Multiple Time-scale Characteristics Analysis of Rainfall in Hunan Province Based on Ensemble Empirical Mode Decomposition

2019 ◽  
Author(s):  
Guoyong Zhang ◽  
Bo Li ◽  
Li Li ◽  
Xiudong Zhou ◽  
Xunjian Xu ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Time Scale ◽  
Ensemble Empirical Mode Decomposition ◽  
Hunan Province ◽  
Multiple Time ◽  
Multiple Time Scale ◽  
Mode Decomposition ◽  
Characteristics Analysis ◽  
Scale Characteristics

scholarly journals The Forecast of The Number of Inbound Tourists and The Analysis of The Source Market During The Epidemic of Coronavirus Disease

2020 ◽  
pp. 1-53
Keyword(s):  
Hong Kong ◽  
New Zealand ◽  
Empirical Mode Decomposition ◽  
Prediction Models ◽  
Ensemble Empirical Mode Decomposition ◽  
Initial Value ◽  
Mode Decomposition ◽  
Inbound Tourism ◽  
Scale Characteristics ◽  
Source Countries

With the rapid development of economy, the competition of inbound tourism market is more and more fierce. The key point of sustainable development of inbound tourism is to ensure a certain number of tourists. Therefore, it is an important step to predict the number of inbound tourists and study the market of inbound tourists. As a leading tourism city in China, how to attract more tourists is not only related to the development of inbound tourism in Shanghai, but also provides some inspiration for other cities during the epidemic of Coronavirus Disease. In this paper, an improved grey markov (GM) model is used to predict the number of inbound tourists in Shanghai during the epidemic of Coronavirus Disease, and then the market changes of inbound tourists are studied by the deviation-share analysis method. Finally, the tim-scale characteristics and trends of inbound tourists in Shanghai are analyzed by ensemble empirical mode decomposition. GM (1,1) model is one of the most widely used grey dynamic prediction models in grey system theory, which is composed of a first order differential equation with a single variable. The initial value correction improves the gray GM (1,1) model, and introduces the center point triangle albino weight function in the state division to improve the Markova model. Comparing with the results of traditional GM (1,1), initial value modified GM (1,1) and traditional grey markov prediction models, the prediction effect of this model is verified to be better. These models are better than linear regression and time series. Deviation-share analysis explores the changes in the inbound tourist market, and the results show that from 2004 to 2017, the inbound tourist market in Shanghai developed faster than that in the whole country, with a more reasonable and competitive structure. In addition to Japan, the number of inbound tourists from each country to the whole country and Shanghai has increased and increased greatly. The time-scale characteristics and trends of inbound tourists in Shanghai are analyzed by ensemble empirical mode decomposition. The results show that: first, the total number of inbound tourists and the number of foreign tourists mainly change within 3 or 6 months, while that of Hong Kong, Macao and Taiwan fluctuates between high and low frequency. Second, the main cyclical fluctuations and no significant trend of the source countries. The fluctuation period of Japan, Thailand, Britain, France and Germany is 3 months; Macau is 3, 6, 12, 60, 180 months; Singapore is 3, 6, 180 months. Third, there is a clear trend and cycle fluctuations as a supplement to the source countries. The fluctuation periods in Hong Kong are 3, 6, 90 and 180 months; In Taiwan, Canada and Russia it is 3 , 6 months; In Indonesia, the United States, Italy and New Zealand it is 3, 6 and 12 months; In Malaysia it is 3, 180 months; In South Korea it is 3 ,45 months; In Australia it's four or seven months. Taiwan, Canada, Russia and New Zealand showing the most significant upward trend. From the above research results, specific Suggestions and strategies of market structure competition can be put forward to the inbound tourism industry in Shanghai according to the predicted number of inbound tourists in Shanghai, the structure of the source market and the cyclical fluctuation and trend of the source country.

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

scholarly journals Short-Term Electricity Price Forecasting by Employing Ensemble Empirical Mode Decomposition and Extreme Learning Machine

Forecasting ◽  
2021 ◽  
Vol 3 (3) ◽  
pp. 460-477
Author(s):  
Sajjad Khan ◽  
Shahzad Aslam ◽  
Iqra Mustafa ◽  
Sheraz Aslam
Keyword(s):  
Extreme Learning Machine ◽  
Empirical Mode Decomposition ◽  
Electricity Market ◽  
Ensemble Empirical Mode Decomposition ◽  
Electricity Price ◽  
Price Forecasting ◽  
Short Term ◽  
Mode Decomposition ◽  
Electricity Price Forecasting ◽  
Learning Machine

Day-ahead electricity price forecasting plays a critical role in balancing energy consumption and generation, optimizing the decisions of electricity market participants, formulating energy trading strategies, and dispatching independent system operators. Despite the fact that much research on price forecasting has been published in recent years, it remains a difficult task because of the challenging nature of electricity prices that includes seasonality, sharp fluctuations in price, and high volatility. This study presents a three-stage short-term electricity price forecasting model by employing ensemble empirical mode decomposition (EEMD) and extreme learning machine (ELM). In the proposed model, the EEMD is employed to decompose the actual price signals to overcome the non-linear and non-stationary components in the electricity price data. Then, a day-ahead forecasting is performed using the ELM model. We conduct several experiments on real-time data obtained from three different states of the electricity market in Australia, i.e., Queensland, New South Wales, and Victoria. We also implement various deep learning approaches as benchmark methods, i.e., recurrent neural network, multi-layer perception, support vector machine, and ELM. In order to affirm the performance of our proposed and benchmark approaches, this study performs several performance evaluation metric, including the Diebold–Mariano (DM) test. The results from the experiments show the productiveness of our developed model (in terms of higher accuracy) over its counterparts.

Sign in / Sign up

Export Citation Format

Share Document