# Evidence-based data mining method to reveal similarities between materials based on physical mechanisms https://mdr.nims.go.jp/datasets/e467d9bf-e291-4e48-90d8-033de57d52ee ## File - [Dam_evidence_based_5.0134999.pdf](https://mdr.nims.go.jp/filesets/77a8d79a-5b34-4a05-bf57-04d84c78b7e0/download) ([Detail](https://mdr.nims.go.jp/filesets/77a8d79a-5b34-4a05-bf57-04d84c78b7e0.md)) ## Id e467d9bf-e291-4e48-90d8-033de57d52ee ## Local identifier ## Visibility open_to_public ## State published ## Created at 2023-02-07T00:37:53.536014Z ## Updated at 2024-01-05T13:13:49.036470Z ## Published at 2023-02-08T02:15:47.701872Z ## Doi ## First published url https://doi.org/10.1063/5.0134999 ## Date published 2023-02-07 ## Recorded date published 2023-2-7 ## Resource type journal_article ## Manuscript type vor ## Collection ## Title - title: NA title_type: alternative lang: ja - title: Evidence-based data mining method to reveal similarities between materials based on physical mechanisms title_type: original lang: en ## Description - description: "Measuring the similarity between materials is essential for estimating their properties and revealing the associated physical mechanisms.\r\nHowever, current methods for measuring the similarity between materials rely on theoretically derived descriptors and parameters fitted\r\nfrom experimental or computational data, which are often insufficient and biased. Furthermore, outliers and data generated by multiple\r\nmechanisms are usually included in the dataset, making the data-driven approach challenging and mathematically complicated. To overcome such issues, we apply the Dempster–Shafer theory to develop an evidential regression-based similarity measurement (eRSM) method,\r\nwhich can rationally transform data into evidence. It then combines such evidence to conclude the similarities between materials, considering their physical properties. To evaluate the eRSM, we used two material datasets, including 3d transition metal–4f rare-earth binary and\r\nquaternary high-entropy alloys with target properties, Curie temperature, and magnetization. Based on the information obtained on the similarities between the materials, a clustering technique is applied to learn the cluster structures of the materials that facilitate the interpretation\r\nof the mechanism. The unsupervised learning experiments demonstrate that the obtained similarities are applicable to detect anomalies and\r\nappropriately identify groups of materials whose properties correlate differently with their compositions. Furthermore, significant improvements in the accuracies of the predictions for the Curie temperature and magnetization of the quaternary alloys are obtained by introducing the similarities, with the reduction in mean absolute errors of 36% and 18%, respectively. The results show that the eRSM can adequately measure the similarities and dissimilarities between materials in these datasets with respect to mechanisms of the target properties." description_type: abstract lang: eng ## Creator - name: Minh-Quyet Ha role: author orcid: https://orcid.org/0000-0003-4617-0059 organization: JAIST - name: Duong-Nguyen Nguyen role: author orcid: https://orcid.org/0000-0003-0980-8754 organization: JAIST - name: Viet-Cuong Nguyen role: author orcid: https://orcid.org/0000-0002-8008-582X organization: HPC Systems Inc - name: Hiori Kino role: author orcid: https://orcid.org/0000-0002-8912-686X organization: National Institute for Materials Science ror: https://ror.org/026v1ze26 - name: Yasunobu Ando role: author orcid: https://orcid.org/0000-0003-3702-034X organization: JAIST - name: Takashi Miyake role: author orcid: https://orcid.org/0000-0003-2658-3470 organization: JAIST - name: Thierry Denœux role: author orcid: https://orcid.org/0000-0002-0660-5436 organization: University of Technology of Compiègne - name: Van-Nam Huynh role: author orcid: https://orcid.org/0000-0002-3860-7815 organization: JAIST - name: Hieu-Chi Dam role: author orcid: https://orcid.org/0000-0001-8252-7719 organization: JAIST ## Contact agent ## Publisher ## Managing organization ## Keyword - subject: Dempster–Shafer theory schema: not_defined - subject: similarity evidence schema: not_defined - subject: evidence theory schema: not_defined - subject: Curie temperature schema: not_defined - subject: visualization schema: not_defined - subject: physical mechanism schema: not_defined - subject: mixture of experts schema: not_defined - subject: transition rare-earth metal binary allloys schema: not_defined - subject: magnetization schema: not_defined ## Rights - description: Creative Commons BY Attribution 4.0 International identifier: https://creativecommons.org/licenses/by/4.0/ ## Other identifier(s) ## Data origin - data_origin_type: other ## Embargo ## Journal - title: JAPANESE JOURNAL OF APPLIED PHYSICS issn: '00214922' volume: '133' start_page: 53904 end_page: 53904 ## Conference ## Related item ## Funding - identifier: the Program for Promoting Research on the Supercomputer Fugaku (DPMSD) funder_name: MEXT - identifier: 20K05301 funder_name: JSPS KAKENHI - identifier: 20K05301 funder_name: JSPS KAKENHI - identifier: 21K14396 funder_name: Grant-in-Aid for Early- Career Scientists - identifier: 20K05068 funder_name: Grant-in-Aid for Early- Career Scientists - identifier: JP19H05815 funder_name: Grants-in-Aid for Scientific Research on Innovative Areas Interface Ionics ## Instrument ## Instrument operator ## Instrument managing organization ## Measurement method ## Specimen ## Chemical composition ## Structure for specimen ## Structural feature for specimen ## Specific property for specimen ## Process for specimen treatment ## Computational method ## Energy level/transition state ## Software ## Custom property ## Fileset - id: 77a8d79a-5b34-4a05-bf57-04d84c78b7e0 filename: Dam_evidence_based_5.0134999.pdf content_type: application/pdf size: 4921761 md5: aaa75bfb61d362df08e2ab4f5ba6fb0c ## Thumbnail fileset_id: 77a8d79a-5b34-4a05-bf57-04d84c78b7e0 filename: Dam_evidence_based_5.0134999.pdf