Nanotechnology is the fabrication and manipulation of novel material at a size of 100 nm or less and is increasingly becoming a promising area in various human endeavors because of its novel, and unique properties. Nanoparticles are commonly applied in medicine, Engineering, and agricultural industries. The unique properties of these materials can be manipulated for beneficial purposes and at the same time may also have side effects through toxicological and environmental impacts. The increasing rate of manufacturing nanomaterials and the end-user’s exposure to a wide variety of nanoproducts has brought about awareness about safety and health consequences of biological systems and the environment. Because of the intrinsic properties, these engineered NMs have ability to easily gain access into human body, accumulate in cells, and cause health challenges [1-3].

 In recent years, it has been shown from various studies, that ENMs have hazardous potentials and harmful to human health. According [4] it was shown that carbon nanotubes (CNTs) have the potential to induce reactive oxygen species (ROS) and pulmonary effects. Further studies have also reported that titanium dioxide (TiO₂) nano-particles have the tendency of inducing cytotoxic [5] genotoxic [6] and inflammatory effects [7]. Similarly, [6] also reported that silver nanoparticle has the ability of inducing harmful effects arising from exposure to nanosilver. More detailed information about the inherent negative effects of various ENMs have been documented by several researchers [8,7][3].

The apprehensions of the potentially harmful effects of nanomaterials constitute a serious setback to nanotechnology commercialization. The objective of the study is to develop a screening protocol to assess, evaluate, and manage the inherent risks. To achieve this, it is imperative to develop models, tools and an acceptable mechanism for screening, predicting, and monitoring the application of nanomaterials. In computational intelligence modeling, it is the specific type of biological activity, such as cell cytotoxicity that will be modeled and predicted. A toxicological endpoint which measures the toxic effects of a nanomaterial on human health or the environment will be predicted by Computational intelligent models provided sufficient toxicity data is provided as input. Here, Computational Intelligent Systems such as Artificial Neural Network, Support Vector Machines, and hybrid systems-fuzzy Support Vector Machines (FuzzySVM), Neuro-Fuzzy systems have been explored as an alternative to establish the relationship between physicochemical properties and biological activity. In this modeling, the important descriptors such as size, shape, and surface charge, can be measured by means of various experimental techniques. So far, with the established consensus on the measurement and modeling descriptors of traditional (Q) SAR analysis, these descriptors are to be applied for nano-Intelligent system [10-13].

The first step in modeling ENM toxicity is the identification of toxicity-related characteristics that can be used as descriptors of harmful effects of ENMs. Because of lack of a complete and exact list of properties influencing the toxicity of ENMs, it is necessary to conduct detailed material characterization before a toxicity test in order to ascertain the factors that are actually affecting the end points of ENMs, and their inherent risks. The characteristics and properties which are recommended by almost all nanotoxicologists as important determinants of toxicity include: size distribution, agglomeration state, shape, crystal structure, chemical composition, surface area, surface chemistry, surface charge, exposure time, dosage, and porosity. This paper, will therefore explore the capability of computational intelligent systems to model physicochemical properties and the toxic effects of nanomaterials in view of the imprecision and uncertainty surrounding the prediction of nanomaterials toxicity.

Section I gives a brief introduction. Section II highlights the toxicity dependent physico-chemical characteristics. Section III discusses nano-Intelligent systems and Modelling techniques. In Section IV, detailed the hybrid Computational Intelligent Systems. Section V discusses the selection of case study materials. Section VI discusses the prediction of Toxicity. Section VII discusses the results and discussion. Finally, Section VIII discusses the conclusion of the study.

Please Go through the full article link:  https://www.pubtexto.com/pdf/?predictive-models-for-characterizing-and-evaluating-risk-of-engineered-nanomaterials-using-computational-intelligence-approach