Search

When using the extended Kalman filter (EKF) to estimate the state of charge (SOC) of an electric vehicle power battery, the change of system noise and model parameters may lead to a reduction in estimation accuracy, due to variable operating conditions, battery aging, and other factors. The NCR18650B ternary lithium-ion battery is selected, and the second-order RC model is established with identified parameters. Then, by using EKF as the main body with a fixed measurement noise covariance and adaptively adjusting process noise covariance based on the maximum likelihood estimation criterion, an adaptive extended Kalman filter is built to estimate the SOC of the battery. Simultaneously, a Kalman filter is used to estimate the ohmic resistance in real time. Thus, an adaptive dual extended Kalman filter (ADEKF) algorithm is formed. Finally, algorithm verifications are performed with testing data and public datasets. The ADEKF proposed is used to estimate the SOC of five groups of aged lithium batteries under three operating conditions, which are constant current, dynamic stress test, and Beijing dynamic stress test, and compared with that of EKF and other algorithms. The results show that compared with EKF, the average absolute error of the estimation results of ADEKF for different aged batteries under three operating conditions decreases by 1.868 percentage points, 2.296 percentage points, and 2.534 percentage points, respectively, which proves that ADEKF algorithm can effectively improve the SOC estimation accuracy under multiple operating conditions, battery aging and the combination of the two factors.

【Objective】 Mulched drip irrigation is a widely used technique in Northwestern China. This paper investigates the combined effects of mulched drip irrigation and nitrogen fertilization on the growth and yield of summer maize. 【Method】 The experiment was conducted in a maize field in Southern Xinjiang and included a mulched drip irrigation (MD) treatment and a conventional drip irrigation treatment without mulching (LD). Each irrigation treatment had five nitrogen applications: 0 kg/hm2 (N0), 224.6 kg/hm2 (N1), 278.4 kg/hm2 (N2), 368.9 kg/hm2 (N3), and 464.0 kg/hm2 (N4). The control was flood irrigation with a nitrogen application of 278.4 kg/hm2. For each treatment, we measured growth traits and grain yield of the maize. 【Result】 ① With increasing nitrogen application, the SPAD value, leaf area index (LAI), and aboveground dry biomass initially increased before plateauing; these metrics were 18.67%, 10.39%, and 10.41% higher in the MD treatment compared to the LD treatment, respectively. ② The relationship between dry matter accumulation and nitrogen application fit a logistic model, with the accumulation plateauing when the nitrogen application was 368.9 kg/hm2. Compared to LD, MD prolonged the period of rapid growth by 7-18 days and delayed its onset by 1-6 days. ③ The yield in the MD treatment was 1 027.52-2 023.04 kg/hm2 higher than that in LD; nitrogen application increased grain yield by 29.41%-84.46%. The combination of MD and nitrogen application increased yield by 52.17%-106.61%. Nonlinear regression indicated an asymptotic increase in maize yield with nitrogen application. The grain yield in MD and LD plateaued to 362.75 kg/hm2 and 364.14 kg/hm2, when their associated nitrogen application exceeded 267.69 kg/hm2 and 274.11 kg/hm2, respectively. ④ In both irrigation treatments, applying 278.4 kg/hm2 of nitrogen fertilizer produced yields comparable to the control, while saving 256.5 mm of water. 【Conclusion】 Mulched drip irrigation combined with a nitrogen application of 278.4 kg/hm2 is optimal for promoting the growth and yield of summer maize in Southern Xinjiang.

For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient's 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

(1) Background: Gliomas are the most common primary brain neoplasms accounting for roughly 40−50% of all malignant primary central nervous system tumors. We aim to develop a deep learning-based framework for automated segmentation and prediction of biomarkers and prognosis in patients with gliomas. (2) Methods: In this retrospective two center study, patients were included if they (1) had a diagnosis of glioma with known surgical histopathology and (2) had preoperative MRI with FLAIR sequence. The entire tumor volume including FLAIR hyperintense infiltrative component and necrotic and cystic components was segmented. Deep learning-based U-Net framework was developed based on symmetric architecture from the 512 × 512 segmented maps from FLAIR as the ground truth mask. (3) Results: The final cohort consisted of 208 patients with mean ± standard deviation of age (years) of 56 ± 15 with M/F of 130/78. DSC of the generated mask was 0.93. Prediction for IDH-1 and MGMT status had a performance of AUC 0.88 and 0.62, respectively. Survival prediction of

The food nutrition and health industry is an important component of the Healthy China strategy in the context of dual circulation. This study summarized the development trend of the industry and analyzed the challenges faced by the industry under the new circumstance. According to the overall strategic layout and planning of China, breakthrough paths were proposed, including establishing a food technology system based on Chinese resident health information in the context of domestic circulation, promoting domestic and international circulation through industrial diversification, and improving global influence of the industry by exploiting both the domestic and international markets and resources. Furthermore, we proposed several suggestions. China should focus on the input of innovative resources in the food nutrition and health field to prompt high-quality achievements; strength policy support and guidance to promote the international competitiveness of enterprises; improve the industry-university-research collaboration system to promote the transformation of achievements; strengthen talent training to provide professional support; optimize the industry supervision system to create a healthy market environment; and promote education and publicity regarding food nutrition and health to improve citizens’ health literacy.

Driven by the rapid advancement of the economy and urbanization, substantial alterations in land use patterns have taken place, exerting certain impacts on groundwater. This study examines the land use changes in Zhengzhou's central urban area from 2000 to 2020 and projects these changes to 2030 using the PLUS model. It optimizes the groundwater vulnerability assessment methodology from two key aspects, namely the evaluation indicators and the associated weights, to enhance its suitability for the study area. This study employs a multi-indicator and dual-method validation approach to verify the groundwater vulnerability assessment results, ensuring the accuracy and reliability of the findings. Urban, rural, and construction lands increased significantly, while paddy fields, drylands, and forests decreased. The 2030 prediction suggests a continuation of these trends. The groundwater vulnerability in 2020 correlated strongly with the groundwater quality, particularly with chloride ions (AUC = 0.804, Spearman's rho = 0.83). The 2030 projection indicates a minimal change in the vulnerability distribution but anticipates an increase in high- and very-high-vulnerability areas, particularly in regions with land use changes, potentially increasing the groundwater contamination risk. This suggests the need for targeted groundwater protection policies to mitigate contamination risks. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical‐level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state‐of‐the‐art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self‐supervised learning, generative models, few‐shot learning, and semi‐supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field—including emerging algorithms, such as contrastive language‐image pretraining, and potential combinations across the methods discussed—that can further increase the efficacy of image segmentation with limited labels. [ABSTRACT FROM AUTHOR]