@article{47c480531b434e3f92688d4647c57fa1,
title = "Computational Estimation by Scientific Data Mining with Classical Methods to Automate Learning Strategies of Scientists",
abstract = "Experimental results are often plotted as 2-dimensional graphical plots (aka graphs) in scientific domains depicting dependent versus independent variables to aid visual analysis of processes. Repeatedly performing laboratory experiments consumes significant time and resources, motivating the need for computational estimation. The goals are to estimate the graph obtained in an experiment given its input conditions, and to estimate the conditions that would lead to a desired graph. Existing estimation approaches often do not meet accuracy and efficiency needs of targeted applications. We develop a computational estimation approach called AutoDomainMine that integrates clustering and classification over complex scientific data in a framework so as to automate classical learning methods of scientists. Knowledge discovered thereby from a database of existing experiments serves as the basis for estimation. Challenges include preserving domain semantics in clustering, finding matching strategies in classification, striking a good balance between elaboration and conciseness while displaying estimation results based on needs of targeted users, and deriving objective measures to capture subjective user interests. These and other challenges are addressed in this work. The AutoDomainMine approach is used to build a computational estimation system, rigorously evaluated with real data in Materials Science. Our evaluation confirms that AutoDomainMine provides desired accuracy and efficiency in computational estimation. It is extendable to other science and engineering domains as proved by adaptation of its sub-processes within fields such as Bioinformatics and Nanotechnology.",
keywords = "Applied research, classification, clustering, domain knowledge, estimation, graphical data mining, machine learning, predictive analytics, scientific applications",
author = "Varde, {Aparna S.}",
note = "Funding Information: The author Dr. Aparna Varde at Montclair State University is currently supported by grants from NSF “MRI: Acquisition of a High-Performance GPU Cluster for Research and Education” Award Number 2018575, and “MRI: Acquisition of a Multimodal Collaborative Robot System (MCROS) to Support Cross-Disciplinary Human-Centered Research and Education at Montclair State University”, Award Number 2117308. She is a visiting researcher in the Databases and Information Systems group of Dr. Gerhard Weikum at the Max Planck Institute for Informatics, Saarbr{\"u}cken, Germany, during her sabbatical from Montclair State University. The valuable contributions of Prof. Elke Rundensteiner, Prof. David Brown and Prof. Richard D. Sisson Jr. from Worcester Polytechnic Institute, Massachusetts, are gratefully acknowledged on significant work related to this journal article. A part of this work has been supported by an esrtwhile grant from the Department of Energy – Industrial Technology Program (DOE-ITP) Award DE-FC-07-01ID14197. The author thanks the funding sources. Author{\textquoteright}s address: A. S. Varde, Department of Computer Science, Montclair State University, NJ, 07043, Visiting Researcher, Max Planck Institute for Informatics, 66123 Saarbr{\"u}cken, Germany; email: vardea@montclair.edu. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. {\textcopyright} 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM. 1556-4681/2022/03-ART86 $15.00 https://doi.org/10.1145/3502736 Publisher Copyright: {\textcopyright} 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM.",
year = "2022",
month = oct,
doi = "10.1145/3502736",
language = "English",
volume = "16",
journal = "ACM Transactions on Knowledge Discovery from Data",
issn = "1556-4681",
publisher = "Association for Computing Machinery (ACM)",
number = "5",
}