Essays about: "Tidsseriedata"

Showing result 1 - 5 of 25 essays containing the word Tidsseriedata.

  1. 1. Anomaly Detection in Time Series Data using Unsupervised Machine Learning Methods: A Clustering-Based Approach

    University essay from KTH/Matematisk statistik; KTH/Matematisk statistik

    Author : Peter Hanna; Erik Swartling; [2020]
    Keywords : Anomaly detection; unsupervised machine learning; high frequency sampled; time series; clustering; dimensionality reduction; DBSCAN; LOF; Anomaly detection; unsupervised machine learning; high frequency sampled; time series; clustering; dimensionality reduction; DBSCAN; LOF;

    Abstract : For many companies in the manufacturing industry, attempts to find damages in their products is a vital process, especially during the production phase. Since applying different machine learning techniques can further aid the process of damage identification, it becomes a popular choice among companies to make use of these methods to enhance the production process even further. READ MORE

  2. 2. Deep Scenario Generation of Financial Markets

    University essay from KTH/Matematisk statistik; KTH/Matematisk statistik

    Author : Filip Carlsson; Philip Lindgren; [2020]
    Keywords : Variational Autoencoder; Generative Models; Latent Space; Dimensionality Reduction; Unsupervised Learning; Clustering; VAE-Clustering; Scenario Generation; Market Regime; Variational Autoencoder; generativa modeller; latent rum; dimensionsreducering; klustring; scenario generering;

    Abstract : The goal of this thesis is to explore a new clustering algorithm, VAE-Clustering, and examine if it can be applied to find differences in the distribution of stock returns and augment the distribution of a current portfolio of stocks and see how it performs in different market conditions. The VAE-clustering method is as mentioned a newly introduced method and not widely tested, especially not on time series. READ MORE

  3. 3. Transformation of Time-based Sensor Data to Material Quality Data in Stainless Steel Production

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Adam Inersjö; [2020]
    Keywords : Time series; Stainless steel; Steel; Sensor data; Digitalization; Aggregation; Continuous production; Outokumpu; Tidsserier; Rostfritt stål; Stål; Sensordata; Digitalisering; Aggregering; Kontinuerlig produktion; Outokumpu;

    Abstract : Quality assurance in the stainless steel production requires large amounts of sensor data to monitor the processing steps. Digitalisation of the production would allow higher levels of control to both evaluate and increase the quality of the end products. READ MORE

  4. 4. Adapting the bundle of capillary tubes model (BCTM) for vertical soil solute transport modelling

    University essay from Lunds universitet/Miljövetenskaplig utbildning

    Author : Martin Larsson; [2019]
    Keywords : soil solute vertical transport modelling vadose; Earth and Environmental Sciences;

    Abstract : This study explores an approach for adapting the bundle of capillary tubes soil model for vertical soil solute transport modelling. The soil is split into thin layers allowing vertical water flow between capillaries of differing width with concomitant advective flow of solutes. Diffusion is included to improve realism. READ MORE

  5. 5. Unsupervised anomaly detection on log-based time series data

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Oskar Granlund; [2019]
    Keywords : ;

    Abstract : Due to a constant increase in the number of connected devices and there is an increased demand for confidentiality, availability, and integrity on applications. This thesis was focused on unsupervised anomaly detection in data centers. READ MORE