Photo credit: Pixabay / CC0 Public Domain

An article by Dr. Qingsheng Wang, Associate Professor and Director of the Safety Engineering Program at the Artie McFerrin Department of Chemical Engineering at Texas A&M University, was selected as the American Chemical Society (ACS) editorial choice. PhD students Zeren Jiao, Pingfan Hu, and Hongfei Xu from the Wang group are co-authors of the paper. In the article, “Machine Learning and Deep Learning of Chemical Health and Safety: A Systematic Review of Techniques and Applications,” originally published in ACS Chemical Health & Safety, Wang and his team examined the current machine learning literature and deep learning in the context of safety technology.

Machine learning and deep learning are subsets of artificial intelligence, and models based on machine learning / deep learning techniques can automatically learn from data and perform tasks such as prediction and decision-making. A large number of interdisciplinary studies have shown that the combination of machine learning and deep learning into a comprehensive security regime has been successful in trend identification and forecasting support, which can significantly save manpower as well as material and financial resources.

While both machine and deep learning pursue very similar goals in the context of safety engineering, there are some key differences. Machine learning includes probability theory, statistics, approximation theory, algorithm complexity theory, and convex analysis to create algorithms that can create mathematical models based on training data for predictions or decisions without being explicitly programmed to do so. In essence, machine learning technology can interpret large amounts of data and make predictions, trends, and informed decisions.

Deep learning, a subset of machine learning, uses artificial neural networks – computer systems inspired by biological neurons – as the architecture for characterizing and learning data. Deep learning forms a more abstract attribute category for high-level representations or is combined by combining low-level features to determine distributed feature representations of data. This can eliminate the feature engineering step of machine learning based algorithms with increasing accuracy, and is extremely useful in tasks such as computer vision and natural language processing. Both areas are developing rapidly and offer great application potential in security technology.

In the article, Wang and his research team analyzed and categorized more than 100 peer-reviewed articles to get a snapshot of the current machine and deep learning scholarship, as well as an overview of advances in the area. In addition, Wang highlights the challenges and gaps in the current machine literature and in-depth learning related to safety engineering.

Application of machine learning to biomedical science

More information:
Zeren Jiao et al. Machine Learning and In-Depth Learning of Chemical Health and Safety: A Systematic Review of Techniques and Applications, ACS Chemical Health & Safety (2020). DOI: 10.1021 / acs.chas.0c00075 Provided by the University of Glasgow

Quote: Identifying and assessing frailty in people with diabetes should be a priority for better treatment and treatment (2020, November 20) to be released on November 20, 2020 at 11-frailty-people- was retrieved. Diabetes Priority.html

This document is subject to copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.