Sökning: "feature dependencies"

Visar resultat 1 - 5 av 29 uppsatser innehållade orden feature dependencies.

  1. 1. Handling Third-Party Component Licenses:A Case Study in a Swedish Company : How well do existing license management tools detect potentially unsafe third-party component licenses?

    Kandidat-uppsats, Högskolan Dalarna/Informatik

    Författare :Fanny Bruckner; Isac Njie; [2023]
    Nyckelord :Third-party components; software licenses; component analysis tools;

    Sammanfattning : Modern software development relies heavily on third-party components, which are pre-built software modules developed by other organisations and can be either open-source or commercial. These components serve as building blocks for developers to create complex applications more efficiently. LÄS MER

  3. 2. Potassium in the Galactic Bulge - as traced by microlensed dwarf & sub-giant stars

    Kandidat-uppsats, Lunds universitet/Astrofysik; Lunds universitet/Fysiska institutionen

    Författare :Lukas Jönsson; [2023]
    Nyckelord :Nucleosynthesis; Galactic Bulge; Potassium; Non-Local-Thermal-Equilibrium; Physics and Astronomy;

    Sammanfattning : During this report the potassium (K) trend in the Galactic Bulge, with respect to metallicity and various α-elements, has been computed and evaluated by a method of line synthesis on the 7698.96 ̊A KI line (7699 KI), where Non-Local-Thermal-Equilibrium (NLTE) effects have been considered. LÄS MER

  4. 3. A Deep Learning Approach To Vehicle Fault Detection Based On Vehicle Behavior

    Master-uppsats, Malmö universitet/Institutionen för datavetenskap och medieteknik (DVMT)

    Författare :Rafi Khaliqi; Cozma Iulian; [2023]
    Nyckelord :Deep learning; attention mechanism; vehicle fault detection; CNN; Bi-LSTM; Bi-GRU; Supervised classification;

    Sammanfattning : Vehicles and machinery play a crucial role in our daily lives, contributing to our transportationneeds and supporting various industries. As society strives for sustainability, the advancementof technology and efficient resource allocation become paramount. LÄS MER

  5. 4. Development of a Novel Heterogeneous Distance Measure with Enhanced Treatment of Ordinal Features

    Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

    Författare :Elina Zake; Salam Hilmi; [2023]
    Nyckelord :;

    Sammanfattning : The rapid generation of data from various sources has led to the emergence of Big Data, characterized by heterogeneity in terms of different types of variables. Machine learning approaches have been utilized to deal with this data, but there is a lack of uniformity in the application of distance measures for this type of data. LÄS MER

  7. 5. LSTM-based Directional Stock Price Forecasting for Intraday Quantitative Trading

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

    Författare :Isabella Mustén Ross; [2023]
    Nyckelord :Deep Learning; Long-Short-Term-Memory LSTM ; ARIMA; Financial Time Series Forecasting; Algorithmic Trading; Intraday Trading; Stock Prediction; Djupinlärning; LSTM; ARIMA; finansiella tidsserier; algoritmisk aktiehandel; intradagshandel; aktieprediktion;

    Sammanfattning : Deep learning techniques have exhibited remarkable capabilities in capturing nonlinear patterns and dependencies in time series data. Therefore, this study investigates the application of the Long-Short-Term-Memory (LSTM) algorithm for stock price prediction in intraday quantitative trading using Swedish stocks in the OMXS30 index from February 28, 2013, to March 1, 2023. LÄS MER