Search

A personalized model of the human knee for enhancing the inter-individual reproducibility of a measurement method for monitoring Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) after transdermal delivery is proposed. The model is based on the solution of Maxwell Equations in the electric-quasi-stationary limit via Finite Element Analysis. The dimensions of the custom geometry are estimated on the basis of knee circumference at the patella, body mass index, and sex of each individual. An optimization algorithm allows to find out the electrical parameters of each subject by experimental impedance spectroscopy data. Muscular tissues were characterized anisotropically, by extracting Cole–Cole equation parameters from experimental data acquired with twofold excitation, both transversal and parallel to tissue fibers. A sensitivity and optimization analysis aiming at reducing computational burden in model customization achieved a worst-case reconstruction error lower than 5%. The personalized knee model and the optimization algorithm were validated in vivo by an experimental campaign on thirty volunteers, 67% healthy and 33% affected by knee osteoarthritis (Kellgren–Lawrence grade ranging in [1,4]), with an average error of 3%.

A wearable system for the personalized EEG-based detection of engagement in learning 4.0 is proposed. The system can be used to make an automated teaching platform adaptable to the cognitive and emotional conditions of the user. For example, the teaching strategy could be personalized by an automatic modulation of the proposed contents. The system is validated by an experimental case study on twenty-one students. The experimental task consisted in learning how a specific human-machine interface works. Both the cognitive and motor skills of participants were involved. De facto standard stimuli based on cognitive task and music background were employed to guarantee a metrologically founded reference. The proposed signal processing pipeline (Filter bank, Common Spatial Pattern, and Support Vector Machine), in within-subject approach, reaches almost 77 % average accuracy by a 3 s time window, in detecting both cognitive and emotional engagement.

A wearable system for the personalized EEG-based detection of engagement in learning 4.0 is proposed. In particular, the effectiveness of the proposed solution is assessed by means of the classification accuracy in predicting engagement. The system can be used to make an automated teaching platform adaptable to the user, by managing eventual drops in the cognitive and emotional engagement. The effectiveness of the learning process mainly depends on the engagement level of the learner. In case of distraction, lack of interest or superficial participation, the teaching strategy could be personalized by an automatic modulation of contents and communication strategies. The system is validated by an experimental case study on twenty-one students. The experimental task was to learn how a specific human-machine interface works. Both the cognitive and motor skills of participants were involved. De facto standard stimuli, namely (1) cognitive task (Continuous Performance Test), (2) music background (Music Emotion Recognition-MER database), and (3) social feedback (Hermans and De Houwer database), were employed to guarantee a metrologically founded reference. In within-subject approach, the proposed signal processing pipeline (Filter bank, Common Spatial Pattern, and Support Vector Machine), reaches almost 77% average accuracy, in detecting both cognitive and emotional engagement.

A method for EEG-based distraction detection during motor-rehabilitation tasks is proposed. A wireless cap guarantees very high wearability with dry electrodes and a low number of channels. Experimental validation is performed on a dataset from 17 volunteers. Different feature extractions from spatial, temporal, and frequency domain and classification strategies were evaluated. The performances of five supervised classifiers in discriminating between attention on pure movement and with distractors were compared. A k-Nearest Neighbors classifier achieved an accuracy of 92.8 ± 1.6%. In this last case, the feature extraction is based on a custom 12 pass-band Filter-Bank (FB) and the Common Spatial Pattern (CSP) algorithm. In particular, the mean Recall of classification (percentage of true positive in distraction detection) is higher than 92% and allows the therapist or an automated system to know when to stimulate the patient’s attention for enhancing the therapy effectiveness.

An on-chip transducer, for monitoring noninvasively the insulin bio-availability in real time after administration in clinical diabetology, is proposed. The bioavailability is assessed as insulin decrease in situ after administration by means of local impedance measurement. Inter-and-intra individual reproducibility is enhanced by a personalized model, specific for the subject, identified and validated during each insulin administration. Such a real-time noninvasive bioavailability measurement allows to increase the accuracy of insulin bolus administration, by attenuating drawbacks of glycemic swings significantly. In the first part of this paper, the concept, the architecture, and the operation of the transducer, as well as details about its prototype, are illustrated. Then, the metrological characterization and validation are reported in laboratory, in vitro on eggplants, ex vivo on pig abdominal non-perfused muscle, and in vivo on a human subject, using injection as a reference subcutaneous delivery of insulin. Results of significant intra-individual reproducibility in vitro and ex vivo point out noteworthy scenarios for assessing insulin bioavailability in clinical diabetology.

The functional analysis of a novel instrumentation for Brain-Computer Interfaces (BCI) is carried out. This consists of a wireless wearable helmet with only 8 dry electrodes. The brain signals to be measured through an electroencephalography are related to the sensorimotor cortex. The final aim is to distinguish between different motor imagery tasks. Furthermore, this analysis also takes into account the discrimination between two executed movements. Features are extracted from the brain signals by means of a Common Spatial Pattern algorithm. Then, two different classifiers are employed to process the brain signals, namely the Random Forest, and the Support Vector Machine with Gaussian kernel. Their performance was compared in terms of classification accuracy and the best accuracy resulted equal to about 80% when distinguishing between left and right imagined movement, classified by means of the Random Forest. The results of this study aim at giving a contribution to the building of wearable BCIs for daily life applications.

In this work, an instrument to measure the bioimpedance is presented for monitoring insulin bioavailability. The instrument is non-invasive, it is built with off-the-shelf components, and it exploits electrodes with a gel film. This hardware, already successfully used in biomedical applications, is now proposed for identification of a personalized insulin model by evaluating in real-time the impedance variation in injection site. A preliminary experimental campaign was conducted on eggplants, in order to evaluate the instrument employability. The final purpose is to integrate the instrument in modern artificial pancreas and to achieve a customized drug therapy.