Sökning: "modeller och metoder"

Visar resultat 21 - 25 av 1118 uppsatser innehållade orden modeller och metoder.

  1. 21. Simulations of a self-stabilizing fully submerged hydrofoil

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Henry Jacobson; [2023]
    Nyckelord :Hydrofoil; Self-Stabilizing; Lifting Line Theory; Fluid Mechanics; Numerical Methods; Backward Differentiation Formula; Fully Submerged Hydrofoil; Bärplan; bärplansbåt; självstabiliserande; lyftande linjeteori; strömningsme- kanik; numeriska metoder; Backward Differentiation Formula; fullt nedsänkt bärplan;

    Sammanfattning : Two models of a self-stabilizing hydrofoil system is developed where the effects from the struts and hydrofoil give torques for angular rotations. Lifting line theory for the hydrofoil which can twist is used. Nonlinear versions of the models are also developed and compared to find that the linear models use valid approximations. LÄS MER

  3. 22. Transformer Offline Reinforcement Learning for Downlink Link Adaptation

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Alexander Mo; [2023]
    Nyckelord :Link Adaptation; Transformers; Reinforcement Learning; Sequence Modelling; Decision Transformer; Deep Neural Networks; Radio Resource Management; Telecommunication; Länkanpassning; Transformers; Reinforcement Learning; Sekvensmodellering; Beslutsstöd; Djupa neurala nätverk; Dataresurshantering; Telekommunikation;

    Sammanfattning : Recent advancements in Transformers have unlocked a new relational analysis technique for Reinforcement Learning (RL). This thesis researches the models for DownLink Link Adaptation (DLLA). LÄS MER

  4. 23. Machine Learning Model for Localization in an Urban Environment

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Erik Wallinder-Mähler; Magdalena Björk; [2023]
    Nyckelord :;

    Sammanfattning : The indoor localization problem has seen great improvements during the last tenyears and today it is possible to determine the location of electronic devices, such assmartphones, with centimeter precision. The aim of this project is to apply similar localizationmethods on multichannel antenna data gathered outdoors in an urban environment andanalyze the viability of this approach. LÄS MER

  5. 24. Adaptive Model-Based Temperature Monitoring for Electric Powertrains : Investigation and Comparative Analysis of Transfer Learning Approaches

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Chenzhou Huang; [2023]
    Nyckelord :Transfer Learning; Condition Monitoring; Domain Adaptation; Neural Network; Powerstrain.; Siirto-oppiminen; kunnonvalvonta; verkkotunnuksen mukauttaminen; neuroverkko; voimansiirto.; Överföring lärande; tillståndsövervakning; domänanpassning; neuralt nätverk; Powerstrain;

    Sammanfattning : In recent years, deep learning has been widely used in industry to solve many complex problems such as condition monitoring and fault diagnosis. Powertrain condition monitoring is one of the most vital and complicated problems in the automation industry since the condition of the drive affects its health, performance, and reliability. LÄS MER

  7. 25. Identification and Classification of TTS Intelligibility Errors Using ASR : A Method for Automatic Evaluation of Speech Intelligibility

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Erik Henriksson; [2023]
    Nyckelord :Automatic Speech Recognition; Natural Language Processing; Speech Technology; Speech Quality Assessment; Text-To-Speech; Taligenkänning; Språkteknologi; Talkvalitetsbedömning; Talsyntes;

    Sammanfattning : In recent years, applications using synthesized speech have become more numerous and publicly available. As the area grows, so does the need for delivering high-quality, intelligible speech, and subsequently the need for effective methods of assessing the intelligibility of synthesized speech. LÄS MER