Blar i SINTEF Open på forfatter "Husom, Erik Johannes"
-
AutoConf: Automated Configuration of Unsupervised Learning Systems using Metamorphic Testing and Bayesian Optimization
Shar, Lwin Khin; Goknil, Arda; Husom, Erik Johannes; Sen, Sagar; Tun, Yan Naing; Kim, Kisub (Chapter, 2023)Unsupervised learning systems using clustering have gained significant attention for numerous applications due to their unique ability to discover patterns and structures in large unlabeled datasets. However, their ... -
A blockchain-based framework for trusted quality data sharing towards zero-defect manufacturing
Isaja, Mauro; Nguyen, Phu Hong; Goknil, Arda; Sen, Sagar; Husom, Erik Johannes; Tverdal, Simeon; Anand, Abhilash Ramanathapuram; Jiang, Yunman; Pedersen, Karl John; Myrseth, Per; Stang, Jørgen; Niavis, Harris; Pfeifhofer, Simon; Lamplmair, Patrick (Peer reviewed; Journal article, 2023)There is a current wave of a new generation of digital solutions based on intelligent systems, hybrid digital twins and AI-driven optimization tools to assure quality in smart factories. Such digital solutions heavily ... -
Bridging the Gap Between Java and Python in Mobile Software Development to Enable MLOps
Dautov, Rustem; Husom, Erik Johannes; Gonidis, Fotis; Papatzelos, Spyridon; Malamas, Nikolaos (Chapter; Peer reviewed, 2022)The role of Machine Learning (ML) engineers in mobile development has become increasingly important in recent years, as more and more business-critical mobile applications depend on AI components. Many development teams ... -
Deep learning to predict power output from respiratory inductive plethysmography data
Husom, Erik Johannes; Bernabé, Pierre; Sen, Sagar (Peer reviewed; Journal article, 2022)Power output is one of the most accurate methods for measuring exercise intensity during outdoor endurance sports, since it records the actual effect of the work performed by the muscles over time. However, power meters ... -
Machine Learning for Fatigue Detection using Fitbit Fitness Trackers
Husom, Erik Johannes; Dautov, Rustem; Nedisan Videsjorden, Adela; Gonidis, Fotis; Papatzelos, Spyridon; Malamas, Nikolaos (Chapter, 2022)Fatigue can be a pre-cursor to many illnesses and injuries, and cause fatal work-related incidents. Fatigue detection has been traditionally performed in lab conditions with stationary medical-grade diagnostics equipment ... -
On The Reliability Of Machine Learning Applications In Manufacturing Environments
Jourdan, Nicolas; Sen, Sagar; Husom, Erik Johannes; Garcia-Ceja, Enrique; Biegel, Tobias; Metternich, Joachim (Chapter, 2021)The increasing deployment of advanced digital technologies such as Internet of Things (IoT) devices and Cyber-Physical Systems (CPS) in industrial environments is enabling the productive use of machine learning (ML) ... -
Replay-Driven Continual Learning for the Industrial Internet of Things
Sen, Sagar; Nielsen, Simon; Husom, Erik Johannes; Goknil, Arda; Tverdal, Simeon; Pinilla, Leonardo (Chapter, 2023)The Industrial Internet of Things (IIoT) leverages thousands of interconnected sensors and computing devices to monitor and control large and complex industrial processes. Machine learning (ML) applications in IIoT use ... -
Taming Data Quality in AI-Enabled Industrial Internet of Things
Sen, Sagar; Husom, Erik Johannes; Goknil, Arda; Tverdal, Simeon; Nguyen, Phu Hong; Mancisidor, Iker (Peer reviewed; Journal article, 2022)We address the problem of taming data quality in artificial intelligence (AI)-enabled Industrial Internet of Things systems by devising machine learning pipelines as part of a decentralized edge-to-cloud architecture. We ... -
Towards MLOps in Mobile Development with a Plug-in Architecture for Data Analytics
Dautov, Rustem; Husom, Erik Johannes; Gonidis, Fotis (Chapter, 2022)Smartphones are increasingly used as universal IoT gateways collecting data from connected sensors in a wide range of industrial applications. With the increasing computing capabilities, they are used not just for simple ... -
UDAVA: an unsupervised learning pipeline for sensor data validation in manufacturing
Husom, Erik Johannes; Tverdal, Simeon; Goknil, Arda; Sen, Sagar (Chapter, 2022)Manufacturing has enabled the mechanized mass production of the same (or similar) products by replacing craftsmen with assembly lines of machines. The quality of each product in an assembly line greatly hinges on continual ... -
Uncertainty-aware Virtual Sensors for Cyber-Physical Systems
Sen, Sagar; Husom, Erik Johannes; Goknil, Arda; Tverdal, Simeon; Nguyen, Phu Hong (Peer reviewed; Journal article, 2023)We present a data pipeline to train and deploy uncertainty-aware virtual sensors in cyber-physical systems. Our virtual sensor predicts the expected values of a physical sensor and a standard deviation indicating the degree ... -
Virtual sensors for erroneous data repair in manufacturing a machine learning pipeline
Sen, Sagar; Husom, Erik Johannes; Goknil, Arda; Politaki, Dimitra; Tverdal, Simeon; Nguyen, Phu Hong; Jourdan, Nicolas (Peer reviewed; Journal article, 2023)Manufacturing converts raw materials into finished products using machine tools for controlled material removal or deposition. It can be observed using sensors installed within and around machine tools. These sensors measure ...