No abstract

This paper describes an adaptive threshold estimation mechanism for speaker authentication systems. The mechanism estimates speaker-dependent thresholds based on successful verifications considering the minimization of a cost function. Speaker authentication systems commonly use a threshold to decide whether a claimed identity matches a voice-print previously enrolled. Speaker independent threshold is a common option but it does not consider specific speaker characteristics that are relevant to achieve better system performance. Speaker dependent threshold on the contrary, uses speaker-specific data to estimate individual thresholds but the system performance can also suffer from suboptimal threshold conditioned by limited number of true scores. The algorithm reported in this paper starts with the speaker dependent threshold and use an adaptive algorithm to perform online re-estimation of the initial threshold based on speaker-dependent data. The threshold is reestimated in each successful authentication transaction according to a custom-made confidence score. The reported technique keep the voice print up-to-date while is less sensitive to score outliers than traditional speaker dependent threshold. The algorithm provided a performance enhancement of up to 36.2% when compared to traditional speaker independent. An ad-hoc database obtained with a practical system was used involving cell and land-line utterances from male and female speakers.

No abstract

No abstract

Background: Diabetes mellitus is a chronic metabolic disease that constitutes a risk factor for patients infected by COVID-19. Aldose reductase (ALR2) is an enzyme that catalyzes the formation of sorbitol in the metabolism of glucose via polyols in diabetic patients and leads to a group of diabetic complications, including cataracts, retinopathies, neuropathies, and nephropathies. Introduction: Inhibitors of this enzyme are therapeutic targets for the prophylaxis and treatment of these conditions. The aim of this work was to identify flavonoids isolated from medicinal plants, fruits, and vegetables as potential inhibitors of ALR2. Method: In this study, using the MATLAB numerical computation system and the molecular descriptors implemented in the DRAGON software, a regression tree was developed with an R2 of 0.953 and adequate parameters for its fit. Results: The model was validated to take into account internal and external validation procedures. Besides, the applicability domain was determined to guarantee the reliability of the predictions. Due to its good predictive power (R2ext = 0.949), the model was used to predict the inhibition of ALR2 by flavonoids reported in dietary sources. The most promising flavonoids are Myricetin and Tricin (pIC50predicted = 7.296), which are within the application domain and meet drug-like properties for oral administration. Conclusion: Finally, we can conclude that the proposed tools are useful for the rapid and economical identification of flavonoid-based potential drug candidates against ALR2 in diabetic complications.