Combining Two Types of Database System for Managing Property Graph Data

Kusu, Kazuma; Hatano, Kenji

doi:10.1109/bigdata.2018.8622050

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20−23 The SiAGDB is a property graph containing nodes, which represent entities in the data, and edges, which represent the relationship between two entities; property graphs also contain (property, value) pairs. 24 The limitations of graph databases can include an insufficient number of variables, the schema or architecture of the database, and the reproducibility, validity, or availability of the data contained within the graph database. 25 Due to the storing and querying of connected data, the advancement of graph databases and graph database management systems has been advantageous for machine learning applications.…”

Section: Introductionmentioning

confidence: 99%

“…The developed information architecture, the silica aerogel graph database (SiAGDB), details the synthesis and processing conditions of approximately 10 3 silica aerogels extracted from previous publications. Graph databases are useful for representing complex processes with intensively connected data where traditional relational databases become inefficient. − The SiAGDB is a property graph containing nodes, which represent entities in the data, and edges, which represent the relationship between two entities; property graphs also contain (property, value) pairs . The limitations of graph databases can include an insufficient number of variables, the schema or architecture of the database, and the reproducibility, validity, or availability of the data contained within the graph database …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Silica Aerogel Synthesis/Process–Property Predictions by Machine Learning

et al. 2023

View full text Add to dashboard Cite

Silica aerogels are mesoporous high surface area materials with extensive synthetic and processing conditions. To effectively synthesize aerogels, the impact of synthetic pathways on the resulting aerogel properties must be understood prior to experimental investigation. We develop an information architecture, the silica aerogel graph database (10 3 ), and a supervised machine learning neural network regression model to examine these relationships. The property graph database enables rapid queries and visualization of the impact of the synthesis and processing conditions on the final aerogel properties. The model maps from silica aerogel synthetic and processing conditions to predict the aerogel BET surface area with an average error of 109 ± 84 m 2 /g. Following a validation experiment, the model was shown to predict the aerogel surface area from new synthetic and processing conditions with an error of less than 5%. The experiment demonstrates the usefulness of the model in surface area prediction through the compatibility between computational and experimental results. Both in its current form and with further expansion, the developed graph database could reduce experimental dimensionality, time, and resources, enabling the successful synthesis of high surface area silica aerogels, which are advantageous for applications including thermal insulation, sorption media, and catalysis.

show abstract

Section: Introductionmentioning

confidence: 99%