Gas concentration prediction by LSTM network combined with wavelet thresholding denoising and phase space reconstruction.

The Long Short-Term Memory neural network is a specialized architecture designed for handling time series data, extensively applied in the field of predicting gas concentrations. In the harsh conditions prevalent in coal mines, the time series data of gas concentrations collected by sensors are susceptible to noise interference. Directly inputting such noisy data into a neural network for training would significantly reduce predictive accuracy and lead to deviations from the actual values. The Empirical Mode Decomposition method, commonly employed in gas concentration prediction, faces challenges in practical engineering applications due to the substantial influence of newly acquired data on the initial decomposition subsequence values. Consequently, it is difficult to use this method as intended. Conversely, the Wavelet Threshold Denoising method does not encounter this issue. Furthermore, gas concentration sequences exhibit chaotic characteristics. Performing phase space reconstruction allows for the extraction of additional valuable hidden information. In light of these factors, a prediction model is proposed, integrating WTD, Phase Space Reconstruction, and LSTM neural networks. Initially, the gas concentration sequence itself is subjected to wavelet threshold denoising. Subsequently, phase space reconstruction is performed, and the resulting reconstructed phase space matrix serves as the input for the LSTM neural network. The outcomes from the final LSTM neural network reveal that the PS method indeed extracts more valuable information. The Mean Absolute Error and Root Mean Square Error are reduced by 35.1% and 25%, respectively. Additionally, when compared to the PS-LSTM model without utilizing the WTD method, the WTD-PS-LSTM predictive model showcases reductions of 77.1% and 80% in MAE and RMSE, respectively. Compared with the LSTM model, the MAE and RMSE of the WTD-PS-LSTM prediction model were reduced by 81.4% and 82.6%, respectively. This greatly improves the credibility of whether or not a response related to coal mine safety management is implemented.

Correlation of thyroid-related hormones with vascular complications in type 2 diabetes patients with euthyroid.

Background: This study aimed to evaluate the relationship between thyroid-related hormones and vascular complications in type 2 diabetes mellitus (T2DM) patients with euthyroidism. Methods: We enrolled 849 patients with T2DM after screening out the ineligible. Multivariate logistic regression was used to analyze the relationship between fT3, fT4, the fT3/fT4 ratio, thyroid-stimulating hormone, and diabetic vascular complications. Spearman correlation analysis was used to determine the correlation between thyroid-related hormones and vascular complications. Results: In this cross-sectional study of T2DM, 538 patients with carotid atherosclerosis (CA) and 299 patients with diabetic peripheral neuropathy (DPN). The prevalence of DPN was negatively correlated with fT3 and the fT3/fT4 ratio but positively correlated with fT4 (all P<0.01). At the same time, the odds ratio for DPN decreased with increasing fT3 (T1: reference; T2: OR: 0.689, 95%CI: 0.477, 0.993; T3: OR: 0.426, 95% CI: 0.286, 0.633, all P<0.05) and fT3/fT4 ratio (T1: reference; T2: OR: 0.528, 95% CI: 0.365, 0.763; T3: OR: 0.413, 95% CI: 0.278, 0.613, all P<0.001). In terms of sensitivity and specificity, fT4 was found to be 39.5% and 71.4% accurate, respectively, with a 95% CI of 0.531-0.611. Conclusions: We found a negative correlation between fT3 and fT3/fT4 ratio and the number of individuals with DPN, and a positive correlation between fT4 and the prevalence of DPN.

Nonlinear Bloch dynamics and spin-wave generation in a Bose-Hubbard ladder subject to effective magnetic field.

The two-leg magnetic ladder is the simplest and ideal model to reflect the coupling effects of lattice and magnetic field. It is of great significance to study some novel phases, topological characteristics, and chiral characteristics in condensed matter physics. In particular, the left-right leg degree of freedom can be regarded as a pseudospin, and the two-leg magnetic ladder also provides an ideal platform for the study of spin dynamics. Here the ground state, Bloch oscillations (BOs), and spin dynamics of the interacting two-leg magnetic ladder subject to an external linear force are studied by using variational approach and numerical simulation. In the absence of the external linear force, the critical condition of transition between the zero-momentum state and plane-wave state is obtained analytically, and the physical mechanism of the ground-state transition is revealed. When the external linear force presents, the occurrence of BOs excites the spin dynamics, and we reveal the chiral BOs and the accompanied spin dynamics of the system in different ground states. In particular, we further study the influence of periodically modulated linear force on BOs and spin dynamics. The frequencies of the linear force corresponding to the resonances and pseudoresonances are obtained analytically, which result in rich nonlinear dynamics. In resonances, stable and strong BOs (with larger amplitude) are observed. In pseudoresonances, because the pseudoresonance frequencies are related to the initial momentum and phase of the wave packet, a dispersion effect takes place and strong diffusion of wave packet occurs. When the frequency is nonresonant, drift and weak dispersion of wave packet occur simultaneously with the wave-packet oscillation. In all cases, the wave-packet dynamics is accompanied with periodic but anharmonic pseudospin oscillation. The BOs and spin dynamics are effectively controlled by periodically modulating the linear force.