GOA-optimized deep learning for soybean yield estimation using multi-source remote sensing data.

Accurately estimating large-area crop yields, especially for soybeans, is essential for addressing global food security challenges. This study introduces a deep learning framework that focuses on precise county-level soybean yield estimation in the United States. It utilizes a wide range of multi-variable remote sensing data. The model used in this study is a state-of-the-art CNN-BiGRU model, which is enhanced by the GOA and a novel attention mechanism (GCBA). This model excels in handling intricate time series and diverse remote sensing datasets. Compared to five leading machine learning and deep learning models, our GCBA model demonstrates superior performance, particularly in the 2019 and 2020 evaluations, achieving remarkable R2, RMSE, MAE and MAPE values. This sets a new benchmark in yield estimation accuracy. Importantly, the study highlights the significance of integrating multi-source remote sensing data. It reveals that synthesizing information from various sensors and incorporating photosynthesis-related parameters significantly enhances yield estimation precision. These advancements not only provide transformative insights for precision agricultural management but also establish a solid scientific foundation for informed decision-making in global agricultural production and food security.

CD4+CD25+ regulatory T cells ex vivo generated from autologous naïve CD4+ T cells suppress EAE progression.

CD4+CD25+ regulatory T cells (Tregs) play an important role in maintaining immune homeostasis in multiple sclerosis (MS). Hence, we aimed to explore the therapeutic efficacy and safety of adoptive cell therapy (ACT) utilizing induced antigen-specific Tregs in an animal model of MS, that is, in an experimental autoimmune encephalomyelitis (EAE) model. B cells from EAE model that were activated with soluble CD40L were used as antigen-presenting cells (APCs) to induce the differentiation of antigen-specific Tregs from naïve CD4 precursors, and then, a stepwise isolation of CD4+CD25highCD127low Tregs was performed using a flow sorter. All EAE mice were divided into Treg-treated group (2 × 104 cells in 0.2 mL per mouse, n = 14) and sham-treated group (0.2 mL normal saline (NS), n = 20), which were observed daily for clinical assessment, and for abnormal appearance for 6 weeks. Afterward, histological analysis, immunofluorescence and real-time PCR were performed. Compared to sham-treated mice, Treg-treated mice exhibited a significant decrease in disease severity scores and reduced inflammatory infiltration and demyelination in the spinal cord. Additionally, Tregs-treated mice demonstrated higher CCN3 protein and mRNA levels than sham-treated mice. The results of this preclinical study further support the therapeutic potential of this ACT approach in the treatment of MS.

Nondestructive detection of nutritional parameters of pork based on NIR hyperspectral imaging technique.

Nondestructive detection of the nutritional parameters of pork is of great importance. This study aimed to investigate the feasibility of applying hyperspectral image technology to detect the nutrient content and distribution of pork nondestructively. Hyperspectral cubes of 100 pork samples were collected using a line-scan hyperspectral system, the effects of different preprocessing methods on the modeling effects were compared and analyzed, the feature wavelengths of fat and protein were extracted, and the full-wavelength model was optimized using the regressor chains (RC) algorithm. Finally, pork's fat, protein, and energy value distributions were visualized using the best prediction model. The results showed that standard normal variate was more effective than other preprocessing methods, the feature wavelengths extracted by the competitive adaptive reweighted sampling algorithm had better prediction performance, and the protein model prediction performance was optimized after using the RC algorithm. The best prediction models were developed, with the correlation coefficient of prediction (RP) = 0.929, the root mean square error in prediction (RMSEP) = 0.699% and residual prediction deviation (RPD) = 2.669 for fat, and RP = 0.934, RMSEP = 0.603% and RPD = 2.586 for protein. The pseudo-color maps were helpful for the analysis of nutrient distribution in pork. Hyperspectral image technology can be a fast, nondestructive, and accurate tool for quantifying the composition and assessing the distribution of nutrients in pork.

Characterization of antigen-specific CD8+ memory T cell subsets in peripheral blood of patients with multiple sclerosis.

Background: Increasing evidence indicates the importance of CD8+ T cells in autoimmune attack against CNS myelin and axon in multiple sclerosis (MS). Previous research has also discovered that myelin-reactive T cells have memory phenotype functions in MS patients. However, limited evidence is available regarding the role of CD8+ memory T cell subsets in MS. This study aimed to explore potential antigen-specific memory T cell-related biomarkers and their association with disease activity. Methods: The myelin oligodendrocyte glycoprotein (MOG)-specific CD8+ memory T cell subsets and their related cytokines (perforin, granzyme B, interferon (IFN)-γ) and negative co-stimulatory molecules (programmed cell death protein 1 (PD-1), T- cell Ig and mucin domain 3 (Tim-3)) were analyzed by flow cytometry and real-time PCR in peripheral blood of patients with relapsing-remitting MS. Results: We found that MS patients had elevated frequency of MOG-specific CD8+ T cells, MOG-specific central memory T cells (TCM), MOG-specific CD8+ effector memory T cells (TEM), and MOG-specific CD8+ terminally differentiated cells (TEMRA); elevated granzyme B expression on MOG-specific CD8+ TCM; and, on MOG-specific CD8+ TEM, elevated granzyme B and reduced PD-1 expression. The Expanded Disability Status Scale score (EDSS) in MS patients was correlated with the frequency of MOG-specific CD8+ TCM, granzyme B expression in CD8+ TCM, and granzyme B and perforin expression on CD8+ TEM, but with reduced PD-1 expression on CD8+ TEM. Conclusion: The dysregulation of antigen-specific CD8+ memory T cell subsets, along with the abnormal expression of their related cytokines and negative co-stimulatory molecules, may reflect an excessive or persistent inflammatory response induced during early stages of the illness. Our findings strongly suggest positive regulatory roles for memory T cell populations in MS pathogenesis, probably via molecular mimicry to trigger or promote abnormal peripheral immune responses. Furthermore, downregulated PD-1 expression may stimulate a positive feedback effect, promoting MS-related inflammatory responses via the interaction of PD-1 ligands. Therefore, these parameters are potential serological biomarkers for predicting disease development in MS.

A Bayesian network-based approach for identifying risk factors and predicting ischemic stroke in infective endocarditis patients.

Objective: This study aimed to seek the risk factors and develop a predictive model for ischemic stroke (IS) in patients with infective endocarditis (IE) utilizing a Bayesian network (BN) approach. Methods: Data were obtained from the electronic medical records of all adult patients at three hospitals between 1 January 2018, and 31 December 2022. Two predictive models, logistic regression and BN, were used. Patients were randomly assigned to the training and test sets in a 7:3 ratio. We established a BN model with the training dataset and validated it with the testing dataset. The Bayesian network model was built by using the Tabu search algorithm. The areas under the receiver operating characteristic curve (AUCs), calibration curve, and decision curve were used to evaluate the prediction performance between the BN and logistic models. Results: A total of 542 patients [mean (SD) age, 49.6 (15.3) years; 137 (25.3%) female] were enrolled, including 151 (27.9%) with IS and 391 (72.1%) without IS. Hyperlipidemia, hypertension, age, vegetation size (>10 mm), S. aureus infection, and early prosthetic valve IE were closely correlated with IS. The BN models outperformed the logistic regression in training and testing sets, with accuracies of 76.06% and 74.1%, AUC of 0.744 and 0.703, sensitivities of 25.93% and 20.93%, and specificities of 96.27% and 90.24%, respectively. Conclusion: The BN model is more efficient than the logistic regression model. Therefore, BN models may be suitable for the early diagnosis and prevention of IS in IE patients.

An Intelligent Detector for Sensing Pork Freshness In Situ Based on a Multispectral Technique.

Fresh pork is prone to spoilage during storage, transportation, and sale, resulting in reduced freshness. The total viable count (TVC) and total volatile basic nitrogen (TVB-N) content are key indicators for evaluating the freshness of fresh pork, and when they reach unacceptable limits, this seriously threatens dietary safety. To realize the on-site, low-cost, rapid, and non-destructive testing and evaluation of fresh pork freshness, a miniaturized detector was developed based on a cost-effective multi-channel spectral sensor. The partial least squares discriminant analysis (PLS-DA) model was used to distinguish fresh meat from deteriorated meat. The detector consists of microcontroller, light source, multi-channel spectral sensor, heat-dissipation modules, display system, and battery. In this study, the multispectral data of pork samples with different freshness levels were collected by the developed detector, and its ability to distinguish pork freshness was based on different spectral shape features (SSF) (spectral ratio (SR), spectral difference (SD), and normalized spectral intensity difference (NSID)) were compared. The experimental results show that compared with the original multispectral modeling, the performance of the model based on spectral shape features is significantly improved. The model established by optimizing the spectral shape feature variables has the best performance, and the discrimination accuracy of its prediction set is 91.67%. In addition, the validation accuracy of the optimal model was 86.67%, and its sensitivity and variability were 87.50% and 85.71%, respectively. The results show that the detector developed in this study is cost-effective, compact in its structure, stable in its performance, and suitable for the on-site digital rapid non-destructive testing of freshness during the storage, transportation, and sale of fresh pork.

Ultrathin, reflective light-field imaging film realized by self-releasing UV-curable nanoimprinting lithography.

Light-field imaging has emerged as a technology allowing the capture of richer visual information from the world. Ultrathin, reflective light-field imaging film is fabricated by using self-releasing ultraviolet (UV)-curable nanoimprinting lithography. The plenoptic function is built to generate the dense reflective light field in a two-dimension plane in which the occlusion perception can be seamlessly incorporated in the recording process. A self-releasing nanoimprinting technique is developed to realize the imaging film with a thickness of 25 µm and a full field of view (FOV). The results pave the way toward developing high-performance light-field imaging device that can be used as a visual security feature or in virtual/augmented reality and computer vision applications, etc.

Holographic near-eye display based on complex amplitude modulation with band-limited zone plates.

A holographic near-eye display (NED) system based on complex amplitude modulation (CAM) with band-limited zone plates is proposed. The whole system mainly consists of a phase-only spatial light modulator (SLM), an Abbe-Porter filter system, an eyepiece, and an image combiner. The point source method based on band limited zone plates is used to accurately control the bandwidth of the target complex amplitude. The effects of intensity modulation coefficient γ in the frequency-filtering method on the intensity and the quality of reconstructed images are analyzed, which provide a judgment basis for selecting the appropriate value of γ. We also derive the expressions of the field of view (FOV) and exit pupil of the NED system. Since the holographic image is magnified in two steps in this system, the large FOV can be obtained. The optical experimental results show that the proposed system can provide a dynamic holographic three-dimensional (3D) augmented reality (AR) display with a 23.5° horizontal FOV.