Abstract

Abstract
Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses on the impact of label noise on the performance of learning models by examining the effect of random and class-dependent label noise on a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal is used to detect physiological changes and its quality can have a significant impact on the subsequent tasks, which makes PPG quality assessment a particularly good target for examining the impact of label noise in the field of biomedicine. Random and class-dependent label noise was introduced separately into the training set to emulate the errors associated with fatigue and bias in labeling data samples. We also tested different representations of the PPG, including features defined by domain experts, 1D raw signal and 2D image. Three different classifiers are tested on the noisy training data, including support vector machine (SVM), XGBoost, 1D Resnet and 2D Resnet, which handle three representations, respectively. The results showed that the two deep learning models were more robust than the two traditional machine learning models for both the random and class-dependent label noise. From the representation perspective, the 2D image shows better robustness compared to the 1D raw signal. The logits from three classifiers are also analyzed, the predicted probabilities intend to be more dispersed when more label noise is introduced. From this work, we investigated various factors related to label noise, including representations, label noise type, and data imbalance, which can be a good guidebook for designing more robust methods for label noise in future work.

Abstract
The paper presents an approach for the retrofitting of industrial looms on the shop floor of a textile industry. This is a real case study, where there was a need to update the equipment, providing the machines with communication features aligned with the concept of Industry 4.0. The work was developed within the scope of the research project PRODUTECH-SIF: Solutions for the Industry of the Future. Temperature, Inductive, Acoustic and 3-axis Accelerometers sensors were installed in different parts of the machines for monitorization. Data acquisition and processing is done by a SmarBox developed on a cRIO 9040 from National Instruments. A SmartBox processes data from one to four looms, allowing these old machines to have communication capacity and to be monitored remotely through the factory plant's MES/ERP. Communication can be done through the OPC UA or MQTT architecture, both protocols aligned with the new trends for industrial communications. The sensor data will be used to feed production and manufacturing KPIs and for predictive maintenance. The approach presented in this paper allows industries with legacy equipment to renew and adapt to new market trends, improving productivity rates and reduced maintenance costs.

Abstract

Abstract
Pressure ulcers are a critical issue not only for patients, decreasing their quality of life, but also for healthcare professionals, contributing to burnout from continuous monitoring, with a consequent increase in healthcare costs. Due to the relevance of this problem, many hardware and software approaches have been proposed to ameliorate some aspects of pressure ulcer prevention and monitoring. In this article, we focus on reviewing solutions that use sensor-based data, possibly in combination with other intrinsic or extrinsic information, processed by some form of intelligent algorithm, to provide healthcare professionals with knowledge that improves the decision-making process when dealing with a patient at risk of developing pressure ulcers. We used a systematic approach to select 21 studies that were thoroughly reviewed and summarized, considering which sensors and algorithms were used, the most relevant data features, the recommendations provided, and the results obtained after deployment. This review allowed us not only to describe the state of the art regarding the previous items, but also to identify the three main stages where intelligent algorithms can bring meaningful improvement to pressure ulcer prevention and mitigation. Finally, as a result of this review and following discussion, we drew guidelines for a general architecture of an intelligent pressure ulcer prevention system.

Abstract
Fiber Bragg grating is widely used in optical fiber applications as a filter or a sensor due to its compact size and high sensitivity to physical conditions, such as temperature and strain. The purpose of this chapter is to describe the implementation and characterization of two tuning methods for optical fiber Bragg gratings, varying the temperature or the length of the fiber. Among the methods using mechanical deformation, compression of the fiber by bending a flexible sheet aggregated with the Bragg grating has shown very interesting tuning results, reaching 19.0 nm with minimum reflection bandwidth variation over the entire tuning range. Stretching the fiber has presented several drawbacks, including breaking of the fiber and a lower tuning range of 4.9 nm. Temperature tuning technique presents good linearity between tuning range and temperature variation but at the cost of a low tuning range (0.4 nm) and a permanent high current electrical source.