Sökning: "ConvLSTM"

Visar resultat 1 - 5 av 7 uppsatser innehållade ordet ConvLSTM.

  1. 1. Demand Forecasting of Outbound Logistics Using Neural Networks

    Master-uppsats, Malmö universitet/Fakulteten för teknik och samhälle (TS)

    Författare :Enobong Paul Otuodung; Gulten Gorhan; [2023]
    Nyckelord :Time Series Prediction; Demand Forecasting; Outbound Logistics; Machine Learning; Deep Learning; Univariate Forecasting; Multivariate Forecasting; Multi-Step Forecasting; LSTM; CNN-LSTM; ConvLSTM; Encoder-Decoder; Design science; Design science;

    Sammanfattning : Long short-term volume forecasting is essential for companies regarding their logistics service operations. It is crucial for logistic companies to predict the volumes of goods that will be delivered to various centers at any given day, as this will assist in managing the efficiency of their business operations. LÄS MER

  3. 2. Data-driven cyberattack detection for microgrids

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

    Författare :Jiaying Mao; [2022]
    Nyckelord :Cyberattack detection; Deep learning network; Microgrid; Smart inverter; Cyber-physical system; Distributed system; Detektering av cyberattacker; Djupinlärning nätverk; Microgrid; Smart växelriktare; Cyberfysiska system; Distribuerade system;

    Sammanfattning : Microgrids are undergoing higher penetrations of renewables and associated power electronics, along with precise and sophisticated control and communication networks. However, such cyber-physical systems might suffer from potential cybersecurity threats and inherent low inertia. LÄS MER

  4. 3. Replicating noise in video : a comparison between physics-based and deep learning models for simulating noise

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

    Författare :Jonas Wedin; [2020]
    Nyckelord :;

    Sammanfattning : Algorithms that track objects in video following Newtonian physics can often be affected by noise in the data. Some types of noise might be hard or expensive to capture, so to be able to augment or generate a new data set from models replicating a certain type of noise can be useful. LÄS MER

  5. 4. Video Saliency Detection using Deep Learning

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

    Författare :Jakob Wiesinger; [2019]
    Nyckelord :;

    Sammanfattning : A deep learning model for video saliency detection is proposed and trained. The neural network architecture combines recent innovations in the field: A twostream approach merges two separate input streams for appearance and motion aspects of saliency. Pre-trained convolutional features detect objectness. LÄS MER

  7. 5. Short-Term Forecasting of Taxi Demand using a two Channelled Convolutional LSTM network

    Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Författare :Anton Silfver; [2019]
    Nyckelord :LSTM; ConvLSTM; Deep Learning; Taxi demand;

    Sammanfattning : In this thesis a model capable of predicting taxidemand with high accuracy across five different real world single company datasets is presented. The model uses historical drop off and arrival information to make accurate shortterm predictions about future taxi demand. The model is compared to and outperforms both LSTM and statistical baselines. LÄS MER