RESUMO
Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.
RESUMO
BACKGROUND: Peripheral nerve injury and bone lesions, well known leprosy complications, lead to deformities and incapacities. The phosphate-regulating gene with homologies to endopeptidase on the X chromosome (PHEX) encodes a homonymous protein (PHEX) implicated in bone metabolism. PHEX/PHEX alterations may result in bone and cartilage lesions. PHEX expression is downregulated by intracellular Mycobacterium leprae (M. leprae) in cultures of human Schwann cells and osteoblasts. M. leprae in vivo effect on PHEX/PHEX is not known. METHODS: Cross-sectional observational study of 36 leprosy patients (22 lepromatous and 14 borderline-tuberculoid) and 20 healthy volunteers (HV). The following tests were performed: PHEX flow cytometric analysis on blood mononuclear cells, cytokine production in culture supernatant, 25-hydroxyvitamin D (OHvitD) serum levels and (99m)Tc-MDP three-phase bone scintigraphy, radiography of upper and lower extremities and blood and urine biochemistry. RESULTS: Significantly lower PHEX expression levels were observed in lepromatous patients than in the other groups (χ(2) = 16.554, p < 0.001 for lymphocytes and χ(2) = 13.933, p = 0.001 for monocytes). Low levels of 25-(OHvitD) were observed in HV (median = 23.0 ng/mL) and BT patients (median = 27.5 ng/mL) and normal serum levels were found in LL patients (median = 38.6 ng/mL). Inflammatory cytokines, such as TNF, a PHEX transcription repressor, were lower after stimulation with M. leprae in peripheral blood mononuclear cells from lepromatous in comparison to BT patients and HV (χ(2) = 10.820, p < 0.001). CONCLUSION: Downregulation of PHEX may constitute an important early component of bone loss and joint damage in leprosy. The present results suggest a direct effect produced by M. leprae on the osteoarticular system that may use this mechanism.
