Ricardo J. Barrientos

This study analyzes the level of compliance with corporate governance practices related to risk management and financial performance, using Machine Learning techniques in Chilean companies. The methodology used covers the phases of the knowledge discovery process in a database. As a result, models based on Unsupervised and Supervised Learning were obtained, which allowed characterizing and then predicting with a high level of accuracy, the degree of compliance with practices. Also, a grouping of companies with different characteristics in terms of the level of compliance and financial performance is determined. Key words: Data Science, Companies, Risk Management, Machine Learning

Randomization-based neural networks have gained wide acceptance in the scientific community owing to the simplicity of their algorithm and generalization capabilities. Random vector functional link (RVFL) networks and their variants are a class of randomization-based neural networks. RVFL networks have shown promising results in classification, regression, and clustering problems. For real-world applications, learning algorithms that can train with new samples over previous results are necessary because of to the constant generation of problems related to large-scale datasets. Various online sequential algorithms, commonly involving an initial learning phase followed by a sequential learning phase, have been proposed to address this issue. This paper presents a training algorithm based on multiple online sequential random vector functional link (OS-RVFL) networks for large-scale databases using a shared memory architecture. The training dataset is distributed among p OS-RVFL networks, which are trained in parallel using p threads. Subsequently, the test dataset samples are classified using each trained OS-RVFL network. Finally, a frequency criterion is applied to the results obtained from each OS-RVFL network to determine the final classification. Additionally, an equation was derived to reasonably predict the total training time of the proposed algorithm based on the learning time in the initial phase and the time scaling factor compared to the sequential learning phase. The results demonstrate a drastic reduction in training time because of data distribution and an improvement in accuracy because of the adoption of the frequency criterion.

The randomization-based feedforward neural network has raised great interest in the scientific community due to its simplicity, training speed, and accuracy comparable to traditional learning algorithms. The basic algorithm consists of randomly determining the weights and biases of the hidden layer and analytically calculating the weights of the output layer by solving a linear overdetermined system using the Moore–Penrose generalized inverse. When processing large volumes of data, randomization-based feedforward neural network models consume large amounts of memory and drastically increase training time. To efficiently solve the above problems, parallel and distributed models have recently been proposed. Previous reviews of randomization-based feedforward neural network models have mainly focused on categorizing and describing the evolution of the algorithms presented in the literature. The main contribution of this paper is to approach the topic from the perspective of the handling of large volumes of data. In this sense, we present a current and extensive review of the parallel and distributed models of randomized feedforward neural networks, focusing on extreme learning machine. In particular, we review the mathematical foundations (Moore–Penrose generalized inverse and solution of linear systems using parallel and distributed methods) and hardware and software technologies considered in current implementations.

The computation of the Moore–Penrose generalized inverse is a commonly used operation in various fields such as the training of neural networks based on random weights. Therefore, a fast computation of this inverse is important for problems where such neural networks provide a solution. However, due to the growth of databases, the matrices involved have large dimensions, thus requiring a significant amount of processing and execution time. In this paper, we propose a parallel computing method for the computation of the Moore–Penrose generalized inverse of large-size full-rank rectangular matrices. The proposed method employs the Strassen algorithm to compute the inverse of a nonsingular matrix and is implemented on a shared-memory architecture. The results show a significant reduction in computation time, especially for high-rank matrices. Furthermore, in a sequential computing scenario (using a single execution thread), our method achieves a reduced computation time compared with other previously reported algorithms. Consequently, our approach provides a promising solution for the efficient computation of the Moore–Penrose generalized inverse of large-size matrices employed in practical scenarios.

Contactless biometric technologies such as palm vein recognition have gained more relevance in the present and immediate future due to the COVID-19 pandemic. Since certain soft biometrics like gender and age can generate variations in the visualization of palm vein patterns, these soft traits can reduce the penetration rate on large-scale databases for mass individual recognition. Due to the limited availability of public databases, few works report on the existing approaches to gender and age classification through vein pattern images. Moreover, soft biometric classification commonly faces the problem of imbalanced data class distributions, representing a limitation of the reported approaches. This paper introduces weighted extreme learning machine (W-ELM) models for gender and age classification based on palm vein images to address imbalanced data problems, improving the classification performance. The highlights of our proposal are that it avoids using a feature extraction process and can incorporate a weight matrix in optimizing the ELM model by exploiting the imbalanced nature of the data, which guarantees its application in realistic scenarios. In addition, we evaluate a new class distribution for soft biometrics on the VERA dataset and a new multi-label scheme identifying gender and age simultaneously. The experimental results demonstrate that both evaluated W-ELM models outperform previous existing approaches and a novel CNN-based method in terms of the accuracy and G-mean metrics, achieving accuracies of 98.91% and 99.53% for gender classification on VERA and PolyU, respectively. In more challenging scenarios for age and gender–age classifications on the VERA dataset, the proposed method reaches accuracies of 97.05% and 96.91%, respectively. The multi-label classification results suggest that further studies can be conducted on multi-task ELM for palm vein recognition.

We have studied a route of chaos in the dissipative Landau–Lifshitz-Gilbert equation representing the magnetization dynamics of an anisotropic nanoparticle subjected to a time-variant magnetic field. This equation presents interesting chaotic dynamics. In the parameter space, for some forcing frequency and magnetic strength of the applied field, one observes a transition from a regular periodic behavior to chaotic dynamics. The chaotic dynamics, close to the bifurcation, are characterized by type-III intermittency. Long epochs of quasi-regular dynamics followed by turbulent bursts. The characterization of the intermittencies has been done through four different techniques. The first method is associated with the computation of the Lyapunov exponents that characterize the chaotic regime. The second and third methods are associated with the statistics of the duration of the laminar epochs prior to a turbulent burst. The fourth method is associated with the subharmonic instability present in those laminar epochs and quantified through a Poincaré section method. At the end of the manuscript, we compare the result obtained by the different techniques and discuss the methods’ limitations.