In this work we propose a workflow to deal with overlaid images—images with superimposed text and company logos—, which is very common in underwater monitoring videos and surveillance camera footage. It is demonstrated that it is possible to use Explaining Artificial Intelligence to improve deep learning models performance for image classification tasks in general. A deep learning model trained to classify metal surface defect, which previously had a low performance, is then evaluated with Layer-wise relevance propagation—an Explaining Artificial Intelligence technique—to identify problems in a dataset that hinder the training of deep learning models in a wide range of applications. Thereafter, it is possible to remove this unwanted information from the dataset—using different approaches: from cutting part of the images to training a Generative Inpainting neural network model—and retrain the model with the new preprocessed images. This proposed methodology improved F1 score in 20% when compared to the original trained dataset, validating the proposed workflow.

The development of an oil reservoir consists in drilling wells that maximize revenue. The quest for this configuration is often based on optimization processes that use the net present value as the evaluation function. Determining quantity, location, type, and trajectory of wells in a reservoir is a complex optimization problem, which has a high computational cost due to the continuous use of simulators. Many researchers have proposed the replacement of the reservoir simulator by a proxy, to reduce the computational cost, with promising results. However, in order to analyze all relevant variables and obtain a better solution, a comprehensive proxy model must also consider the conditions of the surface behavior, incorporating the complete integrated system. None of the previous works has developed a model based on the integrated simulation behavior. This article presents the proposal of a new proxy model based on neural networks, called SimProxy, which integrates reservoir and surface behavior, to reduce the computational cost of a decision support system. The proposed model was evaluated in a real oil reservoir. The results indicate that SimProxy can efficiently replace the use of commercial simulators in an optimization process, providing good accuracy with a substantial decrease in computational cost.

This paper proposes a new approach to Particle Swarm Optimization (PSO) to solve nonlinear problems with linear and nonlinear constraints. A crossover operator and a new particle updating method, named Footholds Concept, were developed to guarantee fully feasible solutions and better search-space coverage, respectively. In addition, a novel swarm initialization heuristic is applied to benchmarks with equality constraints. The algorithm has been tested on 13 common benchmark functions. Experimental results show that it is very competitive as it increases PSO efficiency and improves convergence speed.