A memetic dynamic coral reef optimisation algorithm for simultaneous training, design, and optimisation of artificial neural networks.

Artificial Neural Networks (ANNs) have been used in a multitude of real-world applications given their predictive capabilities, and algorithms based on gradient descent, such as Backpropagation (BP) and variants, are usually considered for their optimisation. However, these algorithms have been shown to get stuck at local optima, and they require a cautious design of the architecture of the model. This paper proposes a novel memetic training method for simultaneously learning the ANNs structure and weights based on the Coral Reef Optimisation algorithms (CROs), a global-search metaheuristic based on corals' biology and coral reef formation. Three versions based on the original CRO combined with a Local Search procedure are developed: (1) the basic one, called Memetic CRO; (2) a statistically guided version called Memetic SCRO (M-SCRO) that adjusts the algorithm parameters based on the population fitness; (3) and, finally, an improved Dynamic Statistically-driven version called Memetic Dynamic SCRO (M-DSCRO). M-DSCRO is designed with the idea of improving the M-SCRO version in the evolutionary process, evaluating whether the fitness distribution of the population of ANNs is normal to automatically decide the statistic to be used for assigning the algorithm parameters. Furthermore, all algorithms are adapted to the design of ANNs by means of the most suitable operators. The performance of the different algorithms is evaluated with 40 classification datasets, showing that the proposed M-DSCRO algorithm outperforms the other two versions on most of the datasets. In the final analysis, M-DSCRO is compared against four state-of-the-art methods, demonstrating its superior efficacy in terms of overall accuracy and minority class performance.

Boosting ridge for the extreme learning machine globally optimised for classification and regression problems.

This paper explores the boosting ridge (BR) framework in the extreme learning machine (ELM) community and presents a novel model that trains the base learners as a global ensemble. In the context of Extreme Learning Machine single-hidden-layer networks, the nodes in the hidden layer are preconfigured before training, and the optimisation is performed on the weights in the output layer. The previous implementation of the BR ensemble with ELM (BRELM) as base learners fix the nodes in the hidden layer for all the ELMs. The ensemble learning method generates different output layer coefficients by reducing the residual error of the ensemble sequentially as more base learners are added to the ensemble. As in other ensemble methodologies, base learners are selected until fulfilling ensemble criteria such as size or performance. This paper proposes a global learning method in the BR framework, where base learners are not added step by step, but all are calculated in a single step looking for ensemble performance. This method considers (i) the configurations of the hidden layer are different for each base learner, (ii) the base learners are optimised all at once, not sequentially, thus avoiding saturation, and (iii) the ensemble methodology does not have the disadvantage of working with strong classifiers. Various regression and classification benchmark datasets have been selected to compare this method with the original BRELM implementation and other state-of-the-art algorithms. Particularly, 71 datasets for classification and 52 for regression, have been considered using different metrics and analysing different characteristics of the datasets, such as the size, the number of classes or the imbalanced nature of them. Statistical tests indicate the superiority of the proposed method in both regression and classification problems in all experimental scenarios.

A mixed distribution to fix the threshold for Peak-Over-Threshold wave height estimation.

Modelling extreme values distributions, such as wave height time series where the higher waves are much less frequent than the lower ones, has been tackled from the point of view of the Peak-Over-Threshold (POT) methodologies, where modelling is based on those values higher than a threshold. This threshold is usually predefined by the user, while the rest of values are ignored. In this paper, we propose a new method to estimate the distribution of the complete time series, including both extreme and regular values. This methodology assumes that extreme values time series can be modelled by a normal distribution in a combination of a uniform one. The resulting theoretical distribution is then used to fix the threshold for the POT methodology. The methodology is tested in nine real-world time series collected in the Gulf of Alaska, Puerto Rico and Gibraltar (Spain), which are provided by the National Data Buoy Center (USA) and Puertos del Estado (Spain). By using the Kolmogorov-Smirnov statistical test, the results confirm that the time series can be modelled with this type of mixed distribution. Based on this, the return values and the confidence intervals for wave height in different periods of time are also calculated.

Valorisation of Olea europaea L. Olive Leaves through the Evaluation of Their Extracts: Antioxidant and Antimicrobial Activity.

Olea europaea L. leaves constitute a source of bioactive compounds with recognized benefits for both human health and technological purposes. In the present work, different extracts from olive leaves were obtained by the application of two extraction methods, Soxhlet and microwave-assisted extraction (MAE), and six solvents (distilled water, ethanolic and glycerol mixtures solvents). MAE was applied under 40, 60 and 80 °C for 3, 6.5 and 10 min. The effect of the extraction method, solvent and treatment factors (the latter in MAE) on the total phenol content (TPC), the antioxidant activity (AA) and the phenolic profile of the extracts were all evaluated. The extracts showed high values of TPC (up to 76.1 mg GAE/g DW) and AA (up to 78 mg TE/g DW), with oleuropein being the most predominant compound in all extracts. The Soxhlet extraction method exhibited better yields in TPC than in MAE, although both methods presented comparable AA values. The water MAE extract presented the strongest antimicrobial activity against five foodborne pathogens, with minimum inhibitory concentration (MIC) values ranging from 2.5 to 60 mg/mL. MAE water extract is proposed to be exploited in the food and nutraceutical industry in the frame of a sustainable economy.

Ordinal classification of the affectation level of 3D-images in Parkinson diseases.

Parkinson's disease is characterised by a decrease in the density of presynaptic dopamine transporters in the striatum. Frequently, the corresponding diagnosis is performed using a qualitative analysis of the 3D-images obtained after the administration of [Formula: see text]I-ioflupane, considering a binary classification problem (absence or existence of Parkinson's disease). In this work, we propose a new methodology for classifying this kind of images in three classes depending on the level of severity of the disease in the image. To tackle this problem, we use an ordinal classifier given the natural order of the class labels. A novel strategy to perform feature selection is developed because of the large number of voxels in the image, and a method for generating synthetic images is proposed to improve the quality of the classifier. The methodology is tested on 434 studies conducted between September 2015 and January 2019, divided into three groups: 271 without alteration of the presynaptic nigrostriatal pathway, 73 with a slight alteration and 90 with severe alteration. Results confirm that the methodology improves the state-of-the-art algorithms, and that it is able to find informative voxels outside the standard regions of interest used for this problem. The differences are assessed by statistical tests which show that the proposed image ordinal classification could be considered as a decision support system in medicine.

Time-Series Clustering Based on the Characterization of Segment Typologies.

Time-series clustering is the process of grouping time series with respect to their similarity or characteristics. Previous approaches usually combine a specific distance measure for time series and a standard clustering method. However, these approaches do not take the similarity of the different subsequences of each time series into account, which can be used to better compare the time-series objects of the dataset. In this article, we propose a novel technique of time-series clustering consisting of two clustering stages. In a first step, a least-squares polynomial segmentation procedure is applied to each time series, which is based on a growing window technique that returns different-length segments. Then, all of the segments are projected into the same dimensional space, based on the coefficients of the model that approximates the segment and a set of statistical features. After mapping, a first hierarchical clustering phase is applied to all mapped segments, returning groups of segments for each time series. These clusters are used to represent all time series in the same dimensional space, after defining another specific mapping process. In a second and final clustering stage, all the time-series objects are grouped. We consider internal clustering quality to automatically adjust the main parameter of the algorithm, which is an error threshold for the segmentation. The results obtained on 84 datasets from the UCR Time Series Classification Archive have been compared against three state-of-the-art methods, showing that the performance of this methodology is very promising, especially on larger datasets.

PVA/(ligno)nanocellulose biocomposite films. Effect of residual lignin content on structural, mechanical, barrier and antioxidant properties.

Nanocelluloses with and without residual lignin were isolated from wheat straw. In addition, the effect of TEMPO-mediated oxidation on the production of lignin-containing nanocellulose was studied. The different nanocelluloses were used as reinforcing agent in Poly(vinyl alcohol) films. The morphology, crystallinity, surface microstructure, barrier properties, light transmittance, mechanical and antioxidant properties were evaluated. The translucency of films was reduced by the addition of nanocellulose, however, the ability to block UV-light increased from 10% for PVA to >50% using lignin-containing nanocellulose, and 30% for lignin-free samples. The mechanical properties increased considerably, however, for loads higher than 5% a negative trend was observed presumptively due to a clustering of nanocellulose components in PVA matrix. The barrier properties of the films were improved with the use of nanocellulose, especially at small amounts (1-3%). The antioxidant capacity of films was increased up to 10% using lignin-containing nanocellulose compared to 4.7% using PVA.

Is vertebrate mortality correlated to potential permeability by underpasses along low-traffic roads?

Road permeability to animal movements depends among several factors on structures which, integrated in the road design, operate as safe conducts to mitigate vehicle collision and barrier effects. There is abundant evidence that wildlife makes use of such structures as safe passages to cross roads. We analyzed the spatial relationship between road drainage elements (N = 253; mostly culverts) as potential faunal underpasses, and mortality due to vehicle collisions in two seasons and on four relatively low-traffic roads (<5000 cars/day) traversing oak rangelands of western Andalusia (S Spain). Focusing on amphibians, reptiles and mammals, we recorded and located casualties (N = 238 individuals, 35 species) along these roads, identifying and characterizing all potential underpasses. Overall frequencies of casualties and spatial distribution were highly variable both within and among these roads. We obtained an estimation of potential permeability for the different roads. We detected, located and described a wide supply and a very variable pattern of drainage culverts and other underpasses, with differences among roads in passage attributes potentially affecting permeability for wildlife, such as spatial arrangement, number, density (frequency or concentration of passages) and dimensions. We used Mantel tests to assess spatial congruence of passages and road-killed animals. We applied generalized linear mixed models fitted by maximum likelihood through Akaike Information Criterion to explain the variation in the distance of the 238 casualties to the nearest underpasses, with road transect and season as random factors, and traffic intensity, speed and vertebrate class as fixed effects. Both road-killed animals and underpass distribution followed aggregated patterns, and casualties were not significantly related to underpasses along any of the 4 roads. There were no differences in distance of casualties to the nearest underpass for the three vertebrate classes. Although existing underpasses were abundant, we could not correlate potential permeability with reduced mortality along these roads, and other factors potentially affecting roadkill aggregations should be evaluated along with permeability assessment. Mitigation of road-caused mortality can still be greatly improved for these roads, through measures of reconditioning and proper management of existing underpasses, aiming to maximize road permeability and reducing major impacts upon animal populations of Andalusian rangelands.