olga; Khan, Zeshan; Tahir, Muhammed Atif; Liu, Yang; Chang, Yuan; Kirkerød, Mathias; Johansen, Dag; Lux, Mathias; Johansen, Håvard D.; Riegler, Michael; Halvorsen, Pål (Peer reviewed; Journal article, 2021)
      Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed ...
    • A dataset for predicting cloud cover over Europe 

      Svennevik, Hanna; Hicks, Steven; Riegler, Michael; Storelvmo, Trude; Hammer, Hugo Lewi (Peer reviewed; Journal article, 2024)
      Clouds are important factors when projecting future climate. Unfortunately, future cloud fractional cover (the portion of the sky covered by clouds) is associated with significant uncertainty, making climate projections ...
    • A Deep Diagnostic Framework Using Explainable Artificial Intelligence and Clustering 

      Thunold, Håvard Horgen; Riegler, Michael; Yazidi, Anis; Hammer, Hugo Lewi (Peer reviewed; Journal article, 2023)
      An important part of diagnostics is to gain insight into properties that characterize a disease. Machine learning has been used for this purpose, for instance, to identify biomarkers in genomics. However, when patient ...
    • Deep Tower Networks for Efficient Temperature Forecasting from Multiple Data Sources 

      Eide, Siri Sofie; Riegler, Michael; Hammer, Hugo Lewi; Bremnes, John Bjørnar (Sensors;Volume 22 / Issue 7, Peer reviewed; Journal article, 2022-04-06)
      Many data related problems involve handling multiple data streams of different types at the same time. These problems are both complex and challenging, and researchers often end up using only one modality or combining them ...
    • Diagnosing Schizophrenia from Activity Records using Hidden Markov Model Parameters 

      Boeker, Matthias; Riegler, Michael; Hammer, Hugo Lewi; Halvorsen, Pål; Fasmer, Ole Bernt; Jakobsen, Petter (Annual IEEE Symposium on Computer-Based Medical Systems;2021 IEEE 34th International Symposium on Computer-Based Medical Systems, Conference object, 2021-07-12)
      The diagnosis of Schizophrenia is mainly based on qualitative characteristics. With the usage of portable devices which measure activity of humans, the diagnosis of Schizophrenia can be enriched through quantitative features. ...
    • DivergentNets: Medical Image Segmentation by Network Ensemble 

      Thambawita, Vajira L B; Hicks, Steven; Halvorsen, Pål; Riegler, Michael (CEUR Workshop Proceedings;Vol-2886 - Proceedings of the 3rd International Workshop and Challenge on Computer Vision in Endoscopy (EndoCV 2021), Conference object, 2021)
      Detection of colon polyps has become a trending topic in the intersecting fields of machine learning and gastrointestinal endoscopy. The focus has mainly been on per-frame classification. More recently, polyp segmentation ...
    • Efficient Estimation of Generative Models Using Tukey Depth 

      Vo, Minh-Quan; Nguyen, Thu; Riegler, Michael; Hammer, Hugo Lewi (Peer reviewed; Journal article, 2024)
      Generative models have recently received a lot of attention. However, a challenge with such models is that it is usually not possible to compute the likelihood function, which makes parameter estimation or training of ...
    • Efficient quantile tracking using an oracle 

      Hammer, Hugo Lewi; Yazidi, Anis; Riegler, Michael; Rue, Håvard (Applied intelligence (Boston);, Peer reviewed; Journal article, 2022-04-14)
      Concept drift is a well-known issue that arises when working with data streams. In this paper, we present a procedure that allows a quantile tracking procedure to cope with concept drift. We suggest using expected quantile ...
    • Explaining deep neural networks for knowledge discovery in electrocardiogram analysis 

      Hicks, Steven; Isaksen, Jonas L; Thambawita, Vajira L B; Ghouse, Jonas; Ahlberg, Gustav; Linneberg, Allan; Grarup, Niels; Strumke, Inga; Ellervik, Christina; Olesen, Morten Salling; Hansen, Torben; Graff, Claus; Holstein-Rathlou, Niels-Henrik; Halvorsen, Pål; Maleckar, Mary Margot Catherine; Riegler, Michael; Kanters, Jørgen K (Scientific Reports;11, Article number: 10949 (2021), Peer reviewed; Journal article, 2021-05-26)
      Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any ...
    • A field assessment of child abuse investigators' engagement with a child-avatar to develop interviewing skills 

      Røed, Ragnhild Klingenberg; Powell, Martine B.; Riegler, Michael; Baugerud, Gunn Astrid (Peer reviewed; Journal article, 2023)
      Background: Child investigative interviewing is a complex skill requiring specialised training. A critical training element is practice. Simulations with digital avatars are cost-effective options for delivering training. ...
    • GridHTM: Grid-Based Hierarchical Temporal Memory for Anomaly Detection in Videos 

      Monakhov, Vladimir; Thambawita, Vajira L B; Halvorsen, Pål; Riegler, Michael (Peer reviewed; Journal article, 2023)
      The interest in video anomaly detection systems that can detect different types of anomalies, such as violent behaviours in surveillance videos, has gained traction in recent years. The current approaches employ deep ...
    • HOST-ATS: automatic thumbnail selection with dashboard-controlled ML pipeline and dynamic user survey 

      Husa, Andreas; Midoglu, Cise; Hammou, Malek; Halvorsen, Pål; Riegler, Michael (MMSys: ACM Multimedia Systems;MMSys '22: Proceedings of the 13th ACM Multimedia Systems Conference, Conference object, 2022)
      We present HOST-ATS, a holistic system for the automatic selection and evaluation of soccer video thumbnails, which is composed of a dashboard-controlled machine learning (ML) pipeline, and a dynamic user survey. The ML ...
    • Huldra: a framework for collecting crowdsourced feedback on multimedia assets 

      Hammou, Malek; Midoglu, Cise; Hicks, Steven; Storås, Andrea; Sabet, Saeed; Strumke, Inga; Riegler, Michael; Halvorsen, Pål (MMSys: ACM Multimedia Systems;MMSys '22: Proceedings of the 13th ACM Multimedia Systems Conference, Conference object, 2022)
      Collecting crowdsourced feedback to evaluate, rank, or score multimedia content can be cumbersome and time-consuming. Most of the existing survey tools are complicated, hard to customize, or tailored for a specific asset ...
    • HYPERAKTIV: An Activity Dataset from Patients with Attention-Deficit/Hyperactivity Disorder (ADHD) 

      Hicks, Steven; Stautland, Andrea; Fasmer, Ole Bernt; Førland, Wenche; Hammer, Hugo Lewi; Halvorsen, Pål; Mjeldheim, Kristin; Ødegaard, Ketil Joachim; Osnes, Berge; Syrstad, Vigdis Elin Giæver; Riegler, Michael; Jakobsen, Petter (MMSys: ACM Multimedia Systems;MMSys '21: Proceedings of the 12th ACM Multimedia Systems Conference, Conference object, 2021-09-22)
      Machine learning research within healthcare frequently lacks the public data needed to be fully reproducible and comparable. Datasets are often restricted due to privacy concerns and legal requirementsthat come with ...
    • Impact of image resolution on deep learning performance in endoscopy image classification: An experimental study using a large dataset of endoscopic images 

      Thambawita, Vajira L B; Strumke, Inga; Hicks, Steven; Halvorsen, Pål; Parasa, Sravanthi; Riegler, Michael (Diagnostics;Volume 11 / Issue 12, Peer reviewed; Journal article, 2021-11-24)
      Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)- based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies ...
    • Man vs. AI: An in silico study of polyp detection performance 

      Smedsrud, Pia Helen; Espeland, Håvard; Berstad, Tor Jan; Petlund, Andreas; de Lange, Thomas; Riegler, Michael; Halvorsen, Pål (Annual IEEE Symposium on Computer-Based Medical Systems;, Chapter; Peer reviewed; Conference object; Journal article, 2023)
      AI-based colon polyp detection systems have received much attention, and several products and prototypes report good results. In silico verification is a crucial step when developing such systems, but very few compare human ...
    • Mask-conditioned latent diffusion for generating gastrointestinal polyp images 

      Macháček, Roman; Mozaffari, Leila; Sepasdar, Zahra; Parasa, Sravanthi; Halvorsen, Pål; Riegler, Michael; Thambawita, Vajira L B; Machacek, Roman (ICDAR: Intelligent Cross-Data Analysis and Retrieval;, Chapter; Peer reviewed; Conference object, 2023)
      In order to take advantage of artificial intelligence (AI) solutions in endoscopy diagnostics, we must overcome the issue of limited annotations. These limitations are caused by the high privacy concerns in the medical ...
    • MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation 

      Srivastava, Abhishek; Jha, Debesh; Chanda, Sukalpa; Pal, Umapada; Johansen, Håvard D.; Johansen, Dag; Riegler, Michael; Ali, Sharib; Halvorsen, Pål (IEEE journal of biomedical and health informatics;Volume: 26, Issue: 5, Peer reviewed; Journal article, 2021-12-23)
      Methods based on convolutional neural networks have improved the performance of biomedical image segmentation. However, most of these methods cannot efficiently segment objects of variable sizes and train on small and ...
    • PolypConnect: Image inpainting for generating realistic gastrointestinal tract images with polyps 

      Fagereng, Jan Andre; Thambawita, Vajira L B; Storås, Andrea; Parasa, Sravanthi; de Lange, Thomas; Halvorsen, Pål; Riegler, Michael (Annual IEEE Symposium on Computer-Based Medical Systems;2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS), Conference object, 2022)
      Early identification of a polyp in the lower gastrointestinal (GI) tract can lead to prevention of life-threatening colorectal cancer. Developing computer-aided diagnosis (CAD) systems to detect polyps can improve detection ...