Sökning: "data preprocessing"

Visar resultat 21 - 25 av 204 uppsatser innehållade orden data preprocessing.

  1. 21. Fault Detection and Diagnosis for Automotive Camera using Unsupervised Learning

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

    Författare :Ziyou Li; [2023]
    Nyckelord :Unsupervised Learning; Autoencoders; Image Clustering; Fault Detection and Diagnosis; Morphological Operations; Hardware-in-Loop; Advanced DriverAssistance System; Oövervakad inlärning; Autoencoders; Bildklustering; Felfindning och Diagnostik; Morfologiska Operationer; Hardware-in-Loop; Avancerade Förarassistanssystem;

    Sammanfattning : This thesis aims to investigate a fault detection and diagnosis system for automotive cameras using unsupervised learning. 1) Can a front-looking wide-angle camera image dataset be created using Hardware-in-Loop (HIL) simulations? 2) Can an Adversarial Autoencoder (AAE) based unsupervised camera fault detection and diagnosis method be crafted for SPA2 Vehicle Control Unit (VCU) using an image dataset created using Hardware-inLoop? 3) Does using AAE surpass the performance of using Variational Autoencoder (VAE) for the unsupervised automotive camera fault diagnosis model? In the field of camera fault studies, automotive cameras stand out for its complex operational context, particularly in Advanced Driver-Assistance Systems (ADAS) applications. LÄS MER

  3. 22. Automatic Analysis of Peer Feedback using Machine Learning and Explainable Artificial Intelligence

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

    Författare :Kevin Huang; [2023]
    Nyckelord :Text classification; Peer feedback; Explainable Artificial Intelligence; BERT; RoBERTa; DistilBERT; Decision Tree; MLP; CSCL; STEM education; Textklassificering; Feedback till kamrater; Förklarig Artificiell Intelligens; BERT; RoBERTa; DistilBERT; Decision Tree; MLP; CSCL; STEM-utbildning;

    Sammanfattning : Peer assessment is a process where learners evaluate and provide feedback on one another’s performance, which is critical to the student learning process. Earlier research has shown that it can improve student learning outcomes in various settings, including the setting of engineering education, in which collaborative teaching and learning activities are common. LÄS MER

  4. 23. ESPRIT for DOA estimation

    Kandidat-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Filip Grimsholm; Martin Saarmann; [2023]
    Nyckelord :ESPRIT; FMCW; DOA; radar; estimation; comparison; ESPRIT; FMCW; DOA; radar; estimering; jämförelse;

    Sammanfattning : Radar is a tool that has had a tremendous impact since its discovery. This thesis evaluates an algorithm called ESPRIT. ESPRIT is used in radar to estimate the angles to detected objects. The angle of an object is referred to as its DOA (Direction of arrival). LÄS MER

  5. 24. Cell Tower Localization using crowdsourced measurments

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

    Författare :Carlos Escandón Álvarez; [2023]
    Nyckelord :Cell Tower Geolocation; Crowdsourced Measurements; Positioning; Machine Learning; Neural Networks;

    Sammanfattning : This thesis explores the application of a neural network approach to cell tower localization using crowdsourced measurements. The deployment of cell tower infrastructure has been increasing exponentially in recent times as it is a crucial element of mobile communications. LÄS MER

  7. 25. Optimizing Consensus Protocols with Machine Learning Models : A cache-based approach

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

    Författare :Kun Wu; [2023]
    Nyckelord :Distributed Systems; Consensus Algorithms; Machine Learning; Caching; Distribuerade system; Konsensusalgoritmer; Maskininlärning; Cachning;

    Sammanfattning : Distributed systems offer a reliable and scalable solution for tackling massive and complex tasks that cannot be handled by a single computer. However, standard consensus protocols used in such systems often replicate data without considering the workload, leading to unnecessary retransmissions. LÄS MER