Blar i Institutt for teknisk kybernetikk på forfatter "Rasheed, Adil"
-
A deep learning enabler for non-intrusive reduced order modeling of fluid flows
Pawar, Suraj; Rahman, Sk. Mashfiqur; Vaddireddy, H; San, Omer; Rasheed, Adil; Vedula, Prakash (Journal article; Peer reviewed, 2019)In this paper, we introduce a modular deep neural network (DNN) framework for data-driven reduced order modeling of dynamical systems relevant to fluid flows. We propose various DNN architectures which numerically predict ... -
A proof-of-concept Digital Twin implementation for monitoring patients through the Clinical Pathway for Prostate Cancer in the Norwegian Health and Care Service
Pedersen, Olav Landmark (Master thesis, 2021) -
A strategy controller for concave obstacle avoidance
Nakken, Daniel (Master thesis, 2021)Denne masteroppgaven utforsker potensialet av forsterkende læring (engelsk: reinforcement learning) for applikasjoner av robotisk manipulator kollisjons unngåelse. Oppgaven presenterer en Proximal Policy Optimization (PPO) ... -
Applications of Data-Driven Equation Discovery to Synthetic and Experimental Data
Sandvik, Fredrik Pettersen (Master thesis, 2021)Fysikkbasert modellering kan være svært nøyaktig og oversiktlig, men krever omfattende kunnskap om dynamikken i systemet man ønsker å modellere. Datadrevne metoder kan i stedet basere seg på observasjonsdata og ikke ... -
Applying Object Detection to Marine Data and Exploring Explainability of a Fully Convolutional Neural Network Using Principal Component Analysis
Stavelin, Peter Herman; Rasheed, Adil; San, Omer; Hestnes, Arne Johan (Peer reviewed; Journal article, 2021)With the rise of focus on man made changes to our planet and wildlife therein, more and more emphasis is put on sustainable and responsible gathering of resources. In an effort to preserve maritime wildlife the Norwegian ... -
Artificial intelligence-driven digital twin of a modern house demonstrated in virtual reality
Elfarri, Elias Mohammed; Rasheed, Adil; San, Omer (Peer reviewed; Journal article, 2023)A digital twin is a powerful tool that can help monitor and optimize physical assets in real-time. Simply put, it is a virtual representation of a physical asset, enabled through data and simulators, that can be used for ... -
Big Data Analytics As a Tool to Monitor Hydrodynamic Performance of a Ship
Gupta, Prateek; Steen, Sverre; Rasheed, Adil (Chapter, 2019)A modern ship is fitted with numerous sensors and Data Acquisition Systems (DAQs) each of which can be viewed as a data collection source node. These source nodes transfer data to one another and to one or many centralized ... -
Building a digital twin of the thermodynamic behaviour of a building using hybrid modeling
Myklebust, Annfrid Hopland (Master thesis, 2022)Denne oppgaven presenterer et Hybrid Analysis and Modeling(HAM) rammeverk med det formål å realisere en prediktiv digital tvilling (DT) av den termodynamiske oppførselen til en boligbygning. En DT er en digital ... -
COLREG-Compliance for Autonomous Surface Vehicles using Deep Reinforcement Learning
Heiberg, Amalie (Master thesis, 2020)Bruken av og forskning innen autonome systemer har økt kraftig i senere år, inkludert i marin sektor. Ettersom transportsektoren samtidig gjennomgår en omfattende elektrifisering, lover autonom skipsfart ikke bare reduserte ... -
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning
Meyer, Eivind; Heiberg, Amalie; Rasheed, Adil; San, Omer (Peer reviewed; Journal article, 2020)Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading ... -
Combining Grid-Based Uncertainty Propagation and Neural Networks With Uncertainty Estimation
Vesterkjær, Eirik Ekjord (Master thesis, 2020)Punktbaserte metoder for deterministisk videresending av usikkerhet kan benyttes i kombinasjon med usikkerhetsestimering for nevrale nettverk. Dette kan brukes for å modellere dynamiske tilstandsromprosesser samt deres ... -
Combining physics-based and data-driven techniques for reliable hybrid analysis and modeling using the corrective source term approach
Blakseth, Sindre Stenen; Rasheed, Adil; Kvamsdal, Trond; San, Omer (Peer reviewed; Journal article, 2022)Upcoming technologies like digital twins, autonomous, and artificial intelligent systems involving safety–critical applications require accurate, interpretable, computationally efficient, and generalizable models. ... -
A Comparative Study of Sparsity Promoting Techniques in Neural Network for Modeling Non-Linear Dynamics
Haugstvedt, Emil Johannesen; Mino Calero, Alberto; Lundby, Erlend Torje Berg; Rasheed, Adil; Gravdahl, Jan Tommy (Journal article; Peer reviewed, 2023)Sparsity-promoting techniques show promising results in improving the generalization of neural networks. However, the literature contains limited information on how different sparsity techniques affect generalization when ... -
Comparing Deep Reinforcement Learning Algorithms’ Ability to Safely Navigate Challenging Waters
Larsen, Thomas Nakken; Teigen, Halvor Ødegård; Laache, Torkel; Varagnolo, Damiano; Rasheed, Adil (Peer reviewed; Journal article, 2021)Reinforcement Learning (RL) controllers have proved to effectively tackle the dual objectives of path following and collision avoidance. However, finding which RL algorithm setup optimally trades off these two tasks is not ... -
Convolutional Neural Network and Generative Adversarial Networks Enabled Resolution Enhancement of Numerical Simulations
Tran, Duy Tan Huynh (Master thesis, 2020)Optimal vindmølleplassering og prognoser av vindmøllers kraftproduksjon krever nøyaktig kunnskap om vindfeltet. Generelt blir målekampanjer foretatt for å innhente informasjon om de rådende vindforholdene i et bestemt ... -
Data-Driven Dynamical Modeling in the Face of Data Limitations
Lundby, Erlend Torje Berg (Doctoral theses at NTNU;2023:206, Doctoral thesis, 2023)Data-driven modeling has experienced an enormous increase in popularity recent years due to the ever-growing data abundance, access to cheap computational resources and great advances in algorithms and methodology. This ... -
Data-driven recovery of hidden hysics in reduced order modeling of fluid flows
Pawar, Suraj; Ahmed, Shady E; San, Omer; Rasheed, Adil (Peer reviewed; Journal article, 2020)In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework ... -
Data-driven recovery of hidden physics in reduced order modeling of fluid flows
Pawar, Suraj; Ahmed, Shady E; San, Omer; Rasheed, Adil (Peer reviewed; Journal article, 2020)In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework ... -
Deep learning assisted physics-based modeling of aluminum extraction process
Robinson, Haakon; Lundby, Erlend Torje Berg; Rasheed, Adil; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2023)Modeling complex physical processes such as the extraction of aluminum is mainly done using pure physics-based models derived from first principles. However, the accuracy of these models can often suffer due to a partial ... -
Deep neural network enabled corrective source term approach to hybrid analysis and modeling
Blakseth, Sindre Stenen; Rasheed, Adil; Kvamsdal, Trond; San, Omer (Peer reviewed; Journal article, 2022)In this work, we introduce, justify and demonstrate the Corrective Source Term Approach (CoSTA)—a novel approach to Hybrid Analysis and Modeling (HAM). The objective of HAM is to combine physics-based modeling (PBM) and ...