Sökning: "Long short-term memory network"

Visar resultat 1 - 5 av 125 uppsatser innehållade orden Long short-term memory network.

  1. 1. Investigation of Machine Learning Methods for Anomaly Detection and Characterisation of Cable Shoe Pressing Processes

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Elliot Härenby Deak; [2021]
    Nyckelord :Machine Learning; LSTM; kNN; Time-series Classification; Anomaly Detection;

    Sammanfattning : The ability to reliably connect electrical cables is important in many applications. A poor connection can become a fire hazard, so it is important that cables are always appropriately connected. This thesis investigates methods for monitoring of a machine that presses cable connectors onto cables. LÄS MER

  2. 2. Anomaly Detection on Embedded Sensor Processing Platform

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

    Författare :Yichen Cao; [2021]
    Nyckelord :Anomaly Detection; ARIMA; STL; LSTM; VAR; Avvikelsedetektion; ARIMA; STL; LSTM; VAR;

    Sammanfattning : Embedded platforms are often used as a sensor data processing node to collect data and transmit the data to the remote server. Due to the poor performance and power limitation, data processing was often left to the remote server. LÄS MER

  3. 3. Machine-Learning for Lattice Models in and out of Equilibrium

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

    Författare :Johannes Sandberg; [2021]
    Nyckelord :Physics and Astronomy;

    Sammanfattning : Machine-learning methods have in recent years seen a great deal of use in condensed matter physics. In this thesis we apply such methods, specifically machine-learning with artificial neural networks, to the equilibrium and non-equilibrium description of the Hubbard and Hubbard-Holstein models. LÄS MER

  4. 4. Detecting Signal Corruptions in Voice Recordings for Speech Therapy

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

    Författare :Helmer Nylén; [2021]
    Nyckelord :Noise; Classification algorithms; Audio recording; Machine learning; Acoustic signal processing; Störning; Klassificeringsalgoritmer; Ljudinspelning; Maskininlärning; Akustisk signalbehandling;

    Sammanfattning : When recording voice samples from a patient in speech therapy the quality of the recording may be affected by different signal corruptions, for example background noise or clipping. The equipment and expertise required to identify small disturbances are not always present at smaller clinics. LÄS MER

  5. 5. Effects of Beam Search Algorithm on Machine Generated Music

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

    Författare :Kartik Mudaliar; [2021]
    Nyckelord :;

    Sammanfattning : In this thesis, we are trying to understand the correlation between the beam-search algorithm and plagiarism. We are training a Long Shortterm Memory (LSTM) network, on a larger data-set of music transcriptions. During sampling from the model, we are employing the beam-search algorithm to generate a specific kind of traditional Irish dance music i. LÄS MER