Ensemble Empirical Mode Decomposition for time series prediction in wireless sensor networks

2014 ◽  
Author(s):  
Gagan Goel ◽  
Dimitrios Hatzinakos
Keyword(s):  
Time Series ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Empirical Mode Decomposition ◽  
Time Series Prediction ◽  
Ensemble Empirical Mode Decomposition ◽  
Wireless Sensor ◽  
Mode Decomposition

Toward a Digital Twin: Time Series Prediction Based on a Hybrid Ensemble Empirical Mode Decomposition and BO-LSTM Neural Networks

2020 ◽  
Vol 143 (5) ◽  
Author(s):  
Weifei Hu ◽  
Yihan He ◽  
Zhenyu Liu ◽  
Jianrong Tan ◽  
Ming Yang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Empirical Mode Decomposition ◽  
Time Series Prediction ◽  
Ensemble Empirical Mode Decomposition ◽  
Bayesian Optimization ◽  
Series Data ◽  
Digital Twin ◽  
Mode Decomposition ◽  
Highly Nonlinear

Abstract Precise time series prediction serves as an important role in constructing a digital twin (DT). The various internal and external interferences result in highly nonlinear and stochastic time series. Although artificial neural networks (ANNs) are often used to forecast time series because of their strong self-learning and nonlinear fitting capabilities, it is a challenging and time-consuming task to obtain the optimal ANN architecture. This paper proposes a hybrid time series prediction model based on an ensemble empirical mode decomposition (EEMD), long short-term memory (LSTM) neural networks, and Bayesian optimization (BO). To improve the predictability of stochastic and nonstationary time series, the EEMD method is implemented to decompose the original time series into several components (each component is a single-frequency and stationary signal) and a residual signal. The decomposed signals are used to train the neural networks, in which the hyperparameters are fine-tuned by the BO algorithm. The following time series data are predicted by summating all the predictions of the decomposed signals based on the trained neural networks. To evaluate the performance of the proposed EEMD-BO-LSTM neural networks, this paper conducts two case studies (the wind speed prediction and the wave height prediction) and implements a comprehensive comparison between the proposed method and other approaches including the persistence model, autoregressive integrated moving average (ARIMA) model, LSTM neural networks, BO-LSTM neural networks, and EEMD-LSTM neural networks. The results show an improved prediction accuracy using the proposed method by multiple accuracy metrics.

A Hybrid Wind Speed Prediction Approach Based on Ensemble Empirical Mode Decomposition and BO-LSTM Neural Networks for Digital Twin

2020 ◽  
Author(s):  
Weifei Hu ◽  
Yihan He ◽  
Zhenyu Liu ◽  
Jianrong Tan ◽  
Ming Yang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Wind Speed ◽  
Empirical Mode Decomposition ◽  
Time Series Data ◽  
Time Series Prediction ◽  
Ensemble Empirical Mode Decomposition ◽  
Series Data ◽  
Digital Twin ◽  
Mode Decomposition

Abstract Precise time series prediction serves as an important role in constructing a Digital Twin (DT). The various internal and external interferences result in highly non-linear and stochastic time series data sampled from real situations. Although artificial Neural Networks (ANNs) are often used to forecast time series for their strong self-learning and nonlinear fitting capabilities, it is a challenging and time-consuming task to obtain the optimal ANN architecture. This paper proposes a hybrid time series prediction model based on ensemble empirical mode decomposition (EEMD), long short-term memory (LSTM) neural networks, and Bayesian optimization (BO). To improve the predictability of stochastic and nonstationary time series, the EEMD method is implemented to decompose the original time series into several components, each of which is composed of single-frequency and stationary signal, and a residual signal. The decomposed signals are used to train the BO-LSTM neural networks, in which the hyper-parameters of the LSTM neural networks are fine-tuned by the BO algorithm. The following time series data are predicted by summating all the predictions of the decomposed signals based on the trained neural networks. To evaluate the performance of the proposed hybrid method (EEMD-BO-LSTM), this paper conducts a case study of wind speed time series prediction and has a comprehensive comparison between the proposed method and other approaches including the persistence model, ARIMA, LSTM neural networks, B0-LSTM neural networks, and EEMD-LSTM neural networks. Results show an improved prediction accuracy using the EEMD-BO-LSTM method by multiple accuracy metrics.

scholarly journals An edge-cloud collaboration architecture for pattern anomaly detection of time series in wireless sensor networks

2021 ◽  
Author(s):  
Cong Gao ◽  
Ping Yang ◽  
Yanping Chen ◽  
Zhongmin Wang ◽  
Yue Wang
Keyword(s):  
Time Series ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Anomaly Detection ◽  
Estimation Method ◽  
Feature Representation ◽  
Sensor Data ◽  
Wireless Sensor ◽  
Data Sets ◽  
Edge Node

AbstractWith large deployment of wireless sensor networks, anomaly detection for sensor data is becoming increasingly important in various fields. As a vital data form of sensor data, time series has three main types of anomaly: point anomaly, pattern anomaly, and sequence anomaly. In production environments, the analysis of pattern anomaly is the most rewarding one. However, the traditional processing model cloud computing is crippled in front of large amount of widely distributed data. This paper presents an edge-cloud collaboration architecture for pattern anomaly detection of time series. A task migration algorithm is developed to alleviate the problem of backlogged detection tasks at edge node. Besides, the detection tasks related to long-term correlation and short-term correlation in time series are allocated to cloud and edge node, respectively. A multi-dimensional feature representation scheme is devised to conduct efficient dimension reduction. Two key components of the feature representation trend identification and feature point extraction are elaborated. Based on the result of feature representation, pattern anomaly detection is performed with an improved kernel density estimation method. Finally, extensive experiments are conducted with synthetic data sets and real-world data sets.

Spatiotemporal Trend and Variability of Precipitation in Taiwan Based on Multi-dimensional Ensemble Empirical Mode Decomposition (MEEMD)

2021 ◽  
Author(s):  
Chun-Hsiang Tang ◽  
Christina W. Tsai
Keyword(s):  
Time Series ◽  
Empirical Mode Decomposition ◽  
Ensemble Empirical Mode Decomposition ◽  
Intrinsic Mode Functions ◽  
Short Term ◽  
Time Frequency ◽  
Spatial Locality ◽  
Temperature And Precipitation ◽  
Mode Decomposition ◽  
Climatic Scenarios

<p>Abstract</p><p>Most of the time series in nature are nonlinear and nonstationary affected by climate change particularly. It is inevitable that Taiwan has also experienced frequent drought events in recent years. However, drought events are natural disasters with no clear warnings and their influences are cumulative. The difficulty of detecting and analyzing the drought phenomenon remains. To deal with the above-mentioned problem, Multi-dimensional Ensemble Empirical Mode Decomposition (MEEMD) is introduced to analyze the temperature and rainfall data from 1975~2018 in this study, which is a powerful method developed for the time-frequency analysis of nonlinear, nonstationary time series. This method can not only analyze the spatial locality and temporal locality of signals but also decompose the multiple-dimensional time series into several Intrinsic Mode Functions (IMFs). By the set of IMFs, the meaningful instantaneous frequency and the trend of the signals can be observed. Considering stochastic and deterministic influences, to enhance the accuracy this study also reconstruct IMFs into two components, stochastic and deterministic, by the coefficient of auto-correlation.</p><p>In this study, the influences of temperature and precipitation on the drought events will be discussed. Furthermore, to decrease the significant impact of drought events, this study also attempts to forecast the occurrences of drought events in the short-term via the Artificial Neural Network technique. And, based on the CMIP5 model, this study also investigates the trend and variability of drought events and warming in different climatic scenarios.</p><p> </p><p>Keywords: Multi-dimensional Ensemble Empirical Mode Decomposition (MEEMD), Intrinsic Mode Function(IMF), Drought</p>

scholarly journals Hierarchical classification of time series data aggregation in underwater wireless sensor networks

2020 ◽  
Vol 37 (2) ◽  
pp. 53-64
Author(s):  
Durairaj Ruby ◽  
Jayachandran Jeyachidra
Keyword(s):  
Time Series ◽  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Error Rate ◽  
Data Aggregation ◽  
Hierarchical Classification ◽  
Wireless Sensor ◽  
Underwater Wireless Sensor Networks

Environmental fluctuations are continuous and provide opportunities for further exploration, including the study of overground, as well as underground and submarine, strata. Underwater wireless sensor networks (UWSNs) facilitate the study of ocean-based submarine and marine parameters details and data. Hardware plays a major role in monitoring marine parameters; however, protecting the hardware deployed in water can be difficult. To extend the lifespan of the hardware, the inputs, processing and output cycles may be reduced, thus minimising the consumption of energy and increasing the lifespan of the devices. In the present study, time series similarity check (TSSC) algorithm is applied to the real-time sensed data to identify repeated and duplicated occurrences of data for reduction, and thus improve energy consumption. Hierarchical classification of ANOVA approach (HCAA) applies ANOVA (analysis of variance) statistical analysis model to calculate error analysis for realtime sensed data. To avoid repeated occurrences, the scheduled time to read measurements may be extended, thereby reducing the energy consumption of the node. The shorter time interval of observations leads to a higher error rate with lesser accuracy. TSSC and HCAA data aggregation models help to minimise the error rate and improve accuracy.

Application of MEEMD-ARIMA combining model for annual runoff prediction in the Lower Yellow River

2019 ◽  
Vol 11 (3) ◽  
pp. 865-876 ◽  
Author(s):  
Xianqi Zhang ◽  
Wei Tuo ◽  
Chao Song
Keyword(s):  
Time Series ◽  
Empirical Mode Decomposition ◽  
Yellow River ◽  
Arima Model ◽  
Ensemble Empirical Mode Decomposition ◽  
Annual Runoff ◽  
Lower Yellow River ◽  
The Lower Yellow River ◽  
Mode Decomposition ◽  
Runoff Prediction

Abstract The prediction of annual runoff in the Lower Yellow River can provide an important theoretical basis for effective reservoir management, flood control and disaster reduction, river and beach management, rational utilization of regional water and sediment resources. To solve this problem and improve the prediction accuracy, permutation entropy (PE) was used to extract the pseudo-components of modified ensemble empirical mode decomposition (MEEMD) to decompose time series to reduce the non-stationarity of time series. However, the pseudo-component was disordered and difficult to predict, therefore, the pseudo-component was decomposed by ensemble empirical mode decomposition (EEMD). Then, intrinsic mode functions (IMFs) and trend were predicted by autoregressive integrated moving average (ARIMA) which has strong ability of approximation to stationary series. A new coupling model based on MEEMD-ARIMA was constructed and applied to runoff prediction in the Lower Yellow River. The results showed that the model had higher accuracy and was superior to the CEEMD-ARIMA model or EEMD-ARIMA model. Therefore, it can provide a new idea and method for annual runoff prediction.

Sign in / Sign up

Export Citation Format

Share Document