Abstract: Computational self-adapting methods (Support Vector Machines, SVM) are compared with an analytical method in effluent composition prediction of a two-stage anaerobic digestion (AD) process. Experimental data for the AD of poultry manure were used. The analytical method considers the protein as the only source of ammonia production in AD after degradation. Total ammonia nitrogen (TAN), total solids (TS), chemical oxygen demand (COD), and total volatile solids (TVS) were measured in the influent and effluent of the process. The TAN concentration in the effluent was predicted, this being the most inhibiting and polluting compound in AD. Despite the limited data available, the SVM-based model outperformed the analytical method for the TAN prediction, achieving a relative average error of 15.2% against 43% for the analytical method. Moreover, SVM showed higher prediction accuracy in comparison with Artificial Neural Networks. This result reveals the future promise of SVM for prediction in non-linear and dynamic AD processes.

Abstract: Vegetation indices can be used to perform quantitative and qualitative assessment of vegetation cover. These indices exploit the reflectance features of leaves to predict their biophysical properties. In general, there are different vegetation indices capable of describing the same biophysical parameter. For instance, vegetation water content can be inferred from at least sixteen vegetation indices, where each one uses the reflectance of leaves in different spectral bands. Therefore, if the leaf moisture content, a vegetation index and the reflectance at the wavelengths to compute the vegetation index are known, then the reflectance in other spectral bands can be computed with a bounded error. The current work proposes a method to predict, by a machine learning regressor, the leaf reflectance (spectral signature) at specific spectral bands using the information of leaf moisture content and a single vegetation index of two tree species (Pinus radiata, and Eucalyptus globulus), which constitute 97.5% of the Valparai ' so forests in Chile. Results suggest that the most suitable vegetation index to predict the spectral signature is the Leaf Water Index, which using a Kernel Ridge Regressor achieved the best prediction results, with an RMSE lower than 0.022, and an average R2 greater than 0.95 for Pinus radiata and 0.81 for Eucalyptus globulus, respectively. (c) 2020 IAgrE. Published by Elsevier Ltd. All rights reserved.

Abstract: Mild cognitive impairment ( AQ1 MCI) is often considered an early stage of dementia, with estimated rates of progression to dementia up to 80�90% after approximately 6 years from the initial diagnosis. Diagnosis of cognitive impairment in dementia is typically based on clinical evaluation, neuropsychological assessments, cerebrospinal fluid (CSF) biomarkers, and neuroimaging. The main goal of diagnosing MCI is to determine its cause, particularly whether it is due to Alzheimer�s disease (AD). However, only a limited percentage of the population has access to etiological confirmation, which has led to the emergence of peripheral fluid biomarkers as a diagnostic tool for dementias, including MCI due to AD. Recent advances in biofluid assays have enabled the use of sophisticated statistical models and multimodal machine learning (ML) algorithms for
the diagnosis of MCI based on fluid biomarkers from CSF, peripheral blood, and saliva, among others. This approach has shown promise for identifying specific causes of MCI, including AD. After a PRISMA analysis, 29 articles revealed a trend
towards using multimodal algorithms that incorporate additional biomarkers such as neuroimaging, neuropsychological tests, and genetic information. Particularly, neuroimaging is commonly used in conjunction with fluid biomarkers for both crosssectional and longitudinal studies. Our systematic review suggests that cost-effective longitudinal multimodal monitoring data, representative of diverse cultural populations and utilizing white-box ML algorithms, could be a valuable contribution to the development of diagnostic models for AD due to MCI. Clinical assessment and biomarkers, together with ML techniques, could prove pivotal in improving diagnostic tools for MCI due to AD.

Abstract: This paper investigates how the choice of stochastic approaches and distribution assumptions impacts strategic investment decisions in energy planning problems. We formulate a two-stage stochastic programming model assuming different distributions for the input parameters and show that there is significant discrepancy among the associated stochastic solutions and other robust solutions published in the literature. To remedy this sensitivity issue, we propose a combined machine learning and distributionally robust optimization (DRO) approach which produces more robust and stable strategic investment decisions with respect to uncertainty assumptions. DRO is applied to deal with ambiguous probability distributions and Machine Learning is used to restrict the DRO model to a subset of important uncertain parameters ensuring computational tractability. Finally, we perform an out-of-sample simulation process to evaluate solutions performances. The Swiss energy system is used as a case study all along the paper to validate the approach.

Abstract: Clustering taxi data is commonly used to understand spatial patterns of urban mobility. In this paper, we propose a new clustering model called Origin-Destination-means (OD-means). OD-means is a hierarchical adaptive k-means
algorithm based on origin-destination pairs. In the first layer of the hierarchy, the clusters are separated automatically based on the variation of the within-cluster distance of each cluster until convergence. The second layer of the hierarchy corresponds to the sub clustering process of small clusters based on the
distance between the origin and destination of each cluster. The algorithm is tested on a large data set of taxi GPS data from Santiago, Chile, and compared to other clustering algorithms.
In contrast to them, our proposed model is capable of detecting general and local travel patterns in the city thanks to its hierarchical structure.

Abstract: There are significant research opportunities in the integration of Machine Learning (ML) methods and Combinatorial Optimization Problems (COPs). In this work, we focus on metaheuristics to solve COPs that have an important learning component. These algorithms must explore a solution space and learn from the information they obtain in order to find high-quality solutions. Among the metaheuristics, we study Hyper-Heuristics (HHs), algorithms that, given a number of low-level heuristics, iteratively select and apply heuristics to a solution. The HH we consider has a Markov model to produce sequences of low-level heuristics, which we combine with a Multi-Armed Bandit Problem (MAB)-based method to learn its parameters. This work proposes several improvements to the HH metaheuristic that yields a better learning for solving problem instances. Specifically, this is the first work in HHs to present Exponential Weights for Exploration and Exploitation (EXP3) as a learning method, an algorithm that is able to deal with adversarial settings. We also present a case study for the Vehicle Routing Problem with Time Windows (VRPTW), for which we include a list of low-level heuristics that have been proposed in the literature. We show that our algorithms can handle a large and diverse list of heuristics, illustrating that they can be easily configured to solve COPs of different nature. The computational results indicate that our algorithms are competitive methods for the VRPTW (2.16% gap on average with respect to the best known solutions), demonstrating the potential of these algorithms to solve COPs. Finally, we show how algorithms can even detect low-level heuristics that do not contribute to finding better solutions to the problem.& COPY

Abstract: Student dropout, defined as the abandonment of a high education program before obtaining the degree without reincorporation, is a problem that affects every higher education institution in the world. This study uses machine learning models over two Chilean universities to predict first-year engineering student dropout over enrolled students, and to analyze the variables that affect the probability of dropout. The results show that instead of combining the datasets into a single dataset, it is better to apply a model per university. Moreover, among the eight machine learning models tested over the datasets, gradient-boosting decision trees reports the best model. Further analyses of the interpretative models show that a higher score in almost any entrance university test decreases the probability of dropout, the most important variable being the mathematical test. One exception is the language test, where a higher score increases the probability of dropout.

Abstract: This paper presents a new approach to the unsupervised training of Bayesian network classifiers. Three models have been analysed: the Chow and Liu (CL) multinets; the tree-augmented naive Bayes; and a new model called the simple Bayesian network classifier, which is more robust in its structure learning. To perform the unsupervised training of these models, the classification maximum likelihood criterion is used. The maximization of this criterion is derived for each model under the classification expectation-maximization ( EM) algorithm framework. To test the proposed unsupervised training approach, 10 well-known benchmark datasets have been used to measure their clustering performance. Also, for comparison, the results for the k-means and the EM algorithm, as well as those obtained when the three Bayesian network classifiers are trained in a supervised way, are analysed. A real-world image processing application is also presented, dealing with clustering of wood board images described by 165 attributes. Results show that the proposed learning method, in general, outperforms traditional clustering algorithms and, in the wood board image application, the CL multinets obtained a 12 per cent increase, on average, in clustering accuracy when compared with the k-means method and a 7 per cent increase, on average, when compared with the EM algorithm.

Abstract: For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a manufacturer’s perspective, conducting a case study in a retail packaged foods manufacturing company located in Latin America. We developed two machine learning based systems to detect OOS events automatically. The first is based on a single Random Forest classifier with balanced data, and the second is an ensemble of six different classification algorithms. We used transactional data from the manufacturer information system and physical audits. The novelty of this work is our use of new predictor variables of OOS events. The system was successfully implemented and tested in a retail packaged foods manufacturer company. By incorporating the new predictive variables in our Random Forest and Ensemble classifier, we were able to improve their system’s predictive power. In particular, the Random Forest classifier presented the best performance in a real-world setting, achieving a detection precision of 72% and identifying 68% of the total OOS events. Finally, the incorporation of our new predictor variables allowed us to improve the performance of the Random Forest by 0.24 points in the F-measure.