Sökning: "The original series"
Visar resultat 1 - 5 av 157 uppsatser innehållade orden The original series.
1. Restaurant Daily Revenue Prediction : Utilizing Synthetic Time Series Data for Improved Model Performance
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för beräkningsvetenskapSammanfattning : 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
2. Autoencoder-Based Likelihood-Free Parameter Inference of Gene Regulatory Network
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Likelihood-free parameter inference is a well-known statistical methodology that estimates the posterior distribution of model parameters even in cases where the likelihood function is intractable. The performance of this method is highly correlated with the learning of summary statistics, which capture the key features from the high dimensional data such as time series. LÄS MER
3. Air quality prediction in metropolitan areas using deep learning methods
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : The rapid growth of the world's urban population shows that people are increasingly moving to cities. In recent decades, the frequent occurrence of smog caused by increasing industrialization has brought environmental pollution to record highs. LÄS MER
4. Playing with the Third Reich: Conceptual Relocation from Nazi Film to WWII Game : An Experiment to measure Filmic concepts in Digital Games
Master-uppsats, Stockholms universitet/FilmvetenskapSammanfattning : Film produced by Nazi Germany has been a classic that has drawn scholars from a wide range of academic disciplines as well as innumerable cineastes from various cultural backgrounds. The simultaneous rise in the number of players acting as observers and operators in digital games with a WWII theme has drawn recent scholarly attention since it is thought that this pattern is contributing to players' hazy understanding of historical events. LÄS MER
5. EVALUATING PERFORMANCE OF GENERATIVE MODELS FOR TIME SERIES SYNTHESIS
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : 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