Sökning: "realworld"

Visar resultat 11 - 15 av 21 uppsatser innehållade ordet realworld.

  1. 11. Federated Learning for Time Series Forecasting Using LSTM Networks: Exploiting Similarities Through Clustering

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

    Författare :Fernando Díaz González; [2019]
    Nyckelord :Federated Learning; Time Series Forecasting; Clustering; Time Series Feature Extraction; Recurrent Neural Networks; Long Short-Term Memory;

    Sammanfattning : Federated learning poses a statistical challenge when training on highly heterogeneous sequence data. For example, time-series telecom data collected over long intervals regularly shows mixed fluctuations and patterns. LÄS MER

  3. 12. Unsupervised Anomaly Detection on Multi-Process Event Time Series

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

    Författare :Nicoló Vendramin; [2018]
    Nyckelord :Anomaly Detection; Recurrent Neural Networks; Time Series Analysis; Unsupervised Learning; Anomalitetsdetektering; Återkommande neurala nätverk; Tidsserieanalys; Oövervakat lärande;

    Sammanfattning : Establishing whether the observed data are anomalous or not is an important task that has been widely investigated in literature, and it becomes an even more complex problem if combined with high dimensional representations and multiple sources independently generating the patterns to be analyzed. The work presented in this master thesis employs a data-driven pipeline for the definition of a recurrent auto-encoder architecture to analyze, in an unsupervised fashion, high-dimensional event time-series generated by multiple and variable processes interacting with a system. LÄS MER

  4. 13. Simplifying smart manufacturing concepts : Commercialization of smart manufacturing concepts to help small and medium-sized enterprises

    Master-uppsats, KTH/Maskinkonstruktion (Avd.)

    Författare :BHARAT SHARMA; PRAVEEN NATARAJAN; [2018]
    Nyckelord :;

    Sammanfattning : Smart manufacturing is a concept that has taken over the manufacturing sector. The definition of smart manufacturing or the German concept Industry 4.0 has not been clearly stated and the transition from Industry 3.0 to 4. LÄS MER

  5. 14. Decentralized Diffusion-Controlled Algorithm for Community Detection : Initialization and Resolution Study

    Master-uppsats, KTH/Skolan för informations- och kommunikationsteknik (ICT)

    Författare :Adrian Ramirez; [2017]
    Nyckelord :community detection; unbalanced communities; adaptive diffusion; decentralized algorithm; Gemenskap detektering; obalanda gemenskaper; adaptativ diffusion; decentraliserad algoritm;

    Sammanfattning : Community detection in graphs has been an important research topic for many fields. The aim of community detection is to extract from graphs those groups of nodes that present more connections between them than with the rest of the network. Detecting such groups at different scales can help understanding the global behaviour of the system. LÄS MER

  7. 15. The Gamification Process : A framework on gamification

    Magister-uppsats, Högskolan i Jönköping/Internationella Handelshögskolan

    Författare :Emil Wiklund; Victor Wakerius; [2016]
    Nyckelord :Gamification;

    Sammanfattning : In this thesis a gamification framework was built based upon the existing body of literature on gamification to more easily describe the processes in how a gamified experience is developed. We interviewed different international gamification companies that are currently working with gamification to test if the theoretically developed framework had practical relevance. LÄS MER