A data completion method for dam safety monitoring based on spatiotemporal multi-view fusion

Abstract

The invention discloses a dam safety monitoring data completion method based on spatiotemporal multi-view fusion. Abstract the view model; fuse the four models using lasso regression to generate a spatiotemporal multi-view fusion model; use the spatiotemporal multi-view fusion model to generate complementary data. In the case of strong correlation between temporal and spatial characteristics, this method can well solve the problems of block deletion and local deletion in dam safety monitoring data, and has been verified on real dam safety monitoring data. Algorithms and traditional spatiotemporal models have smaller errors and better completions.

Description

technical field [0001] The invention relates to a missing data complementing method, in particular to a dam safety monitoring data complementing method based on spatiotemporal multi-view fusion. Background technique [0002] With the maturity of Internet technology and the rapid development of data collection and storage capabilities, big data technology has completely penetrated into the field of data information. However, due to the lack of real data, the models and methods based on ideal data sets can no longer meet the real needs of data mining. In order to mine reliable information and establish a more effective application data mining model, it is necessary to complete the missing data. A deep learning-based framework reconstructs missing data to facilitate time series analysis. The framework is built on the time series of observed data, based on a collection of multiple forecasting models, and completes the coupling between forecasting modules with the help of virtu...

AI Technical Summary

Problems solved by technology

However, this kind of proposed method cannot deal with problems such as continuous missing of mixed classification. The method proposed by Vincent based on DAE also needs to have better accuracy under the premise of complete data, so the effect is not ideal for incomplete data.

Images