Search
Adv Search
Machine Learning & Data Mining
Importance identification method based on multi-order neighborhood hierarchical association contribution of nodes
Gang HU,Lemeng WANG,Zhiyu LU,Qin WANG,Xiang XU
2024, 54(1):  1-10, 24.  doi:10.6040/j.issn.1672-3961.0.2022.390
Abstract ( 76 )   HTML( 86 )   ( 2 )   PDF (5411KB) ( 86 )   Save
Figures and Tables | References | Related Articles | Metrics

In order to identify the node importance more finely and extend the scope and category of effective information gathering of nodes, the spatial location attribute information of network nodes and their direct and indirect neighbor nodes were fused and clustered, a node importance identification method of multi-order neighbor hierarchical association contribution of complex networks was proposed. The definition of the contribution of node level location attributes was given based on the network node spatial location hierarchical differences and inter-layer association information. A complex network target node multi-order neighbor hierarchical association contributions matrix was constructed to characterize the hierarchical contribution of the associations between direct neighbor nodes, indirect neighbor nodes and target nodes to their influence. A node importance identification method that fused node topological location contribution across layers and levels of space with multi-order neighborhood hierarchical association contribution was proposed. The simulation experiments showed that the proposed method could effectively improve the precision and accuracy of node importance identification on six real networks. This study provided a scientific theoretical basis for in-depth exploration of the dynamic evolution mechanism behind the network, and then made prediction and regulation by exploring the multi-order hierarchical interaction behaviors among the network nodes.

Machine Learning & Data Mining
Progressive training strategy of physics-informed neural networks based on curriculum regularization
FAN Lilin, LIU Shihao, LI Yuan, MAO Wentao, CHEN Zongtao
2024, 54(1):  11-24.  doi:10.6040/j.issn.1672-3961.0.2023.155
Abstract ( 51 )   PDF (15260KB) ( 38 )   Save
References | Related Articles | Metrics
Nonlinear system identification based on fuzzy brain emotional learning with particle swarm algorithm
SUN Yuan, ZENG Huiquan, OUYANG Sujian, GAO Jiaqian, WANG Qinan, LIN Zhiyong
2024, 54(1):  25-32.  doi:10.6040/j.issn.1672-3961.0.2022.383
Abstract ( 51 )   PDF (4680KB) ( 49 )   Save
References | Related Articles | Metrics
Adaptive label information learning for intention detection
MA Kun, LIU Xiaoyun, LI Leping, JI Ke, CHEN Zhenxiang, YANG Bo
2024, 54(1):  45-51.  doi:10.6040/j.issn.1672-3961.0.2023.168
Abstract ( 34 )   PDF (2366KB) ( 87 )   Save
References | Related Articles | Metrics
A trajectory prediction-based edge offloading strategy for internet of vehicles
ZHAO Xiaoyan, GAO Yuanzhi, ZHANG Jiale, ZHANG Junna, YUAN Peiyan
2024, 54(1):  52-62.  doi:10.6040/j.issn.1672-3961.0.2023.149
Abstract ( 39 )   PDF (8259KB) ( 81 )   Save
References | Related Articles | Metrics
Evaluation of aviation equipment supplier based on BP-Adaboost algorithm and TOPSIS
GU Yulei, MA Hui, WANG Yuqin, HU Hui, LIU Fuxin
2024, 54(1):  63-73.  doi:10.6040/j.issn.1672-3961.0.2022.366
Abstract ( 27 )   PDF (1120KB) ( 88 )   Save
References | Related Articles | Metrics
Robot fish path planning method based on improved Bi-RRT algorithm
HUANG Jiankun, XUE Gang, LIU Yanjun, WANG Yu, LI Houchi, BAI Fagang
2024, 54(1):  74-82.  doi:10.6040/j.issn.1672-3961.0.2023.159
Abstract ( 34 )   PDF (6317KB) ( 73 )   Save
References | Related Articles | Metrics
A collaborative service offloading approach for Internet of Things based on deep reinforcement learning
CAO Yuhui, HUANG Yuze, FENG Beipeng, ZHANG Miao, GUO Zhenzhen
2024, 54(1):  83-90.  doi:10.6040/j.issn.1672-3961.0.2022.344
Abstract ( 28 )   PDF (3070KB) ( 36 )   Save
References | Related Articles | Metrics
Entity recognition based on lexicon information and GlobalPointer
LI Mingjian, LI Weijun, WANG Hairong
2024, 54(1):  91-99.  doi:10.6040/j.issn.1672-3961.0.2022.350
Abstract ( 35 )   PDF (1338KB) ( 29 )   Save
References | Related Articles | Metrics
Interpretable knowledge tracing based on the feature relevance of interaction sequence
CHEN Cheng, DONG Yongquan, JIA Rui, LIU Yuan
2024, 54(1):  100-108.  doi:10.6040/j.issn.1672-3961.0.2023.143
Abstract ( 43 )   PDF (4203KB) ( 22 )   Save
References | Related Articles | Metrics
Civil Engineering
Experiment of the model of hydration heat temperature field and strain field of concrete single box and three chamber girder
Peng WANG,Cheng HUANG,Guohao ZHAO,Feng ZHANG
2024, 54(1):  109-122, 130.  doi:10.6040/j.issn.1672-3961.0.2022.363
Abstract ( 42 )   HTML( 13 )   ( 1 )   PDF (23691KB) ( 13 )   Save
Figures and Tables | References | Related Articles | Metrics

In order to study the distribution law of concrete hydration heat temperature field and strain field in concrete single box and three chamber girder, a concrete box girder scaled-down(1∶2) model was cast in Laibin, 148 temperature sensors and 20 strain sensors were embedded in the concrete. Meteorological sensors were arranged, and the distribution law of hydration heat field of C60 high-strength concrete box girder was obtained through the analysis of field actual measurement data. The research results showed that the hydration heat of single-box three-compartment box girder was divided into three stages: temperature rise stage (0-24 h), rapid temperature drop stage (24-96 h) and smooth temperature drop stage (96-240 h). The average temperature of the box girder cross-section needed 179 h before it was lower than the entering temperature, the heat generated by the hydration of the box girder needed at least 7 d to be completely dissipated; the peak temperature of the whole cross-section was 24 h after pouring, and the highest area was at the pedicle axillary position, with the highest temperature reaching 90.2 ℃, and the maximum horizontal temperature difference of the top plate reached 32.2 ℃ at this time. Influenced by the layered pouring, the maximum vertical temperature difference of the side web reached 12 h after pouring 40.1 ℃, and the construction cold joints could be observed on the site. The temperature field distribution at the stalk axle was complicated, and the maximum transverse temperature difference at the stalk axle was 22.5 ℃ and the maximum vertical temperature difference was 29.9 ℃, and the transverse shrinkage strain at the surface of the stalk axil is smaller than the vertical one. The strain on the outer surface of the stalk axil is lower and constrained by the template, so the strain is smaller than that inside the stalk axil. it was calculated that there was a risk of vertical cracking in six pedicle axils, and the maximum shrinkage tensile stress was 1.51 times of the tensile strength.

Effect of carbonation freeze-thaw on chloride ion transport in aeolian sand concrete
DONG Wei, ZHOU Menghu, WANG Xuesong, XUE Gang, WANG Dong
2024, 54(1):  123-130.  doi:10.6040/j.issn.1672-3961.0.2022.249
Abstract ( 39 )   PDF (5561KB) ( 33 )   Save
References | Related Articles | Metrics
Analysis of the bearing capacity of the elliptical deep tunnel under the action of the anchor rod reinforcement
HAO Yanguang, XU Jiansheng, MING Daogui, LEI Ting, QIU Mingxi, CHEN Diyang
2024, 54(1):  131-140.  doi:10.6040/j.issn.1672-3961.0.2022.309
Abstract ( 30 )   PDF (6708KB) ( 66 )   Save
References | Related Articles | Metrics
    [an error occurred while processing this directive]