PLUX - Wireless Biosignals (Portugal)

The latest European Union regulations mandate a risk-based approach to electromagnetic compatibility (EMC). In this context, this study addresses challenges in assessing medical devices’ risk over diverse electromagnetic environments and extended service periods. Combining an ECG signal with waveforms representing various interferences, it explores a novel concept for statistically evaluating interference impact on cyclic biosignals, such as the electrocardiogram (ECG), akin to statistical eye diagrams. The tool offers utility for risk analysis and EMC debugging as it extends insight beyond basic statistical parameters, such as mean or standard deviation, by visualizing the distribution of the total signal for each sample on a unit interval.

When long-term biosignal monitoring is required via surface electrodes, the use of conventional silver/silver chloride (Ag/AgCl) gelled electrodes may not be the best solution, as the gel in the electrodes tends to dry out over time. In this work, the electrical behaviour and performance of dry electrodes for biopotential monitoring was assessed. Three materials were investigated and compared against the gold-standard Ag/AgCl gelled electrodes. To characterize their electrical behaviour, the impedance response over the frequency was evaluated, as well as its signal to noise ratio. The electrodes’ performance was evaluated by integrating them in a proven electrocardiogram (ECG) acquisition setup where an ECG signal was acquired simultaneously with a set of dry electrodes and a set of standard Ag/AgCl gelled electrodes as reference. The obtained results were morphologically compared using the Normalised Root Mean Squared Error (nRMSE) and the Cosine Similarity (CS). The findings of this work suggest that the use of dry electrodes for biopotential monitoring is a suitable replacement for the conventional Ag/AgCl gelled electrodes. The signal obtained with dry electrodes is comparable to the one obtained with the gold standard, with the advantage that these do not require the use of gel and can be easily integrated into fabric to facilitate their use in long-term monitoring scenarios.

AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system’s effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.

Biosensing technologies are increasingly available as off-the-shelf products, yet for many designers, artists and non-engineers, these technologies remain difficult to design with. Through a soma design stance, we devised a novel approach for exploring qualities in biodata. Our explorative process culminated in the design of three artefacts, coupling biosignals to tangible actuation formats. By making biodata perceivable as sound, in tangible form or directly on the skin, it became possible to link qualities of the measurements to our own somatics – our felt experience of our bodily bioprocesses – as they dynamically unfold, spurring somatically-grounded design discoveries of novel possible interactions. We show that making biodata attainable for a felt experience – or as we frame it: turning biodata into somadata – enables not only first-person encounters, but also supports collaborative design processes as the somadata can be shared and experienced dynamically, right at the moment when we explore design ideas.

Research in physiology and sports science has shown that fatigue, a complex psychophysiological phenomenon, has a relevant impact in performance and in the correct functioning of our motricity system, potentially being a cause of damage to the human organism. Fatigue can be seen as a subjective or objective phenomenon. Subjective fatigue corresponds to a mental and cognitive event, while fatigue referred as objective is a physical phenomenon. Despite the fact that subjective fatigue is often undervalued, only a physically and mentally healthy athlete is able to achieve top performance in a discipline. Therefore, we argue that physical training programs should address the preventive assessment of both subjective and objective fatigue mechanisms in order to minimize the risk of injuries. In this context, our paper presents a machine-learning system capable of extracting individual fatigue descriptors (IFDs) from electromyographic (EMG) and heart rate variability (HRV) measurements. Our novel approach, using two types of biosignals so that a global (mental and physical) fatigue assessment is taken into account, reflects the onset of fatigue by implementing a combination of a dimensionless (0-1) global fatigue descriptor (GFD) and a support vector machine (SVM) classifier. The system, based on 9 main combined features, achieves fatigue regime classification performances of 0.82 ± 0.24, ensuring a successful preventive assessment when dangerous fatigue levels are reached. Training data were acquired in a constant work rate test (executed by 14 subjects using a cycloergometry device), where the variable under study (fatigue) gradually increased until the volunteer reached an objective exhaustion state.

The study of the autonomous nervous system (ANS) has played an important role, over the last years, in prognostic and diagnostic of cardiac diseases, as well as, in the assessment of psychological stress. The most common techniques to evalute the balance of the ANS are invasive and unable to provide a continuous monitoring of the patients. The advances in technology and the development of wearable sensors have provided new alternative methods to study the ANS. The analysis of Heart Rate Variability (HRV) and Electrodermal Activity (EDA) are nonivasive methods to assess the ANS with wearables devices. The wearable device used provides information about HRV with the acquisition of photoplethysmography signals from the wrist and EDA from the fingers. The processing of the biosignals was performed by submitting the participants to a mental arithmetic stress test. The results showed that the participants exhibited two distinct response during stress - “Flight or Fight”. These responses were classified using machine-learning techniques. The constructed models were able to predict how the subjects will respond in a situation of stress, based only on baseline features. The accuracy of the models using only HRV baseline features was of approximately 80% and the accuracy using simultaneously HRV and EDA baseline features was of 77%, when assigning the correct response during stress to the participant.