Time Series Complexities and Their Relationship to Forecasting Performance

Ponce-Flores, Mirna Patricia; Frausto–Solís, Juan; Santamaría-Bonfil, Guillermo; Pérez-Ortega, Joaquín; González-Barbosa, Juan J.

doi:10.3390/e22010089

Cited by 18 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity of the time series is a topic explored in [36]. In fact, smart building monitored data is a recommended complexity time series example, giving importance to sensor data measuring several devices that should provide more complete information, including heating and air conditioning data [37].…”

Section: Time Series Forecastingmentioning

confidence: 99%

Industrial Facility Electricity Consumption Forecast Using Artificial Neural Networks and Incremental Learning

et al. 2020

View full text Add to dashboard Cite

Society’s concerns with electricity consumption have motivated researchers to improve on the way that energy consumption management is done. The reduction of energy consumption and the optimization of energy management are, therefore, two major aspects to be considered. Additionally, load forecast provides relevant information with the support of historical data allowing an enhanced energy management, allowing energy costs reduction. In this paper, the proposed consumption forecast methodology uses an Artificial Neural Network (ANN) and incremental learning to increase the forecast accuracy. The ANN is retrained daily, providing an updated forecasting model. The case study uses 16 months of data, split in 5-min periods, from a real industrial facility. The advantages of using the proposed method are illustrated with the numerical results.

show abstract

Section: Time Series Forecastingmentioning

confidence: 99%

Industrial Facility Electricity Consumption Forecast Using Artificial Neural Networks and Incremental Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To this aim, we studied synchronization phenomena between two unidirectional chaotic systems, where GS takes place as a function of coupling factor C. We studied the optimal dimension m of the systems assuming, as we did for noncoupled systems, that entropy is well described by a nonextensive function of number of elements S ∼ N m . at assumption is especially well posed when the system is weakly sensitive to initial conditions, where it was proven [38,39] that the usual Shannon entropy measures are not appropriate and a new measure of entropy has to be introduced that depends on sensitivity to initial conditions and the multifractal spectrum.…”

Section: Unidirectionally Coupled Systemsmentioning

confidence: 99%

Compressing Phase Space Detects State Changes in Nonlinear Dynamical Systems

d’Andrea

Domenico

2020

Complexity

View full text Add to dashboard Cite

Equations governing the nonlinear dynamics of complex systems are usually unknown, and indirect methods are used to reconstruct their manifolds. In turn, they depend on embedding parameters requiring other methods and long temporal sequences to be accurate. In this paper, we show that an optimal reconstruction can be achieved by lossless compression of system’s time course, providing a self-consistent analysis of its dynamics and a measure of its complexity, even for short sequences. Our measure of complexity detects system’s state changes such as weak synchronization phenomena, characterizing many systems, in one step, integrating results from Lyapunov and fractal analysis.

show abstract

“…Entropy has been widely used in the field of prediction. Mirna et al [ 3 ] and Guan et al [ 4 ] used the theory of entropy in predicting time series. Carles et al [ 5 ] combined entropy with machine learning to predict macroeconomics.…”

Section: Introductionmentioning

confidence: 99%

A Method Based on GA-CNN-LSTM for Daily Tourist Flow Prediction at Scenic Spots

Rui

Liang

et al. 2020

Entropy

View full text Add to dashboard Cite

Accurate tourist flow prediction is key to ensuring the normal operation of popular scenic spots. However, one single model cannot effectively grasp the characteristics of the data and make accurate predictions because of the strong nonlinear characteristics of daily tourist flow data. Accordingly, this study predicts daily tourist flow in Huangshan Scenic Spot in China. A prediction method (GA-CNN-LSTM) which combines convolutional neural network (CNN) and long-short-term memory network (LSTM) and optimized by genetic algorithm (GA) is established. First, network search data, meteorological data, and other data are constructed into continuous feature maps. Then, feature vectors are extracted by convolutional neural network (CNN). Finally, the feature vectors are input into long-short-term memory network (LSTM) in time series for prediction. Moreover, GA is used to scientifically select the number of neurons in the CNN-LSTM model. Data is preprocessed and normalized before prediction. The accuracy of GA-CNN-LSTM is evaluated using mean absolute percentage error (MAPE), mean absolute error (MAE), Pearson correlation coefficient and index of agreement (IA). For a fair comparison, GA-CNN-LSTM model is compared with CNN-LSTM, LSTM, CNN and the back propagation neural network (BP). The experimental results show that GA-CNN-LSTM model is approximately 8.22% higher than CNN-LSTM on the performance of MAPE.

show abstract

Time Series Complexities and Their Relationship to Forecasting Performance

Cited by 18 publications

References 43 publications

Industrial Facility Electricity Consumption Forecast Using Artificial Neural Networks and Incremental Learning

Industrial Facility Electricity Consumption Forecast Using Artificial Neural Networks and Incremental Learning

Compressing Phase Space Detects State Changes in Nonlinear Dynamical Systems

A Method Based on GA-CNN-LSTM for Daily Tourist Flow Prediction at Scenic Spots

Contact Info

Product

Resources

About