In membrane separation technologies, membrane modules are used to separate chemical components. In membrane technology, understanding the behavior of fluids inside membrane module is challenging, and numerical methods are possible by using computational fluid dynamics (CFD). On the other hand, the optimization of membrane technology via CFD needs time and computational costs. Artificial Intelligence (AI) and CFD together can model a chemical process, including membrane technology and phase separation. This process can learn the process by learning the neural networks, and point by point learning of CFD mesh elements (computing nodes), and the fuzzy logic system can predict this process. In the current study, the adaptive neuro-fuzzy inference system (ANFIS) model and different parameters of ANFIS for learning a process based on membrane technology was used. The purpose behind using this model is to see how different tuning parameters of the ANFIS model can be used for increasing the exactness of the AI model and prediction of the membrane technology. These parameters were changed in this study, and the accuracy of the prediction was investigated. The results indicated that with low number of inputs, poor regression was obtained, less than 0.32 (R-value), but by increasing the number of inputs, the AI algorithm led to an increase in the prediction capability of the model. When the number of inputs increased to 4, the R-value was increased to 0.99, showing the high accuracy of model as well as its high capability in prediction of membrane process. The AI results were in good agreement with the CFD results. AI results were achieved in a limited time and with low computational costs. In terms of the categorization of CFD data-set, the AI framework plays a critical role in storing data in short memory, and the recovery mechanism can be very easy for users. Furthermore, the results were compared with Particle Swarm Optimization (PSOFIS), and Genetic Algorithm (GAFIS). The time for prediction and learning were compared to study the capability of the methods in prediction and their accuracy.

In current decades, significant advancements in robotics engineering and autonomous vehicles have improved the requirement for precise depth measurements. Depth estimation (DE) is a traditional task in computer vision that can be appropriately predicted by applying numerous procedures. This task is vital in disparate applications such as augmented reality and target tracking. Conventional monocular DE (MDE) procedures are based on depth cues for depth prediction. Various deep learning techniques have demonstrated their potential applications in managing and supporting the traditional ill-posed problem. The principal purpose of this paper is to represent a state-of-the-art review of the current developments in MDE based on deep learning techniques. For this goal, this paper tries to highlight the critical points of the state-of-the-art works on MDE from disparate aspects. These aspects include input data shapes and training manners such as supervised, semi-supervised, and unsupervised learning approaches in combination with applying different datasets and evaluation indicators. At last, limitations regarding the accuracy of the DL-based MDE models, computational time requirements, real-time inference, transferability, input images shape and domain adaptation, and generalization are discussed to open new directions for future research.

Machine learning models based on sensitive data in the real-world promise advances in areas ranging from medical screening to disease outbreaks, agriculture, industry, defense science, and more. In many applications, learning participant communication rounds benefit from collecting their own private data sets, teaching detailed machine learning models on the real data, and sharing the benefits of using these models. Due to existing privacy and security concerns, most people avoid sensitive data sharing for training. Without each user demonstrating their local data to a central server, Federated Learning allows various parties to train a machine learning algorithm on their shared data jointly. This method of collective privacy learning results in the expense of important communication during training. Most large-scale machine learning applications require decentralized learning based on data sets generated on various devices and places. Such datasets represent an essential obstacle to decentralized learning, as their diverse contexts contribute to significant differences in the delivery of data across devices and locations. Researchers have proposed several ways to achieve data privacy in Federated Learning systems. However, there are still challenges with homogeneous local data. This research's approach is to select nodes (users) to share their data in Federated Learning for independent data-based equilibrium to improve accuracy, reduce training time, and increase convergence. Therefore, this research presents a combined Deep-Q-Reinforcement Learning Ensemble based on Spectral Clustering called DQRE-SCnet to choose a subset of devices in each communication round. Based on the results, it has been displayed that it is possible to decrease the number of communication rounds needed in Federated Learning. The realized reduction in the communication rounds are 51%, 25%, and 44% on the three datasets MNIST, Fashion MNIST, and CIFAR-10, respectively.

No abstract