Parallel Ictal-Net, a Parallel CNN Architecture with Efficient Channel Attention for Seizure Detection.

Around 70 million people worldwide are affected by epilepsy, a neurological disorder characterized by non-induced seizures that occur at irregular and unpredictable intervals. During an epileptic seizure, transient symptoms emerge as a result of extreme abnormal neural activity. Epilepsy imposes limitations on individuals and has a significant impact on the lives of their families. Therefore, the development of reliable diagnostic tools for the early detection of this condition is considered beneficial to alleviate the social and emotional distress experienced by patients. While the Bonn University dataset contains five collections of EEG data, not many studies specifically focus on subsets D and E. These subsets correspond to EEG recordings from the epileptogenic zone during ictal and interictal events. In this work, the parallel ictal-net (PIN) neural network architecture is introduced, which utilizes scalograms obtained through a continuous wavelet transform to achieve the high-accuracy classification of EEG signals into ictal or interictal states. The results obtained demonstrate the effectiveness of the proposed PIN model in distinguishing between ictal and interictal events with a high degree of confidence. This is validated by the computing accuracy, precision, recall, and F1 scores, all of which consistently achieve around 99% confidence, surpassing previous approaches in the related literature.

PSCF and CWT methods as a tool to identify potential sources of 7Be and 210Pb aerosols in Granada, Spain.

This research is focused on studying the preferred source regions and the pathways of the air masses with high particulate concentrations impacting on the activity concentrations of 7Be and 210Pb aerosols in Granada atmosphere. For this purpose, three different source-receptor methods have been used: Cluster Analysis, Potential Source Contribution Function (PSCF), and Concentration Weighted Trajectory (CWT). Air filter samples were weekly collected and analysed in Granada university (Spain 37.177N, 3.598 W, 687m a.s.l.) during 12 years (2006-2017) for the activity concentration of 7Be, and during 5 years (2010-2014) for the one of 210Pb. The time series of the collected data indicate that the concentration of both radiotracers present a cyclical and seasonal pattern, in association with their origins and atmospheric conditions. Clustering analysis showed that the air masses arriving to Granada can be classified as: (1) tropical continental air masses coming from the Mediterranean Sea, (2) tropical and warm polar maritime air masses produced over the Atlantic Ocean, and (3) continental air masses originated over Europe and Northern Africa. The PSCF and CWT methods confirmed that the main source areas of 7Be are located in the Atlantic coast of southern Morocco, and Northern Africa. On the other hand, southern France and the Algerian desert were found to be the main region sources of 210Pb. In addition, the Mediterranean Basin has been postulated as a strong source region for 7Be and 210Pb. Furthermore, the PSCF and CWT models show that the regions with larger 7Be/210Pb ratios are located in the Atlantic Ocean, due to frequent stratospheric intrusions specially during the winter months.

Uterine activity modifies the response of the fetal autonomic nervous system at preterm active labor.

Background: The autonomic nervous system of preterm fetuses has a different level of maturity than term fetuses. Thus, their autonomic response to transient hypoxemia caused by uterine contractions in labor may differ. This study aims to compare the behavior of the fetal autonomic response to uterine contractions between preterm and term active labor using a novel time-frequency analysis of fetal heart rate variability (FHRV). Methods: We performed a case-control study using fetal R-R and uterine activity time series obtained by abdominal electrical recordings from 18 women in active preterm labor (32-36 weeks of gestation) and 19 in active term labor (39-40 weeks of gestation). We analyzed 20 minutes of the fetal R-R time series by applying a Continuous Wavelet Transform (CWT) to obtain frequency (HF, 0.2-1 Hz; LF, 0.05-0.2 Hz) and time-frequency (Flux0, Flux90, and Flux45) domain features. Time domain FHRV features (SDNN, RMSSD, meanNN) were also calculated. In addition, ultra-short FHRV analysis was performed by segmenting the fetal R-R time series according to episodes of the uterine contraction and quiescent periods. Results: No significant differences between preterm and term labor were found for FHRV features when calculated over 20 minutes. However, we found significant differences when segmenting between uterine contraction and quiescent periods. In the preterm group, the LF, Flux0, and Flux45 were higher during the average contraction episode compared with the average quiescent period (p<0.01), while in term fetuses, vagally mediated FHRV features (HF and RMSSD) were higher during the average contraction episode (p<0.05). The meanNN was lower during the strongest contraction in preterm fetuses compared to their consecutive quiescent period (p=0.008). Conclusion: The average autonomic response to contractions in preterm fetuses shows sympathetic predominance, while term fetuses respond through parasympathetic activity. Comparison between groups during the strongest contraction showed a diminished fetal autonomic response in the preterm group. Thus, separating contraction and quiescent periods during labor allows for identifying differences in the autonomic nervous system cardiac regulation between preterm and term fetuses.