Billi, M., Mascareno, A., Henriquez, P. A., Rodriguez, I., Padilla, F., & Ruz, G. A. (2022). Learning from crises? The long and winding road of the salmon industry in Chiloe Island, Chile. Mar. Pol., 140, 105069.
Abstract: The rapid development of salmon aquaculture worldwide and the growing criticism of the activity in recent decades have raised doubts about the capacity of the sector to learn from its own crises. In this article, we assess the discursive, behavioral and outcome performance dimensions of the industry to identify actual learning and lessons to be learned. We focus on the case of Chiloe Island, Chile, a global center of salmon production since 1990 that has gone through two severe crises in the last 15 years (2007-2009 ISAV crisis and 2016 red tide crisis). On the basis of a multi-method approach combining qualitative analysis of interviews and statistical data analysis, we observe that the industry has discursively learned the relevance of both self-regulation and the wellbeing of communities. However, at the behavioral and outcome performance levels, the data show a highly heterogeneous conduct that questions the ability of the sector as a whole to learn from crises. We conclude that detrimental effects for ecosystems and society will increase if learning remains at the level of discourses. Without significant changes in operational practices and market performance there are no real perspectives for the sustainability of the industry. This intensifies when considering the uneven responses to governance mechanisms. The sector needs to adapt its factual performance to sustainable goals and reflexively monitor this process. The first step for achieving this is to produce reliable data to make evidence-based decisions that align the operational dynamics of the entire sector with a more sustainable trajectory in the near future, as well as advancing towards hybrid and more reflexive governance arrangements.
|
Cillero, J. I., Henriquez, P. A., Ledger, T. W., Ruz, G. A., & Gonzalez, B. (2022). Individual competence predominates over host nutritional status in Arabidopsis root exudate-mediated bacterial enrichment in a combination of four Burkholderiaceae species. BMC Microbiol., 22(1), 218.
Abstract: Background Rhizosphere microorganisms play a crucial role in plant health and development. Plant root exudates (PRE) are a complex mixture of organic molecules and provide nutritional and signaling information to rhizosphere microorganisms. Burkholderiaceae species are non-abundant in the rhizosphere but exhibit a wide range of plant-growth-promoting and plant-health-protection effects. Most of these plant-associated microorganisms have been studied in isolation under laboratory conditions, whereas in nature, they interact in competition or cooperation with each other. To improve our understanding of the factors driving growth dynamics of low-abundant bacterial species in the rhizosphere, we hypothesized that the growth and survival of four Burkholderiaceae strains (Paraburkholderia phytofirmans PsJN, Cupriavidus metallidurans CH34, C. pinatubonensis JMP134 and C. taiwanensis LMG19424) in Arabidopsis thaliana PRE is affected by the presence of each other. Results Differential growth abilities of each strain were found depending on plant age and whether PRE was obtained after growth on N limitation conditions. The best-adapted strain to grow in PRE was P. phytofirmans PsJN, with C. pinatubonensis JMP134 growing better than the other two Cupriavidus strains. Individual strain behavior changed when they succeeded in combinations. Clustering analysis showed that the 4-member co-culture grouped with one of the best-adapted strains, either P. phytofirmans PsJN or C. pinatubonensis JMP134, depending on the PRE used. Sequential transference experiments showed that the behavior of the 4-member co-culture relies on the type of PRE provided for growth. Conclusions The results suggest that individual strain behavior changed when they grew in combinations of two, three, or four members, and those changes are determined first by the inherent characteristics of each strain and secondly by the environment.
|
Cordero, R., Mascareno, A., Henriquez, P. A., & Ruz, G. A. (2022). Drawing constitutional boundaries: A digital historical analysis of the writing process of Pinochet's 1980 authoritarian constitution. Hist. Methods, 55(3), 145–167.
Abstract: Drawing conceptual boundaries is one of the defining features of constitution-making processes. These historically situated operations of boundary making are central to the definition of what counts as “constitutional” in a political community. In this article, we study the operations of conceptual delimitation performed by the Constitutional Commission (1973-1978) that drafted the 1980 Chilean Constitution, the trademark of Augusto Pinochet's dictatorship. Using the eleven volumes of the Commission's Official Records as our textual material (10,915 pages and 80,005 distinct words), we apply vector semantics, spectral clustering and bigram graph-based analysis to explore conceptual boundaries and the behavior of specific keywords shaping the space of constitutional meanings. Our results identify the ways in which the Commission defines the normative horizon of the new social and political order by transforming old semantic references into a renewed conceptual framework. This analysis shows the immanent relations between political action and conceptual elaboration that underlie the creation of constitutional texts, as well as the potential of computational methods for the study of constitutional history and constitution-making processes.
|
Henriquez, P. A., & Ruz, G. A. (2017). Extreme learning machine with a deterministic assignment of hidden weights in two parallel layers. Neurocomputing, 226, 109–116.
Abstract: Extreme learning machine (ELM) is a machine learning technique based on competitive single-hidden layer feedforward neural network (SLFN). However, traclitional ELM and its variants are only based on random assignment of hidden weights using a uniform distribution, and then the calculation of the weights output using the least-squares method. This paper proposes a new architecture based on a non-linear layer in parallel by another non-linear layer and with entries of independent weights. We explore the use of a deterministic assignment of the hidden weight values using low-discrepancy sequences (LDSs). The simulations are performed with Halton and Sobol sequences. The results for regression and classification problems confirm the advantages of using the proposed method called PL-ELM algorithm with the deterministic assignment of hidden weights. Moreover, the PL-ELM algorithm with the deterministic generation using LDSs can be extended to other modified ELM algorithms.
|
Henriquez, P. A., & Ruz, G. A. (2018). A non-iterative method for pruning hidden neurons in neural networks with random weights. Appl. Soft. Comput., 70, 1109–1121.
Abstract: Neural networks with random weights have the advantage of fast computational time in both training and testing. However, one of the main challenges of single layer feedforward neural networks is the selection of the optimal number of neurons in the hidden layer, since few/many neurons lead to problems of underfitting/overfitting. Adapting Garson's algorithm, this paper introduces a new efficient and fast non-iterative algorithm for the selection of neurons in the hidden layer for randomization based neural networks. The proposed approach is divided into three steps: (1) train the network with h hidden neurons, (2) apply Garson's algorithm to the matrix of the hidden layer, and (3) perform pruning reducing hidden layer neurons based on the harmonic mean. Our experiments in regression and classification problems confirmed that the combination of the pruning technique with these types of neural networks improved their predictive performance in terms of mean square error and accuracy. Additionally, we tested our proposed pruning method with neural networks trained under sequential learning algorithms, where Random Vector Functional Link obtained, in general, the best predictive performance compared to online sequential versions of extreme learning machines and single hidden layer neural network with random weights. (C) 2018 Elsevier B.V. All rights reserved.
|
|
Henriquez, P. A., & Ruz, G. A. (2018). Twitter Sentiment Classification Based on Deep Random Vector Functional Link. In 2018 International Joint Conference on Neural Networks (IJCNN).
|
Henriquez, P. A., & Ruz, G. A. (2019). Noise reduction for near-infrared spectroscopy data using extreme learning machines. Eng. Appl. Artif. Intell., 79, 13–22.
Abstract: The near infrared (NIR) spectra technique is an effective approach to predict chemical properties and it is typically applied in petrochemical, agricultural, medical, and environmental sectors. NIR spectra are usually of very high dimensions and contain huge amounts of information. Most of the information is irrelevant to the target problem and some is simply noise. Thus, it is not an easy task to discover the relationship between NIR spectra and the predictive variable. However, this kind of regression analysis is one of the main topics of machine learning. Thus machine learning techniques play a key role in NIR based analytical approaches. Pre-processing of NIR spectral data has become an integral part of chemometrics modeling. The objective of the pre-processing is to remove physical phenomena (noise) in the spectra in order to improve the regression or classification model. In this work, we propose to reduce the noise using extreme learning machines which have shown good predictive performances in regression applications as well as in large dataset classification tasks. For this, we use a novel algorithm called C-PL-ELM, which has an architecture in parallel based on a non-linear layer in parallel with another non-linear layer. Using the soft margin loss function concept, we incorporate two Lagrange multipliers with the objective of including the noise of spectral data. Six real-life dataset were analyzed to illustrate the performance of the developed models. The results for regression and classification problems confirm the advantages of using the proposed method in terms of root mean square error and accuracy.
|
Mascareno, A., Cordero, R., Azocar, G., Billi, M., Henriquez, P. A., & Ruz, G. A. (2018). Controversies in social-ecological systems: lessons from a major red tide crisis on Chiloe Island, Chile. Ecol. Soc., 23(4), 25 pp.
Abstract: Connecting the discussions on resilience and governance of social-ecological systems (SESs) with the sociological analysis of social controversies, we explore a major red tide crisis on Chiloe Island, southern Chile, in 2016. Theoretically, we argue that controversies not only are methodological devices for the observation of the complex relations between nature and society in moments of crisis, but also are materially embedded in the SES dynamics and can work for or against systemic resilience. Empirically, we show that Chiloe's SES is an unstable regime prone to sudden shifts and identify the configuration of different lock-in mechanisms expressed in the reproduction of structural fragilities over the last three decades. From the examination of the social controversies on the 2016 red tide crisis, we draw several lessons. First, there is a complex interplay of visible and hidden fragilities of Chiloe's SES that, while being ignored or their resolution postponed to the future, materialize in the daily experience of inhabitants as a series of historical disappointments. Second, the unfolding of Chiloe's social-ecological crises involves epistemic disputes not only over concrete events but also on the very construction of the SES as a social-natural reality. In turn, this creates conditions for the emergence of strategic alignments between local, national, and transnational actors and shows the extent to which the socio-political articulation of knowledge may contribute to either improve or block the governance of the SES. Third, the social resources that came to light with the controversies reveal pathways for improving the governance regime of Chiloe Island's SES. This dimension highlights the normative relevance of commitments to recognize multiple scales of knowledge and articulate a plurality of actors in a nonhierarchical logic of cooperation.
|
Mascareno, A., Henriquez, P. A., Billi, M., & Ruz, G. A. (2020). A Twitter-Lived Red Tide Crisis on Chiloe Island, Chile: What Can Be Obtained for Social-Ecological Research through Social Media Analysis? Sustainability, 12(20), 38 pp.
Abstract: Considering traditional research on social-ecological crises, new social media analysis, particularly Twitter data, contributes with supplementary exploration techniques. In this article, we argue that a social media approach to social-ecological crises can offer an actor-centered meaningful perspective on social facts, a depiction of the general dynamics of meaning making that takes place among actors, and a systemic view of actors' communication before, during and after the crisis. On the basis of a multi-technique approach to Twitter data (TF-IDF, hierarchical clustering, egocentric networks and principal component analysis) applied to a red tide crisis on Chiloe Island, Chile, in 2016, the most significant red tide in South America ever, we offer a view on the boundaries and dynamics of meaning making in a social-ecological crisis. We conclude that this dynamics shows a permanent reflexive work on elucidating the causes and effects of the crisis that develops according to actors' commitments, the sequence of events, and political conveniences. In this vein, social media analysis does not replace good qualitative research, it rather opens up supplementary possibilities for capturing meanings from the past that cannot be retrieved otherwise. This is particularly relevant for studying social-ecological crises and supporting collective learning processes that point towards increased resilience capacities and more sustainable trajectories in affected communities.
|
|
Ruz, G. A., & Henriquez, P. A. (2019). Random Vector Functional Link with Naive Bayes for Classification Problems of Mixed Data. In IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) (Vol. 2019).
|
Ruz, G. A., Araya-Diaz, P., & Henriquez, P. A. (2022). Facial biotype classification for orthodontic treatment planning using an alternative learning algorithm for tree augmented Naive Bayes. BMC Med. Inform. Decis. Mak., 22, 316.
Abstract: Background
When designing a treatment in orthodontics, especially for children and teenagers, it is crucial to be aware of the changes that occur throughout facial growth because the rate and direction of growth can greatly affect the necessity of using different treatment mechanics. This paper presents a Bayesian network approach for facial biotype classification to classify patients’ biotypes into Dolichofacial (long and narrow face), Brachyfacial (short and wide face), and an intermediate kind called Mesofacial, we develop a novel learning technique for tree augmented Naive Bayes (TAN) for this purpose.
Results
The proposed method, on average, outperformed all the other models based on accuracy, precision, recall, F1-score, and kappa, for the particular dataset analyzed. Moreover, the proposed method presented the lowest dispersion, making this model more stable and robust against different runs.
Conclusions
The proposed method obtained high accuracy values compared to other competitive classifiers. When analyzing a resulting Bayesian network, many of the interactions shown in the network had an orthodontic interpretation. For orthodontists, the Bayesian network classifier can be a helpful decision-making tool.
|
Ruz, G. A., Henriquez, P. A., & Mascareno, A. (2020). Sentiment analysis of Twitter data during critical events through Bayesian networks classifiers. Futur. Gener. Comp. Syst., 106, 92–104.
Abstract: Sentiment analysis through machine learning using Twitter data has become a popular topic in recent years. Here we address the problem of sentiment analysis during critical events such as natural disasters or social movements. We consider Bayesian network classifiers to perform sentiment analysis on two datasets in Spanish: the 2010 Chilean earthquake and the 2017 Catalan independence referendum. In order to automatically control the number of edges that are supported by the training examples in the Bayesian network classifier, we adopt a Bayes factor approach for this purpose, yielding more realistic networks. The results show the effectiveness of using the Bayes factor measure as well as its competitive predictive results when compared to support vector machines and random forests, given a sufficient number of training examples. Also, the resulting networks allow to identify the relations amongst words, offering interesting qualitative information to historically and socially comprehend the main features of the event dynamics. (C) 2020 Elsevier B.V. All rights reserved.
|
Ruz, G. A., Henriquez, P. A., & Mascareno, A. (2022). Bayesian Constitutionalization: Twitter Sentiment Analysis of the Chilean Constitutional Process through Bayesian Network Classifiers. Mathematics, 10(2), 166.
Abstract: Constitutional processes are a cornerstone of modern democracies. Whether revolutionary or institutionally organized, they establish the core values of social order and determine the institutional architecture that governs social life. Constitutional processes are themselves evolutionary practices of mutual learning in which actors, regardless of their initial political positions, continuously interact with each other, demonstrating differences and making alliances regarding different topics. In this article, we develop Tree Augmented Naive Bayes (TAN) classifiers to model the behavior of constituent agents. According to the nature of the constituent dynamics, weights are learned by the model from the data using an evolution strategy to obtain a good classification performance. For our analysis, we used the constituent agents' communications on Twitter during the installation period of the Constitutional Convention (July-October 2021). In order to differentiate political positions (left, center, right), we applied the developed algorithm to obtain the scores of 882 ballots cast in the first stage of the convention (4 July to 29 September 2021). Then, we used k-means to identify three clusters containing right-wing, center, and left-wing positions. Experimental results obtained using the three constructed datasets showed that using alternative weight values in the TAN construction procedure, inferred by an evolution strategy, yielded improvements in the classification accuracy measured in the test sets compared to the results of the TAN constructed with conditional mutual information, as well as other Bayesian network classifier construction approaches. Additionally, our results may help us to better understand political behavior in constitutional processes and to improve the accuracy of TAN classifiers applied to social, real-world data.
|
