Dynamic Fusion Algorithm of Building Surface Data in Heterogeneous Environment
- PDF / 534,279 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 249 Views
Dynamic Fusion Algorithm of Building Surface Data in Heterogeneous Environment Jing Zhu 1 & Jing Gao 2 Accepted: 20 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The existing building surface data fusion algorithms do not extract the segmented data features, resulting in inaccurate fusion results. In heterogeneous environment, a Clustering Fusion Algorithm Based on mutual information and fractal dimension is proposed. The regression coefficient is used to express the sequence, and the data feature representation and data dimension reduction are realized. The dynamic data series are processed by similarity measure function method. For the long dynamic data series, the piecewise aggregation approximation method is used to segment the data and then extract the features. Through the incremental clustering processing data based on fractal dimension clustering algorithm, the research of data fusion algorithm is realized. The experimental results show that the accuracy of building surface data fusion is greatly improved by using the dynamic data fusion algorithm, the highest is 0.98, the sum of square error is reduced, and the lowest is only 90.44. Keywords Heterogeneous environment . Building surface data . Metric function . Dynamic data . Clustering fusion
1 Introduction With the wide application of Internet, the whole social life and work are gradually affected and changed by computer technology, network technology and communication technology [1, 2]. In recent years, with the rapid development of the construction industry, building surface data plays an important role in building development [3, 4]. There are differences in the selection of different types of building surface data, but the main content of building surface data is the same, and other data which have little impact on building surface can be ignored. The main contents of building data include: material corrosion, solar radiation, wind pressure, wind load, cracks and temperature. The influence of the above data content on the building surface is very direct. Through the fusion calculation of the building surface data, the hidden data in the building surface can be found effectively, and the security of the building surface can be improved. Full clustering and fusion of building surface data can provide an important basis
* Jing Gao [email protected] 1
Department of architecture and civil engineering, Shijiazhuang Vocational Technology Institute, Shijiazhuang 050086, China
2
College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot 010012, China
for the development and innovation of construction industry. In order to adapt to the development of Internet and big data environment, the potential value information mining technology of building surface data continues to innovate. Due to the development and application of the corresponding information technology, the data generation, collection, storage and processing capabilities have been greatly improved [5, 6]. Even i
Data Loading...