Direction-Aware User Recommendation Based on Asymmetric Network Embedding

User recommendation aims at recommending users with potential interests in the social network. Previous works have mainly focused on the undirected social networks with symmetric relationship such as friendship, whereas recent advances have been made on the asymmetric relationship such as the following and followed by relationship. Among the few existing direction-aware user recommendation methods, the random walk strategy has been widely adopted to extract the asymmetric proximity between users. However, according to our analysis on real-world directed social networks, we argue that the asymmetric proximity captured by existing random walk based methods are insufficient due to the inbalance in-degree and out-degree of nodes. To tackle this challenge, we propose InfoWalk, a novel informative walk strategy to efficiently capture the asymmetric proximity solely based on random walks. By transferring the direction information into the weights of each step, InfoWalk is able to overcome the limitation of edges while simultaneously maintain both the direction and proximity. Based on the asymmetric proximity captured by InfoWalk, we further propose the qualitative (DNE-L) and quantitative (DNE-T) directed network embedding methods, capable of preserving the two properties in the embedding space. Extensive experiments conducted on six real-world benchmark datasets demonstrate the superiority of the proposed DNE model over several state-of-the-art approaches in various tasks.

Development and Application of Ancient Timber Buildings Structural Condition Assessment Model Based on a Fuzzy Matter-Element Model that Includes Asymmetric Proximity

To properly protect ancient buildings, it is vitally important to determine the health status of these structures in a timely manner. To easily, quickly, reliably, and quantitatively assess the structure health of ancient timber buildings, this paper proposes a structure health assessment method based on fuzzy matter-element theory improved by asymmetric proximity, and the specific assessment steps are given. First, a fuzzy matter-element model is constructed; then, to effectively solve the failure problem of the maximum membership principle, the fuzzy matter-element assessment model is improved by using the theory of asymmetric proximity. The weights determined by the entropy weight and clustering methods are then combined through the game theory combination weighting concept and, finally, the structural condition of the ancient timber buildings is classified into five grades: I favorable, II ordinary, III poor, IV inferior, and V dangerous. Ten evaluation factors were chosen: bearing capacity of the foundation soil, subbase deformation, foundation damage, column and foundation connection, bearing capacity of members, connection construction, member deformation, crack slope, crack depth, and decayed/insect attacked. Taking a building built in the Republican Period in Sino-Ocean Taikoo Li, Chengdu, as an example, this model was used to assess the building’s structural condition. The results show that this method is feasible to quantitatively assess the structural condition of ancient timber buildings. It is a simple and practical assessment method that can provide a decision-making basis for maintenance, protection, and reinforcement of ancient timber buildings.

The Evaluation Method for Tunnel Structure Health Condition Based on Asymmetric Proximity

In order to achieve the quantitative health diagnosis of operational tunnel, established the health diagnosis system and the evaluating criterion based on the mechanism of tunnel disease, used the weighted average operator to obtain comprehensive evaluation results, applied the asymmetric proximity to decide the grade of tunnel structure health, thus build a complete fuzzy comprehensive evaluation model. Finally, by taking the example of Lilong tunnel located at LiuHe Express way, and made analysis and evaluation to its structure health status. The results show that the improved grey relevancy method to determine the index weight can avoid the subjective arbitrariness and improve the reliability of the evaluation model, making a decision and analysis by asymmetric proximity insures the diagnosis results more correspond with the objective reality.