1 October 2018 in Signal Processing: Image Communication
24 May 2021 in JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT
Public Private Partnership (PPP) mode is increasingly applied in civil air defense (CAD) projects to improve project quality and reduce the government’s financial pressure. Because CAD project has different attributes during wartime and peacetime states, it’s necessary to comprehensively consider the project performance under different states to conduct scientific performance measurement. This paper focuses on the process of construction, operation, and handover of CAD PPP project to construct a unified project performance measurement indicator system, then a system dynamics (SD) model is established to carry out dynamic performance measurement and simulation of CAD PPP project under different social states respectively. A case study is conducted to verify the effectiveness of the proposed SD model, model validation, sensitivity analysis and result analysis were included as well. The study result can make the project performance management of CAD PPP more scientific and reasonable, and help decision-makers to formulate effective performance improvement strategies. It’s found out that government plays an important role in CAD PPP projects, when resources are limited, the government should give priority to measures such as reducing tax rates and increasing subsidies to ensure project benefits. The research methods can also provide reference for performance measurement of other PPP projects.
8 April 2023 in ACM Transactions on Information Systems
Recently, recommender systems based on knowledge graphs (KGs) have become a popular research direction. Graph neural network (GNN) is the key technology of KG-based recommendation systems. However, existing GNNs have a significant flaw: They cannot explicitly model users’ intent in recommendations. Intent plays an essential role in users’ behaviors. For example, users may first generate an intent to purchase a certain group of items and then select a specific item from the group based on their preferences. Therefore, explicitly modeling intent has a positive significance for improving recommendation performance and providing explanations for recommendations. In this article, we propose a new model called Topic-aware Intention Network (TIN) for explainable recommendations with KGs. TIN models user representations from both preference and intent views. Specifically, we design a relational attention graph neural network to selectively aggregate information in KG to learn user preferences, and we propose a knowledge-enhanced topic model to learn user intent, which is viewed as topics hidden in user behavior sequences. Finally, we obtain the user representation by fusing user preference and intent through an attention network. The experimental results show that our proposed model outperforms the state-of-the-art methods and can generate reasonable explanations for the recommendation results.