Multimodal Spatio-Temporal Prediction with Stochastic Adversarial Networks

2022 ◽  
Vol 13 (2) ◽  
pp. 1-23
Author(s):  
Divya Saxena ◽  
Jiannong Cao
Keyword(s):  
Latent Variables ◽  
Time Series Data ◽  
Series Data ◽  
Generative Adversarial Networks ◽  
Multiple Time ◽  
Model Learning ◽  
Temporal Prediction ◽  
Adversarial Networks ◽  
Spatio Temporal ◽  
Real World Datasets

Spatio-temporal (ST) data is a collection of multiple time series data with different spatial locations and is inherently stochastic and unpredictable. An accurate prediction over such data is an important building block for several urban applications, such as taxi demand prediction, traffic flow prediction, and so on. Existing deep learning based approaches assume that outcome is deterministic and there is only one plausible future; therefore, cannot capture the multimodal nature of future contents and dynamics. In addition, existing approaches learn spatial and temporal data separately as they assume weak correlation between them. To handle these issues, in this article, we propose a stochastic spatio-temporal generative model (named D-GAN) which adopts Generative Adversarial Networks (GANs)-based structure for more accurate ST prediction in multiple time steps. D-GAN consists of two components: (1) spatio-temporal correlation network which models spatio-temporal joint distribution of pixels and supports a stochastic sampling of latent variables for multiple plausible futures; (2) a stochastic adversarial network to jointly learn generation and variational inference of data through implicit distribution modeling. D-GAN also supports fusion of external factors through explicit objective to improve the model learning. Extensive experiments performed on two real-world datasets show that D-GAN achieves significant improvements and outperforms baseline models.

scholarly journals Causal inference with multiple time series: principles and problems

2013 ◽  
Vol 371 (1997) ◽  
pp. 20110613 ◽  
Author(s):  
Michael Eichler
Keyword(s):  
Time Series ◽  
Causal Inference ◽  
Granger Causality ◽  
Latent Variables ◽  
Time Series Data ◽  
Series Data ◽  
Multiple Time ◽  
Identification Algorithm ◽  
Multiple Time Series ◽  
Theoretical Justification

I review the use of the concept of Granger causality for causal inference from time-series data. First, I give a theoretical justification by relating the concept to other theoretical causality measures. Second, I outline possible problems with spurious causality and approaches to tackle these problems. Finally, I sketch an identification algorithm that learns causal time-series structures in the presence of latent variables. The description of the algorithm is non-technical and thus accessible to applied scientists who are interested in adopting the method.

scholarly journals Generating Energy Data for Machine Learning with Recurrent Generative Adversarial Networks

Energies ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 130 ◽  
Author(s):  
Mohammad Navid Fekri ◽  
Ananda Mohon Ghosh ◽  
Katarina Grolinger
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Energy Consumption ◽  
Smart Grid ◽  
Time Series Data ◽  
Security And Privacy ◽  
Series Data ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Networks

The smart grid employs computing and communication technologies to embed intelligence into the power grid and, consequently, make the grid more efficient. Machine learning (ML) has been applied for tasks that are important for smart grid operation including energy consumption and generation forecasting, anomaly detection, and state estimation. These ML solutions commonly require sufficient historical data; however, this data is often not readily available because of reasons such as data collection costs and concerns regarding security and privacy. This paper introduces a recurrent generative adversarial network (R-GAN) for generating realistic energy consumption data by learning from real data. Generativea adversarial networks (GANs) have been mostly used for image tasks (e.g., image generation, super-resolution), but here they are used with time series data. Convolutional neural networks (CNNs) from image GANs are replaced with recurrent neural networks (RNNs) because of RNN’s ability to capture temporal dependencies. To improve training stability and increase quality of generated data, Wasserstein GANs (WGANs) and Metropolis-Hastings GAN (MH-GAN) approaches were applied. The accuracy is further improved by adding features created with ARIMA and Fourier transform. Experiments demonstrate that data generated by R-GAN can be used for training energy forecasting models.

scholarly journals Multi-scale analysis of linear data in a two-dimensional space

2013 ◽  
Vol 13 (3) ◽  
pp. 248-265 ◽  
Author(s):  
Yi Qiang ◽  
Seyed H Chavoshi ◽  
Steven Logghe ◽  
Philippe De Maeyer ◽  
Nico Van de Weghe
Keyword(s):  
Time Series ◽  
Visual Analysis ◽  
Time Series Data ◽  
Dimensional Space ◽  
Series Data ◽  
Multiple Time ◽  
Two Dimensional ◽  
Map Algebra ◽  
Real World Datasets ◽  
Triangular Model

Many disciplines are faced with the problem of handling time-series data. This study introduces an innovative visual representation for time series, namely the continuous triangular model. In the continuous triangular model, all subintervals of a time series can be represented in a two-dimensional continuous field, where every point represents a subinterval of the time series, and the value at the point is derived through a certain function (e.g. average or summation) of the time series within the subinterval. The continuous triangular model thus provides an explicit overview of time series at all different scales. In addition to time series, the continuous triangular model can be applied to a broader sense of linear data, such as traffic along a road. This study shows how the continuous triangular model can facilitate the visual analysis of different types of linear data. We also show how the coordinate interval space in the continuous triangular model can support the analysis of multiple time series through spatial analysis methods, including map algebra and cartographic modelling. Real-world datasets and scenarios are employed to demonstrate the usefulness of this approach.

scholarly journals Denoising EEG Signals for Real-World BCI Applications Using GANs

2022 ◽  
Vol 2 ◽  
Author(s):  
Eoin Brophy ◽  
Peter Redmond ◽  
Andrew Fleury ◽  
Maarten De Vos ◽  
Geraldine Boylan ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Real World ◽  
Time Series Data ◽  
Benchmark Dataset ◽  
Series Data ◽  
Generative Adversarial Networks ◽  
Eeg Signals ◽  
Adversarial Networks ◽  
Resource Setting

As a measure of the brain's electrical activity, electroencephalography (EEG) is the primary signal of interest for brain-computer-interfaces (BCI). BCIs offer a communication pathway between a brain and an external device, translating thought into action with suitable processing. EEG data is the most common signal source for such technologies. However, artefacts induced in BCIs in the real-world context can severely degrade their performance relative to their in-laboratory performance. In most cases, the recorded signals are so heavily corrupted by noise that they are unusable and restrict BCI's broader applicability. To realise the use of portable BCIs capable of high-quality performance in a real-world setting, we use Generative Adversarial Networks (GANs) that can adopt both supervised and unsupervised learning approaches. Although our approach is supervised, the same model can be used for unsupervised tasks such as data augmentation/imputation in the low resource setting. Exploiting recent advancements in Generative Adversarial Networks (GAN), we construct a pipeline capable of denoising artefacts from EEG time series data. In the case of denoising data, it maps noisy EEG signals to clean EEG signals, given the nature of the respective artefact. We demonstrate the capability of our network on a toy dataset and a benchmark EEG dataset developed explicitly for deep learning denoising techniques. Our datasets consist of an artificially added mains noise (50/60 Hz) artefact dataset and an open-source EEG benchmark dataset with two artificially added artefacts. Artificially inducing myogenic and ocular artefacts for the benchmark dataset allows us to present qualitative and quantitative evidence of the GANs denoising capabilities and rank it among the current gold standard deep learning EEG denoising techniques. We show the power spectral density (PSD), signal-to-noise ratio (SNR), and other classical time series similarity measures for quantitative metrics and compare our model to those previously used in the literature. To our knowledge, this framework is the first example of a GAN capable of EEG artefact removal and generalisable to more than one artefact type. Our model has provided a competitive performance in advancing the state-of-the-art deep learning EEG denoising techniques. Furthermore, given the integration of AI into wearable technology, our method would allow for portable EEG devices with less noisy and more stable brain signals.

Sign in / Sign up

Export Citation Format

Share Document