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: The ODMeans R package implements the OD-Means model, a two-layer hierarchical clustering algorithm designed for extracting both global and local travel patterns from Origin–Destination Pairs (OD-Pairs). In contrast to existing models, OD-Means automates cluster determination and offers advantages such as smaller Within-Cluster Distance (WCD) and dual hierarchies. The package includes functions for applying the model and visualizing the results on maps. Using real taxi data from Santiago, Chile, we demonstrate the package’s capabilities, showcasing its flexibility and impact on understanding urban mobility patterns.

Abstract: IntroductionEpilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy.MethodTo optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis.ResultIn this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%.Conclusion Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.

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: This paper presents a method called Interval Incremental Learning (IIL) to capture spatial and temporal patterns in uncertain data streams. The patterns are represented by information granules and a granular rule base with the purpose of developing explainable human-centered computational models of virtual and physical systems. Fundamentally, interval data are either included into wider and more meaningful information granules recursively, or used for structural adaptation of the rule base. An Uncertainty-Weighted Recursive-Least-Squares (UW-RLS) method is proposed to update affine local functions associated with the rules. Online recursive procedures that build interval-based models from scratch and guarantee balanced information granularity are described. The procedures assure stable and understandable rule-based modeling. In general, the model can play the role of a predictor, a controller, or a classifier, with online sample-per-sample structural adaptation and parameter estimation done concurrently. The IIL method is aligned with issues and needs of the Internet of Things, Big Data processing, and eXplainable Artificial Intelligence. An application example concerning real-time land-vehicle localization and tracking in an uncertain environment illustrates the usefulness of the method. We also provide the Driving Through Manhattan interval dataset to foster future investigation.

Abstract: High energy consumption in size reduction operations is one of the most significant issues concerning the sustainability of raw material beneficiation. Thus, process optimization should be done to reduce energy consumption. This study aimed to investigate the applicability of artificial neural networks (ANNs) to predict the particle size distributions (PSDs) of mill products. PSD is one of the key sources of information after milling since it significantly affects the subsequent beneficiation processes. Thus, precise PSD prediction can contribute to process optimization and energy consumption reduction by avoiding over-grinding. In this study, coal particles (-2 mm) were ground with a rod mill under different conditions, and their PSDs were measured. The variables studied included volume% (vol.%) of feed (coal particle), vol.% rod load, and grinding time. Our supervised ANN models were developed to predict PSDs and trained by experimental data sets. The trained models were verified with the other experimental data sets. The results showed that the PSDs predicted by ANN fitted very well with the experimental data after the training. Root mean squared error (RMSE) was calculated for each milling condition, with results between 0.165 and 0.965. Also, the developed ANN models can predict the PSDs of ground products under different milling conditions (i.e., vol.% feed, vol.% rod load, and grinding time). The results confirmed the applicability of ANNs to predict PSD and, thus the potential contribution to reducing energy consumption by optimizing the grinding conditions.

Abstract: In this paper, we present a novel algorithm that uses machine learning and natural language processing techniques to facilitate the coding of feature listing data. Feature listing is a method in which participants are asked to provide a list of features that are typically true of a given concept or word. This method is commonly used in research studies to gain insights into people's understanding of various concepts. The standard procedure for extracting meaning from feature listings is to manually code the data, which can be time-consuming and prone to errors, leading to reliability concerns. Our algorithm aims at addressing these challenges by automatically assigning human-created codes to feature listing data that achieve a quantitatively good agreement with human coders. Our preliminary results suggest that our algorithm has the potential to improve the efficiency and accuracy of content analysis of feature listing data. Additionally, this tool is an important step toward developing a fully automated coding algorithm, which we are currently preliminarily devising.