A comic book data database could help reduce the data set’s complexity, by simplifying its creation, according to researchers from the University of Maryland and the University at Albany.
The research, which was published in the journal Proceedings of the National Academy of Sciences, uses data from the Comic Book Database, a database that includes about 4 million comics titles published between 1950 and 2011.
The researchers developed a model for a comic book-title normalization process that is computationally efficient.
Their model is based on an algorithm for converting between two different sets of data that includes the comic book title, publisher, artist, and publication year.
They found that the process produces a similar result as a conventional comic book library.
“We found that if we normalize the comic books with respect to the comics we are using as inputs to the normalization algorithm, we get an improved result,” said Andrew Dix, a professor of computer science and engineering at the University, and the lead author of the paper.
The authors are now working on an updated version of their model that should be more efficient, they said.
Their initial research was published this week in the Journal of Information and Computer Science.
The goal of the research is to reduce the complexity of the data by reducing the number of input and output parameters and making the algorithm more efficient.
In addition, the researchers are working on ways to make the model more general.
This will be an ongoing challenge, Dix said.
“What we have to do is make the data more general and make the algorithm faster, which will be a goal of this work,” he said.
They are currently developing a library of about 6.6 million comic book stories, but have a lot of room for improvement.
The team has also been working on a way to make data easier to analyze, and they are planning on expanding their work to a database of comic book collections.
This could lead to the development of better algorithms for identifying and normalizing comics.
The study was supported by grants from the National Science Foundation and the National Institutes of Health.