Search

Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems.

Soil temperature is a key parameter in many disciplines, and its research has important practical significance. In recent years, the prediction of soil temperature by deep learning has achieved good results. However, deep learning is difficult to popularize in practical use because of its opacity. This study aims to interpret and analyze the Long Short Term Memory Network (LSTM) model for global soil temperature prediction using SHapley Additive exPlanation (SHAP), Permutation Importance (PI) and Partial Dependence Plot (PDP). The results show that Temperature of air at 2 m above the surface of land has the greatest influence on the prediction of soil temperature, and its SHAP and PI characteristic values have significant seasonality. Meanwhile, radiation also has a certain influence on the prediction results. There was a significant positive correlation between the temperature of 2 m and the soil temperature. The explanatory insights provided in this paper enhance the transparency and confidence of the model, which promotes the applicability of soil temperature prediction models in relevant fields.

Calcium influx into neurons triggers neuronal death during cerebral ischemia/reperfusion injury. Various calcium channels are involved in cerebral ischemia/reperfusion injury. Cav3.2 channel is a main subtype of T-type calcium channels. T-type calcium channel blockers, such as pimozide and mibefradil, have been shown to prevent cerebral ischemia/reperfusion injury-induced brain injury. However, the role of Cav3.2 channels in cerebral ischemia/reperfusion injury remains unclear. Here, in vitro and in vivo models of cerebral ischemia/reperfusion injury were established using middle cerebral artery occlusion in mice and high glucose hypoxia/reoxygenation exposure in primary hippocampal neurons. The results showed that Cav3.2 expression was significantly upregulated in injured hippocampal tissue and primary hippocampal neurons. We further established a Cav3.2 gene-knockout mouse model of cerebral ischemia/reperfusion injury. Cav3.2 knockout markedly reduced infarct volume and brain water content, and alleviated neurological dysfunction after cerebral ischemia/reperfusion injury. Additionally, Cav3.2 knockout attenuated cerebral ischemia/reperfusion injury-induced oxidative stress, inflammatory response, and neuronal apoptosis. In the hippocampus of Cav3.2-knockout mice, calcineurin overexpression offset the beneficial effect of Cav3.2 knockout after cerebral ischemia/reperfusion injury. These findings suggest that the neuroprotective function of Cav3.2 knockout is mediated by calcineurin/nuclear factor of activated T cells 3 signaling. Findings from this study suggest that Cav3.2 could be a promising target for treatment of cerebral ischemia/reperfusion injury.

In recent years, deep learning methods have shown significant potential in soil moisture modeling. However, a prominent limitation of deep learning approaches has been the absence of physical mechanisms. To address this challenge, this study introduces two novel loss functions designed around physical mechanisms to guide deep learning models in capturing physical information within the data. These two loss functions are crafted to leverage the monotonic relationships between surface water variables and shallow soil moisture as well as deep soil water. Based on these physically-guided loss functions, two physically-guided Long Short-Term Memory (LSTM) networks, denoted as PHY-LSTM and PHYs-LSTM, are proposed. These networks are trained on the global ERA5-Land dataset, and the results indicate a notable performance improvement over traditional LSTM models. When used for global soil moisture forecasting for the upcoming day, PHY-LSTM and PHYs-LSTM models exhibit closely comparable results. In comparison to conventional data-driven LSTM models, both models display a substantial enhancement in various evaluation metrics. Specifically, PHYs-LSTM exhibits improvements in several key performance indicators: an increase of 13.6% in Kling-Gupta Efficiency (KGE), a 20.7% increase in Coefficient of Determination (R2), an 8.2% reduction in Root Mean Square Error (RMSE), and a 4.4% increase in correlation coefficient (R). PHY-LSTM also demonstrates improvements, with a 14.8% increase in KGE, a 19.6% increase in R2, an 8.2% reduction in RMSE, and a 4.4% increase in R. Additionally, both models exhibit enhanced physical consistency over a wide geographical area. Experimental results strongly emphasize that the incorporation of physical mechanisms can significantly bolster the predictive capabilities of data-driven soil moisture models.

Abstract Introduction We estimated the safety and efficacy of ultrasound-guided multipoint fascial plane block, including serratus anterior plane block (SAPB) and bilateral transversus abdominis plane block (TAPB) in elderly patients who underwent combined thoracoscopic–laparoscopic esophagectomy (TLE). Methods The authors enrolled 80 patients in this prospective study after patient selection using the inclusion and exclusion criteria who were scheduled for elective TLE from May 2020 to May 2021. Patients were randomly assigned to the treated group (group N) or the control group (group C) (n = 40 per group) using the sealed-envelope method. Multipoint fascial plane blocks, including serratus anterior plane block (SAPB) and bilateral TAPB, were performed on patients undergoing TLE using a solution of 60 mL 0.375% ropivacaine plus 2.5 mg dexamethasone by 3 injections of 20 mL each (group N) or no interventions (group C). Results Systolic blood pressure (SBP), diastolic blood pressure (DBP), and heart rate (HR) at T incision and 30 min after T incision were significantly higher in group C than in group N, and also significantly higher than at baseline (P

Vehicle speed prediction plays an important role in vehicle energy saving and safety research. It can contribute to vehicle energy saving and safety assistant driving, route navigation, automatic transmission gear control, and hybrid electric vehicle predictive control. The research on vehicle speed prediction has important theoretical basis and application value. The data-driven deep learning (DL) model provides a powerful method for building an accurate speed prediction model. However, the traditional vehicle speed prediction model has some limitations in prediction efficiency and accuracy, which fails to take into account the characteristics of the time dimension of speed data. This paper proposes an Long-Short Term Memory(LSTM) vehicle speed prediction model based on heuristic adaptive time-span strategy. The model mainly includes three parts: 1. In view of the instantaneity of the time series, we add weights to the input data, increase the weight of the data near the prediction point, and accelerate the convergence speed and accuracy of the model. 2. Simulated annealing algorithm is adopted to adaptively select the most appropriate time span for the current data. Compared with the traditional vehicle speed prediction model, this approach does not fix the time span and has better data universality. 3. The basic unit of the model is the LSTM model. The time series model is used to make prediction of speed, which is in line with the law of speed data. Validation of the model using driving data from ten vehicles over a 1-year period reveals that the LSTM speed prediction model based on a heuristic adaptive time-span strategy exhibits impressive accuracy and outperforms existing state-of-the-art machine learning models.

The air-cooled proton exchange membrane fuel cell is widely used in unmanned aerial vehicle since its small size and high efficiency. The bipolar plate structure is an important factor affecting the performance of fuel cells. This article conducts experimental research on the impact of different channel structures on performance based on the annular bipolar plate designed by the team. A single air-cooled fuel cell with 50cm2 is used in the experiment to investigate the dynamic response under different current loading rates of 0–40 A. The test results show that the hydrogen and oxygen in different flow directions have a significant impact on the performance of the fuel cell, with a performance improvement of 8.1% by the hydrogen and oxygen in vertical and staggered flow directions for the enhancement of heat and mass transfer ability, and a decrease of about 3.5° compared with the hot spot temperature. In addition, this study further demonstrated the applicability of the annular bipolar plate structure, and verified the impact of different channels on cathode side and ridge shaped structure on performance, wind speed, temperature distribution, stability and mass power density, of which the performance of the fan channel/linear ridge is the best, which is about 8.5% higher than the output power of the worst fan channel/fan back. These test results provide basic data and technical support for the system design and application of air-cooled fuel cell of open cathode.

Soil temperature (Ts) is a vital meteorological parameter for ecological, physical and biological research. Ts estimation is very important for a variety of fields and presents great challenges because the relevant areas have complex characteristics, human activities, and a nonlinear nature between Ts and its environmental factors. Hence, a novel model based on long short-term memory (LSTM), is proposed here as an alternative data-intelligence tool. The proposed model designs a novel function that combines LSTM loss with an adversarial term for enhancing the correlation between Ts and its environmental factors. For this purpose, we designed a novel function that combines LSTM loss with an adversarial term. The adversarial term encourages the LSTM model to estimate Ts, which cannot be distinguished from the observed Ts by an adversarial model. In this study, the proposed model is trained using meteorological information from two stations in China (Changbai Mountain and Haibei). The model is constructed using hourly input variables, including air temperature (Ta), wind speed (W), relative humidity (RH), solar radiation (SR), and vapor pressure deficit(VPD), while the objective variable is the Ts measurement at a 5 cm depth for the period 2003-2005. Different statistical evaluation criteria, including the root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe model efficiency coefficient (NS), Willmott index of agreement(WI) and the Legates and McCabe index (LMI), have been employed to assess the model performance. Through experimentation, the proposed model generally performs superior to the other seven state-of-the-art estimation models (autoregressive integrated moving average model, linear regression, backpropagation neural networks, support vector regression, extreme learning machine, eXtreme gradient boosting and long short-term memory) in Ts estimation at a 5 cm depth over the Changbai Mountain and Haibei stations. For this case, the most accurate performance is attained for Ts estimation at a 5 cm depth, with the highest values of NS = 0.915, WI = 0.978, and LMI = 0.686, and the lowest values of the relative RMSE and MAE being 2.276 and 1.796, respectively. In accordance with the present results, it is concluded that the proposed model can serve as an alternative approach for estimating Ts, while ensuring that an appropriate combination of meteorological inputs is applied to yield an optimal model.

Background and aims: Postoperative pain can cause serious adverse reactions that severely affect postoperative outcome. The present study evaluated the effect of dexmedetomidine (DEX) added to sufentanil in intravenous patient-controlled analgesia (PCA) on the relief of pain and inflammatory responses during postoperative recovery of patients undergoing a combined thoracoscopic-laparoscopic esophagectomy (TLE). Methods: Sixty patients undergoing TLE were randomly allocated to receive 1 μg/ml of sufentanil alone (Group S) or 1 μg/ml of sufentanil plus 2.5 μg/ml of DEX (Group D) for postoperative intravenous (IV) PCA. Postoperative pain relief, cumulative PCA requirements, inflammatory marker levels, delirium and recovery were assessed. Results: A joint DEX and sufentanil regimen significantly reduced the area under the curve of numerical rating scores for pain at rest (NRSR) and coughing (NRSC) at 1-48 h postoperatively (P = 0.000) that were associated with lower PCA-delivered cumulative sufentanil consumption and less PCA frequency until 48 h postoperatively (P < 0.05 and P < 0.0001, respectively). The simultaneous administration of DEX and sufentanil significantly reduced plasma IL-6 and TNF-α concentrations and increased IL-10 level (P < 0.0001, P = 0.0003 and P = 0.0345, respectively), accompanied by better postoperative delirium categories and health statuses of patients (P = 0.024 and P < 0.05, respectively). There was no hypotension, bradycardia, respiratory depression or oversedation in Group D. Conclusion: Patients receiving DEX in addition to IV PCA sufentanil for TLE exhibited better postoperative analgesia, fewer inflammatory responses and lower postoperative delirium categories and better health statuses. [ABSTRACT FROM AUTHOR]