scholarly journals Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series

2020 ◽  
Vol 34 (02) ◽  
pp. 1395-1402
Author(s):  
Dongkuan Xu ◽  
Wei Cheng ◽  
Bo Zong ◽  
Dongjin Song ◽  
Jingchao Ni ◽  
...  
Keyword(s):  
Time Series ◽  
Shared Memory ◽  
Multivariate Time Series ◽  
Temporal Patterns ◽  
Series Data ◽  
Short Term ◽  
Trend Prediction ◽  
Multiple Variables ◽  
Parameter Sharing

The problem of learning and forecasting underlying trends in time series data arises in a variety of applications, such as traffic management, energy optimization, etc. In literature, a trend in time series is characterized by the slope and duration, and its prediction is then to forecast the two values of the subsequent trend given historical data of the time series. For this problem, existing approaches mainly deal with the case in univariate time series. However, in many real-world applications, there are multiple variables at play, and handling all of them at the same time is crucial for an accurate prediction. A natural way is to employ multi-task learning (MTL) techniques in which the trend learning of each time series is treated as a task. The key point of MTL is to learn task relatedness to achieve better parameter sharing, which however is challenging in trend prediction task. First, effectively modeling the complex temporal patterns in different tasks is hard as the temporal and spatial dimensions are entangled. Second, the relatedness among tasks may change over time. In this paper, we propose a neural network, DeepTrends, for multivariate time series trend prediction. The core module of DeepTrends is a tensorized LSTM with adaptive shared memory (TLASM). TLASM employs the tensorized LSTM to model the temporal patterns of long-term trend sequences in an MTL setting. With an adaptive shared memory, TLASM is able to learn the relatedness among tasks adaptively, based upon which it can dynamically vary degrees of parameter sharing among tasks. To further consider short-term patterns, DeepTrends utilizes a multi-task 1dCNN to learn the local time series features, and employs a task-specific sub-network to learn a mixture of long-term and short-term patterns for trend prediction. Extensive experiments on real datasets demonstrate the effectiveness of the proposed model.

scholarly journals Track Irregularity Time Series Analysis and Trend Forecasting

2012 ◽  
Vol 2012 ◽  
pp. 1-15 ◽  
Author(s):  
Jia Chaolong ◽  
Xu Weixiang ◽  
Wang Futian ◽  
Wang Hanning
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Short Term ◽  
Measuring Point ◽  
Trend Forecasting ◽  
Changing Trend ◽  
Track Irregularity ◽  
Linear Differential

The combination of linear and nonlinear methods is widely used in the prediction of time series data. This paper analyzes track irregularity time series data by using gray incidence degree models and methods of data transformation, trying to find the connotative relationship between the time series data. In this paper, GM(1,1)is based on first-order, single variable linear differential equations; after an adaptive improvement and error correction, it is used to predict the long-term changing trend of track irregularity at a fixed measuring point; the stochastic linear AR, Kalman filtering model, and artificial neural network model are applied to predict the short-term changing trend of track irregularity at unit section. Both long-term and short-term changes prove that the model is effective and can achieve the expected accuracy.

scholarly journals Compound Autoregressive Network for Prediction of Multivariate Time Series

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Yuting Bai ◽  
Xuebo Jin ◽  
Xiaoyi Wang ◽  
Tingli Su ◽  
Jianlei Kong ◽  
...  
Keyword(s):  
Time Series ◽  
Time Series Prediction ◽  
Multivariate Time Series ◽  
Prediction Algorithm ◽  
Short Term ◽  
Advanced Control ◽  
Multiple Variables ◽  
Nonlinear Autoregressive Model ◽  
Interactive Relation ◽  
Nonlinear Autoregressive

The prediction information has effects on the emergency prevention and advanced control in various complex systems. There are obvious nonlinear, nonstationary, and complicated characteristics in the time series. Moreover, multiple variables in the time-series impact on each other to make the prediction more difficult. Then, a solution of time-series prediction for the multivariate was explored in this paper. Firstly, a compound neural network framework was designed with the primary and auxiliary networks. The framework attempted to extract the change features of the time series as well as the interactive relation of multiple related variables. Secondly, the structures of the primary and auxiliary networks were studied based on the nonlinear autoregressive model. The learning method was also introduced to obtain the available models. Thirdly, the prediction algorithm was concluded for the time series with multiple variables. Finally, the experiments on environment-monitoring data were conducted to verify the methods. The results prove that the proposed method can obtain the accurate prediction value in the short term.

scholarly journals Long Short Term Memory Recurrent Network for Standard and Poor’s 500 Index Modelling

2018 ◽  
Vol 7 (4.15) ◽  
pp. 25 ◽  
Author(s):  
Said Jadid Abdulkadir ◽  
Hitham Alhussian ◽  
Muhammad Nazmi ◽  
Asim A Elsheikh
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Data ◽  
Short Term Memory ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Forecasting time-series data are imperative especially when planning is required through modelling using uncertain knowledge of future events. Recurrent neural network models have been applied in the industry and outperform standard artificial neural networks in forecasting, but fail in long term time-series forecasting due to the vanishing gradient problem. This study offers a robust solution that can be implemented for long-term forecasting using a special architecture of recurrent neural network known as Long Short Term Memory (LSTM) model to overcome the vanishing gradient problem. LSTM is specially designed to avoid the long-term dependency problem as their default behavior. Empirical analysis is performed using quantitative forecasting metrics and comparative model performance on the forecasted outputs. An evaluation analysis is performed to validate that the LSTM model provides better forecasted outputs on Standard & Poor’s 500 Index (S&P 500) in terms of error metrics as compared to other forecasting models.  

scholarly journals A Multivariate Forecasting Model for the COVID-19 Hospital Census Based on Local Infection Incidence

2021 ◽  
Author(s):  
Hieu M. Nguyen ◽  
Philip Turk ◽  
Andrew McWilliams
Keyword(s):  
Time Series ◽  
Multivariate Time Series ◽  
Healthcare Systems ◽  
Leading Indicators ◽  
Short Term ◽  
Correction Model ◽  
Vector Error Correction ◽  
Infection Incidence ◽  
Vector Error

AbstractCOVID-19 has been one of the most serious global health crises in world history. During the pandemic, healthcare systems require accurate forecasts for key resources to guide preparation for patient surges. Fore-casting the COVID-19 hospital census is among the most important planning decisions to ensure adequate staffing, number of beds, intensive care units, and vital equipment. In the literature, only a few papers have approached this problem from a multivariate time-series approach incorporating leading indicators for the hospital census. In this paper, we propose to use a leading indicator, the local COVID-19 infection incidence, together with the COVID-19 hospital census in a multivariate framework using a Vector Error Correction model (VECM) and aim to forecast the COVID-19 hospital census for the next 7 days. The model is also applied to produce scenario-based 60-day forecasts based on different trajectories of the pandemic. With several hypothesis tests and model diagnostics, we confirm that the two time-series have a cointegration relationship, which serves as an important predictor. Other diagnostics demonstrate the goodness-of-fit of the model. Using time-series cross-validation, we can estimate the out-of-sample Mean Absolute Percentage Error (MAPE). The model has a median MAPE of 5.9%, which is lower than the 6.6% median MAPE from a univariate Autoregressive Integrated Moving Average model. In the application of scenario-based long-term forecasting, future census exhibits concave trajectories with peaks lagging 2-3 weeks later than the peak infection incidence. Our findings show that the local COVID-19 infection incidence can be successfully in-corporated into a VECM with the COVID-19 hospital census to improve upon existing forecast models, and to deliver accurate short-term forecasts and realistic scenario-based long-term trajectories to help healthcare systems leaders in their decision making.Author summaryDuring the COVID-19 pandemic, healthcare systems need to have adequate resources to accommodate demand from COVID-19 cases. One of the most important metrics for planning is the COVID-19 hospital census. Only a few papers make use of leading indicators within multivariate time-series models for this problem. We incorporated a leading indicator, the local COVID-19 infection incidence, together with the COVID-19 hospital census in a multivariate framework called the Vector Error Correction model to make 7-day-ahead forecasts. This model is also applied to produce 60-day scenario forecasts based on different trajectories of the pandemic. We find that the two time-series have a stable long-run relationship. The model has a good fit to the data and good forecast performance in comparison with a more traditional model using the census data alone. When applied to different 60-day scenarios of the pandemic, the census forecasts show concave trajectories that peak 2-3 weeks later than the infection incidence. Our paper presents this new model for accurate short-term forecasts and realistic scenario-based long-term forecasts of the COVID-19 hospital census to help healthcare systems in their decision making. Our findings suggest using the local COVID-19 infection incidence data can improve and extend more traditional forecasting models.

scholarly journals Credit Risk Determinants in Indonesia

2018 ◽  
Vol 1 (2) ◽  
pp. 106-115
Author(s):  
Amin Yusuf Efendi
Keyword(s):  
Time Series ◽  
Interest Rate ◽  
Credit Risk ◽  
Error Correction ◽  
Error Correction Model ◽  
Series Data ◽  
Short Term ◽  
Correction Model ◽  
Spurious Regression

Credit is the main business of the banking industry, therefore, in running the business, the bank is always overshadowed by the credit risk the which can be determined by the ratio of non-performing loans (NPL). The development of technology, finance digital brings the outside could impact on the financial industry both positive and negative. The purpose of this study was to analyze the interest rate, inflation, exchange rates, gross domestic product (GDP), a dummy finance digitalization policies in the long term and the short term of the non-performing loan (NPL) of conventional commercial banks in Indonesia The analytical method used in this research is-EG Error Correction Model (ECM), The Data used in this research is secondary quarterly time series data from the 2008 quarter 1-2017 4. The time series of data are not stationar Often that can cause spurious regression results, the exact models used is-EG Error Correction Model (ECM), This models may explain the behavior of short-term and long-term. The results Showed in the short-term variable interest rates significanly to non-performing loans, while in the long-term variable interest rate, exchange rate, and GDP Significantly, non-performing loans. Kredit merupakan bisnis utama dari industri perbankan, oleh karena itu dalam menjalankan bisnisnya, bank selalu dibayangi oleh risiko kredit yang dapat diketahui melalui rasio non-performing loans (NPL). Perkembangan teknologi, menghadirkan digital finance yang membawa dampak luar bisa terhadap industri keuangan baik positif dan negatif. Tujuan dari penelitian ini adalah untuk menganalisis suku bunga, inflasi, kurs, produk domestik bruto (PDB) dummy kebijakan digitalisasi keuangan dalam jangka panjang dan jangka pendek terhadap non-performing loan (NPL) bank umum konvensional di Indonesia  Metode analisis yang digunakan dalam penelitian ini adalah Error Correction Model-EG (ECM). Data yang digunakan dalam penelitian ini adalah data sekunder runtut waktu kuartalan dari 2008 kuartal 1 – 2017 kuartal 4. Data runtun waktu sering tidak stationar sehingga bisa menyebabkan hasil regresi palsu (spurious regression), Model yang tepat digunakan adalah Error Correction Model-EG (ECM), model ini dapat menjelaskan perilaku jangka pendek dan jangka panjang. Hasil penelitian menunjukkan dalam jangka pendek variabel suku bunga berpengaruh secara signifikan terhadap non performing loan, sedangkan dalam jangka panjang variabel suku bunga, kurs, dan PDB berpengaruh secara signifikan terhadap non perfoming loan.

scholarly journals Construction of Complex Network with Multiple Time Series Relevance

Information ◽  
2018 ◽  
Vol 9 (8) ◽  
pp. 202
Author(s):  
Zongwen Huang ◽  
Lingyu Xu ◽  
Lei Wang ◽  
Gaowei Zhang ◽  
Yaya Liu
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Weather Conditions ◽  
Series Data ◽  
Multiple Time ◽  
Multiple Time Series ◽  
Optimal Network ◽  
Multiple Variables ◽  
Threshold Network

Multivariate time series data, which comprise a set of ordered observations for multiple variables, are pervasively generated in weather conditions, traffic, financial stocks, etc. Therefore, it is of great significance to analyze the correlation between multiple time series. Financial stocks generate a significant amount of multivariate time series data that can be used to build networks that reflect market behavior. However, traditional commercial complex networks cannot fully utilize the multiple attributes of stocks and redundant filter relationships and reveal a more authentic financial stock market. We propose a fusion similarity of multiple time series and construct a threshold network with similarity. Furthermore, we define the connectivity efficiency to choose the best threshold, establishing a high connectivity efficiency network with the optimal network threshold. By searching the central node in the threshold network, we have found that the network center nodes constructed by our proposed method have a more comprehensive industry coverage than the traditional techniques to build the systems, and this also proves the superiority of this method.

scholarly journals Multivariate analysis of nonlinearity in sandbar behavior

2008 ◽  
Vol 15 (1) ◽  
pp. 145-158 ◽  
Author(s):  
L. Pape ◽  
B. G. Ruessink
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Nonlinear Models ◽  
Multivariate Time Series ◽  
Series Data ◽  
Small Scale ◽  
Synthetic Datasets ◽  
Long Term Prediction ◽  
Sandbar Migration

Abstract. Alongshore sandbars are often present in the nearshore zones of storm-dominated micro- to mesotidal coasts. Sandbar migration is the result of a large number of small-scale physical processes that are generated by the incoming waves and the interaction between the wave-generated processes and the morphology. The presence of nonlinearity in a sandbar system is an important factor determining its predictability. However, not all nonlinearities in the underlying system are equally expressed in the time-series of sandbar observations. Detecting the presence of nonlinearity in sandbar data is complicated by the dependence of sandbar migration on the external wave forcings. Here, a method for detecting nonlinearity in multivariate time-series data is introduced that can reveal the nonlinear nature of the dependencies between system state and forcing variables. First, this method is applied to four synthetic datasets to demonstrate its ability to qualify nonlinearity for all possible combinations of linear and nonlinear relations between two variables. Next, the method is applied to three sandbar datasets consisting of daily-observed cross-shore sandbar positions and hydrodynamic forcings, spanning between 5 and 9 years. Our analysis reveals the presence of nonlinearity in the time-series of sandbar and wave data, and the relative importance of nonlinearity for each variable. The relation between the results of each sandbar case and patterns in bar behavior are discussed, together with the effects of noise. The small effect of nonlinearity implies that long-term prediction of sandbar positions based on wave forcings might not require sophisticated nonlinear models.

Sign in / Sign up

Export Citation Format

Share Document