Sökning: "Matrix Decomposition"

Visar resultat 1 - 5 av 50 uppsatser innehållade orden Matrix Decomposition.

  1. 1. Fractional Cointegration and Price Discovery in FX Markets

    D-uppsats, Handelshögskolan i Stockholm/Institutionen för nationalekonomi

    Författare :Johan Faxner; [2023]
    Nyckelord :exchange rates; price discovery; fractional cointegration; market microstructure; covered interest rate parity;

    Sammanfattning : I employ bivariate fractionally cointegrated vector autoregressive models to analyze price discovery on the EUR/GBP market. Using daily spot rates between 2010 and 2022 along with corresponding one-month and three-month forward rates, I extract parameter estimates for pairwise long-run relationships, each pair containing a spot and a forward. LÄS MER

  3. 2. Evolving Community Detection in Dynamic Networks using Nonnegative Tensor Decomposition : An Approach Toward Green Networking

    Master-uppsats, Luleå tekniska universitet/Datavetenskap

    Författare :Manasik Hassan Adam Ali; [2023]
    Nyckelord :;

    Sammanfattning : Around 1.8–2.8% of the world’s total greenhouse gas emissions are contributed by the ICT sector, with telecommunications networks accounting for 26.4% of this total ICT share. LÄS MER

  4. 3. Acoustic Characterization of Catalyst

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

    Författare :Surachit Dokson; [2023]
    Nyckelord :;

    Sammanfattning : The WHO has set a sound level threshold of 55 dB, beyond which noise is considered harmful to humans when exposed for an extended period of time. It is, however, estimated by the European Environmental Agency that over 110 million people in the EU are regularly exposed to levels of traffic noise above 55 dB. LÄS MER

  5. 4. The Bloch-Messiah theorem and its application to overlaps

    Kandidat-uppsats, Lunds universitet/Matematisk fysik; Lunds universitet/Fysiska institutionen

    Författare :Frieder Selisko; [2023]
    Nyckelord :Physics and Astronomy;

    Sammanfattning : The Bogoliubov transformation is the starting point for the Hartree-Fock-Bogoliubov method and thus for many theoretical approaches that describe heavy nuclei. This transformation is based on two matrices, denoted by U and V, which are called Bogoliubov amplitudes. In this paper the properties of these matrices are investigated. LÄS MER

  7. 5. Graph Neural Network for Traffic Flow Forecasting : Does an enriched adjacency matrix with low dimensional dataenhance the performance of GNN for traffic flow forecasting?

    Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Fredrik Kortetjärvi; Rohullah Khorami; [2023]
    Nyckelord :Graph Neural Network;

    Sammanfattning : Nowadays, machine learning methods are used in many applications and deployed in manyelectronic devices to solve problems and predict future states. One of the challenges mostbig cities confront is traffic jams since the roads are crammed with more and more vehicles, which will easily cause traffic congestion. LÄS MER