A decoder-only foundation model for time-series forecasting

A Das, W Kong, R Sen, Y Zhou - arXiv preprint arXiv:2310.10688, 2023 - arxiv.org
Motivated by recent advances in large language models for Natural Language Processing
(NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero …

Weather4cast at neurips 2022: Super-resolution rain movie prediction under spatio-temporal shifts

A Gruca, F Serva, L Lliso, P Rípodas… - NeurIPS 2022 …, 2023 - proceedings.mlr.press
Weather4cast again advanced modern algorithms in AI and machine learning through a
highly topical interdisciplinary competition challenge: The prediction of hi-res rain radar …

Traffic4cast at neurips 2021-temporal and spatial few-shot transfer learning in gridded geo-spatial processes

C Eichenberger, M Neun, H Martin… - NeurIPS 2021 …, 2022 - proceedings.mlr.press
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks
can successfully predict future traffic conditions 1 hour into the future on simply aggregated …

Spatiotemporal prediction of microstructure evolution with predictive recurrent neural network

AAK Farizhandi, M Mamivand - Computational Materials Science, 2023 - Elsevier
Prediction of microstructure evolution during material processing is essential to control the
material properties. Simulation tools for microstructure evolution prediction based on …

Urban traffic forecasting using federated and continual learning

C Lanza, E Angelats, M Miozzo… - 2023 6th Conference on …, 2023 - ieeexplore.ieee.org
Smart cities are instrumented with several types pf sensors, which allow to transmit,
elaborate and exploit the collected data for different services. In this paper we focus on the …

Metropolitan segment traffic speeds from massive floating car data in 10 cities

M Neun, C Eichenberger, Y Xin, C Fu… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Traffic analysis is crucial for urban operations and planning, while the availability of dense
urban traffic data beyond loop detectors is still scarce. We present a large-scale floating …

Pauli gaussian fibonacci and pauli gaussian lucas quaternions

AZ Azak - Mathematics, 2022 - mdpi.com
We have investigated new Pauli Fibonacci and Pauli Lucas quaternions by taking the
components of these quaternions as Gaussian Fibonacci and Gaussian Lucas numbers …

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

C Feng, L Huang, D Krompass - arXiv preprint arXiv:2402.07570, 2024 - arxiv.org
We present General Time Transformer (GTT), an encoder-only style foundation model for
zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M …

Deep Hypercomplex Networks for Spatiotemporal Data Processing: Parameter efficiency and superior performance [Hypercomplex Signal and Image Processing]

A Bojesomo, P Liatsis… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
Hypercomplex numbers, such as quaternions and octonions, have recently gained attention
because of their advantageous properties over real numbers, eg, in the development of …

SwinUNet3D--A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers

A Bojesomo, HA Marzouqi, P Liatsis - arXiv preprint arXiv:2201.06390, 2022 - arxiv.org
Traffic forecasting is an important element of mobility management, an important key that
drives the logistics industry. Over the years, lots of work have been done in Traffic …