IntroductionBrain age prediction has been shown to be clinically relevant, with errors in its prediction associated with various psychiatric and neurological conditions. While the prediction from structural and functional magnetic resonance imaging data has been feasible with high accuracy, whether the same results can be achieved with electroencephalography is unclear.MethodsThe current study aimed to create a new deep learning solution for brain age prediction using raw resting-state scalp EEG. To this end, we utilized the TD-BRAIN dataset, including 1,274 subjects (both healthy controls and individuals with various psychiatric disorders, with a total of 1,335 recording sessions). To achieve the best age prediction, we used data augmentation techniques to increase the diversity of the training set and developed a deep convolutional neural network model.ResultsThe model’s training was done with 10-fold cross-subject cross-validation, with the EEG recordings of the subjects used for training not considered to test the model. In training, using the relative rather than the absolute loss function led to a better mean absolute error of 5.96 years in cross-validation. We found that the best performance could be achieved when both eyes-open and eyes-closed states are used simultaneously. The frontocentral electrodes played the most important role in age prediction.DiscussionThe architecture and training method of the proposed deep convolutional neural networks (DCNN) improve state-of-the-art metrics in the age prediction task using raw resting-state EEG data by 13%. Given that brain age prediction might be a potential biomarker of numerous brain diseases, inexpensive and precise EEG-based estimation of brain age will be in demand for clinical practice.

No abstract

No abstract

The phase recrystallization of medium carbon steel with the initial structure of lamellar pearlite in the process of short term heating to different temperatures above Ac 1 and subsequent cooling has been studied. The structure of steel formed under the nonequilibrium conditions corresponding to the decompo sition of supercooled austenite has been described. It has been shown that the changes in the structure and phase composition that arise during this treatment have a noticeable effect on the characteristics of the defor mation behavior of the material determined based on the results of dynamic indentation.

The present work has been devoted to studying the effect of rolling in a double-phase (austenite-ferrite) region on the mechanical properties of rod from steel 08G2S. The steel was rolled in a 150 mill of the Beloretsk Metallurgical Works (BMW).The final temperature of the rolling was decreased by decreasing the rolling rate and the temperature in the roll furnace before the semifinishing group of stands and by water cooling of the feed before the finishing group of stands. The temperature of the rod before and after the finishing block and in the Stelmor line for delayed cooling was determined by a Promin-4Kh optical pyrometer.As compared with the standard regime used at the base enterprise we managed to decrease the rolling temperature by 160~ which allowed us to cool the rod to a temperature below the critical point Ar 3. An analysis of the microstructure has shown that the ferrite grains disintegrate, the pearlite colonies diminish, and their appearance becomes less coarse.The results of mechanical tests have shown that the ductility of the steel was increased, whereas the hardness margin was preserved. The relative reduction of area was increased by 14%.Thus, the process of rolling of steel 08G2S can be performed under the conditions of a 150 mill at BMW in the two-phase austenite-ferrite region with improvement of the combination of mechanical properties of the rod. 1380026-0673/00/0304-0138525.00 ~