In some application fields, series are affected by two different types of effects: abrupt changes (or change-points) and functional effects. We propose here a Bayesian approach that allows us to estimate these two parts. Here, the underlying piecewise-constant part (associated to the abrupt changes) is expressed as the product of a lower triangular matrix by a sparse vector and the functional part as a linear combination of functions from a large dictionary where we want to select the relevant ones. This problem can thus lead to a global sparse estimation and a stochastic search variable selection approach is used to this end. The performance of our proposed method is assessed using simulation experiments. Applications to three real datasets from geodesy, agronomy and economy fields are also presented.

Exchange rates are determined by factors such as interest rates, political stability, confidence, the current account on balance of payments, government intervention, economic growth and relative inflation rates, among other variables. In October 2019, an increased climate of citizen discontent with current social policies resulted in a series of massive protests that ignited important political changes in Chile. This event along with the global COVID-19 pandemic were two major factors that affected the value of the US dollar and produced sudden changes in the typically stable USD/CLP (Chilean Peso) exchange rate. In this paper, we use a Bayesian approach to detect and locate change points in the currency exchange rate process in order to identify and relate these points with the important dates related to the events described above. The implemented method can successfully detect the onset of the social protests, the beginning of the COVID-19 pandemic in Chile and the economic reactivation in the US and Europe. In addition, we evaluate the performance of the proposed MCMC algorithms using a simulation study implemented in Python and R.

Bio-inspired computing is an engaging area of artificial intelligence which studies how natural phenomena provide a rich source of inspiration in the design of smart procedures able to become powerful algorithms. Many of these procedures have been successfully used in classification, prediction, and optimization problems. Swarm intelligence methods are a kind of bio-inspired algorithm that have been shown to be impressive optimization solvers for a long time. However, for these algorithms to reach their maximum performance, the proper setting of the initial parameters by an expert user is required. This task is extremely comprehensive and it must be done in a previous phase of the search process. Different online methods have been developed to support swarm intelligence techniques, however, this issue remains an open challenge. In this paper, we propose a hybrid approach that allows adjusting the parameters based on a state deducted by the swarm intelligence algorithm. The state deduction is determined by the classification of a chain of observations using the hidden Markov model. The results show that our proposal exhibits good performance compared to the original version.

Contemporary education is a vast field that is concerned with the performance of education systems. In a formal e-learning context, student dropout is considered one of the main problems and has received much attention from the learning analytics research community, which has reported several approaches to the development of models for the early prediction of at-risk students. However, maximizing the results obtained by predictions is a considerable challenge. In this work, we developed a solution using only students’ interactions with the virtual learning environment and its derivative features for early predict at-risk students in a Brazilian distance technical high school course that is 103 weeks in duration. To maximize results, we developed an elitist genetic algorithm based on Darwin’s theory of natural selection for hyperparameter tuning. With the application of the proposed technique, we predicted the student at risk with an Area Under the Receiver Operating Characteristic Curve (AUROC) above 0.75 in the initial weeks of a course. The results demonstrate the viability of applying interaction count and derivative features to generate prediction models in contexts where access to demographic data is restricted. The application of a genetic algorithm to the tuning of hyperparameters classifiers can increase their performance in comparison with other techniques.

Communicating in social and public environments are considered professional skills that can strongly influence career development. Therefore, it is important to proper train and evaluate students in this kind of abilities so that they can better interact in their professional relationships, during the resolution of problems, negotiations and conflict management. This is a complex problem as it involves corporal analysis and the assessment of aspects that until recently were almost impossible to quantitatively measure. Nowadays, a number of new technologies and sensors have being developed for the capture of different kinds of contextual and personal information, but these technologies were not yet fully integrated inside learning settings. In this context, this paper presents a framework to facilitate the analysis and detection of patterns of students in oral presentations. Four steps are proposed for the given framework: Data collection, Statistical Analysis, Clustering, and Sequential Pattern Mining. Data Collection step is responsible for the collection of students interactions during presentations and the arrangement of data for further analysis. Statistical Analysis provides a general understanding of the data collected by showing the differences and similarities of the presentations along the semester. The Clustering stage segments students into groups according to well-defined attributes helping to observe different corporal patterns of the students. Finally, Sequential Pattern Mining step complements the previous stages allowing the identification of sequential patterns of postures in the different groups. The framework was tested in a case study with data collected from 222 freshman students of Computer Engineering (CE) course at three different times during two different years. The analysis made it possible to segment the presenters into three distinct groups according to their corporal postures. The statistical analysis helped to assess how the postures of the students evolved throughout each year. The sequential pattern mining provided a complementary perspective for data evaluation and helped to observe the most frequent postural sequences of the students. Results show the framework could be used as a guidance to provide students automated feedback throughout their presentations and can serve as background information for future comparisons of students presentations from different undergraduate courses.

While technology has helped improve process efficiency in several domains, it still has an outstanding debt to education. In this article, we introduce NAIRA, a Multimodal Learning Analytics platform that provides Real-Time Feedback to foster collaborative learning activities’ efficiency. NAIRA provides real-time visualizations for students’ verbal interactions when working in groups, allowing teachers to perform precise interventions to ensure learning activities’ correct execution. We present a case study with 24 undergraduate subjects performing a remote collaborative learning activity based on the Jigsaw learning technique within the COVID-19 pandemic context. The main goals of the study are (1) to qualitatively describe how the teacher used NAIRA’s visualizations to perform interventions and (2) to identify quantitative differences in the number and time between students’ spoken interactions among two different stages of the activity, one of them supported by NAIRA’s visualizations. The case study showed that NAIRA allowed the teacher to monitor and facilitate the learning activity’s supervised stage execution, even in a remote learning context, with students working in separate virtual classrooms with their video cameras off. The quantitative comparison of spoken interactions suggests the existence of differences in the distribution between the monitored and unmonitored stages of the activity, with a more homogeneous speaking time distribution in the NAIRA supported stage.

Classifying histopathology images on a pixel-level requires sets of features able to capture the complex characteristics of the images, like the irregular cell morphology and the color heterogeneity on the tissue aspect. In this context, feature selection becomes a crucial step in the classification process such that it reduces model complexity and computational costs, avoids overfitting, and thereby it improves the model performance. In this study, we propose a new ensemble feature selection method by combining a set of base selectors, classifiers, and rank aggregation methods, aiming to determine from any initial set of handcrafted features, a smaller set of relevant color and texture pixel-level features, subsequently used for segmenting HER2 overexpression on a pixel-level, in breast cancer tissue images. We have been able to significantly reduce the set of initial features, using the proposed ensemble feature selection method. The best results are obtained using , Random Forest, and Runoff as the based selector, classifier, and aggregation method, respectively. The classification performance of the best model trained on the selected features set results in 0.939 recall, 0.866 specificity, 0.903 accuracy, 0.875 precision, and 0.906 F1-score.

This paper aims to perform an exhaustive revision of relevant and recent related studies, which reveals that both extraction methods are currently used to analyze credibility on Twitter. Thus, there is clear evidence of the need of having different options to extract different data for this purpose. Nevertheless, none of these studies perform a comparative evaluation of both extraction techniques. Moreover, the authors extend a previous comparison, which uses a recent developed framework that offers both alternates of data extraction and implements a previously proposed credibility model, by adding a qualitative evaluation and a Twitter-Application Programming Interface (API) performance analysis from different locations.

In this paper, we integrate the autonomous search paradigm on a swarm intelligence algorithm in order to incorporate the auto-adjust capability on parameter values during the run. We propose an independent procedure that begins to work when it detects a stagnation in a local optimum, and it can be applied to any population-based algorithms. For that, we employ the autonomous search technique which allows solvers to automatically re-configure its solving parameters for enhancing the process when poor performances are detected. This feature is dramatically crucial when swarm intelligence methods are developed and tested. Finding the best parameter values that generate the best results is known as an optimization problem itself. For that, we evaluate the behavior of the population size to autonomously be adapted and controlled during the solving time according to the requirements of the problem. The proposal is testing on the dolphin echolocation algorithm which is a recent swarm intelligence algorithm based on the dolphin feature to navigate underwater and identify prey. As an optimization problem to solve, we test a machine-part cell formation problem which is a widely used technique for improving production flexibility, efficiency, and cost reduction in the manufacturing industry decomposing a manufacturing plant in a set of clusters called cells. The goal is to design a cell layout in such a way that the need for moving parts from one cell to another is minimized. Using statistical non-parametric tests, we demonstrate that the proposed approach efficiently solves 160 well-known cell manufacturing instances outperforming the classic optimization algorithm as well as other approaches reported in the literature, while keeping excellent robustness levels.

We approach the problem of non‐parametric estimation for autoregressive Markov switching processes. In this context, the Nadaraya–Watson‐type regression functions estimator is interpreted as a solution of a local weighted least‐square problem, which does not admit a closed‐form solution in the case of hidden Markov switching. We introduce a non‐parametric recursive algorithm to approximate the estimator. Our algorithm restores the missing data by means of a Monte Carlo step and estimates the regression function via a Robbins–Monro step.

Using the approximate algorithms, we are faced with the problem of determining the appropriate values of their input parameters, which is always a complex task and is considered an optimization problem. In this context, incorporating online control parameters is a very interesting issue. The aim is to vary the parameters during the run so that the studied algorithm can provide the best convergence rate and, thus, achieve the best performance. In this paper, we compare the performance of a self-adaptive approach for the biogeography-based optimization algorithm using the mutation rate parameter with respect to its original version and other heuristics. This work proposes altering some parameters of the metaheuristic according to its exhibited efficiency. To test this approach, we solve the set covering problem, which is a classical optimization benchmark with many industrial applications such as line balancing production, crew scheduling, service installation, databases, among several others. We illustrate encouraging experimental results, where the proposed approach is capable of reaching various global optimums for a well-known instance set taken from the Beasleys OR-Library, and sometimes, it improves the results obtained by the original version of the algorithm.

Linear functional analysis historically founded by Fourier and Legendre played a significant role to provide a unified vision of mathematical transformations between vector spaces. The possibility of extending this approach is explored when basis of vector spaces is built Tailored to the Problem Specificity (TPS) and not from the convenience or effectiveness of mathematical calculations. Standardized mathematical transformations, such as Fourier or polynomial transforms, could be extended toward TPS methods, on a basis, which properly encodes specific knowledge about a problem. Transition between methods is illustrated by comparing what happens in conventional Fourier transform with what happened during the development of Jewett Transform, reported in previous articles. The proper use of computational intelligence tools to perform Jewett Transform allowed complexity algorithm optimization, which encourages the search for a general TPS methodology.

Electric power forecasting plays a substantial role in the administration and balance of current power systems. For this reason, accurate predictions of service demands are needed to develop better programming for the generation and distribution of power and to reduce the risk of vulnerabilities in the integration of an electric power system. For the purposes of the current study, a systematic literature review was applied to identify the type of model that has the highest propensity to show precision in the context of electric power forecasting. The state-of-the-art model in accurate electric power forecasting was determined from the results reported in 257 accuracy tests from five geographic regions. Two classes of forecasting models were compared: classical statistical or mathematical (MSC) and machine learning (ML) models. Furthermore, the use of hybrid models that have made significant contributions to electric power forecasting is identified, and a case of study is applied to demonstrate its good performance when compared with traditional models. Among our main findings, we conclude that forecasting errors are minimized by reducing the time horizon, that ML models that consider various sources of exogenous variability tend to have better forecast accuracy, and finally, that the accuracy of the forecasting models has significantly increased over the last five years.

Striatal dopamine dysfunction is associated with the altered top-down modulation of pain processing. The dopamine D2-like receptor family is a potential substrate for such effects due to its primary expression in the striatum, but evidence for this is currently lacking. Here, we investigated the effect of pharmacologically manipulating striatal dopamine D2 receptor activity on the anticipation and perception of acute pain stimuli in humans. Participants received visual cues that induced either certain or uncertain anticipation of two pain intensity levels delivered via a CO2 laser. Rating of the pain intensity and unpleasantness was recorded. Brain activity was recorded with EEG and analysed via source localisation to investigate neural activity during the anticipation and receipt of pain. Participants completed the experiment under three conditions, control (Sodium Chloride), D2 receptor agonist (Cabergoline), and D2 receptor antagonist (Amisulpride), in a repeated-measures, triple-crossover, double-blind study. The antagonist reduced an individuals’ ability to distinguish between low and high pain following uncertain anticipation. The EEG source localisation showed that the agonist and antagonist reduced neural activations in specific brain regions associated with the sensory integration of salient stimuli during the anticipation and receipt of pain. During anticipation, the agonist reduced activity in the right mid-temporal region and the right angular gyrus, whilst the antagonist reduced activity within the right postcentral, right mid-temporal, and right inferior parietal regions. In comparison to control, the antagonist reduced activity within the insula during the receipt of pain, a key structure involved in the integration of the sensory and affective aspects of pain. Pain sensitivity and unpleasantness were not changed by D2R modulation. Our results support the notion that D2 receptor neurotransmission has a role in the top-down modulation of pain.

Multimodal emotion recognition implies the use of different resources and techniques for identifying and recognizing human emotions. A variety of data sources such as faces, speeches, voices, texts and others have to be processed simultaneously for this recognition task. However, most of the techniques, which are based mainly on Deep Learning, are trained using datasets designed and built in controlled conditions, making their applicability in real contexts with real conditions more difficult. For this reason, the aim of this work is to assess a set of in-the-wild datasets to show their strengths and weaknesses for multimodal emotion recognition. Four in-the-wild datasets are evaluated: AFEW, SFEW, MELD and AffWild2. A multimodal architecture previously designed is used to perform the evaluation and classical metrics such as accuracy and F1-Score are used to measure performance in training and to validate quantitative results. However, strengths and weaknesses of these datasets for various uses indicate that by themselves they are not appropriate for multimodal recognition due to their original purpose, e.g., face or speech recognition. Therefore, we recommend a combination of multiple datasets in order to obtain better results when new samples are being processed and a good balance in the number of samples by class.

The evaluation of white blood cells is essential to assess the quality of the human immune system; however, the assessment of the blood smear depends on the pathologist’s expertise. Most machine learning tools make a one-level classification for white blood cell classification. This work presents a two-stage hybrid multi-level scheme that efficiently classifies four cell groups: lymphocytes and monocytes (mononuclear) and segmented neutrophils and eosinophils (polymorphonuclear). At the first level, a Faster R-CNN network is applied for the identification of the region of interest of white blood cells, together with the separation of mononuclear cells from polymorphonuclear cells. Once separated, two parallel convolutional neural networks with the MobileNet structure are used to recognize the subclasses in the second level. The results obtained using Monte Carlo cross-validation show that the proposed model has a performance metric of around 98.4% (accuracy, recall, precision, and F1-score). The proposed model represents a good alternative for computer-aided diagnosis (CAD) tools for supporting the pathologist in the clinical laboratory in assessing white blood cells from blood smear images.

During the last years, highly-recognized computational intelligence techniques have been proposed to treat classification problems. These automatic learning approaches lead to the most recent researches because they exhibit outstanding results. Nevertheless, to achieve this performance, artificial learning methods firstly require fine tuning of their parameters and then they need to work with the best-generated model. This process usually needs an expert user for supervising the algorithm’s performance. In this paper, we propose an optimized Extreme Learning Machine by using the Bat Algorithm, which boosts the training phase of the machine learning method to increase the accuracy, and decreasing or keeping the loss in the learning phase. To evaluate our proposal, we use the Parkinson’s Disease audio dataset taken from UCI Machine Learning Repository. Parkinson’s disease is a neurodegenerative disorder that affects over 10 million people. Although its diagnosis is through motor symptoms, it is possible to evidence the disorder through variations in the speech using machine learning techniques. Results suggest that using the bio-inspired optimization algorithm for adjusting the parameters of the Extreme Learning Machine is a real alternative for improving its performance. During the validation phase, the classification process for Parkinson’s Disease achieves a maximum accuracy of 96.74% and a minimum loss of 3.27%.

This paper studies the updated estimation method for estimating the transmission rate changes over time. The models for the population dynamics under SEIR epidemic models with stochastic perturbations are analysed the dynamics of the COVID-19 pandemic in Bogotá, Colombia. We performed computational experiments to interpret COVID-19 dynamics using actual data for the proposed models. We estimate the model parameters and updated their estimates for reported infected and recovered data.

The web-based tool ARClim provides an atlas of climate change-related risk assessments spanning over 50 environmental and productive sectors in Chile. This paper illustrates the implementation of ARClim on two coastal sectors, operational downtime in fishing coves and flooding in coastal settlements, aiming to provide a tool to visualize comparative estimates of risk, which may enable decision makers and stakeholders to prioritize adaptation measures. The risk is calculated as a function of the hazard, exposure, and sensitivity. Exposure and sensitivity are characterized using present day information. To assess the hazard, wave climate for a historical period (1985–2004) and a projection (2026–2045) were modeled with six general circulation models (GCMs) for an RCP8.5 scenario. Similarly, sea-level rise was computed from 21 GCMs. Results show that the flooding hazard is mostly dependent on sea-level rise, with waves playing a minor role. However, the flooding risk is highly variable along the coast, due to differences in the exposure, which strongly depends on the population of each settlement. The analysis of increased operational downtime in fishing coves also shows risk, which is dependent of the size of each site. Lastly, limitations of the analysis and opportunities for improvement are discussed.

In the world of optimization, especially concerning metaheuristics, solving complex problems represented by applying big data and constraint instances can be difficult. This is mainly due to the difficulty of implementing efficient solutions that can solve complex optimization problems in adequate time, which do exist in different industries. Big data has demonstrated its efficiency in solving different concerns in information management. In this paper, an approach based on multiprocessing is proposed wherein clusterization and parallelism are used together to improve the search process of metaheuristics when solving large instances of complex optimization problems, incorporating collaborative elements that enhance the quality of the solution. The proposal deals with machine learning algorithms to improve the segmentation of the search space. Particularly, two different clustering methods belonging to automatic learning techniques, are implemented on bio-inspired algorithms to smartly initialize their solution population, and then organize the resolution from the beginning of the search. The results show that this approach is competitive with other techniques in solving a large set of cases of a well-known NP-hard problem without incorporating too much additional complexity into the metaheuristic algorithms.