Abstract
Biochemical-chemical sensing with plasmonic sensors is widely performed by tracking the responses of surface plasmonic resonance peaks to changes in the medium. Interestingly, consistent sensitivity and resolution improvements have been demonstrated for gold nanoparticles by analyzing other spectral features, such as spectral inflection points or peak curvatures. Nevertheless, such studies were only conducted on planar platforms and were restricted to gold nanoparticles. In this work, such methodologies are explored and expanded to plasmonic optical fibers. Thus, we study-experimentally and theoretically-the optical responses of optical fiber-doped gold or silver nanospheres and optical fibers coated with continuous gold or silver thin films. Both experimental and numerical results are analyzed with differentiation methods, using total variation regularization to effectively minimize noise amplification propagation. Consistent resolution improvements of up to 2.2x for both types of plasmonic fibers are found, demonstrating that deploying such analysis with any plasmonic optical fiber sensors can lead to sensing resolution improvements.

Abstract
Automated image classification is a thriving field of machine learning, and various successful applications dealing with biological images have recently emerged. In this work, we address the ability of these methods to identify species that are difficult to tell apart by humans due to their morphological similarity. We focus on distinguishing species of wall lizards, namely those belonging to the Podarcis hispanicus species complex, which constitutes a well-known example of cryptic morphological variation. We address two classification experiments: (1) assignment of images of the morphologically relatively distinct P. bocagei and P. lusitanicus; and (2) distinction between the overall more cryptic nine taxa that compose this complex. We used four datasets (two image perspectives and individuals of the two sexes) and three deep-learning models to address each problem. Our results suggest a high ability of the models to identify the correct species, especially when combining predictions from different perspectives and models (accuracy of 95.9% and 97.1% for females and males, respectively, in the two-class case; and of 91.2% to 93.5% for females and males, respectively, in the nine-class case). Overall, these results establish deep-learning models as an important tool for field identification and monitoring of cryptic species complexes, alleviating the burden of expert or genetic identification.

Abstract
Purpose The purpose of this paper is to assess the impact of a maintenance philosophy, Total Productive Maintenance (TPM), on the operational performance of the Portuguese industry, identifying how it enables the systematic reduction of waste in maintenance. Design/methodology/approach A structured questionnaire was constructed and sent to 472 Portuguese enterprises, having obtained a sample constituted of 84 valid answers. With a five-point Likert scale, it was possible to assess the impact of the TPM on five operational performance dimensions, being them: quality, flexibility, productivity, safety and costs. Findings It was found that the planned maintenance, together with education and training are the practices with the highest degree of implementation in the Portuguese industry, exceeding 70% for both. The productivity is the dimension with a higher degree of impact from the implementation of TPM and costs the dimension that suffered a lesser impact. Practical implications This paper shows and analyses the current state of TPM implementation in the Portuguese industry and it will be useful for maintenance professionals, researchers and others concerned with maintenance, in order to understand the effects of TPM implementation on the operational performance of the Portuguese industries. Originality/value The findings from this paper will be valuable for professionals who desire and are looking forward to implement an effective maintenance approach in the maintenance management system, in order to achieve the excellence in maintenance.

Abstract
Self-localization of a robot is one of the most important requirements in mobile robotics. There are several approaches to providing localization data. The Ultra Wide Band Time of Flight provides position information but lacks the angle. Odometry data can be combined by using a data fusion algorithm. This paper addresses the application of data fusion algorithms based on odometry and Ultra Wide Band Time of Flight positioning using a Kalman filter that allows performing the data fusion task which outputs the position and orientation of the robot. The proposed solution, validated in a real developed platform can be applied in service and industrial robots.

Abstract
Radon concentration was continuously monitored in a horizontal dead-end gallery near Vyhne (Central Slovakia) from October 2005 to April 2008. Hourly average of radon varied from 2800 to 10 500 Bq/m(3). Temporal variation of radon, which contains periodic and non-periodic signals, spans variation of annual to diurnal scale. Time series of radon were analyzed together with meteorological parameters. The annual variation of radon seems to be connected with the annual variation of atmospheric pressure. The amplitude and shape of diurnal variation of radon changed during the year and is correlated with corresponding changes in the daily amplitude of atmospheric pressure.

Abstract
Transthyretin (TTR)-related familial amyloid polyneuropathy (ATTRv) is a life-threatening autosomal dominant disease and the age of onset represents the moment when first symptoms are felt. Accurately predicting the age of onset for a given patient is relevant for risk assessment and treatment management. In this work, we evaluate the impact of combining prediction models obtained from neighboring time windows on prediction error. We propose Symmetric (Sym) and Asymmetric (Asym) models which represent two different averaging approaches. These are incorporated with a weighting mechanism as to create Symmetric (Sym), Symmetric-weighted (Sym-w), Asymmetric (Asym), and Asymmetric-weighted (Asym-w). These four ensemble models are then compared to the original approach which is focused on individual regression base learners namely: Baseline (BL), Decision Tree (DT), Elastic Net (EN), Lasso (LA), Linear Regression (LR), Random Forest (RF), Ridge (RI), Support Vector Regressor (SV) and XGBoost (XG). Our results show that by aggregating predictions from neighbor models the average mean absolute error obtained by each base learner decreases. Overall, the best results are achieved by regression-based ensemble tree models as base learners.