Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 25 for “"Temporal Fusion Transformer"”.
-
Multiprevisão de geração fotovoltaica baseada em clusterização hierárquica e temporal fusion transformer
… Hierárquica com distância DTW e a arquitetura Temporal Fusion Transformer (TFT), utilizando exclusivamente dados públicos de geração (ONS) e meteorologia (NASA POWER). A metodologia inclui: imputação de dados faltantes guiada pela curva de radiação solar, clusterização de dez usinas FV para …
-
Sparse Time Series Demand Forecasting for Intermittent Availability
… an interpretable novel method that improves the Temporal Fusion Transformer model with cluster encodings by applying random convolutional kernel transformations to time series. The study found that the compared deep learning models outperformed the baseline statistical models, particularly the …
-
Machine Learning based Restaurant Sales Forecasting
… and the best for one-week forecasting is the temporal fusion transformer with an MAE of 216.
-
Temporal Fusion Transformers: A Novel Approach to Streamflow Prediction
… explores these approaches and introduces the Temporal Fusion Transformer model for streamflow prediction, which requires minimal input data and can adapt to various prediction scenarios.To train this model, hydrological data from thousands of North American locations over several decades were …
-
Federated and Multi-Task Learning for Privacy-Preserving Short-Term Electric Load Forecasting
… non-personalized FL. We also propose training a Temporal Fusion Transformer (TFT), which improved load forecasting accuracy and reduced communication and computation costs compared to other common deep learning models. Recommendations are presented regarding several TFT architecture …
-
An Attention-Based Deep Learning Approach for Forecasting Electricity Prices in Real-Time Electricity Markets
… The proposed methodology integrates the Temporal Fusion Transformer (TFT), a deep learning model applied to time series forecasting, with dynamic clustering techniques to enhance forecasting accuracy. This is done by combining Hierarchical Density-Based Spatial Clustering of Applications …
-
Small-Scale Demand Forecasting: Exploring the Potential of Machine Learning and Hierarchical Reconciliation
… machine learning models, such as the Temporal Fusion Transformer (TFT) and the LightGBM to an exponential smoothing state-space model. Furthermore, I investi gated whether the hierarchical structure of the time series data could be exploited through forecast reconciliation to further …
-
Time-Series Forecasting for Industrial Demand: A Comparative Study
… state-of-the-art deep learning architectures (Temporal Fusion Transformer, TimeXer, TiDE, N-HiTS, SOFTS). Expanding-window cross-validation is employed to generate multi-horizon forecasts up to 12 months and accuracy is evaluated using RMSE and sMAPE. Models are compared with and without the …
-
Safer Learning-enabled Autonomous Systems
… of several forecasting models. Among them, the Temporal Fusion Transformer (TFT) demonstrates superior performance in predicting imminent safety violations while maintaining acceptable computational overhead. Together, these contributions advance the state of the art in safety assurance of …
-
Interpretable Machine Learning for the Modelling of Spatiotemporal Crop Data
… performance prediction problems across genomic, temporal, and spatial settings. We first paired Bayesian additive regression trees with genomic markers to predict winter wheat variety performance in Ontario multi-environment trials. This combination reduced mean square prediction error by up to …
-
Deep learning for time series prediction and decision making over time
… For multi-horizon forecasting, we propose the Temporal Fusion Transformer (TFT) -- an attention-based model designed to accommodate the full range of inputs present in common problem scenarios. Secondly, we investigate the use of hybrid models to enhance traditional quantitative models with …
-
Electricity Price Forecasting with Attention-Based Neural Network Architectures
… προσοχής (attention), και συγκεκριμένα του Transformer, του Temporal Fusion Transformer (TFT), του PatchTST και του θεμελιώδους μοντέλου (foundation model) Chronos-2, προσαρμοσμένων ώστε να παράγουν προβλέψεις ποσοστημορίων. Τα μοντέλα αξιολογούνται αρχικά στο σύνολο δεδομένων GEFCom2014, …
-
Σχεδίαση και υλοποίηση προηγμένων αλγορίθμων μηχανικής μάθησης για την ανάλυση και πρόγνωση χρονοσειρών
… method with the advanced Deep Learning algorithm Temporal Fusion Transformer demonstrates the value of innovation in the analysis of environmental data and enhances the applicability of Machine Learning techniques. This dissertation presents a comprehensive effort to improve the capability of …
-
Machine learning on building energy modeling : city and building scale
… CityTFT, a surrogate model based on the Temporal Fusion Transformer, designed to accelerate computationally intensive physics-based Urban Building Energy Modeling (UBEM). CityTFT successfully models both static building parameters and dynamic weather data, predicting heating and cooling …
-
Physics-Informed Interpretable Attention-based Machine Learning for Jet Turbine Prediction
… utilize an attention-based neural network, the Temporal Fusion Transformer, on experimental data for prediction, allowing for interpretability and insight into model dynamics. We describe a series of experiments on different configurations of the model architecture and show that through the …
-
Machine learning applications for demand response and renewable forecasting: towards optimal market participation
… theoretical power curves with the temporal fusion transformer is shown to significantly reduce forecast errors compared to standard DL baselines. Additionally, a federated learning framework for photovoltaic forecasting is validated, proving that collaborative training can ensure …
-
MACHINE LEARNING AND COASTAL SHORELINE MODELLING: EXPLORING GENERALISATION, ROBUSTNESS, AND INTERPRETABILITY
… generalised ML shoreline models. Here, a Temporal Fusion Transformer (TFT) was trained across 2000km of the Australian coastline, generating stable and coherent forecasts without requiring site-specific calibration, marking a first in the field of coastal shoreline modelling. This …
-
Real-Time Short-Term Intersection Turning Movement Flows Forecasting Using Deep Learning Models for Advanced Traffic Management and Information Systems
… limitations in capturing the complex spatial and temporal patterns inherent in intersection-level TMFs, as they primarily rely on historical traffic data without adequately modeling these dependencies. Moreover, most existing approaches fail to incorporate exogenous factors, such as weather …
-
Saulės fotovoltinių elektrinių valandinės energijos prognozavimo modelių ir sezoninių dėsningumų analizė /
… and ensuring a chronological sequence to prevent temporal data leakage. Additionally, days with fewer than 12 hours of observations were excluded. Following feature engineering, the final datasets contained 104 features. Five models were selected for day-ahead forecasting: support vector machine …
-
A Reinforcement Learning Guided Hybrid Neural Framework for Sparse Feature Selection
… steps, failing to capture the evolving temporal relevance of features in dynamic environments. Although deep neural networks and reinforcement learning (RL) techniques have shown promise, most existing methods remain static or semi-static, limiting their adaptability to nonstationary …
Page 1 of 2