This DC-YOLO Model was designed in order to improve the efficiency for appraising dangerous class of buildings and avoid manual intervention,thereby making the appraisal results more objective.It is an automated metho...This DC-YOLO Model was designed in order to improve the efficiency for appraising dangerous class of buildings and avoid manual intervention,thereby making the appraisal results more objective.It is an automated method designed based on deep learning and target detection algorithms to appraise the dangerous class of building masonry component.Specifically,it(1)adopted K-means clustering to obtain the quantity and size of the prior boxes;(2)expanded the grid size to improve identification to small targets;(3)introduced in deformable convolution to adapt to the irregular shape of the masonry component cracks.The experimental results show that,comparing with the conventional method,the DC-YOLO model has better recognition rates for various targets to different extents,and achieves good effects in precision,recall rate and F1 value,which indicates the good performance in classifying dangerous classes of building masonry component.展开更多
A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground o...A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground on the uncertainty measure theory. Then the single-index measure function of sixteen influential factors and the calculation method of computing the index weight ground on entropy theory were respectively established. The value assignment of sixteen influential factors was carried out by the qualitative analysis and observational data, respectively, in succession. The sequence of fire danger class of four experimental coalfaces could be obtained by the computational aids of Matlab according to the confidence level criterion. Some conclusions that the fire danger class of the No.l, No.2 and No.3 coalface belongs to high criticality can be obtained. But the fire danger class of the No.4 coalface belongs to higher criticality. The fire danger class of the No.4 coalface is more than that of the No.2 coalface. The fire danger class of the No.2 coalface is more than that of the No.1 coalface. Finally, the fire danger class of the No.1 coalface is more than that of the No.3 coalface.展开更多
基金The work is supported by National key research and development plan of China(2016YFC0801408)the Graduate Science and Technology Innovation Project of Shandong University of Science and Technology(SDKDYC180344).
文摘This DC-YOLO Model was designed in order to improve the efficiency for appraising dangerous class of buildings and avoid manual intervention,thereby making the appraisal results more objective.It is an automated method designed based on deep learning and target detection algorithms to appraise the dangerous class of building masonry component.Specifically,it(1)adopted K-means clustering to obtain the quantity and size of the prior boxes;(2)expanded the grid size to improve identification to small targets;(3)introduced in deformable convolution to adapt to the irregular shape of the masonry component cracks.The experimental results show that,comparing with the conventional method,the DC-YOLO model has better recognition rates for various targets to different extents,and achieves good effects in precision,recall rate and F1 value,which indicates the good performance in classifying dangerous classes of building masonry component.
基金Supported by the National Foundation of China(50974055)the Program for Changjiang Scholars and Innovative Research Team in University(IRT0618)Henan Province Basic and Leading-edge Technology Research Program(082300463205)
文摘A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground on the uncertainty measure theory. Then the single-index measure function of sixteen influential factors and the calculation method of computing the index weight ground on entropy theory were respectively established. The value assignment of sixteen influential factors was carried out by the qualitative analysis and observational data, respectively, in succession. The sequence of fire danger class of four experimental coalfaces could be obtained by the computational aids of Matlab according to the confidence level criterion. Some conclusions that the fire danger class of the No.l, No.2 and No.3 coalface belongs to high criticality can be obtained. But the fire danger class of the No.4 coalface belongs to higher criticality. The fire danger class of the No.4 coalface is more than that of the No.2 coalface. The fire danger class of the No.2 coalface is more than that of the No.1 coalface. Finally, the fire danger class of the No.1 coalface is more than that of the No.3 coalface.
