Affiliations: Department of Computer Science, University of Houston-Clear Lake, Houston, TX, USA
Correspondence:
[*]
Corresponding author: Dr. Hisham Al-Mubaid, Chair, Computer Information Systems. Associate professor, Computer Science and Computer Information Systems, University of Houston-Clear Lake, 2700 Bay Area Blvd, Box 40, Houston, TX 77058, USA. Tel.: +1 281 283 3802; E-mail: [email protected].
Abstract: Radiation shielding has been an active subject of research in the space industry for many years. We propose a new model for mining material properties for radiation shielding. This work represents an effective way of using learning and feature selection for selecting the material properties that most affect the shielding effectiveness of materials. The methodology relies on machine learning as a measure for the identified subsets of material properties for radiation shielding. This is a new direction in working with radiation shielding using purely computational techniques with machine learning. The experimental results showed that the approach is quite effective in eliminating redundant features and identifying the most significant properties related to radiation shielding capability of materials. For example, we have identified some material properties, besides Density, like Heat of Fusion, Atomic Number, X-ray Absorption Edge, Electrical Resistivity, and Specific Heat Capacity that are highly related to the radiation shielding as they have been proved computationally. The evaluation results also show that all machine learning algorithms can induce more robust separating models for the subsets of reduced number of features that are highly significant in the domain of radiation shielding.
