Sleep staging is crucial for assessing sleep quality and diagnosing sleep disorders. Recent advances in deep learning methods with electroencephalogram (EEG) signals have shown remarkable success in automatic sleep staging. However, the use of deeper neural networks may lead to the issues of gradient disappearance and explosion, while the non-stationary nature and low signal-to-noise ratio of EEG signals can negatively impact feature representation. To overcome these challenges, we proposed a novel lightweight sequence-to-sequence deep learning model, 1D-ResNet-SE-LSTM, to classify sleep stages into five classes using single-channel raw EEG signals. Our proposed model consists of two main components: a one-dimensional residual convolutional neural network with a squeeze-and-excitation module to extract and reweight features from EEG signals, and a long short-term memory network to capture the transition rules among sleep stages. In addition, we applied the weighted cross-entropy loss function to alleviate the class imbalance problem. We evaluated the performance of our model on two publicly available datasets; Sleep-EDF Expanded consists of 153 overnight PSG recordings collected from 78 healthy subjects and ISRUC-Sleep includes 100 PSG recordings collected from 100 subjects diagnosed with various sleep disorders, and obtained an overall accuracy rate of 86.39% and 81.97%, respectively, along with corresponding macro average F1-scores of 81.95% and 79.94%. Our model outperforms existing sleep staging models in terms of overall performance metrics and per-class F1-scores for several sleep stages, particularly for the N1 stage, where it achieves F1-scores of 59.00% and 55.53%. The kappa coefficient is 0.812 and 0.766 for the Sleep-EDF Expanded and ISRUC-Sleep datasets, respectively, indicating strong agreement with certified sleep experts. We also investigated the effect of different weight coefficient combinations and sequence lengths of EEG epochs used as input to the model on its performance. Furthermore, the ablation study was conducted to evaluate the contribution of each component to the model’s performance. The results demonstrate the effectiveness and robustness of the proposed model in classifying sleep stages, and highlights its potential to reduce human clinicians’ workload, making sleep assessment and diagnosis more effective. However, the proposed model is subject to several limitations. Firstly, the model is a sequence-to-sequence network, which requires input sequences of EEG epochs. Secondly, the weight coefficients in the loss function could be further optimized to balance the classification performance of each sleep stage. Finally, apart from the channel attention mechanism, incorporating more advanced attention mechanisms could enhance the model’s effectiveness.
In this article, we propose that the idea that nothing is thrown away becomes an integral part of the daily management of precariousness in schools affected by the logics of New Public Management (NPM). We retrieve results of qualitative investigation on special education schools in urban poverty and environmental degradation contexts in the Metropolitan Area of Buenos Aires. We discuss urban recycling and the ways in which these dynamics affect schools and their teachers, and we maintain that teachers adopt basic subsistence practices like scavenging as one way of classroom management. The notion of scavenger-teacher refers, precisely, to that condition; the way in which teachers integrate the recovery of waste to get the necessary materials to do their work.
Electronic band structure, type of Schottky contact and Schottky barrier height established at the interface of the CS–MX2 (M = Mo, W; X = S, Se, Te) and CS–MXY ((X ≠ Y) = S, Se, Te) MS vdWH.
Se consideran diferentes factores intervinientes en la producción de concordancia plural en cuatro aprendices italianos de ELE, en un estudio de caso longitudinal, utilizando un análisis de tiempo hasta el evento “error de concordancia”. Se aplicó un modelo de eventos de errores múltiples y otro de riesgos competitivos. Se categorizaron cuatro tipos de errores: género, -e- epentética, plural, mixto. Se hallaron efectos significativos para los siguientes factores: (i) ‘determinantes’ (adjetivos posesivos, indefinidos, demostrativos, interrogativos, exclamativos) y ‘adjetivos’ (calificativos, numerales, ordinales); (ii) sustantivos animados; (iii) concordancias en donde se podía aplicar la estrategia de poner plural en “-os” en plurales italianos terminados en “-i”; (iv) en aquellas donde se podía aplicar la estrategia de poner plural en “-es” con palabras italianas singulares terminados en “-e”; (v) con palabras cuyas desinencias tenían similitud media o baja con las del italiano; (vi) con sustantivos familiares y/o frecuentes; (vii) instancias con TYPES más frecuentes.
A recent theoretical work indicates that intermetallic materials LiMnZ (Z = N, P) with a half-Heusler structure exhibit half-metallic (HM) behaviors at their strained lattice constants, and the magnetic moments of these alloys are expected to reach as high as 5 μB per formula unit. (Damewood et al. Phys. Rev. B 2015, 91, 064409). This work inspired us to find new Heusler-based half-metals with the largest magnetic moment. With the help of the first-principles calculation, we reveal that XCrZ (X = K, Rb, Cs; Z = S, Se, Te) alloys show a robust, half-metallic nature with a large magnetic moment of 5 μB at their equilibrium and strained lattice constants in their most stable phases, while the excellent HM nature of LiCrZ (Z = S, Se, Te) alloys can be observed in one of their metastable phases. Moreover, the effects of uniform strain in LiCrZ (Z = S, Se, Te) alloys in type II arrangement have also been discussed.
AbstractCs2Ga2Se5 is obtained by thermal decomposition of CsN3 in the presence of stoichiometric amounts of GaSe and Se (evacuated quartz ampoule, 873 K, several days).
AbstractCs3AsGeSe5 and Cs4Ge2Se6 can be prepared by methanolothermal reaction of elemental As, Ge and Se with Cs2CO3 at 190 °C. The former quaternary phase contains zweier $^{1}_{\infty}$[{AsGeSe5}3−] chains consisting of corner‐bridged GeSe4 tetrahedra and AsSe3 pyramids and represents the first GeIV‐AsIII chalcogenidometalate. Cs4Ge2Se6 exhibits discrete [Ge2Se6]4− anions formed by two edge‐sharing GeSe4 tetrahedra.
AbstractCs3Se22 can be prepared together with the known compounds Cs2Sn2Se6 and Cs4Sn2Se6 by reacting Cs2CO3 and Sn in a CH3OH/en solution at 120 °C. The presence of CuCl and the macrocyclic ligand 1,10‐dithia‐18‐crown‐6 are essential for product formation. The caesium polyselenide consists of anionic nets $^{3}_{\infty}\rm [Se_{6}^{3-}]$ that are separated by two layers of discrete Se8 rings. Within the polymeric anions pairs of Se3·− radical anions and Se32− anions are linked through secondary interactions.
AbstractThe eight title compounds are prepared by reaction of elemental Co powder with the corresponding alkali metal carbonate in a stream of hydrogen loaded with sulfur and selenium, resp. (1030 K, 10 h).
AbstractChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 100 leading journals. To access a ChemInform Abstract of an article which was published elsewhere, please select a “Full Text” option. The original article is trackable via the “References” option.
Department of CS & SE, Andhra University College of Engineering, AP, India, Sunita A Yadwad, Valli Kumari Vatsavayi
Minimization of network downtime is the biggest challenge for service providers and one of its prime causes is equipment failure. On-time prediction and rectification of faults can reduce downtimes. Dynamic and very adaptive algorithms are required for processing huge torrents of data and the generation of predictions based on patterns and trends in the data obtained from trouble tickets and system logs. A novel strategy for fault detection based on the data accumulated has to be applied where the equipment behavior is monitored closely to prevent its failure and further prevent a network failure or downtime. Paper proposes Service Outage Prediction (SOP) that uses hidden Markov models (HMMs) which have a successful record in tasks related to pattern recognition and have been successfully used in the prediction of failures. The features of the aggregated fault data are subject to the supervised learning algorithm, in the initial phase of training. The samples are traced at different stages, and the failures are detected through high priority in tickets. Among the many solutions possible one of the best solutions being the approach of combining the Hidden Markov model and Bayesian Network. The results indicate the strengths of Hidden Markov Models as the probabilistic approach increases the accuracy of the prediction when compared to the other prediction algorithms. The likelihood of a customer raising a trouble ticket with high priority is predicted by the SOP model proposed.
The objective of this study was to compare the breathing pattern of patients who failed to wean from mechanical ventilation to the pattern during acute respiratory failure. We hypothesized that a similar breathing pattern occurs under both conditions. Breathing pattern, mouth occlusion pressure (P[0.1]) and maximum inspiratory pressure (P[I,max]) were measured in 15 patients during acute respiratory failure, within 24 h of the institution of mechanical ventilation, and in 49 patients during recovery, when they were ready for discontinuation from mechanical ventilation. The following indices were calculated: rapid shallow breathing index (respiratory frequency/tidal volume (fR/VT)); rapid shallow breathing-occlusion pressure index (ROP = P[0.1 x fR/VT]); P(0.1)/P(I,max); and effective inspiratory impedance (P[0.1]/VT/(inspiratory time (tI)). Patients who failed to wean (n=11) had a similar ROP,fR/VT and P(0.1)/P(I,max) to those with acute respiratory failure despite a significantly reduced P(0.1)/VT/tI, the value of which was comparable to that of patients who weaned successfully (n=38). The P(I,max) of patients who failed to wean was similar to that of patients who weaned successfully. We conclude that patients who failed to wean had a breathing pattern similar to that during acute respiratory failure, despite a reduced mechanical load on the respiratory muscles and a relatively adequate inspiratory muscle strength. This suggests that strategies that enhance respiratory muscle endurance may facilitate weaning.