Advancing risk assessment of engineered nanomaterials using deep learning approach
1 TIMFLO SOFTSEARCH Ltd- Software Development Company, Abuja, Nigeria.
2 Raw Materials Research & Development Council, (RMRDC), Abuja, Nigeria.
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2022, 06(01), 073–085.
Article DOI: 10.30574/wjaets.2022.6.1.0073
Publication history:
Received on 16 May 2022; revised on 20 June 2022; accepted on 22 June 2022
Abstract:
Nanotechnology is a novel technology that develops material at a size of 100 nm or less which has become beneficial in various human endeavors because of its unique characteristic features. Nano-materials are utilized in medicine, Engineering, and agricultural industries. The unique properties of these materials are applied for beneficial purposes and at the same time may also have negative toxicological and environmental impacts. Considering the impacts on the environment and human health, nanomaterials could be harmful because they are easily distributed through the environment, aquatic, and human systems. Particularly in human body system, the unique properties have made its transportation and distribution through the skin, lungs, gastrointestinal tract very easy. However, several toxicological studies have shown considerable inherent toxicity of some nano-particles to living organisms, and their negative and harmful effects on the environment and aquatic systems for which both quantitative structure activity relationship and relatively tedious animal testing procedures are available in various literatures for their characterization. Because of the large number of nanoparticles manufactured with the different intrinsic properties especially sizes and coatings, there is therefore need to explore an alternative approach that will not necessitate conducting test on every nano-particle produced. It is the apprehensions of these potentially harmful effects of nanomaterials that constitute serious setback to nanotechnology commercialization. The objective of the study is to develop intelligent models to assess, evaluate, and manage the inherent risks. In view of these side effects, there is therefore the need to design and develop classification and nanomaterials toxicity predictive models using deep learning intelligent systems. This paper, therefore, focuses on the capability of deep learning techniques to model physicochemical properties and toxic effects of nanomaterials. Hence, the main motivation of this research work is to assist the users of nanomaterials in classifying, assessing and determining the risk of nanomaterials toxicity.
Keywords:
Deep learning; Artificial Neural Network; Long Short-term Memory; Gated Recurrent Unit; Nanotechnology; Toxicity
Full text article in PDF:
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0