scholarly journals Validation Methods for Energy Time Series Scenarios from Deep Generative Models

IEEE Access ◽  
2022 ◽  
pp. 1-1
Author(s):  
Eike Cramer ◽  
Leonardo Rydin Gorjao ◽  
Alexander Mitsos ◽  
Benjamin Schafer ◽  
Dirk Witthaut ◽  
...  
Keyword(s):  
Time Series ◽  
Generative Models ◽  
Validation Methods

scholarly journals Pix2pix Conditional Generative Adversarial Network with MLP Loss Function for Cloud Removal in a Cropland Time Series

2021 ◽  
Vol 14 (1) ◽  
pp. 144
Author(s):  
Luiz E. Christovam ◽  
Milton H. Shimabukuro ◽  
Maria de Lourdes B. T. Galo ◽  
Eija Honkavaara
Keyword(s):  
Time Series ◽  
Loss Function ◽  
Visual Analysis ◽  
Spectral Response ◽  
Semantic Segmentation ◽  
Generative Models ◽  
Synthetic Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Crop Type

Clouds are one of the major limitations to crop monitoring using optical satellite images. Despite all efforts to provide decision-makers with high-quality agricultural statistics, there is still a lack of techniques to optimally process satellite image time series in the presence of clouds. In this regard, in this article it was proposed to add a Multi-Layer Perceptron loss function to the pix2pix conditional Generative Adversarial Network (cGAN) objective function. The aim was to enforce the generative model to learn how to deliver synthetic pixels whose values were proxies for the spectral response improving further crop type mapping. Furthermore, it was evaluated the generalization capacity of the generative models in producing pixels with plausible values for images not used in the training. To assess the performance of the proposed approach it was compared real images with synthetic images generated with the proposed approach as well as with the original pix2pix cGAN. The comparative analysis was performed through visual analysis, pixel values analysis, semantic segmentation and similarity metrics. In general, the proposed approach provided slightly better synthetic pixels than the original pix2pix cGAN, removing more noise than the original pix2pix algorithm as well as providing better crop type semantic segmentation; the semantic segmentation of the synthetic image generated with the proposed approach achieved an F1-score of 44.2%, while the real image achieved 44.7%. Regarding the generalization, the models trained utilizing different regions of the same image provided better pixels than models trained using other images in the time series. Besides this, the experiments also showed that the models trained using a pair of images selected every three months along the time series also provided acceptable results on images that do not have cloud-free areas.

scholarly journals Monte Carlo Filtering Objectives

2021 ◽  
Author(s):  
Shuangshuang Chen ◽  
Sihao Ding ◽  
Yiannis Karayiannidis ◽  
Mårten Björkman
Keyword(s):  
Time Series ◽  
Monte Carlo ◽  
Sequential Monte Carlo ◽  
Time Series Data ◽  
Generative Models ◽  
Gradient Estimates ◽  
Series Data ◽  
Stable Model ◽  
Model Learning ◽  
Marginal Likelihoods

Learning generative models and inferring latent trajectories have shown to be challenging for time series due to the intractable marginal likelihoods of flexible generative models. It can be addressed by surrogate objectives for optimization. We propose Monte Carlo filtering objectives (MCFOs), a family of variational objectives for jointly learning parametric generative models and amortized adaptive importance proposals of time series. MCFOs extend the choices of likelihood estimators beyond Sequential Monte Carlo in state-of-the-art objectives, possess important properties revealing the factors for the tightness of objectives, and allow for less biased and variant gradient estimates. We demonstrate that the proposed MCFOs and gradient estimations lead to efficient and stable model learning, and learned generative models well explain data and importance proposals are more sample efficient on various kinds of time series data.

Learning Nonlinear Generative Models of Time Series With a Kalman Filter in RKHS

2014 ◽  
Vol 62 (1) ◽  
pp. 141-155 ◽  
Author(s):  
Pingping Zhu ◽  
Badong Chen ◽  
Jose C. Principe
Keyword(s):  
Time Series ◽  
Kalman Filter ◽  
Generative Models

scholarly journals An empirical survey of data augmentation for time series classification with neural networks

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254841
Author(s):  
Brian Kenji Iwana ◽  
Seiichi Uchida
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Data Augmentation ◽  
Time Series Data ◽  
Decomposition Methods ◽  
Generative Models ◽  
Series Data ◽  
Time Series Classification ◽  
Empirical Survey ◽  
Advantages And Disadvantages

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.

scholarly journals A Functional Dynamic Boltzmann Machine

2017 ◽  
Author(s):  
Hiroshi Kajino
Keyword(s):  
Time Series ◽  
Online Learning ◽  
Learning Algorithm ◽  
Interpolation Method ◽  
Time Series Prediction ◽  
Generative Models ◽  
Boltzmann Machine ◽  
Continuous Space ◽  
Functional Time Series ◽  
Consistent Error

Dynamic Boltzmann machines (DyBMs) are recently developed generative models of a time series. They are designed to learn a time series by efficient online learning algorithms, whilst taking long-term dependencies into account with help of eligibility traces, recursively updatable memory units storing descriptive statistics of all the past data. The current DyBMs assume a finite-dimensional time series and cannot be applied to a functional time series, in which the dimension goes to infinity (e.g., spatiotemporal data on a continuous space). In this paper, we present a functional dynamic Boltzmann machine (F-DyBM) as a generative model of a functional time series. A technical challenge is to devise an online learning algorithm with which F-DyBM, consisting of functions and integrals, can learn a functional time series using only finite observations of it. We rise to the above challenge by combining a kernel-based function approximation method along with a statistical interpolation method and finally derive closed-form update rules. We design numerical experiments to empirically confirm the effectiveness of our solutions. The experimental results demonstrate consistent error reductions as compared to baseline methods, from which we conclude the effectiveness of F-DyBM for functional time series prediction.

scholarly journals On the Usage of Generative Models for Network Anomaly Detection in Multivariate Time-Series

2021 ◽  
Vol 48 (4) ◽  
pp. 49-52
Author(s):  
Gastón García González ◽  
Pedro Casas ◽  
Alicia Fernández ◽  
Gabriel Gómez
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Communication Networks ◽  
Multivariate Time Series ◽  
Data Communication ◽  
Generative Models ◽  
Sensor Data ◽  
Underlying Distribution ◽  
Novel Approach ◽  
Network Anomaly Detection

Despite the many attempts and approaches for anomaly de- tection explored over the years, the automatic detection of rare events in data communication networks remains a com- plex problem. In this paper we introduce Net-GAN, a novel approach to network anomaly detection in time-series, us- ing recurrent neural networks (RNNs) and generative ad- versarial networks (GAN). Different from the state of the art, which traditionally focuses on univariate measurements, Net-GAN detects anomalies in multivariate time-series, ex- ploiting temporal dependencies through RNNs. Net-GAN discovers the underlying distribution of the baseline, multi- variate data, without making any assumptions on its nature, offering a powerful approach to detect anomalies in com- plex, difficult to model network monitoring data. We further exploit the concepts behind generative models to conceive Net-VAE, a complementary approach to Net-GAN for net- work anomaly detection, based on variational auto-encoders (VAE). We evaluate Net-GAN and Net-VAE in different monitoring scenarios, including anomaly detection in IoT sensor data, and intrusion detection in network measure- ments. Generative models represent a promising approach for network anomaly detection, especially when considering the complexity and ever-growing number of time-series to monitor in operational networks.

The LDE-Type Flare Occurrence (1969-1993)

1994 ◽  
Vol 144 ◽  
pp. 279-282
Author(s):  
A. Antalová
Keyword(s):  
Time Series ◽  
Fourier Analysis ◽  
Sunspot Cycle ◽  
List Type ◽  
Type Number ◽  
Solar Cycles ◽  
Type Iv ◽  
Long Duration ◽  
Cycle Maximum ◽  
Flare Index

AbstractThe occurrence of LDE-type flares in the last three cycles has been investigated. The Fourier analysis spectrum was calculated for the time series of the LDE-type flare occurrence during the 20-th, the 21-st and the rising part of the 22-nd cycle. LDE-type flares (Long Duration Events in SXR) are associated with the interplanetary protons (SEP and STIP as well), energized coronal archs and radio type IV emission. Generally, in all the cycles considered, LDE-type flares mainly originated during a 6-year interval of the respective cycle (2 years before and 4 years after the sunspot cycle maximum). The following significant periodicities were found:• in the 20-th cycle: 1.4, 2.1, 2.9, 4.0, 10.7 and 54.2 of month,• in the 21-st cycle: 1.2, 1.6, 2.8, 4.9, 7.8 and 44.5 of month,• in the 22-nd cycle, till March 1992: 1.4, 1.8, 2.4, 7.2, 8.7, 11.8 and 29.1 of month,• in all interval (1969-1992):a)the longer periodicities: 232.1, 121.1 (the dominant at 10.1 of year), 80.7, 61.9 and 25.6 of month,b)the shorter periodicities: 4.7, 5.0, 6.8, 7.9, 9.1, 15.8 and 20.4 of month.Fourier analysis of the LDE-type flare index (FI) yields significant peaks at 2.3 - 2.9 months and 4.2 - 4.9 months. These short periodicities correspond remarkably in the all three last solar cycles. The larger periodicities are different in respective cycles.

Sign in / Sign up

Export Citation Format

Share Document