EResNet-SVM: an overfitting-relieved deep learning model for recognition of plant diseases and pests.

BACKGROUND: The accurate recognition and early warning for plant diseases and pests are a prerequisite of intelligent prevention and control for plant diseases and pests. As a result of the phenotype similarity of the hazarded plant after plant diseases and pests occur, as well as the interference of the external environment, traditional deep learning models often face the overfitting problem in phenotype recognition of plant diseases and pests, which leads to not only the slow convergence speed of the network, but also low recognition accuracy. RESULTS: Motivated by the above problems, the present study proposes a deep learning model EResNet-support vector machine (SVM) to alleviate the overfitting for the recognition and classification of plant diseases and pests. First, the feature extraction capability of the model is improved by increasing feature extraction layers in the convolutional neural network. Second, the order-reduced modules are embedded and a sparsely activated function is introduced to reduce model complexity and alleviate overfitting. Finally, a classifier fused by SVM and fully connected layers are introduced to transforms the original non-linear classification problem into a linear classification problem in high-dimensional space to further alleviate the overfitting and improve the recognition accuracy of plant diseases and pests. The ablation experiments further demonstrate that the fused structure can effectively alleviate the overfitting and improve the recognition accuracy. The experimental recognition results for typical plant diseases and pests show that the proposed EResNet-SVM model has 99.30% test accuracy for eight conditions (seven plant diseases and one normal), which is 5.90% higher than the original ResNet18. Compared with the classic AlexNet, GoogLeNet, Xception, SqueezeNet and DenseNet201 models, the accuracy of the EResNet-SVM model has improved by 5.10%, 7%, 8.10%, 6.20% and 1.90%, respectively. The testing accuracy of the EResNet-SVM model for 6 insect pests is 100%, which is 3.90% higher than that of the original ResNet18 model. CONCLUSION: This research provides not only useful references for alleviating the overfitting problem in deep learning, but also a theoretical and technical support for the intelligent detection and control of plant diseases and pests. © 2024 Society of Chemical Industry.

Metal-Polyphenol-Network Coated Prussian Blue Nanoparticles for Synergistic Ferroptosis and Apoptosis via Triggered GPX4 Inhibition and Concurrent In Situ Bleomycin Toxification.

Given that traditional anticancer therapies fail to significantly improve the prognoses of triple negative breast cancer (TNBC), new modalities with high efficiency are urgently needed. Herein, by mixing the metal-phenolic network formed by tannic acid (TA), bleomycin (BLM), and Fe3+ with glutathione peroxidase 4 (GPX4) inhibitor (ML210) loaded hollow mesoporous Prussian blue (HMPB) nanocubes, the HMPB/ML210@TA-BLM-Fe3+ (HMTBF) nanocomplex is prepared to favor the ferroptosis/apoptosis synergism in TNBC. During the intracellular degradation, Fe3+ /Fe2+ conversion mediated by TA can initiate the Fenton reaction to drastically upregulate the reactive oxygen species level in cells, subsequently induce the accumulation of lipid peroxidation, and thereby cause ferroptotic cell death; meanwhile, the released ML210 efficiently represses the activity of GPX4 to activate ferroptosis pathway. Besides, the chelation of Fe2+ with BLM leads to in situ BLM toxification at tumor site, then triggers an effective apoptosis to synergize with ferroptosis for tumor therapy. As a result, the superior in vivo antitumor efficacy of HMTBF is corroborated in a 4T1 tumor-bearing mice model regarding tumor growth suppression, indicating that the nanoformulations can serve as efficient ferroptosis and apoptosis inducers for use in combinatorial TNBC therapy.

Synthetic Porcine Hepcidin Exhibits Different Roles in Escherichia coli and Salmonella Infections.

Hepcidin, an antimicrobial peptide, was discovered to integrate diverse signals from iron status and an infection threat and orchestrate a series of host-protective responses. Several studies have investigated the antimicrobial role of hepcidin, but the results have been controversial. Here, we aimed to examine the role of hepcidin in bacterial adherence and invasion in vitro We found that porcine hepcidin could decrease the amount of the extracellular pathogen enterotoxigenic Escherichia coli (ETEC) K88 that adhered to cells because it caused the aggregation of the bacteria. However, addition of hepcidin to macrophages infected with the intracellular pathogen Salmonella enterica serovar Typhimurium enhanced the intracellular growth of the pathogen through the degradation of ferroportin, an iron export protein, and then the sequestration of intracellular iron. Intracellular iron was unavailable by use of the iron chelator deferiprone (DFO), which reduced intracellular bacterial growth. These results demonstrate that hepcidin exhibits different functions in extracellular and intracellular bacterial infections, which suggests that different defense strategies should be taken to prevent bacterial infection.

Porcine ß-defensin 2 attenuates inflammation and mucosal lesions in dextran sodium sulfate-induced colitis.

Intestinal permeability plays a critical role in the etiopathogenesis of ulcerative colitis. Defensins, including porcine ß-defensin (pBD)2, are crucial antimicrobial peptides for gut protection owing to their antibacterial and immunomodulatory activities. The purpose of this study was to investigate the protective effects of pBD2 on mucosal injury and the disruption of the epithelial barrier during the pathological process of dextran sodium sulfate (DSS)-induced colitis. The effects and mechanism of pBD2 were evaluated both using a DSS-induced C57BL/6 mouse model and, in vitro, using Caco-2 and RAW264.7 cells. DSS-induced colitis was characterized by higher disease activity index, shortened colon length, elevated activities of myeloperoxidase and eosinophil peroxidase, histologic evidence of inflammation, and increased expression levels of TNF-α, IL-6, and IL-8. pBD2 increased the expression of zonula occludens-1, zonula occludens-2, claudin-1, mucin-1, and mucin-2 mRNA and proteins, and it decreased permeability to FITC-D, as well as apoptosis, in DSS-treated mice. pBD2 also decreased inflammatory infiltrates of the colon epithelium. In Caco-2 cells, pBD2 increased transepithelial electrical resistance and mucin mRNA expression, and it decreased the permeability of FITC-D while preserving the structural integrity of the tight junctions. The effects of pBD2 appeared to be through upregulation of the expression of genes associated with tight junctions and mucins, and by suppressing DSS-induced increases in inflammation, inducible NO synthase, cyclooxygenase-2, and apoptosis. These results show that pBD2 improves DSS-induced changes in mucosal lesions and paracellular permeability, possibly by affecting the activation of NF-κB signaling. The present study demonstrates that intrarectal administration of pBD2 may be a novel preventive option for ulcerative colitis.

Label-free electrochemiluminescence detection of specific-sequence DNA based on DNA probes capped ion nanochannels.

As one of the powerful molecular recognition elements, the functional DNA probes have been successfully utilized to construct various biosensors. However, the accurate readout of the recognition event of DNA probe binding to the specific target by label-free means is still challenging. Here, a simple and label-free electrochemiluminescence (ECL) method for sensing the recognition event of DNA probe to sequence-specific DNA is developed. Oxalate is used as an ECL co-reactant and p53 tumor suppressor gene as a model of target analyte. In the ECL sensing platform, the nanochannel structural film, which contains silica-sol, chitosan and Ru(bpy)3(2+), is prepared by an electrochemical deposition method. Then, DNA probes are attached onto the surface of the nanochannel-based composite film electrode based on the stronger interaction between DNA probes and chitosan embedded in the ECL composite film. These nanochannels were capped by the DNA probes. As a result, the mass-transfer channel between the Ru(bpy)3(2+) embedded in the nanochannel-based composite film and the ECL co-reactant in the bulk solution was greatly blocked and a weak ECL signal was observed. Conversely, in the presence of target sequences, the hybridizing reaction of targets with DNA probes could result in the escape of the DNA probes from the composite film due to the rigid structure of the duplex DNA. Thus, these nanochannels were uncapped and a stronger ECL signal was detected. Our results show that this ECL method could effectively discriminate complementary from single-base mismatch DNA sequences. Under the optimal conditions, the linear range for target DNA was from 1.0 × 10(-11) to 1.0 × 10(-9) mol L(-1) with a detect limit of 2.7 × 10(-12) mol L(-1). This work demonstrates that porous structures on the silica-chitosan composite film can provide a label-free and general platform to measure the change of DNA configuration.

A multicriteria decision making approach based on fuzzy theory and credibility mechanism for logistics center location selection.

As a hot topic in supply chain management, fuzzy method has been widely used in logistics center location selection to improve the reliability and suitability of the logistics center location selection with respect to the impacts of both qualitative and quantitative factors. However, it does not consider the consistency and the historical assessments accuracy of experts in predecisions. So this paper proposes a multicriteria decision making model based on credibility of decision makers by introducing priority of consistency and historical assessments accuracy mechanism into fuzzy multicriteria decision making approach. In this way, only decision makers who pass the credibility check are qualified to perform the further assessment. Finally, a practical example is analyzed to illustrate how to use the model. The result shows that the fuzzy multicriteria decision making model based on credibility mechanism can improve the reliability and suitability of site selection for the logistics center.

TiO2/Ag-based photodeposited catalyst boosted electrochemiluminescence of ninhydrin-hydrogen peroxide system for ultrasensitive sensing of copper (II).

Photodeposited TiO2/Ag nanocomposites were generally used to be a friendly catalyst for degrading organic contaminant in environmental field. However, electrochemiluminescence (ECL) sensing analysis based on photocatalysts remains a significant challenge. Herein, polyvinylimide (PEI)-TiO2/Ag nanocomposites (PEI-TiO2/AgNCPs) film with reduced graphene oxide(r-GO) was constructed as a sensing interface for copper(II) ECL detection. TiO2/Ag nanocomposites was prepared by reversed phase microemulsion method and photodeposition technique. Moreover, it was discovered that a small amount of Cu2+ could obviously boost the ECL signal of ninhydrin-hydrogen peroxide system. Signal amplification was achieved by using the synergistic effect between r-GO and TiO2/Ag nanocomposites, and the efficiently concentrated effect of PEI to Cu2+. Furthermore, the investigation showed that ECL mechanism of ninhydrin-hydrogen peroxide system was attributed to the generated hydroxyl radical and superoxide anion during the several type of reactions. Thus for the first time, an ultrasensitive ECL approach for detecting Cu2+ could be performed using ninhydrin as an ECL signal probe and hydrogen peroxide as a co-reaction reagent. Under the suitable circumstances, the proposed method showed an excellent linear relationship in the concentration range of Cu2+ from 1.0 fM to 5.0 nM. Detection limit was estimated to be as low as 0.26 fM. The sensing interface expanded the application of photodeposited TiO2/Ag nanocomposites in ultrasensitive ECL detection. It has potential applications in other components and biological analysis.

Class-dependent and cross-modal memory network considering sentimental features for video-based captioning.

The video-based commonsense captioning task aims to add multiple commonsense descriptions to video captions to understand video content better. This paper aims to consider the importance of cross-modal mapping. We propose a combined framework called Class-dependent and Cross-modal Memory Network considering SENtimental features (CCMN-SEN) for Video-based Captioning to enhance commonsense caption generation. Firstly, we develop class-dependent memory for recording the alignment between video features and text. It only allows cross-modal interactions and generation on cross-modal matrices that share the same labels. Then, to understand the sentiments conveyed in the videos and generate accurate captions, we add sentiment features to facilitate commonsense caption generation. Experiment results demonstrate that our proposed CCMN-SEN significantly outperforms the state-of-the-art methods. These results have practical significance for understanding video content better.

Food safety in health: a model of extraction for food contaminants.

Contaminants are the critical targets of food safety supervision and risk assessment. In existing research, food safety knowledge graphs are used to improve the efficiency of supervision since they supply the relationship between contaminants and foods. Entity relationship extraction is one of the crucial technologies of knowledge graph construction. However, this technology still faces the issue of single entity overlap. This means that a head entity in a text description may have multiple corresponding tail entities with different relationships. To address this issue, this work proposes a pipeline model with neural networks for multiple relations enhanced entity pairs extraction. The proposed model can predict the correct entity pairs in terms of specific relations by introducing the semantic interaction between relation identification and entity extraction. We conducted various experiments on our own dataset FC and on the open public available data set DuIE2.0. The results of experiments show our model reaches the state-of-the-art, and the case study indicates our model can correctly extract entity-relationship triplets to release the problem of single entity overlap.

Evidence for cell apoptosis suppressing white spot syndrome virus replication in Procambarus clarkii at high temperature.

In shrimp, higher water temperatures (~32°C) can suppress the ability of white spot syndrome virus (WSSV) to replicate and cause mortality, but the mechanisms remain unclear. To investigate whether cell apoptosis might be involved, a Tdt-mediated dUTP nick-end label (TUNEL) method was used to assess levels of chromosomal DNA fragmentation in hepatopancreas and gill cells of Procambarus clarkii crayfish infected with WSSV and maintained at either 32 ± 1°C or 24 ± 1°C. Based on relative cell numbers with yellow-green colored TUNEL-positive nuclei, the apoptotic index was elevated in WSSV-infected crayfish maintained at 32°C. In gill tissue sections examined by transmission electron microscope, cells with nuclei displaying apoptotic bodies or marginated, condensed and fragmented chromatin without concurrent cell cytoplasm damage were also more prevalent. Flow cytometry sorting of annexin-stained cells showed apoptosis to be most prevalent in granular haemocytes, and assays for caspase-3 activity showed it to be most elevated in hepatopancreas tissue. Despite these indicators of cell apoptosis but consistent with WSSV replication being restricted at elevated temperatures, no increases in transcription of the viral anti-apoptosis genes ORF390 and ORF222 were detected by RT-PCR in shrimp maintained at 32°C, possibly due to the elevated levels of cellular apoptosis.