Sökning: "Random forest"

Visar resultat 1 - 5 av 386 uppsatser innehållade orden Random forest.

  1. 1. Convolutional neural networks for semantic segmentation of FIB-SEM volumetric image data

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Fredrik Skärberg; [2020-11-26]
    Nyckelord :Deep learning; convolutional neural networks; image analysis; semantic segmentation; focused ion beam scanning electron microscopy; porous materials; controlled drug release;

    Sammanfattning : Focused ion beam scanning electron microscopy (FIB-SEM) is a well-established microscopytechnique for 3D imaging of porous materials. We investigate three poroussamples of ethyl cellulose microporous films made from ethyl cellulose and hydroxypropylcellulose (EC/HPC) polymer blends. LÄS MER

  2. 2. Clustering and Classification of Time Series in Real-Time Strategy Games - A machine learning approach for mapping StarCraft II games to clusters of game state time series while limited by fog of war

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Olof Enström; Fredrik Hagström; John Segerstedt; Fredrik Viberg; Arvid Wartenberg; David Weber Fors; [2020-10-29]
    Nyckelord :Classification problem; Cluster analysis; Hierarchical clustering; Machine learning; Neural network; Random forest; Real-time strategy; StarCraft II; Time series;

    Sammanfattning : Real-time strategy (RTS) games feature vast action spaces and incomplete information,thus requiring lengthy training times for AI-agents to master them at the level of ahuman expert. Based on the inherent complexity and the strategical interplay betweenthe players of an RTS game, it is hypothesized that data sets of played games exhibitclustering properties as a result of the actions made by the players. LÄS MER

  3. 3. Predicting Pedestrian Counts per Street Segment in Urban Environments

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Simon Karlsson; [2020-07-08]
    Nyckelord :data science; pedestrian movement; machine learning; random forest; negative binomial; spatial morphology; road network; street centrality; built environment; built density; attractions; land division;

    Sammanfattning : Cities are continuously growing all over the world and the complexity of designingurban environments increases. Therefore, there is a need to build a better understandingin how our cities work today. One of the essential parts of this is understandingthe pedestrian movement. LÄS MER

  4. 4. Cropland and tree cover mapping using Sentinel-2 data in an agroforestry landscape, Burkina Faso

    Master-uppsats, Göteborgs universitet/Institutionen för geovetenskaper

    Författare :Ntandokazi Masimula; [2020-06-29]
    Nyckelord :Sentinel-2; Cropland mask; Tree cover estimation; Burkina Faso; Agroforestry; Random Forest;

    Sammanfattning : Sentinel-2, with high spatial resolution bands and increased number of spectral channels,has provided increased capabilities for vegetation mapping. Cropland masks withinheterogeneous areas such as the Sudano-Sahel zone have become useful for monitoringlandscapes. LÄS MER

  5. 5. Deployment failure analysis using machine learning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Joosep Franz Moorits Alviste; [2020]
    Nyckelord :machine learning; log mining; log parsing; pipedrive; deployment failure analysis; failure analysis; classification; log files;

    Sammanfattning : Manually diagnosing recurrent faults in software systems can be an inefficient use of time for engineers. Manual diagnosis of faults is commonly performed by inspecting system logs during the failure time. LÄS MER