Essays about: "Datasamling"

Showing result 1 - 5 of 8 essays containing the word Datasamling.

  1. 1. Data Collection and Layout Analysis on Visually Rich Documents using Multi-Modular Deep Learning.

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Mattias Stahre; [2022]
    Keywords : DeepLearning; Machine Learning; Dataset Collection; Annotation; Labeling; Transformer Network; Multi-Modal; Computer Vision; Natural Language Processing; Embedding; LayoutLMv2; DocBank; Djupinlärning; Maskininlärning; Datasamling; Annotering; Märkning; Transformernätverk; Multi-modulär; Datorsyn; Naturlig Språkbehandling; Inbäddning; LayoutLMv2; DocBank;

    Abstract : The use of Deep Learning methods for Document Understanding has been embraced by the research community in recent years. A requirement for Deep Learning methods and especially Transformer Networks, is access to large datasets. READ MORE

  3. 2. Investigating Search Algorithms for Shorter Documents : A study on how to search for titles

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Lara Rostami; [2022]
    Keywords : information retrieval; search engine; search algorithm; BM25; short documents; titles; title search; informationssökning; sökmotor; sökalgoritm; BM25; korta dokument; titlar; titelsökning;

    Abstract : The objective of this thesis was to explore whether there are alternatives to the established search ranking algorithm Best Matching 25 (BM25) when searching for shorter documents, in particular for the search of titles. Five search engines were compared to BM25, three of them being variants of the BM25 algorithm and the other two being based on a binary independence model that does not take term frequency or length normalisation into account. READ MORE

  4. 3. Evasion Attacks Against Behavioral Biometric Continuous Authentication Using a Generative Adversarial Network

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Herman Blenneros; Erik Sävenäs; [2021]
    Keywords : Continuous Authentication; Generative Adversarial Network; evasion; biometrics;

    Abstract : The aim of the project was to examine the feasibilityof evading continuous authentication systems with a generativeadversarial network. To this end, a group of supervised andunsupervised state-of-the-art classifiers were trained on a publiclyavailable dataset of stroke patterns on mobile devices. READ MORE

  5. 4. IR Image Macine Learning for Smart Homes

    University essay from Högskolan i Halmstad/Akademin för informationsteknologi

    Author : Amanda Nerborg; Elias Josse; [2020]
    Keywords : machine learning; infrared radiation; low resolution; Panasonic Grid-EYE; human detection;

    Abstract : Sweden is expecting an aging population and a shortage of healthcare professionals in the near future. This amounts to problems like providing a safe and dignified life for the elderly both economically and practically. Technical solutions that contribute to safety, comfort and quick help when needed is essential for this future. READ MORE

  6. 5. Mobile Device Gaze Estimation with Deep Learning : Using Siamese Neural Networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Julien Adler; [2019]
    Keywords : Siamese Neural Network; GazeCapture; Gaze Estimation; Mobile; Unconstrained; Calibration Points;

    Abstract : Gaze tracking has already shown to be a popular technology for desktop devices. When it comes to gaze tracking for mobile devices, however, there is still a lot of progress to be made. There’s still no high accuracy gaze tracking available that works in an unconstrained setting for mobile devices. READ MORE