ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Abstract and Image Analysis of High-Temperature Materials from Scientific Journals Using Deep Learning and Rule-Based Machine Learning Approaches

Jayaram, K and Gopalakrishnan, P and Vishakantaiah, J (2022) Abstract and Image Analysis of High-Temperature Materials from Scientific Journals Using Deep Learning and Rule-Based Machine Learning Approaches. In: 2nd International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2020, 21-22 Nov 2020, Pune, pp. 489-500.

Full text not available from this repository. (Request a copy)
Official URL: https://doi.org/10.1007/978-981-16-3690-5_43


In this digital world, many research papers have been getting added to the scientific journals in PDF format. It has become essential to the process and needs digitalization due to the exponential growth of newly published research papers. Survey of Abstract, Figures, and Captions convey the necessary information and extracted from scientific research journals. The section algorithm is used for extracting �Abstract� and �Result and Discussion� sections from the published research papers about high-temperature materials (HTM) by converting PDF to word documents. HTM got complete applications in aerospace engineering and electronic. After exposure to high-temperature test facilities, various characterization techniques are used to produce numerous high-resolution images. Abstract summarization, SEM figures, and caption extraction from HTM documents are performed using Deep learning, PDFFigure, and Machine learning (ML) techniques. MatLab is used for feature extraction and to classify SEM images by rule-based ML techniques. This summarization helps new researchers understand existing research datasets and proceed with new approaches to solve more complex problems. This research paper presents automatic extraction and summary of abstract, high-resolution figures, and captions from scientific journals on HTM; all these documents will be analyzed to categorize with a different tailor-made approach using deep learning and machine learning techniques. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Item Type: Conference Paper
Publication: Lecture Notes in Electrical Engineering
Publisher: Springer Science and Business Media Deutschland GmbH
Additional Information: The copyright for this article belongs to Springer Science and Business Media Deutschland GmbH
Keywords: Abstracting; Deep learning; Image classification, Deep learning; Figures and captions; High temperature materials; Images classification; Machine learning techniques; PDF extraction; Research papers; Rule based; Scientific journals; Summarization, Extraction
Department/Centre: Division of Chemical Sciences > Solid State & Structural Chemistry Unit
Date Deposited: 21 Dec 2021 05:48
Last Modified: 21 Dec 2021 05:48
URI: http://eprints.iisc.ac.in/id/eprint/70670

Actions (login required)

View Item View Item