Sökning: "learning-based"

Visar resultat 1 - 5 av 142 avhandlingar innehållade ordet learning-based.

1. 1. Pith location and annual ring detection for modelling of knots and fibre orientation in structural timber : A Deep-Learning-Based Approach

   Författare :Tadios Habite; Anders Olsson; Osama Abdeljaber; Jan Oscarsson; Welf Löwe; Julie Cool; Linnéuniversitetet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Sawn timber; Pith location; Deep learning; Artificial neural networks; Convolutional neural network; Conditional generative adversarial network; Knot detection; Knot modelling; Knot reconstruction; Fibre orientation; Annual ring profile; Byggteknik; Civil engineering;

   Sammanfattning : Detection of pith, annual rings and knots in relation to timber board cross-sections is relevant for many purposes, such as for modelling of sawn timber and for real-time assessment of strength, stiffness and shape stability of wood materials. However, the methods that are available and implemented in optical scanners today do not always meet customer accuracy and/or speed requirements. LÄS MER

3. 2. Algorithms and Tools for Learning-based Testing of Reactive Systems

   Författare :Muddassar Sindhu; Karl Meinke; Brian Nielsen; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; specification-based testing; learning-based testing; reactive systems; LBTest; case studies;

   Sammanfattning : In this thesis we investigate the feasibility of learning-based testing (LBT) as a viable testing methodology for reactive systems. In LBT, a large number of test cases are automatically generated from black-box requirements for the system under test (SUT) by combining an incremental learning algorithm with a model checking algorithm. LÄS MER

4. 3. Learning-based Testing for Automotive Embedded Systems : A requirements modeling and Fault injection study

   Författare :Hojat Khosrowjerdi; Karl Meinke; Dilian Gurov; Cristina Seceleanu; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Machine learning; fault injection; requirements testing; embedded systems; model checking; automotive software; requirements modeling; Computer Science; Datalogi;

   Sammanfattning : This thesis concerns applications of learning-based testing (LBT) in the automotive domain. In this domain, LBT is an attractive testing solution, since it offers a highly automated technology to conduct safety critical requirements testing based on machine learning. LÄS MER

5. 4. Deep learning based simulation for automotive software development

   Författare :Dhasarathy Parthasarathy; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; automotive software testing; latent space arithmetic; generative adversarial networks; explainable AI; sample selection bias;

   Sammanfattning : The automotive industry is in the midst of a new reality where software is increasingly becoming the primary tool for delivering value to customers. While this has vastly improved their product offerings, vehicle manufacturers are increasingly facing the need to continuously develop, test, and deliver functionality, while maintaining high levels of quality. LÄS MER

7. 5. Harvesting Based Communications for Wireless Control Systems : Event-Trigger and Reinforcement Learning Based Transmission Policies

   Författare :Ruslan Seifullaev; Steffi Knorn; Anders Ahlén; Fredrik Gustafsson; Uppsala universitet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; wireless control systems; energy harvesting; event-triggered control; Lyapunov stability analysis; fading channel; quantized data; Markov models; Bayesian estimation; reinforcement learning; dynamic programming; Electrical Engineering with specialization in Signal Processing; Elektroteknik med inriktning mot signalbehandling;

   Sammanfattning : Wireless control systems have gained considerable attention in recent years due to their numerous advantages, including increased flexibility and scalability, reduced wiring complexity, and cost-efficiency. Despite these benefits, the use of communication networks in control loops poses various challenges, such as sampled data, latency, packet dropouts, etc. LÄS MER