Financial time series are nonlinear,non-stationary and have a long memory,which make it difficult to achieve the desired prediction *** this paper,we propose a forecasting method,combining the wavelet analysis and the...
详细信息
Financial time series are nonlinear,non-stationary and have a long memory,which make it difficult to achieve the desired prediction *** this paper,we propose a forecasting method,combining the wavelet analysis and the particle swarm optimization(PSO) neural *** use the wavelet analysis to de-noise the non-stationary time series,and then employ bp neural network based on PSO to predict the time series after *** paper researches the selection criteria of a wavelet function,forecasts the time series of Shanghai Composite Index closing prices with wavelet analysis and compares the results with traditional prediction *** is obvious that after wavelet de-noising,the same neural network analysis increases the forecasting prediction accuracy by almost an order of magnitude and the prediction error is much smaller than the prediction error without wavelet *** method improves the hysteretic nature and can achieve the ideal *** facilitates the analysis of the characteristics of financial risks and financial markets.
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network contr...
详细信息
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ bp network） , based on which the paper proposes introducing momentum to improve bp network.
This paper introduces the application of the distinguishing heart pulse based on an artificial neural network. We propose a new method – changing the derivative to increase the speed of the bp algorithm and duplicati...
详细信息
ISBN:
(纸本)9781784660529
This paper introduces the application of the distinguishing heart pulse based on an artificial neural network. We propose a new method – changing the derivative to increase the speed of the bp algorithm and duplicating using the sample. The artificial neural network, which learns from the sample, is able to distinguish the pulse.
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network contr...
详细信息
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and humidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network(bp network), based on which the paper proposes introducing momentum to improve bp network.
Based on a review of the basic concepts, basic structure and algorithm principle of neural networks, this paper sets out to develop a bp neural network-based engineering cost prediction model. Based on the conclusions...
详细信息
Based on a review of the basic concepts, basic structure and algorithm principle of neural networks, this paper sets out to develop a bp neural network-based engineering cost prediction model. Based on the conclusions of the model and in combination with MATLAB's Neural Networks Toolbox, further program design is made. Finally, a case analysis approach is adopted to expound on the specific applications of the model. It is concluded that it is fully feasible to adopt bp neural networks to predict construction costs. A summary of the deficiencies of this study and those aspects for more in-depth research is also given.
The advantages and weakens of traditional bp algorithm is briefly analyzed and an efficient global optimization algorithm is *** basic principle of the algorithm is presented,and a new bp neural network algorithm base...
详细信息
The advantages and weakens of traditional bp algorithm is briefly analyzed and an efficient global optimization algorithm is *** basic principle of the algorithm is presented,and a new bp neural network algorithm based on the existing bp algorithm and the new global optimization algorithm is proposed, considering the new global optimization algorithm can solve the problem of local minimum efficiently. To verify the effectiveness of the new bp algorithm,the paper compared the experimental results of various algorithms in solving function fitting problem.
Adaptive beamforming can achieve better SNR by varying the weights of each of the sensors used in the *** traditional beamforming methods cannot achieve the optimal performance in beamforming because of the mismatch b...
详细信息
Adaptive beamforming can achieve better SNR by varying the weights of each of the sensors used in the *** traditional beamforming methods cannot achieve the optimal performance in beamforming because of the mismatch between the assumed array response and true array response.A radial basis function neural network algorithm has been proposed in this paper to solve this problem by turning the processing of calculating weighting of arrays to mapping *** simulation results indicate that the proposed method can adapt the weighting according to the direction of source signal automotive,and the SNR can be increased significantly with the DOA mismatch at 2 degrees.
In petrochemical industries, one of the most concerned problems is the leaking of toxic gas. Once leaking occurs, the safety of equipments located in production site is greatly threatened, thereby affecting surroundin...
详细信息
ISBN:
(纸本)9781479940318
In petrochemical industries, one of the most concerned problems is the leaking of toxic gas. Once leaking occurs, the safety of equipments located in production site is greatly threatened, thereby affecting surrounding environment. In order to solve this problem, it is necessary to predict the possible location of leak points from sensors which are located in gas pipe. On the other hand, data from sensors of petrochemical industries need to be timely operated because of time sensitivity, and it is hard to achieve associated information from sensors located in production site. To this end, an OLA-Ibp (Online Learning algorithm based on Improved Back Propagation) is proposed. The adaptive structure of this algorithm is settled on-line. Meanwhile, real-time data streams are parallelly processed according to arriving time in input layer. Simulation results show that OLA-Ibp can efficiently improve learning time and accuracy rate. Finally, the adaptability of OLA-Ibp is verified in leak points prediction of petrochemical equipments from processed data.
In order to detect the SIP flooding attacks in IMS (IP Multimedia Subsystem) network, the paper proposes a flooding attack detection method based on bp neural network, and analyses causes of SIP flooding attack, and t...
详细信息
ISBN:
(纸本)9783037855744
In order to detect the SIP flooding attacks in IMS (IP Multimedia Subsystem) network, the paper proposes a flooding attack detection method based on bp neural network, and analyses causes of SIP flooding attack, and thus determine the bp the input of the neural network characteristics. The simulation results show that this method has better detection performance.
Because of the diversity and complexity of soft fault in analog circuit, the rapid and accurate diagnosis is very difficult. For this, an adaptive bp wavelet neural network diagnosis method of soft fault is proposed. ...
详细信息
ISBN:
(纸本)9783037856598
Because of the diversity and complexity of soft fault in analog circuit, the rapid and accurate diagnosis is very difficult. For this, an adaptive bp wavelet neural network diagnosis method of soft fault is proposed. It combines the time-frequency localization characteristics of wavelet and the self-learning ability of neural network in soft fault diagnosis of analog circuit, and by introducing the adaptive learning rate the diagnosis ability of bp wavelet neural network model can effectively be improved. In addition, PSPICE software is used to obtain the simulation data of actual analog circuit for the experiment. The results also verify the validity of the proposed method.
暂无评论