Software sensors for biomass concentration in a SSC process using artificial neural networks and support vector machine.

The lack of sensors for some relevant state variables in fermentation processes can be coped by developing appropriate software sensors. In this work, NARX-ANN, NARMAX-ANN, NARX-SVM and NARMAX-SVM models are compared when acting as software sensors of biomass concentration for a solid substrate cultivation (SSC) process. Results show that NARMAX-SVM outperforms the other models with an SMAPE index under 9 for a 20 % amplitude noise. In addition, NARMAX models perform better than NARX models under the same noise conditions because of their better predictive capabilities as they include prediction errors as inputs. In the case of perturbation of initial conditions of the autoregressive variable, NARX models exhibited better convergence capabilities. This work also confirms that a difficult to measure variable, like biomass concentration, can be estimated on-line from easy to measure variables like CO2 and O2 using an adequate software sensor based on computational intelligence techniques.

Llaima volcano dataset: In-depth comparison of deep artificial neural network architectures on seismic events classification.

This data manuscript presents a set of signals collected from the Llaima volcano located at the western edge of the Andes in Araucania Region, Chile. The signals were recorded from the LAV station between 2010 and 2016. After individually processing and analyzing every signal, specialists from the Observatorio Vulcanológico de los Andes Sur (OVDAS) classified them into four class according to their event source: i) Volcano-Tectonic (VT); ii) Long Period (LP); iii) Tremor (TR), and iv) Tectonic (TC). The dataset is composed of 3592 signals separated by class and filtered to select the segment that contains the most representative part of the seismic event. This dataset is important to support researchers interested in studying seismic signals from active volcanoes and developing new methods to model time-dependent data. In this sense, we have published the manuscript "In-Depth Comparison of Deep Artificial Neural Network Architectures on Seismic Events Classification" [1] analyzing such signals with different Deep Neural Networks (DNN). The main contribution of such manuscript is a new DNN architecture called SeismicNet, which provided classification results among the best in the literature without demanding explicit signal pre-processing steps. Therefore, the reader is referred to such manuscript for the interpretation of the data.

Non-invasive intracranial pressure estimation using support vector machine.

Intracranial Pressure (ICP) measurements are of great importance for the diagnosis, monitoring and treatment of many vascular brain disturbances. The standard measurement of the ICP is performed invasively by the perforation of the cranial scalp in the presence of traumatic brain injury (TBI). Measuring the ICP in a noninvasive way is relevant for a great number of pathologies where the invasive measurement represents a high risk. The method proposed in this paper uses the Arterial Blood Pressure (ABP) and the Cerebral Blood Flow Velocity (CBFV) - which may be obtained by means of non-invasive methods - to estimate the ICP. A non-linear Support Vector Machine was used and reached a low error between the real ICP signal and the estimated one, allowing an on-line implementation of the ICP estimation, with an adequate temporal resolution.

Comparison of artificial neural networks an support vector machines for feature selection in electrogastrography signal processing.

The paper describes a feature selection process applied to electrogastrogram (EGG) processing. The data set is formed by 42 EGG records from functional dyspeptic (FD) patients and 22 from healthy controls. A wrapper configuration classifier was implemented to discriminate between both classes. The aim of this work is to compare artificial neural networks (ANN) and support vector machines (SVM) when acting as fitness functions of a genetic algorithm (GA) that performs a feature selection process over some features extracted from the EGG signals. These features correspond to those that literature shows to be the most used in EGG analysis. The results show that the SVM classifier is faster, requires less memory and reached the same performance (86% of exactitude) than the ANN classifier when acting as the fitness function for the GA.