Motivated by the idea of 'decomposition and ensemble', this paper proposes a novel method based on the wavelet-denoisingalgorithm and multiple echo state networks to improve the prediction accuracy of noisy m...
详细信息
Motivated by the idea of 'decomposition and ensemble', this paper proposes a novel method based on the wavelet-denoisingalgorithm and multiple echo state networks to improve the prediction accuracy of noisy multivariate time series. The noisy time series is first denoised by a wavelet soft thresholding algorithm and decomposed into a set of well-behaved constitutive series. Each constitutive series is then predicted by a separate echo state network with proper parameters that match the specified dynamics. Finally, the overall prediction is achieved by a linear combination of the constitutive series. For each constitutive series, we use the correlation integral method to select the phase-reconstruction parameters and to construct the appropriate input. Two sets of multivariate time series are investigated using the proposed model and some other related work. The simulation results demonstrate the effectiveness of the proposed method. (C) 2018 Published by Elsevier Inc.
In recent years, exchange markets are increasingly integrated together. Fluctuations and risks across different exchange markets exhibit co-moving and complex dynamics. In this paper we propose the entropy-based multi...
详细信息
In recent years, exchange markets are increasingly integrated together. Fluctuations and risks across different exchange markets exhibit co-moving and complex dynamics. In this paper we propose the entropy-based multivariate wavelet based approaches to analyze the multiscale characteristic in the multidimensional domain and improve further the Value at Risk estimation reliability. wavelet analysis has been introduced to construct the entropy-based Multiscale Portfolio Value at Risk estimation algorithm to account for the multiscale dynamic correlation. The entropy measure has been proposed as the more effective measure with the error minimization principle to select the best basis when determining the wavelet families and the decomposition level to use. The empirical studies conducted in this paper have provided positive evidence as to the superior performance of the proposed approach, using the closely related Chinese Renminbi and European Euro exchange market. (C) 2014 Elsevier BM. All rights reserved.
The aim of this study is to propose a complete instrumentation and signal processing method able to detect the presence of a person seated on the rear bench of a vehicle. The sensor is based on a piezoelectric film (E...
详细信息
The aim of this study is to propose a complete instrumentation and signal processing method able to detect the presence of a person seated on the rear bench of a vehicle. The sensor is based on a piezoelectric film (EMFI sensor), designed to detect mechanical vibrations. In order to avoid confusion between humans and heavy objects or empty seats, the authors focused on the extraction of a biological signature from the acquired signals. This physiological pattern was extracted using an original wavelet denoising algorithm and was used further as a matched filter, in order to detect human presence in the vibration signals. Physiologically significant features were extracted from the output of the (on-line) filtering process and fed further-on into a classical Bayes-based classifier. After training, the proposed method yielded very promising results, the output of the classifier being almost error-free for different acquisition conditions (stopped and on-road vehicle, new and artificially aged sensor).
In recent years, photo-voltaic (PV) system has become one of the most potential renewable energy power generation technologies because of its many advantages. Considering the influence of the randomness of PV system o...
详细信息
In recent years, photo-voltaic (PV) system has become one of the most potential renewable energy power generation technologies because of its many advantages. Considering the influence of the randomness of PV system on the operation and dispatching of power system, the necessity of a comprehensive forecasting model is increased rapidly. This paper proposes a short-term PV power forecasting method based on MDCM-GA-LSTM model to solve the problem of low accuracy of traditional and single forecasting model. First, the meteorological data are pre-processed based on wavelet denoising algorithm to improve the data quality. Second, a meteorological model is established based on genetic algorithm (GA) to optimize long short-term memory (LSTM) neural network. Finally, the network is trained with the modified data of the meteorological model as the input and the actual power as the output, and the power forecasting model is established. In this study, the forecasting accuracy is evaluated based on mean absolute error (MAE) and root mean square error (RMSE). The experimental results demonstrated that the MDCM-GA-LSTM model outperforms the conventional and single model by a difference of about 98.43% of the MAE and 98.97% of the RMSE error.
With the accelerating level of global integration, the volatilities across exchange markets are co-moving with higher level of fluctuation as well as more complicated dynamic inter correlations, which are key to the d...
详细信息
ISBN:
(纸本)9781479947775
With the accelerating level of global integration, the volatilities across exchange markets are co-moving with higher level of fluctuation as well as more complicated dynamic inter correlations, which are key to the deeper understanding and proper measurement of risk. Thus, we propose the multivariate wavelet based Value at Risk estimation algorithm to account for the multiscale dynamic correlation characteristics as the new stylized facts. The multivariate wavelet analysis unveils the time varying correlations over different time horizons, which corresponds to the regime switching across different time horizons. The incorporation of this information during the modeling process leads to the advanced semi parametric model, consisting of mixture of models of different specifications and parameters at different scales. Empirical studies using the proposed approach to investigate the Chinese RMB and Europe Euro as the closely related exchange markets have shown evidence of multiscale dynamic correlation characteristics. The proposed approach has demonstrated the improved performance in the VaR forecasting exercise.
Melanoma, a malignant tumor of melanocytes, is the most serious type of skin cancer in the world. It accounts for about 80% of deaths of all skin cancer. For cancer detection, circulating tumor cells (CTCs) serve as a...
详细信息
ISBN:
(纸本)9780819498571
Melanoma, a malignant tumor of melanocytes, is the most serious type of skin cancer in the world. It accounts for about 80% of deaths of all skin cancer. For cancer detection, circulating tumor cells (CTCs) serve as a marker for metastasis development, cancer recurrence, and therapeutic efficacy. Melanoma tumor cells have high content of melanin, which has high light absorption and can serve as endogenous biomarker for CTC detection without labeling. Here, we have developed an in vivo photoacoustic flow cytometry (PAFC) to monitor the metastatic process of melanoma cancer by counting CTCs of melanoma tumor bearing mice in vivo. To test in vivo PAFC's capability of detecting melanoma cancer, we have constructed a melanoma tumor model by subcutaneous inoculation of highly metastatic murine melanoma cancer cells, B16F10. In order to effectively distinguish the targeting PA signals from background noise, we have used the algorithm of waveletdenoising method to reduce the background noise. The in vivo flow cytometry (IVFC) has shown a great potential for detecting circulating tumor cells quantitatively in the blood stream. Compared with fluorescence-based in vivo flow cytometry (IVFC), PAFC technique can be used for in vivo, label-free, and noninvasive detection of circulating tumor cells (CTCs).
This paper proposes a wavelet denoising algorithm based on an improved lion optimization threshold strategy. By introducing weight and adjustment factors into the standard lion optimization algorithm, the local and gl...
详细信息
ISBN:
(纸本)9798400709630
This paper proposes a wavelet denoising algorithm based on an improved lion optimization threshold strategy. By introducing weight and adjustment factors into the standard lion optimization algorithm, the local and global optimization capabilities are enhanced. During the algorithm verification, forward modeling and theoretical signals generated with different noise were processed, showing that this algorithm significantly improved the signal-to-noise ratio and root mean square error of the signals. When applied to measured transient electromagnetic signals after data preprocessing, the inversion accuracy was further improved. The results demonstrate that this method can accurately separate useful signals from noise and improve signal quality, making it an effective signal denoising method.
暂无评论