No abstract

In this work, different types of artificial neural networks are investigated for the estimation of the time of arrival (ToA) in acoustic emission (AE) signals. In particular, convolutional neural network (CNN) models and a novel capsule neural network are proposed in place of standard statistical strategies which cannot handle, with enough robustness, very noisy scenarios and, thus, cannot be sufficiently reliable when the signal statistics are perturbed by local drifts or outliers. This concept was validated with two experiments: the pure ToA identification capability was firstly assessed on synthetic signals for which a ground truth is available, showing a 10× gain in accuracy when compared to the classical Akaike information criterion (AIC). Then, the same models were tested via experimental data acquired in the framework of a localization problem to identify targets with known coordinates on a square aluminum plate, demonstrating an overreaching precision under significant noise levels.

No abstract

No abstract

The paper aims to examine the proliferation of bone marrow cell pool in Djungarian hamsters and the subsequent restoration of their genetic stability after the action of thiotepa (TT). The study involved 36 animals, of which 16 were in the control group (injected with 0.25 ml of physiological solution), and 20 in the experimental group (0.25 ml of thiotepa at a dose of 1.5 mg per 1 kg of body weight). The maximum number of cells with CA amounting to 30.0% was observed 13 hours after TT injection (p≤0.05 between the control and experimental groups) and rapidly declined to 5.7% over subsequent periods by the 37th hour of the experiment (p≤0.05). The results suggest that the restoration of cell pool genetic stability is largely associated with the cell selection mechanisms, which confers an advantage over cell proliferation without chromosome anomalies.