Abstract
The challenge of noise attenuation in images has led to extensive research on improved noise reduction techniques, preserving important image characteristics, improving not only visual perception, but also enabling the use for special purposes, such as in medicine to increase clarity of medical images. In this paper, a technique for noise attenuation in medical images is proposed. Its operation takes place through the application of an adapted genetic algorithm. The results of experiments show that the proposed approach works best in suppressing artifacts and the preservation of the structure compared with several existing methods.

Abstract

Abstract

Abstract
This work presents a neural network used to diagnosis patients with benign or malignant breast cancer. The study is carried out using the Breast Cancer Wisconsin dataset. To solve the problem a feedforward neural network (NN) with multilayers was used. In the work, the implementation was made in Python, using two different libraries (sklearn and keras). Experimental results were obtained by performing simulations in both developed applications, and the performance of the neural classifier was evaluated through the performance measures of the classification systems and the ROC curve. The results were promising, since the NN was able to discriminate with high accuracy the two separable sets discriminating the benign or malignant tumor patients.

Abstract

Abstract
This paper compares optimal path planning algorithms based on a Genetic Algorithm and a Particle Swarm Optimization algorithm applied to multiple bioinspired robots in a 2D environment simulation. The planning objectives are related to the harvesting of an apple plantation in which three swarm of butterflies were run, counting the fruits on the ground to optimize the harvest in a cooperative way. Robotic swarms must travel through points on the map to count the fruits. The time for each swarm was also counted for the comparison results. © Springer Nature Switzerland AG 2019.