Sökning: "k-NN"

Visar resultat 1 - 5 av 27 uppsatser innehållade ordet k-NN.

  1. 1. Maskininlärning för diagnosticering av perifer neuropati

    Kandidat-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Margareta Carlerös; Nina Malmqvist; Josefin Nilsson; Fredrik Skärberg; [2019-07-02]
    Nyckelord :Klassificering; AI; Statistiskinlärning; k-NN; Slumpmässig skog; Neurala nätverk; Medicinsk diagnostik; Dynamiskt Svettest;

    Sammanfattning : This report investigates the possibility of diagnosing peripheral neuropathy with the help ofnon-parametic classification methods. Peripheral neuropathy is a disease state characterizedby damage on the nerves furthest out in the nervous system, with symptoms first occuring inthe feet. The data used in this project comes from Dr. LÄS MER

  2. 2. Crime Prediction in Swedish Municipalities with machine learning algorithms

    Kandidat-uppsats, Lunds universitet/Statistiska institutionen

    Författare :Nils Dominguez Berndtsson; [2019]
    Nyckelord :Crime rates; machine learning algorithms; Random forest; K-NN; Mathematics and Statistics;

    Sammanfattning : In this thesis we use a number of common machine learning algorithms to predict crime rates in Swedish municipalities. As predictors we use a mix of municipal socioeconomic variables. For some years we are able to correctly classify up to 85% of the municipalities that have a high crime rate. LÄS MER

  3. 3. Fraud or Not?

    Kandidat-uppsats, Uppsala universitet/Statistiska institutionen

    Författare :Thea Åkerblom; Tobias Thor; [2019]
    Nyckelord :Logistic Regression; K-Nearest Neighbour; classification; random forest; fraud; transactions and statistical learning;

    Sammanfattning : This paper uses statistical learning to examine and compare three different statistical methods with the aim to predict credit card fraud. The methods compared are Logistic Regression, K-Nearest Neighbour and Random Forest. LÄS MER

  4. 4. Diagnostics and Prognostics of safety critical systems using machine learning, time and frequency domain analysis

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för tillämpad signalbehandling

    Författare :Pratik Purkayastha; [2019]
    Nyckelord :Diagnostics; Prognostics; PHM; predictive maintenance;

    Sammanfattning : The prime focus of this thesis was to develop a robust Prognostic and Diagnostic Health Management module (PDHM), capable of detecting faults, classifying faults, fault progression tracking and estimating time to failure. Priority was to obtain as much accuracy as possible with the bare minimum amount of sensors as possible. LÄS MER

  5. 5. IoT for fresh water quality monitoring

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

    Författare :Duarte Maher; [2018]
    Nyckelord :IoT; Machine Learning; Water Quality Monitoring; iWater; IoT; Maskininlärning; Vattenkvalitetsövervakning; iWater;

    Sammanfattning : Water is one of the most important resources in the world. It has direct impact on the daily life ofmankind and sustainable development of society. Water quality affects biological life and has to obeystrict regulations. Traditional water quality assurance methods, used today, involve manual samplingfollowed by laboratory analysis. LÄS MER