Sökning: "TimeGAN"

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

1. 1. Restaurant Daily Revenue Prediction : Utilizing Synthetic Time Series Data for Improved Model Performance

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för beräkningsvetenskap

   Författare :Stella Jarlöv; Anton Svensson Dahl; [2023]
   Nyckelord :demand forecasting; data augmentation; time series data; machine learning; restaurant industry; generative adversarial networks; TimeGAN; XGBoost;

   Sammanfattning : This study aims to enhance the accuracy of a demand forecasting model, XGBoost, by incorporating synthetic multivariate restaurant time series data during the training process. The research addresses the limited availability of training data by generating synthetic data using TimeGAN, a generative adversarial deep neural network tailored for time series data. LÄS MER

3. 2. EVALUATING PERFORMANCE OF GENERATIVE MODELS FOR TIME SERIES SYNTHESIS

   Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

   Författare :Muhammad Junaid Haris; [2023]
   Nyckelord :GAN; Generative Adversarial Network; VQ-VAE; Vector Quantized Variational AutoEncoder; AutoEncoder; VAE; Time Series; Synthesizing; Data Synthesis;

   Sammanfattning : Motivated by successes in the image generation domain, this thesis presents a novel Hybrid VQ-VAE (H-VQ-VAE) approach for generating realistic synthetic time series data with categorical features. The primary motivation behind this work is to address the limitations of existing generative models in accurately capturing the underlying structure and patterns of time series data, especially when dealing with categorical features. LÄS MER

4. 3. Generative AI for Synthetic Data

   Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknik

   Författare :Esaias Belfrage; August Borna; [2023]
   Nyckelord :Technology and Engineering;

   Sammanfattning : Synthetic data generation has emerged as a valuable technique for addressing data scarcity and privacy concerns and improving machine learning algorithms. This thesis focuses on progressing the field of synthetic data generation, which may play a crucial role in AI-heavy industries such as telecommunications. LÄS MER

5. 4. Option Modelling by Deep Learning

   Kandidat-uppsats, Göteborgs universitet/Institutionen för nationalekonomi med statistik

   Författare :Niclas Klausson; Victor Tisell; [2021-02-10]
   Nyckelord :Deep learning; deep hedging; generative adversial networks; arbitrage pricing;

   Sammanfattning : In this thesis we aim to provide a fully data driven approach for modelling financial derivatives, exclusively using deep learning. In order for a derivatives model to be plausible, it should adhere to the principle of no-arbitrage which has profound consequences on both pricing and risk management. LÄS MER

7. 5. Multivariate Time Series Data Generation using Generative Adversarial Networks : Generating Realistic Sensor Time Series Data of Vehicles with an Abnormal Behaviour using TimeGAN

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

   Författare :Sofia Nord; [2021]
   Nyckelord :Time Series Data Generation; Generative Adversarial Network; Deep Neural Network; Data Augmentation; Synthetic Data Generation; Generering av Tidsseriedata; Generativa Motstridande Nätverk; Djupa Neurala Nätverk; Dataökning; Syntetisk Datagenerering;

   Sammanfattning : Large datasets are a crucial requirement to achieve high performance, accuracy, and generalisation for any machine learning task, such as prediction or anomaly detection, However, it is not uncommon for datasets to be small or imbalanced since gathering data can be difficult, time-consuming, and expensive. In the task of collecting vehicle sensor time series data, in particular when the vehicle has an abnormal behaviour, these struggles are present and may hinder the automotive industry in its development. LÄS MER