Miah M Saef Ullah, Sulaiman Junaida, Sarwar Talha Bin, Ibrahim Nur, Masuduzzaman Md, Jose Rajan
Faculty of Computing, College of Computing and Applied Sciences, Universiti Malaysia Pahang, Pekan, Pahang, 26600, Malaysia.
Department of Computer Science, FST, American International University-Bangladesh (AIUB), 1229, Dhaka, Bangladesh.
Heliyon. 2023 Sep 14;9(9):e20003. doi: 10.1016/j.heliyon.2023.e20003. eCollection 2023 Sep.
This article reports a tool that enables Materials Informatics, termed as MatRec, via a deep learning approach. The tool captures data, makes appropriate domain suggestions, extracts various entities such as materials and processes, and helps to establish entity-value relationships. This tool uses keyword extraction, a document similarity index to suggest relevant documents, and a deep learning approach employing Bi-LSTM for entity extraction. For example, materials and processes for electrical charge storage under an electric double layer capacitor (EDLC) mechanism are demonstrated herewith. A knowledge graph approach finds and visualizes different latent knowledge sets from the processed information. The MatRec received an F1 score of 9̃6% for entity extraction, 8̃3% for material-value relationship extraction, and 8̃7% for process-value relationship extraction, respectively. The proposed MatRec could be extended to solve material selection issues for various applications and could be an excellent tool for academia and industry.
本文报道了一种通过深度学习方法实现材料信息学的工具，称为MatRec。该工具捕获数据，提出适当的领域建议，提取各种实体，如材料和工艺，并有助于建立实体-值关系。此工具使用关键词提取、文档相似性索引来推荐相关文档，以及采用双向长短期记忆网络（Bi-LSTM）进行实体提取的深度学习方法。例如，本文展示了基于双电层电容器（EDLC）机制的电荷存储材料和工艺。知识图谱方法从处理后的信息中发现并可视化不同的潜在知识集。MatRec在实体提取方面的F1分数分别为9̃6%，在材料-值关系提取方面为8̃3%，在工艺-值关系提取方面为8̃7%。所提出的MatRec可以扩展以解决各种应用中的材料选择问题，并且可能成为学术界和工业界的优秀工具。
