A Bayesian regularized feed-forward neural network model for conductivity prediction of PS/MWCNT nanocomposite film coatings

Synthesis and Characterization of Polyhydroxyalkanoate/Graphene Oxide/Nanoclay Bionanocomposites: Experimental Results and Theoretical Predictions via Machine Learning Models

Predicting the mechanical properties of multiscale nanocomposites requires simulations that are costly from a practical viewpoint and time consuming. The use of algorithms for property prediction can reduce the extensive experimental work, saving time and costs. To assess this, ternary poly(hydroxybutyrate-co-hydroxyvalerate) (PHBV)-based bionanocomposites reinforced with graphene oxide (GO) and montmorillonite nanoclay were prepared herein via an environmentally friendly electrochemical process followed by solution casting. The aim was to evaluate the effectiveness of different Machine Learning (ML) models, namely Artificial Neural Network (ANN), Decision Tree (DT), and Support Vector Machine (SVM), in predicting their mechanical properties. The algorithms' input data were the Young's modulus, tensile strength, and elongation at break for various concentrations of the nanofillers (GO and nanoclay). The correlation coefficient (R2), mean absolute error (MAE), and mean square error (MSE) were used as statistical indicators to assess the performance of the models. The results demonstrated that ANN and SVM are useful for estimating the Young's modulus and elongation at break, with MSE values in the range of 0.64-1.0% and 0.14-0.28%, respectively. On the other hand, DT was more suitable for predicting the tensile strength, with the indicated error in the range of 0.02-9.11%. This study paves the way for the application of ML models as confident tools for predicting the mechanical properties of polymeric nanocomposites reinforced with different types of nanofiller, with a view to using them in practical applications such as biomedicine.

Digital Innovation Enabled Nanomaterial Manufacturing; Machine Learning Strategies and Green Perspectives

Machine learning has been an emerging scientific field serving the modern multidisciplinary needs in the Materials Science and Manufacturing sector. The taxonomy and mapping of nanomaterial properties based on data analytics is going to ensure safe and green manufacturing with consciousness raised on effective resource management. The utilization of predictive modelling tools empowered with artificial intelligence (AI) has proposed novel paths in materials discovery and optimization, while it can further stimulate the cutting-edge and data-driven design of a tailored behavioral profile of nanomaterials to serve the special needs of application environments. The previous knowledge of the physics and mathematical representation of material behaviors, as well as the utilization of already generated testing data, received specific attention by scientists. However, the exploration of available information is not always manageable, and machine intelligence can efficiently (computational resources, time) meet this challenge via high-throughput multidimensional search exploration capabilities. Moreover, the modelling of bio-chemical interactions with the environment and living organisms has been demonstrated to connect chemical structure with acute or tolerable effects upon exposure. Thus, in this review, a summary of recent computational developments is provided with the aim to cover excelling research and present challenges towards unbiased, decentralized, and data-driven decision-making, in relation to increased impact in the field of advanced nanomaterials manufacturing and nanoinformatics, and to indicate the steps required to realize rapid, safe, and circular-by-design nanomaterials.

Improved Artificial Neural Network Training Based on Response Surface Methodology for Membrane Flux Prediction

This paper presents an improved artificial neural network (ANN) training using response surface methodology (RSM) optimization for membrane flux prediction. The improved ANN utilizes the design of experiment (DoE) technique to determine the neural network parameters. The technique has the advantage of training performance, with a reduced training time and number of repetitions in achieving good model prediction for the permeate flux of palm oil mill effluent. The conventional training process is performed by the trial-and-error method, which is time consuming. In this work, Levenberg–Marquardt (lm) and gradient descent with momentum (gdm) training functions are used, the feed-forward neural network (FFNN) structure is applied to predict the permeate flux, and airflow and transmembrane pressure are the input variables. The network parameters include the number of neurons, the learning rate, the momentum, the epoch, and the training functions. To realize the effectiveness of the DoE strategy, central composite design is incorporated into neural network methodology to achieve both good model accuracy and improved training performance. The simulation results show an improvement of more than 50% of training performance, with less repetition of the training process for the RSM-based FFNN (FFNN-RSM) compared with the conventional-based FFNN (FFNN-lm and FFNN-gdm). In addition, a good accuracy of the models is achieved, with a smaller generalization error.

A Multi-Layer Classification Approach for Intrusion Detection in IoT Networks Based on Deep Learning

The security of IoT networks is an important concern to researchers and business owners, which is taken into careful consideration due to its direct impact on the availability of the services offered by IoT devices and the privacy of the users connected with the network. An intrusion detection system ensures the security of the network and detects malicious activities attacking the network. In this study, a deep multi-layer classification approach for intrusion detection is proposed combining two stages of detection of the existence of an intrusion and the type of intrusion, along with an oversampling technique to ensure better quality of the classification results. Extensive experiments are made for different settings of the first stage and the second stage in addition to two different strategies for the oversampling technique. The experiments show that the best settings of the proposed approach include oversampling by the intrusion type identification label (ITI), 150 neurons for the Single-hidden Layer Feed-forward Neural Network (SLFN), and 2 layers and 150 neurons for LSTM. The results are compared to well-known classification techniques, which shows that the proposed technique outperforms the others in terms of the G-mean having the value of 78% compared to 75% for KNN and less than 50% for the other techniques.