Multisource hierarchical neural network for knowledge graph embedding

Jiang, Dan; Wang, Ronggui; Xue, Lixia; Yang, Juan

doi:10.1016/j.eswa.2023.121446

Cited by 11 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al (2023a) put forward an innovative rule-based embedding technique that extracts attributes from entities, employing logical rules to augment datasets, which in turn enhances the precision of knowledge graph completion endeavors. Jiang et al (2024) unveiled a cutting-edge link prediction framework that leverages a multisource hierarchical neural network based on knowledge graph embeddings, aimed at overcoming challenges in extracting intricate graph information and fostering the fusion of multiple feature knowledge semantics.…”

Section: Overview Of Related Work On Knowledge Graphsmentioning

confidence: 99%

Construction of a large-scale maritime element semantic schema based on knowledge graph models for unmanned automated decision-making

Li,

Liu,

Wang

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

In maritime logistics optimization, considerable research efforts are focused on the extraction of deep behavioral characteristics from comprehensive shipping data to discern patterns in maritime vessel behavior. The effective linkage of these characteristics with maritime infrastructure, such as berths, is critical for the enhancement of ship navigation systems. This endeavor is paramount not only as a research focus within maritime information science but also for the progression of intelligent maritime systems. Traditional methodologies have primarily emphasized the analysis of navigational paths of vessels without an extensive consideration of the geographical dynamics between ships and port infrastructure. However, the introduction of knowledge graphs has enabled the integration of disparate data sources, facilitating new insights that propel the development of intelligent maritime systems. This manuscript presents a novel framework using knowledge graph technology for profound analysis of maritime data. Utilizing automatic identification system (AIS) data alongside spatial information from port facilities, the framework forms semantic triplet connections among ships, anchorages, berths, and waterways. This enables the semantic modeling of maritime behaviors, offering precise identification of ships through their diverse semantic information. Moreover, by exploiting the semantic relations between ships and berths, a reverse semantic knowledge graph for berths is constructed, which is specifically tailored to ship type, size, and category. The manuscript critically evaluates a range of graph embedding techniques, dimensionality reduction methods, and classification strategies through experimental frameworks to determine the most efficacious methodologies. The findings reveal that the maritime knowledge graph significantly enhances the semantic understanding of unmanned maritime equipment, thereby improving decision-making capabilities. Additionally, it establishes a semantic foundation for the development of expansive maritime models, illustrating the potential of knowledge graph technology in advancing intelligent maritime systems.

show abstract

Section: Overview Of Related Work On Knowledge Graphsmentioning

confidence: 99%

Construction of a large-scale maritime element semantic schema based on knowledge graph models for unmanned automated decision-making

Li,

Liu,

Wang

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…Buosi et al [10] use knowledge graph embedding to train models in order to predict recurrence in early stage non-small cell lung cancer patients, which can be used as an effective complement in classification systems and contribute to the treatment of cancer patients. Jiang et al [11] perform link prediction of knowledge graphs based on KG embedding of multi-source hierarchical neural networks to cope with the heterogeneity of KG entities and relationships, and effectively extract complex graph information. The study of federated KG embedding has attracted attention due to privacy protection and other needs.…”

Section: A Knowledge Graph Embeddingmentioning

confidence: 99%

Vaccine Coverage and Effectiveness in a School-Based Varicella Outbreak in Jinan Prefecture, Shandong Province

Liu

et al. 2022

Vaccines

View full text Add to dashboard Cite

Background: Licheng District of Jinan Prefecture reported a school-based varicella outbreak. We conducted an investigation to analyze the epidemiology and scope of the outbreak, determine varicella vaccine coverage on the school campus, and estimate varicella vaccine effectiveness (VE). Methods: In the epidemiological investigation, we determined the attack rate, the clinical manifestations of varicella cases, and histories of prior varicella disease and varicella vaccination. We tested students for presence of serum IgM antibodies, and we attempted to isolate the varicella virus from vesicular fluid samples. We used chi-square to compare incidences between classes and floors. VE was estimated using a retrospective cohort study. Results: There were 13 varicella cases in the outbreak. All were among fourth grade students - twelve in Class 7 and one in Class 6. The attack rate in the two classrooms was 14.3% (13/91). Clinical symptoms were rash (100%) and fever (46.15%). All cases were reported within one average incubation period, and the epidemic curve suggested common exposure. Six of the 13 cases previously received one dose of varicella vaccine with a median time between vaccination and infection of 9 years; the other seven cases had not been vaccinated. Varicella vaccine coverage with one or more doses was 81.31%; 2-dose coverage was 38.15%. The median age of receipt of dose 1 was 1.18 years, and median age for receiving dose 2 was 5.12 years. One-dose varicella VE was 73.2% (95% confidence interval: 37.0%, 88.6%), and two-dose VE was 100%. Conclusions: Varicella vaccine coverage has been gradually increasing in recent years, as ≥1-dose and 2-dose coverage rates are higher in younger children than older children. High one-dose vaccination coverage limited the outbreak scope and led to the breakthrough cases being mild. Mild cases were difficult to detect in a timely manner. Varicella vaccine was highly effective, with 1-dose VE of 73% nine years after vaccination and 2-dose VE of 100%. We strongly recommended that all school students receive two doses of varicella vaccine.

show abstract

Construction of a Large-Scale Maritime Elements Semantic Schema Based on Heterogeneous Graph Models

Liu,

Li,

Wang

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Multisource hierarchical neural network for knowledge graph embedding

Cited by 11 publications

References 34 publications

Construction of a large-scale maritime element semantic schema based on knowledge graph models for unmanned automated decision-making

Construction of a large-scale maritime element semantic schema based on knowledge graph models for unmanned automated decision-making

Vaccine Coverage and Effectiveness in a School-Based Varicella Outbreak in Jinan Prefecture, Shandong Province

Construction of a Large-Scale Maritime Elements Semantic Schema Based on Heterogeneous Graph Models

Contact Info

Product

Resources

About