Essays about: "tidsserie metoder"

Showing result 1 - 5 of 23 essays containing the words tidsserie metoder.

  1. 1. Extraction of Global Features for enhancing Machine Learning Performance

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

    Author : Abyel Tesfay; [2023]
    Keywords : Machine Learning; Deep Learning; Feature Extraction; Global Features; Time-series data; Bioprocessing; Maskininlärning; Djupinlärning; Funktionsextraktion; Globala Funktioner; Tidsserie data; Biobearbetning;

    Abstract : Data Science plays an essential role in many organizations and industries to become data-driven in their decision-making and workflow, as models can provide relevant input in areas such as social media, the stock market, and manufacturing industries. To train models of quality, data preparation methods such as feature extraction are used to extract relevant features. READ MORE

  3. 2. An empirical study of the impact of data dimensionality on the performance of change point detection algorithms

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

    Author : Léo Noharet; [2023]
    Keywords : Time series segmentation; Change point detection; Multivariate time series; Data dimensionality; Tidsserie-segmentering; Förändringspunkts detektering; Mulitvariabla tidsserier; Data dimentionalitet;

    Abstract : When a system is monitored over time, changes can be discovered in the time series of monitored variables. Change Point Detection (CPD) aims at finding the time point where a change occurs in the monitored system. READ MORE

  4. 3. Non-Bayesian Out-of-Distribution Detection Applied to CNN Architectures for Human Activity Recognition

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

    Author : Serghei Socolovschi; [2022]
    Keywords : Human Activity Recognition; Deep Learning; Time Series; Uncertainty Estimation; Outofdistribution Detection; Convolutional Neural Network; Human Activity Recognition; Deep Learning; Tidsserie; Uppskattning av Osäkerheten; Outofdistribution Detection; Convolutional Neural Network;

    Abstract : Human Activity Recognition (HAR) field studies the application of artificial intelligence methods for the identification of activities performed by people. Many applications of HAR in healthcare and sports require the safety-critical performance of the predictive models. READ MORE

  5. 4. Evaluation of Machine Learning Methods for Time Series Forecasting on E-commerce Data

    University essay from KTH/Matematisk statistik

    Author : Peter Abrahamsson; Niklas Ahlqvist; [2022]
    Keywords : Thesis; Time Series; Machine Learning; E-commerce; Demand Forecasting; Multiple Linear Regression; SARIMAX; XGBoost; LSTM; Model Evaluation; Examensarbete; tidsserier; maskininlärning; e-handel; efterfrågeprognoser; multipel linjär regression; SARIMAX; XGBoost; LSTM; modellutvärdering;

    Abstract : Within demand forecasting, and specifically within the field of e-commerce, the provided data often contains erratic behaviours which are difficult to explain. This induces contradictions to the common assumptions within classical approaches for time series analysis. Yet, classical and naive approaches are still commonly used. READ MORE

  6. 5. Federated Learning for Market Surveillance

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

    Author : Philip Song; [2022]
    Keywords : Federated Learning; Machine Learning; Market Surveillance; Anomaly Detection; LSTMAutoencoder; Federated Learning; Maskininlärning; Marknadsövervakning; Anomaliupptäckande; LSTMAutoencoder;

    Abstract : The increasing complexity of trading strategies, when combined with machine learning models, forces market surveillance corporations to develop increasingly sophisticated methods for recognizing potential misuse. One strategy is to employ traders’ weapons against themselves, namely machine learning. READ MORE