Blar i NTNU Open på forfatter "Bach, Kerstin"
-
FishNet: A Unified Embedding for Salmon Recognition
Mathisen, Bjørn Magnus; Bach, Kerstin; Meidell, Espen; Måløy, Håkon; Sjøblom, Edvard Schreiner (Chapter, 2020)Identifying individual salmon can be very beneficial for the aquaculture industry as it enables monitoring and analyzing fish behavior and welfare. For aquaculture researchers identifying indi- vidual salmon is imperative ... -
From a Low-Cost Air Quality Sensor Network to Decision Support Services: Steps towards Data Calibration and Service Development
Veiga, Tiago Santos; Munch-Ellingsen, Arne; Papastergiopoulos, Christoforos; Tzovaras, Dimitrios; Kalamaras, Ilias; Bach, Kerstin; Votis, Konstantinos; Akselsen, Sigmund (Peer reviewed; Journal article, 2021)Air pollution is a widespread problem due to its impact on both humans and the environment. Providing decision makers with artificial intelligence based solutions requires to monitor the ambient air quality accurately and ... -
From data to context-aware decision making: Challenges and opportunities
Bach, Kerstin (Journal article; Peer reviewed, 2018)This extended abstract presents the research challenges for developing context-aware, explainable artificial intelligence challenges and briefly presents the opportunities ahead when utilizing the vast amount of data generated. -
Harth: A human activity recognition dataset for machine learning
Logacjov, Aleksej; Bach, Kerstin; Kongsvold, Atle; Bårdstu, Hilde Bremseth; Mork, Paul Jarle (Peer reviewed; Journal article, 2021)Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We ... -
Human Activity Recognition With Two Body-Worn Accelerometer Sensors
Hessen, Hans-Olav; Tessem, Astrid Johnsen (Master thesis, 2016)Data used in studies about physical activity is primarily collected from questionnaires and other subjective methods, which may lead to biased and inaccurate data. As subjective data collection methods have shown to be ... -
Individually tailored self-management app-based intervention (selfBACK) versus a self-management web-based intervention (e-Help) or usual care in people with low back and neck pain referred to secondary care: protocol for a multiarm randomised clinical trial
Marcuzzi, Anna; Bach, Kerstin; Nordstoga, Anne Lovise; Bertheussen, Gro Falkener; Ashikhmin, Ilya; Boldermo, Nora; Kvarner, Else-Norun; Nilsen, Tom Ivar Lund; Marchand, Gunn Hege; Ose, Solveig Osborg; Aasdahl, Lene; Kaspersen, Silje Lill; Bardal, Ellen Marie; Børke, Janne-Birgitte; Mork, Paul Jarle; Gismervik, Sigmund Østgård (Peer reviewed; Journal article, 2021)Introduction: Low back pain (LBP) and neck pain (NP) are common and costly conditions. Self-management is a key element in the care of persistent LBP and NP. Artificial intelligence can be used to support and tailor ... -
Information-Driven Adaptive Sensing Based on Deep Reinforcement Learning
Murad, Abdulmajid; Kraemer, Frank Alexander; Bach, Kerstin; Taylor, Gavin (Chapter, 2020)In order to make better use of deep reinforcement learning in the creation of sensing policies for resource-constrained IoT devices, we present and study a novel reward function based on the Fisher information value. This ... -
IoT Sensor Gym: Training Autonomous IoT Devices with Deep Reinforcement Learning
Murad, Abdulmajid Abdullah Yahya; Kraemer, Frank Alexander; Bach, Kerstin; Taylor, Gavin (Chapter, 2019)We describe IoT Sensor Gym, a framework to train the behavior of constrained IoT devices using deep reinforcement learning. We focus on the main architectural choices to align problems from the IoT domain with cutting-edge ... -
Learning neural representations for the processing of temporal data in deep neutral networks
Måløy, Håkon (Doctoral theses at NTNU;2023:6, Doctoral thesis, 2023)Ever since the third spring of artificial intelligence a decadeago, representation learning through deep neural networks hasbeen the dominating approach for most research in machinelearning. However, typical deep neural ... -
Learning similarity measures from data
Mathisen, Bjørn Magnus; Aamodt, Agnar; Langseth, Helge; Bach, Kerstin (Journal article; Peer reviewed, 2019)Defining similarity measures is a requirement for some machine learning methods. One such method is case-based reasoning (CBR) where the similarity measure is used to retrieve the stored case or a set of cases most similar ... -
A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living
Bach, Kerstin; Kongsvold, Atle Austnes; Bårdstu, Hilde Bremseth; Bardal, Ellen Marie; Kjærnli, Håkon Slåtten; Herland, Sverre; Logacjov, Aleksej; Mork, Paul Jarle (Journal article; Peer reviewed, 2021)Accelerometer-based measurements of physical activity types are commonly used to replace self-reports. To advance the field, it is desirable that such measurements allow accurate detection of key daily physical activity ... -
Machine learning methods for sleep-wake classification using two body-worn accelerometers
Hay, Aileen (Master thesis, 2019)Søvn er en viktig faktor for beskytte en persons fysiske og mentale trivsel. Derfor utføres mange studier som fokuserer på forebygge, diagnostisere og behandle søvnforstyrrelser. En avgjørende del av disse studiene er ... -
Mobile User Interface for a patient-centered health care application
Stokvik, Linn Kristin (Master thesis, 2017)Low back pain is a prevalent issue in the developed world as people adopt a more sedentary lifestyle. This thesis gives insight to available interactive health communication applications for self-managing non-specific low ... -
Modelling Similarity for Comparing Physical Activity Profiles - A Data-Driven Approach
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle (Journal article; Peer reviewed, 2018)Objective measurements of physical behaviour are an interesting research field from the public health and computer science perspective. While for public health research, measurements with a high quality and feasible setup ... -
Monocular Action Classification
Birkeland, Vetle Gustav (Master thesis, 2022)Treningsspill er spill som bruker aspekter som belønninger eller utfordringer fra videospill for å få folk til å trene. Bruk av treningsspill har vist potensiale innenfor fysisk rehabilitering ved å hjelpe pasienter med å ... -
Multi-label image classification with language-image models: an approach for a fine-grained domain-specific dataset
Bynke, Mathias (Master thesis, 2022)Nylige framskritt innen selvveiledede bildemodeller (self-supervised pre-trained image models) har gjort det mulig å bygge gode modeller for oppgavespesifikk (task-specific) bildeklassifisering lettere og med mindre ... -
On the Use of Air Quality Microsensors for Supporting Decision Makers
Bach, Kerstin; Akselsen, Sigmund; Veiga, Tiago Santos; Kalamaras, Ilias (Chapter, 2020)In this poster we present how a network of Internet-of-things (IoT) devices facilitated through machine learning can improve decision making. Our application domain is air quality in the municipality of Trondheim. Ambient ... -
Online Machine Learning for 1-Day-Ahead Prediction of Indoor Photovoltaic Energy
Krämer, Frank Alexander; Asad, Hafiz Areeb; Bach, Kerstin; Renner, Christian (Peer reviewed; Journal article, 2023)We explore the potential for predicting indoor photovoltaic energy on a forecasting horizon of up to 24 hours. The objective is to enable energy management approaches that exploit harvesting opportunities more strategically, ... -
Performance of machine learning models in estimation of ground reaction forces during balance exergaming
Vonstad, Elise Klæbo; Bach, Kerstin; Vereijken, Beatrix; Su, Xiaomeng; Nilsen, Jan Harald (Peer reviewed; Journal article, 2022)Background Balance training exercise games (exergames) are a promising tool for reducing fall risk in elderly. Exergames can be used for in-home guided exercise, which greatly increases availability and facilitates ... -
PertCF: A Perturbation-Based Counterfactual Generation Approach
Bayrak, Betül; Bach, Kerstin (Chapter, 2023)Post-hoc explanation systems offer valuable insights to increase understanding of the predictions made by black-box models. Counterfactual explanations, an instance-based post-hoc explanation method, aim to demonstrate how ...