Sökning: "Non-parametric models"

Visar resultat 11 - 15 av 63 uppsatser innehållade orden Non-parametric models.

  1. 11. Improving Brain Tumor Segmentation using synthetic images from GANs

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Aashana Nijhawan; [2021]
    Nyckelord :Image segmentation; Generative Adversarial Networks; GANs; Computer Vision; synthetic images; generator; discriminator; uncertainty estimation; deep neural networks; U-net; PGGAN;

    Sammanfattning : Artificial intelligence (AI) has been seeing a great amount of hype around it for a few years but more so now in the field of diagnostic medical imaging. AI-based diagnoses have shown improvements in detecting the smallest abnormalities present in tumors and lesions. This can tremendously help public healthcare. LÄS MER

  3. 12. Quantifying nitrogen oxides and ammonia via frequency modulation in gas sensors

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Marcos Freitas Mourao dos Santos; [2021]
    Nyckelord :Nitrogen oxides; nox; ammonia; sic-fet; PLSR; quantification;

    Sammanfattning : The use of Silicon Carbide Field Effect Transistor (SiC-FET) sensors in cyclic operation is a proven way to quantify different gases. The standard workflow involves extracting shape-defining features such as averages and slopes of the sensor signal. LÄS MER

  4. 13. The Broker's Invisible Ties : Brokerage and Balance in Signed Networks

    Master-uppsats, Linköpings universitet/Institutet för analytisk sociologi, IAS; Linköpings universitet/Filosofiska fakulteten

    Författare :Paul Schuler; [2021]
    Nyckelord :;

    Sammanfattning : Brokerage is one of the most popular and well-studied concepts in the literature on social networks. It has so far been analysed, however, without taking negative ties in so-called signed networks into account. The central role of tension for brokerage motivates an integration with the hitherto not explicitly related social balance theory. LÄS MER

  5. 14. Early-Stage Prediction of Lithium-Ion Battery Cycle Life Using Gaussian Process Regression

    Master-uppsats, KTH/Matematisk statistik

    Författare :Love Wikland; [2020]
    Nyckelord :Statistical learning; prediction; regression; Gaussian processes; lithium-ion battery; battery health; battery lifetime; Statistisk inlärning; prediction; regression; Gaussiska processer; litiumjonbatteri; batterihälsa; batterilivstid;

    Sammanfattning : Data-driven prediction of battery health has gained increased attention over the past couple of years, in both academia and industry. Accurate early-stage predictions of battery performance would create new opportunities regarding production and use. LÄS MER

  7. 15. Traffic State Estimation for Signalized Intersections : A Combined Gaussian Process Bayesian Filter Approach

    Master-uppsats, KTH/Transportplanering

    Författare :Michael Sederlin; [2020]
    Nyckelord :Traffic State Estimation; Traffic Flow modelling; Gaussian Processes; Bayesian Filtering; Kalman Filter; Traffic Signals; Intersection; Non-parametric;

    Sammanfattning : Traffic State Estimation (TSE) is a vital component in traffic control which requires an accurate viewof the current traffic situation. Since there is no full sensor coverage and the collected measurementsare inflicted with random noise, statistical estimation techniques are necessary to accomplish this. LÄS MER