Artificial neural networks (ANNs) are one of the artificial intelligence techniques used in real-world problems and applications encountered in almost all industries such as education, health, chemistry, food, informatics, logistics, transportation. ANN is widely used in many techniques such as optimization, modelling, classification and forecasting, and many empirical studies have been carried out in areas such as planning, inventory management, maintenance, quality control, econometrics, supply chain management and logistics related to ANN. The most important and just as hard stage of ANNs is the learning process. This process is about finding optimal values in the search space for different datasets. In this process, the values generated by training algorithms are used as network parameters and are directly effective in the success of the neural network (NN). In classical training techniques, problems such as local optimum and slow convergence are encountered. Meta-heuristic algorithms for the training of ANNs in the face of this negative situation have been used in many studies as an alternative. In this study, a new hybrid algorithm namely MVOSANN is suggested for the training of ANNs, using Simulated annealing (SA) and Multi-verse optimizer (MVO) algorithms. The suggested MVOSANN algorithm has been experimented on 12 prevalently classification datasets. The productivity of MVOSANN has been compared with 12 well-recognized and current meta-heuristic algorithms. Experimental results show that MVOSANN produces very successful and competitive results.

The effectiveness and efficiency of a machine learning model can be improved by feature selection, especially for high-dimensional datasets such as in cybersecurity. The proposed approach utilizes an enhanced version of the Rainbow agent with a memory storage structure. The suggested approach is assessed using two benchmark datasets namely RT-IoT2022 which is targeted towards IoT network security and the Android Malware Detection dataset which is meant for mobile security. The specification of the reinforcement learning model has been trained for 20 epochs and it is progressively enhanced through feature subsets to enhance classification accuracy. The results show that the AUC scores continuously increase were the one for RT-IoT2022 achieves 0.91 and Android at 0.93. Three well-known classifiers XGBoost, Random Forest and multi-layer perceptron (MLP) are used to test the power of the selected features. The outcome evaluation on RT-IoT2022 dataset shows that Random Forest achieved maximum accuracy (99.48%), followed by XGBoost (99.16%), while MLP secured 94.04% accuracy. In the Android malware dataset, XGBoost model gave the best accuracy of 89.50%, followed closely by Random Forest with 87.00% and MLP with 86.50%. This clearly shows that reinforcement learning based feature selection enhances accuracy and reduces computation. The research emphasizes utilizing dynamic feature selection in any cyber security application. The future will experiment with incorporating deep reinforcement learning as well as hybrid selection.

For many years, supplier selection as an important multi-criteria decision has attracted both the researchers and practitioners. Recently, high incidences of natural disasters, terrorism attacks, labor strikes, and other kinds of risks, also known as disruptions, indicate the vulnerability of procurement process to these unpredicted events. In this study, a new framework is introduced to select suppliers while considering the supply risks. In the proposed framework, an expert is asked to determine the reliability of each procurement element (i.e., production, transportation, and communication) based on some proposed risk factors. Then, a distinct Multi-Layer Perceptron (MLP) network is trained to play the role of the expert opinion for estimating the reliability scores of each procurement. In addition to reliabilities, the Data Envelopment Analysis (DEA) is used to take into account the conventional selection criteria: price, delivery, quality, and capacity. A set of Pareto-optimal suppliers is obtained from the combination of efficiencies and reliability scores. Finally, the decision maker is recommended to choose between the non-dominated suppliers. Obtained experiment results indicate the effectiveness of the proposed framework.

Stock market prediction is one of the most important interesting areas of research in business. Stock markets prediction is normally assumed as tedious task since there are many factors influencing the market. The primary objective of this paper is to forecast trend closing price movement of Tehran Stock Exchange (TSE) using financial accounting ratios from year 2003 to year 2008. The proposed study of this paper uses two approaches namely Artificial Neural Networks and multi-layer perceptron. Independent variables are accounting ratios and dependent variable of stock price , so the latter was gathered for the industry of Motor Vehicles and Auto Parts. The results of this study show that neural networks models are useful tools in forecasting stock price movements in emerging markets but multi-layer perception provides better results in term of lowering error terms.