This paper proposes an exhaustive evaluation of five different filter-based feature selection methods in combination with a Gaussian mixture model classifier for the classification of long-period (LP) and volcano-tectonic (VT) seismic events recorded at Cotopaxi volcano in Ecuador. The experimentation included both exploring and ranking search spaces of seismic-signal-based features, and selecting subsets of optimal features for event classification. The evaluation was carried out by using an experimental dataset formed by 587 LP and 81 VT feature vectors, each composed of 84 statistical, temporal, spectral, and scale-domain features extracted from the original seismic signals. The best result in accuracy, precision, recall, and processing time for LP seismic event classification was obtained by using the Chi2 discretization method with five features, achieving 95.62%, 99.08%, 95.94%, and 3.7 ms, respectively, whereas for VT seismic event classification, the uFilter method with five features reached the scores of 96.71%, 85.23%, 96.00%, and 4.1 ms, respectively. For the classification of both seismic events simultaneously, the uFilter method with five features yielded 96.70%, 97.77%, 96.7%, and 4.1 ms, respectively. According to the Wilcoxon statistical test, these classification schemes provide competitive seismic event classification, while reducing the required processing time.

Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from theiNaturalistproject. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.

With the growing ability to collect large volumes of volcano seismic data, the detection and labeling process of these records is increasingly challenging. Clearly, analyzing all available data through manual inspection is no longer a viable option. Supervised machine learning models might be considered to automatize the analysis of data acquired by in situ monitoring stations. However, the direct application of such algorithms is defiant, given the high complexity of waveforms and the scarce and often imbalanced amount of labeled data. In light of this and motivated by the wide success that generative adversarial networks (GANs) have seen at generating images, we present ESeismic-GAN, a GAN model to generate the magnitude frequency response of volcanic events. Our experiments demonstrate that ESeismic-GAN learns to generate the frequency components that characterize long-period and volcano-tectonic events from Cotopaxi volcano. We evaluate the performance of ESeismic-GAN during the training stage using Fréchet distance, and, later on, we reconstruct the signals into time-domain to be finally evaluated with Frechet inception distance.

A hybrid control framework is proposed as an alternative for long time delays in chemical processes. The hybrid approach mixes the numerical methods in an internal mode control (IMC) structure, which uses the particle swarm optimization (PSO) algorithm to improve the adjustment of the controller parameters. Simulation tests are carried out on linear systems of high order and inverse response, both with dominant delay, and tests on a nonlinear process (chemical reactor). The performance of the proposed controller is stable and satisfactory despite nonlinearities in various operating conditions, set-point changes, process disturbances, and modeling errors. In addition, experimental tests were performed on a setup composed of two heaters and two temperature sensors mounted on an Arduino microcontroller-based board called the Temperature Control Laboratory (TCLab), with an additional software delay introduced. The merits and drawbacks of each scheme are analyzed using radar charts, comparing the control methods with different performance measures for set-point and disturbance changes. Furthermore, the new controller uses PSO to improve the tuning parameters.

We systematically and comprehensively tested almost 100 feature groups in four commonly used automatic event classifiers to find the combinations that maximize the classification performance for long-period and volcano-tectonic seismic events at Cotopaxi volcano, Ecuador. The feature groups tested fall into the following categories: time, fast-Fourier, wavelet transform, intensity-statistics, shape, and texture. An analysis of the relevance of feature groups highlights and finds that each classifier performs similar to one another when using the best combination of features, as determined by the mean of the area under the curve metric, with no statistically significant differences between them. The feed-forward back-propagation neural network and random forest classifiers achieved scores of 0.96 while the naive Bayes and k-nearest neighbor (kNN) classifiers achieved scores of 0.95. The shape and texture feature groups were the most frequently utilized (three times each) among the different classifiers, and thus, the most appropriate for classifying both types of seismic events. The kNN ( $k=3$ ) classifier using the shape feature group reached an excellent performance with lower algorithmic complexity. Moreover, nontraditional features like those computed from spectrogram images overcame traditional time, Fourier, and scale features when classifying seismic events.