Sökning: "nearest neighbor algorithms"

Visar resultat 6 - 10 av 53 uppsatser innehållade orden nearest neighbor algorithms.

  1. 6. Simple RSRP Fingerprint Collection Setup and Indoor Positioning in 5G

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Sofi Flink; Annie Tallund; [2022]
    Nyckelord :5G; indoor positioning; radio fingerprint; k nearest neighbor; naive bayes; automated data collection; Technology and Engineering;

    Sammanfattning : Solving for a way to accurately predict the position of a user equipment is crucial in an array of applications within 5G new radio. One approach is to form unique identifiers, also known as fingerprints, and map them to positional data in an area. LÄS MER

  3. 7. CArDIS: A Swedish Historical Handwritten Character and Word Dataset for OCR

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Shivani Thummanapally; Sakib Rijwan; [2022]
    Nyckelord :Handwritten Text Recognition; Optical Character Recognition; Machine learning methods; historical handwritten character recognition; handwritten character dataset;

    Sammanfattning : Background: To preserve valuable sources and cultural heritage, digitization of handwritten characters is crucial. For this, Optical Character Recognition (OCR) systems were introduced and most widely used to recognize digital characters. LÄS MER

  4. 8. Image classification of pediatric pneumonia : A comparative study of supervised statistical learning techniques

    Kandidat-uppsats, Uppsala universitet/Statistiska institutionen

    Författare :Jacob Rönnefall; Jakob Wendel; [2022]
    Nyckelord :Machine learning; Algorithm; Logistic regression; K-nearest-neighbor; Support vector machine; Neural network; Sensitivity; Specificity; ROC; Accuracy;

    Sammanfattning : A child dies of pneumonia every 39 seconds, and the process of preventing deaths caused by pneumonia has been considerably slower compared to other infectious diseases. Meanwhile, the traditional method of manually diagnosing patients has reached its ceiling on performance. LÄS MER

  5. 9. Recommender system for IT security scanning service : Collaborative filtering in an error report scenario

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

    Författare :Jonas Thunberg; [2022]
    Nyckelord :Collaborative Filtering; Vulnerability Scanning; IT-Security; Recommender System;

    Sammanfattning : Recommender systems have become an integral part of the user interface of many web applications. Recommending items to buy, media to view or similar “next choice”-recommendations has proven to be a powerful tool to improve costumer experience and engagement. LÄS MER

  7. 10. Comparison of Machine Learning Algorithms for Anomaly Detection in Train’s Real-Time Ethernet using an Intrusion Detection System

    Kandidat-uppsats,

    Författare :Trayi Chaganti; Tadi Rohith; [2022]
    Nyckelord :Anomaly detection; Computing methodologies; Machine learning; Real-time Ethernet; Supervised learning;

    Sammanfattning : Background: The train communication network is vulnerable to intrusion assaultsbecause of the openness of the ethernet communication protocol. Therefore, an intru-sion detection system must be incorporated into the train communication network. LÄS MER