基于大数据分析的复值BP神经网络方法

Picking up Complex Valued BP Neural Network Based on Big Data Analysis

神经网络分析方法,现在已经成为极为成功的大数据分析方法,并在学术界和工业界全部被人所熟知,与传统的方式相比较,神经网络方法能够运用数据驱动等自动从数据中提取信息,并且在数据结构不明确、跨领域的大数据中具有极为明显的优势。复值BP神经网络对数据进行特征提取和抽象能力,从大量数据源中处理大数据中异构数据,这种分析方法的优势在于能够提取静态数据之间的相关信息。复值BP神经网络方法将会更加适用于提取信息的时序特征,从而加强对大数据的分析预测。基于大数据分析的神经网络方法可以对数据的时空关联以实现大数据的预测,解决大数据分析中的核心问题,为大数据分析研究提供了一定的科学依据。

The purpose neural network analysis method has now become an extremely successful big data analysis method, and it is well known in academia and industry. Compared with the traditional methods, the neural network method can use data-driven and other methods to automatically extract data In the extraction of information, and in the data structure is not clear, cross-cutting big data has a very obvious advantage. Methods： The complex-valued BP neural network is used to extract and abstract the features of data, and to process heterogeneous data in large data from a large number of data sources. The advantage of this method is that it can extract the related information between static data. Results： The complex-valued BP neural network method will be more suitable for extracting temporal characteristics of information, thus strengthening the analysis and prediction of big data. Conclusion： Neural network method based on big data analysis can predict spatio-temporal correlation of data in order to realize big data and solve the core problem in big data analysis, which provides a scientific basis for big data analysis and research.