Sökning: "HMM"

Visar resultat 1 - 5 av 49 uppsatser innehållade ordet HMM.

  1. 1. Online intra-day portfolio optimization using regime based models

    Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Matematisk statistik

    Författare :Sara Hafström Fremlin; [2019]
    Nyckelord :Multi-period portfolio selection; Model predictive control; Hidden Markov model; Mathematics and Statistics;

    Sammanfattning : In this thesis model predictive control (MPC) is used to dynamically optimize a portfolio where the data is sampled every 5 minutes. Previous research has shown how MPC optimization applied to daily sampled financial data can generate a portfolio that exceeds the value of standard portfolio strategies such as Strategic asset allocation. LÄS MER

  2. 2. Speech recognition for telephone conversations in Icelandic using Kaldi

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

    Författare :Thorsteinn Dadi Gunnarsson; [2019]
    Nyckelord :;

    Sammanfattning : In this thesis we train and evaluate an Automatic Speech Recognition system for phone communication in Icelandic. We use Kaldi, an open source toolkit, to build both GMM-HMM and Neural Network based models for general speech recognition in Icelandic. LÄS MER

  3. 3. A comparative study between algorithms for time series forecasting on customer prediction : An investigation into the performance of ARIMA, RNN, LSTM, TCN and HMM

    Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

    Författare :Olof Almqvist; [2019]
    Nyckelord :machine learning; deep learning; time series forecasting; time series regression; data science; prediction; crisp-dm; keras; markov model; neural network; exploratory data analysis; maskininlärning; djupinlärning; tidsserieprediktion; tidsserieprognos; neurala nätverk; markovmodell; explorativ dataanalys; dataanalys;

    Sammanfattning : Time series prediction is one of the main areas of statistics and machine learning. In 2018 the two new algorithms higher order hidden Markov model and temporal convolutional network were proposed and emerged as challengers to the more traditional recurrent neural network and long-short term memory network as well as the autoregressive integrated moving average (ARIMA). LÄS MER

  4. 4. Supersonic Retro Propulsion Flight Vehicle Engineering of a Human Mission to Mars

    Master-uppsats, Luleå tekniska universitet/Rymdteknik

    Författare :Hanna Marklund; [2019]
    Nyckelord :Supersonic retro propulsion; SRP; Mars; Human mission; Inflatable heat shield;

    Sammanfattning : A manned Mars mission will require a substantial increase in landed mass compared to previous robotic missions, beyond the capabilities of current Entry Descent and Landing, EDL, technologies, such as blunt-body aeroshells and supersonic disk-gap-band parachutes. The heaviest payload successfully landed on Mars to date is the Mars Science Laboratory which delivered the Curiosity rover with an approximate mass of 900 kg. LÄS MER

  5. 5. A Multi-Target Graph-Constrained HMM Localisation Approach using Sparse Wi-Fi Sensor Data

    Master-uppsats, KTH/Optimeringslära och systemteori; KTH/Optimeringslära och systemteori

    Författare :Simon Danielsson; Jakob Flygare; [2018]
    Nyckelord :Hidden Markov Model; Localisation; Wi-Fi Sensors; Forward-Backward Algorithm; Baum-Welch Algorithm; Machine Learning; Time Series Analysis.; Hidden Markov Model; Lokalisering; Wi-Fi Sensorer; Forward-Backward Algoritm; Baum-Welch Algoritm; Maskinlärning; Tidsserieanalys.;

    Sammanfattning : This thesis explored the possibilities of using a Hidden Markov Model approach for multi-target localisation in an urban environment, with observations generated from Wi-Fi sensors. The area is modelled as a network of nodes and arcs, where the arcs represent sidewalks in the area and constitutes the hidden states in the model. LÄS MER