Learning-Based Approaches to Current Identification from Magnetic Sensors.

Direct measurement of electric currents can be prevented by poor accessibility or prohibitive technical conditions. In such cases, magnetic sensors can be used to measure the field in regions adjacent to the sources, and the measured data then can be used to estimate source currents. Unfortunately, this is classified as an Electromagnetic Inverse Problem (EIP), and data from sensors must be cautiously treated to obtain meaningful current measurements. The usual approach requires using suited regularization schemes. On the other hand, behavioral approaches are recently spreading for this class of problems. The reconstructed model is not obliged to follow the physics equations, and this implies approximations which must be accurately controlled, especially if aiming to reconstruct an inverse model from examples. In this paper, a systematic study of the role of different learning parameters (or rules) on the (re-)construction of an EIP model is proposed, in comparison with more assessed regularization techniques. Attention is particularly devoted to linear EIPs, and in this class, a benchmark problem is used to illustrate in practice the results. It is shown that, by applying classical regularization methods and analogous correcting actions in behavioral models, similar results can be obtained. Both classical methodologies and neural approaches are described and compared in the paper.

An optical fiber-based point-of-care test for periodontal MMP-8 detection: A proof of concept.

OBJECTIVES: The evaluation of salivary biomarkers has been proposed as a simple and non-invasive aid to the conventional periodontal diagnosis based on clinical-radiographic parameters. Matrix metalloproteinase-8 (MMP-8), especially in its active form, is considered one of the most reliable biomarkers of periodontitis, and point-of-care tests (POCTs) have been proposed for its clinical monitoring. In this proof-of-concept study, a novel highly sensitive POCT based on a plastic optical fiber (POF) biosensor exploiting surface plasmon resonance (SPR) to detect salivary MMP-8 is described. METHODS: A SPR-POF biosensor was functionalized with a specific antibody to develop a surface-assembled monolayer (SAM) for the detection of total MMP-8. A white light source and a spectrometer connected to the biosensor were used to quantify MMP-8 level in both buffer and real matrix (saliva) by analysing the shift of the resonance wavelength determined by the specific antigen-antibody binding upon the SAM. RESULTS: Dose-response curves by serial dilutions of human recombinant MMP-8 were realized, obtaining a limit of detection (LOD) of 40 pM (1.76 ng/ml) in buffer and 225 pM (9.9 ng/ml) in saliva and high selectivity compared to interferent analytes (MMP-2 and IL-6). CONCLUSIONS: The proposed optical fiber-based POCT was able to detect and measure total MMP-8 with high selectivity and very low LOD in both buffer and saliva. CLINICAL SIGNIFICANCE: The SPR-POF technology may be employed to create highly sensitive biosensors to monitor salivary MMP-8 levels. The possibility of specifically detecting its active, rather than total, form need to be further investigated. If confirmed and clinically validated, such a device may represent a promising tool to make an immediate, highly sensitive and reliable diagnosis of periodontitis, and to carry out a timely and targeted therapy, possibly helping to prevent the onset of local and systemic periodontitis-related complications.