The use of artificial neural networks has enabled applications that would be impossible to achieve with conventional electronics, through to versatility that them have, they can be configured as needed and use as required such as classifiers, adaptive filters, controllers and predictors. This paper describes a experimental implementation of virtual speed sensor for DC motor using back-propagation artificial neural networks through voltage and current acquisition. In implementation process a comparative between both logsig and tansig activation function in hidden layer is made. The training of the neural network is performed by acquiring signals of voltage, current and speed sensor, later the response efficiency of the network is analyzed by comparing the result produced by physical sensor and virtual sensor implemented using neural networks. In this experiment training pattern values has a large range, a several process training with both small and large section range is made. Results show a good performance and a minimum error with both logsig and tansig activation function in hidden layer when pattern signal is full training.

It is well known that electromagnetic fields (EMF) are presented or produced on Utilities elements especially distribution feeders (DFs), which due to the demand, these have increased their capacity. However, DFs are operating near of their limits, which have produced an increase in EMF values, being a preoccupation for their possible effects on the human health. In this context, it is necessary to determine EMF values, which are exposed the population in order to guarantee the functioning of Utilities. In this research by using the Quickfield software based on Finite Elements (FE), EMF values on distribution feeders corresponding to three real electrical substations are determined. Furthermore, these simulated values are compared with measured values and reference threshold values suggested by international norms. Results show that the simulation procedure is effective to determine EMF on distribution feeders.

The use of Artificial Neural Networks with different type of configuration has enabled to develop many applications with higher complex degree. This paper presents an implementation example of noise canceller using Adaline Network for evaluation of performance when change different parameters in audio acquisition, also an analysis of synaptic weights to evaluate the performance of adaptive filter is done. In this document the mathematical modeling of adaptive canceler, the structure for acquisition and algorithm implementation into Matlab are presented. The results show a variant performance using differentes parameters, but when using the correct values parameters the performance better.

In modern industry, continuous production systems require the integration of monitoring systems capable of real-time inspection and anomaly detection of final products. This necessitates high-speed capture of product images and rapid information processing to determine the rejection of defective products. To address the challenges of reducing processing time and increasing fault recognition accuracy in products, a novel detection method based on image analysis and subsequent classification is proposed. While the techniques employed, such as image histograms and Principal Component Analysis, are well-established in image and data processing, the innovative integration of these methods in this approach provides a streamlined and highly efficient solution for classification. Specifically, the classification process relies on prior image processing, where the histograms of the 3 color channels of each image are obtained and concatenated, then PCA is applied, resulting in separable clusters. Cluster classification is achieved through a simple SVM. A significant advantage of this method is that it requires a reduced amount of image data for training the SVM, simplifying this stage of the process. The proposed method is benchmarked using a dataset of images aimed at detecting defects in a pill blister pack, which may include missing pills, while a data augmentation process is implemented. The relationship between the image histogram and the presence of faults is demonstrated under controlled lighting and sensor arrangement environments.

The objective of this study is to analyze the march of the individual at the time of climbing the steps, to obtain the variations of the angles of the main involved joints as they are the hip, knees and ankle. In order to make this study a standardized set of steps was built according to the Mexican norm NOM026STPS-2008. The data acquisition and results of the curves produced in the course of the march were made by means of the Kinect sensor. The tests for this study were made in 5 young adult men with an average of stature of 1,71 meters, an average of weight of 63 kg, without any type of injury or physical incapacity in their inferior extremities.