Optimization of Enzyme-assisted Extraction Technology for Tartary Buckwheat Shell Procyanidins with Response Surface Methodology

This study was conducted to investigate the effects of cellulase dosage, enzymolysis time, pH and enzymolysis temperature on procyanidin extraction rate by single factor experiment, with tartary buckwheat shell as an experimental material.Main process parameters were optimized to obtain a regression model by response surface methodology. The results of variance analysis indicated that the regression model reflected the relationship between buckwheat shell procyanidin extraction rate with enzyme dosage, enzymolysis time, pH and enzymolysis temperature; and the optimal process parameters were enzyme dosage of 6.5 mg/g, enzymolysis time of 1.5 h, pH at 4.7 and enzymolysis temperature at 46 ℃. Three parallel experiments were conducted under these process parameters. In practice, the highest procyanidin extraction rate was 6.78 g/100 g. The relative error between the predicted value of regression model and the actual value was 1.3%. The regression equation fitted the real situation better.

Technical Study on Extraction of Procyanidins in Lycium ruthenicum Murr. Using Sub-critical Fluid 1,1,1,2-Tetrafluoroethane( R134a)and Content Determination from Different Producing Areas

[Objectives] To study the optimal conditions for extracting procyanidins fromLycium ruthenicum Murr. with sub-critical fluid R134 a( 1,1,1,2-tetrafluoroethane) in 1 L extraction kettle. [Methods]Taking the extraction rate of procyanidins as an indicator,the influence of pressure,temperature,and extraction time on extraction rate of procyanidins fromL. Ruthenicum Murr. was studied by single factor experimental methods and orthogonal array design. [Results]The order of factors affecting extraction rate of procyanidins was extraction temperature > extraction pressure > extraction time. The optimum extraction conditions were as follows: the extraction rate of procyanidins fromL. ruthenicum Murr. was the highest with extraction pressure of 1. 2 MPa,extraction temperature of 50℃ and extraction time of 90 min. The content of procyanidins in L. ruthenicum Murr. from different producing areas was determined by vanillin-HCl method under the optimal conditions. [Conclusions] The method has the advantages of easy operation,good selectivity,low extraction temperature and high extraction efficiency,which is suitable for extraction of procyanidins in L. ruthenicum Murr.

Effect of enzymatic extraction conditions on the yield and the polymerization degree of procyanidins

Grape seeds are rich sources of procyanidin(PCs)known for potential health benefi ts.In this study,PCs were extracted from defatted grape seeds by enzymatic method in which pectinase and cellulase were used.The enzyme extraction process was further optimized by single factor experiment and response surface methodology.The optimal conditions were as follows:ethanol concentration of 70%,extraction time of 70 min,extraction temperature of 35℃,liquid/solid ratio of 103:1(mL/g),pectinase/cellulase ratio of 1:1,enzyme/solid ratio of 1:314 w/w.Under the above conditions,the extraction yields and mean degree of polymerisation(mDP)of PCs reached 47.18 mg/g dry material weight and 11.2,respectively.Compared with other extraction methods,enzyme extraction can obtain PCs with higher yield and lower mDP.According to the antioxidant activity test,PCs extracts with lower mDP showed better ability to clear 1,1-Diphenyl-2-picrylhydrazyl radical(DPPH).Enzymatic extraction was an effi cient method to obtain oligomeric procyanidin which has stronger antioxidant activity.

Effects of conductive agent type on lithium extraction from salt lake brine with LiFePO_(4) electrodes

Electrochemical lithium extraction from salt lakes is an effective strategy for obtaining lithium at a low cost.Nevertheless,the elevated Mg:Li ratio and the presence of numerous coexisting ions in salt lake brines give rise to challenges,such as prolonged lithium extraction periods,diminished lithium extraction efficiency,and considerable environmental pollution.In this work,Li FePO4(LFP)served as the electrode material for electrochemical lithium extraction.The conductive network in the LFP electrode was optimized by adjusting the type of conductive agent.This approach resulted in high lithium extraction efficiency and extended cycle life.When the single conductive agent of acetylene black(AB)or multiwalled carbon nanotubes(MWCNTs)was replaced with the mixed conductive agent of AB/MWCNTs,the average diffusion coefficient of Li+in the electrode increased from 2.35×10^(-9)or 1.77×10^(-9)to 4.21×10^(-9)cm^(2)·s^(-1).At the current density of 20 mA·g^(-1),the average lithium extraction capacity per gram of LFP electrode increased from 30.36 mg with the single conductive agent(AB)to 35.62 mg with the mixed conductive agent(AB/MWCNTs).When the mixed conductive agent was used,the capacity retention of the electrode after 30 cycles reached 82.9%,which was considerably higher than the capacity retention of 65.8%obtained when the single AB was utilized.Meanwhile,the electrode with mixed conductive agent of AB/MWCNTs provided good cycling performance.When the conductive agent content decreased or the loading capacity increased,the electrode containing the mixed conductive agent continued to show excellent electrochemical performance.Furthermore,a self-designed,highly efficient,continuous lithium extraction device was constructed.The electrode utilizing the AB/MWCNT mixed conductive agent maintained excellent adsorption capacity and cycling performance in this device.This work provides a new perspective for the electrochemical extraction of lithium using LFP electrodes.

A comprehensive review of existing corpora and methods for creating annotated corpora for event extraction tasks

Purpose:The purpose of this study is to serve as a comprehensive review of the existing annotated corpora.This review study aims to provide information on the existing annotated corpora for event extraction,which are limited but essential for training and improving the existing event extraction algorithms.In addition to the primary goal of this study,it provides guidelines for preparing an annotated corpus and suggests suitable tools for the annotation task.Design/methodology/approach:This study employs an analytical approach to examine available corpus that is suitable for event extraction tasks.It offers an in-depth analysis of existing event extraction corpora and provides systematic guidelines for researchers to develop accurate,high-quality corpora.This ensures the reliability of the created corpus and its suitability for training machine learning algorithms.Findings:Our exploration reveals a scarcity of annotated corpora for event extraction tasks.In particular,the English corpora are mainly focused on the biomedical and general domains.Despite the issue of annotated corpora scarcity,there are several high-quality corpora available and widely used as benchmark datasets.However,access to some of these corpora might be limited owing to closed-access policies or discontinued maintenance after being initially released,rendering them inaccessible owing to broken links.Therefore,this study documents the available corpora for event extraction tasks.Research limitations:Our study focuses only on well-known corpora available in English and Chinese.Nevertheless,this study places a strong emphasis on the English corpora due to its status as a global lingua franca,making it widely understood compared to other languages.Practical implications:We genuinely believe that this study provides valuable knowledge that can serve as a guiding framework for preparing and accurately annotating events from text corpora.It provides comprehensive guidelines for researchers to improve the quality of corpus annotations,especially for event extraction tasks across various domains.Originality/value:This study comprehensively compiled information on the existing annotated corpora for event extraction tasks and provided preparation guidelines.

A Joint Entity Relation Extraction Model Based on Relation Semantic Template Automatically Constructed

The joint entity relation extraction model which integrates the semantic information of relation is favored by relevant researchers because of its effectiveness in solving the overlapping of entities,and the method of defining the semantic template of relation manually is particularly prominent in the extraction effect because it can obtain the deep semantic information of relation.However,this method has some problems,such as relying on expert experience and poor portability.Inspired by the rule-based entity relation extraction method,this paper proposes a joint entity relation extraction model based on a relation semantic template automatically constructed,which is abbreviated as RSTAC.This model refines the extraction rules of relation semantic templates from relation corpus through dependency parsing and realizes the automatic construction of relation semantic templates.Based on the relation semantic template,the process of relation classification and triplet extraction is constrained,and finally,the entity relation triplet is obtained.The experimental results on the three major Chinese datasets of DuIE,SanWen,and FinRE showthat the RSTAC model successfully obtains rich deep semantics of relation,improves the extraction effect of entity relation triples,and the F1 scores are increased by an average of 0.96% compared with classical joint extraction models such as CasRel,TPLinker,and RFBFN.

Feature extraction for machine learning-based intrusion detection in IoT networks

A large number of network security breaches in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems(NIDSs).Consequently,network interruptions and loss of sensitive data have occurred,which led to an active research area for improving NIDS technologies.In an analysis of related works,it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction(FR)and Machine Learning(ML)techniques on NIDS datasets.However,these datasets are different in feature sets,attack types,and network design.Therefore,this paper aims to discover whether these techniques can be generalised across various datasets.Six ML models are utilised:a Deep Feed Forward(DFF),Convolutional Neural Network(CNN),Recurrent Neural Network(RNN),Decision Tree(DT),Logistic Regression(LR),and Naive Bayes(NB).The accuracy of three Feature Extraction(FE)algorithms is detected;Principal Component Analysis(PCA),Auto-encoder(AE),and Linear Discriminant Analysis(LDA),are evaluated using three benchmark datasets:UNSW-NB15,ToN-IoT and CSE-CIC-IDS2018.Although PCA and AE algorithms have been widely used,the determination of their optimal number of extracted dimensions has been overlooked.The results indicate that no clear FE method or ML model can achieve the best scores for all datasets.The optimal number of extracted dimensions has been identified for each dataset,and LDA degrades the performance of the ML models on two datasets.The variance is used to analyse the extracted dimensions of LDA and PCA.Finally,this paper concludes that the choice of datasets significantly alters the performance of the applied techniques.We believe that a universal(benchmark)feature set is needed to facilitate further advancement and progress of research in this field.

Experimental investigation on coal pore-fracture variation and fractal characteristics synergistically affected by solvents for improving clean gas extraction

Chemical solvents instead of pure water being as hydraulic fracturing fluid could effectively increase permeability and improve clean methane extraction efficiency.However,pore-fracture variation features of lean coal synergistically affected by solvents have not been fully understood.Ultrasonic testing,nuclear magnetic resonance analysis,liquid phase mass spectrometry was adopted to comprehensively analyze pore-fracture change characteristics of lean coal treated by combined solvent(NMP and CS_(2)).Meanwhile,quantitative characterization of above changing properties was conducted using geometric fractal theory.Relationship model between permeability,fractal dimension and porosity were established.Results indicate that the end face fractures of coal are well developed after CS2and combined solvent treatments,of which,end face box-counting fractal dimensions range from 1.1227 to 1.4767.Maximum decreases in ultrasonic longitudinal wave velocity of coal affected by NMP,CS_(2)and combined solvent are 2.700%,20.521%,22.454%,respectively.Solvent treatments could lead to increasing amount of both mesopores and macropores.Decrease ratio of fractal dimension Dsis 0.259%–2.159%,while permeability increases ratio of NMR ranges from 0.1904 to 6.4486.Meanwhile,combined solvent could dissolve coal polar and non-polar small molecules and expand flow space.Results could provide reference for solvent selection and parameter optimization of permeability-enhancement technology.

Automatic Extraction Method of 3D Feature Guidelines for Complex Cultural Relic Surfaces Based on Point Cloud

Cultural relics line graphic serves as a crucial form of traditional artifact information documentation,which is a simple and intuitive product with low cost of displaying compared with 3D models.Dimensionality reduction is undoubtedly necessary for line drawings.However,most existing methods for artifact drawing rely on the principles of orthographic projection that always cannot avoid angle occlusion and data overlapping while the surface of cultural relics is complex.Therefore,conformal mapping was introduced as a dimensionality reduction way to compensate for the limitation of orthographic projection.Based on the given criteria for assessing surface complexity,this paper proposed a three-dimensional feature guideline extraction method for complex cultural relic surfaces.A 2D and 3D combined factor that measured the importance of points on describing surface features,vertex weight,was designed.Then the selection threshold for feature guideline extraction was determined based on the differences between vertex weight and shape index distributions.The feasibility and stability were verified through experiments conducted on real cultural relic surface data.Results demonstrated the ability of the method to address the challenges associated with the automatic generation of line drawings for complex surfaces.The extraction method and the obtained results will be useful for line graphic drawing,displaying and propaganda of cultural relics.

Preferentially selective extraction of lithium from spent LiCoO_(2)cathodes by medium-temperature carbon reduction roasting

Lithium recovery from spent lithium-ion batteries(LIBs)have attracted extensive attention due to the skyrocketing price of lithium.The medium-temperature carbon reduction roasting was proposed to preferential selective extraction of lithium from spent Li-CoO_(2)(LCO)cathodes to overcome the incomplete recovery and loss of lithium during the recycling process.The LCO layered structure was destroyed and lithium was completely converted into water-soluble Li2CO_(3)under a suitable temperature to control the reduced state of the cobalt oxide.The Co metal agglomerates generated during medium-temperature carbon reduction roasting were broken by wet grinding and ultrasonic crushing to release the entrained lithium.The results showed that 99.10%of the whole lithium could be recovered as Li2CO_(3)with a purity of 99.55%.This work provided a new perspective on the preferentially selective extraction of lithium from spent lithium batteries.

Oligomeric procyanidins combined with Parabacteroides distasonis ameliorate high-fat diet-induced atherosclerosis by regulating lipid metabolism,inflammation reaction and bile acid metabolism in ApoE^(-/-)mice

Atherosclerosis(AS)is the main pathological basis of cardiovascular diseases.Hence,the prevention and treatment strategies of AS have attracted great research attention.As a potential probiotic,Pararabacteroides distasonis has a positive regulatory effect on lipid metabolism and bile acids(BAs)profile.Oligomeric procyanidins have been confirmed to be conducive to the prevention and treatment of AS,whose antiatherosclerotic effect may be associated with the promotion of gut probiotics.However,it remains unclear whether and how oligomeric procyanidins and P.distasonis combined(PPC)treatment can effectively alleviate high-fat diet(HFD)-induced AS.In this study,PPC treatment was found to significantly decrease atherosclerotic lesion,as well as alleviate the lipid metabolism disorder,inflammation and oxidative stress injury in ApoE^(-/-)mice.Surprisingly,targeted metabolomics demonstrated that PPC intervention altered the BA profile in mice by regulating the ratio of secondary BAs to primary BAs,and increased fecal BAs excretion.Further,quantitative polymerase chain reaction(qPCR)analysis showed that PPC intervention facilitated reverse cholesterol transport by upregulating Srb1 expression;In addition,PPC intervention promoted BA synthesis from cholesterol in liver by upregulating Cyp7a1 expression via suppression of the farnesoid X receptor(FXR)pathway,thus exhibiting a significant serum cholesterol-lowering effect.In summary,PPC attenuated HFD-induced AS in ApoE^(-/-)mice,which provides new insights into the design of novel and efficient anti-atherosclerotic strategies to prevent AS based on probiotics and prebiotics.

Diet with high content of advanced glycation end products induces oxidative stress damage and systemic inflammation in experimental mice: protective effect of peanut skin procyanidins

Non-enzymatic glycation reaction in food can produce diet-derived advanced glycation end products(dAGEs),which have potential health risks.Thus,it is of great significance to find efficient substances to improve the negative effects induced by dAGEs on human health.This study investigated the intervening effects of peanut skin procyanidins(PSP)on the dAGEs-induced oxidative stress and systemic inflammation in experimental mice model.Results showed that the accumulation of AGEs in serum,liver,and kidney was significantly increased after mice were fed dAGEs(P<0.05).The expression of advanced glycation product receptor(RAGE)was also significantly increased in liver and kidney(P<0.05).PSP could not only effectively reduce the accumulation of AGEs in serum,liver and kidney of mice,but also reduce the expression of RAGE in liver and kidney of mice.And the levels of pro-inflammatory cytokines interleukin-6(IL-6),tumor necrosis factor(TNF-α),and IL-1βin serum of mice were significantly decreased(P<0.05),while the levels of antiinflammatory factor IL-10 were increased,and the inflammatory injury in mice was improved.In addition,the levels of superoxide dismutase(SOD),glutathione(GSH),catalase(CAT)in liver and kidney of mice were increased(P<0.05),and the level of malondialdehyde(MDA)was decreased(P<0.05),which enhanced the antioxidant capacity of mice in vivo,and improved the oxidative damage of liver and kidney.Molecular docking technique was used to confirm that the parent compound of procyanidins and its main metabolites,such as 3-hydroxyphenylacetic acid,could interact with RAGE,which might inhibit the activation of nuclear transcription factor(NF-κB),and ultimately reduce oxidative stress and inflammation in mice.

Development of Extraction and Detection Method for a Chemotherapeutic Drug with Phenytoin in Biological Samples

Dexamethasone is classified as a corticosteroid and is commonly used among cancer patients to decrease the amount of swelling around the tumor. Among patients with cancer, in particular brain tumors, seizures can become a daily routine in their everyday lives. To counteract the seizures, an antiepileptic drug such as phenytoin is administered to act as an anticonvulsant. Phenytoin and dexamethasone are frequently administrated concurrently to brain cancer patients. A previous study has shown that phenytoin serum concentration decreases when administrated concurrently with dexamethasone. Thus, it is important to monitor the concentration of these two drugs in biological samples to ensure that the proper dosages are administrated to the patients. This study aims to develop an effective extraction and detection method for dexamethasone and phenytoin. A reverse-phase high-performance liquid chromatography (HPLC) method with UV/Vis detection has been developed to separate phenytoin and dexamethasone at 219 nm and 241 nm respectively from urine samples. The mobile phase consists of a mixture of 0.01 M KH2PO4, acetonitrile, and methanol adjusted to pH 5.6 (48:32:20) and is pumped at a flow rate of 1.0 mL/min. Calibration curves were prepared for phenytoin and dexamethasone (r2 > 0.99). An efficient solid-phase extraction (SPE) method for the extraction of dexamethasone and phenytoin from urine samples was developed with the use of C-18 cartridges. The percent recovery for phenytoin and dexamethasone is 95.4% (RSD = 1.15%) and 81.1% (RSD = 3.56%) respectively.

Feature extraction and learning approaches for cancellable biometrics:A survey

Biometric recognition is a widely used technology for user authentication.In the application of this technology,biometric security and recognition accuracy are two important issues that should be considered.In terms of biometric security,cancellable biometrics is an effective technique for protecting biometric data.Regarding recognition accuracy,feature representation plays a significant role in the performance and reliability of cancellable biometric systems.How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community,especially from researchers of cancellable biometrics.Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance,while the privacy of biometric data is protected.This survey informs the progress,trend and challenges of feature extraction and learning for cancellable biometrics,thus shedding light on the latest developments and future research of this area.

A bulk extraction method to determine the stable isotope ratios of iron,nickel,copper,zinc,and cadmium in seawater using multi-collector inductively coupled plasma mass spectrometry

The oceanic trace metals iron(Fe),nickel(Ni),copper(Cu),zinc(Zn),and cadmium(Cd)are crucial to marine phytoplankton growth and global carbon cycle,and the analysis of their stable isotopes can provide valuable insights into their biogeochemical cycles within the ocean.However,the simultaneous isotopic analysis of multiple elements present in seawater is challenging because of their low concentrations,limited volumes of the test samples,and high salt matrix.In this study,we present the novel method developed for the simultaneous analysis of five isotope systems by 1 L seawater sample.In the developed method,the NOBIAS Chelate-PA1 resin was used to extract metals from seawater,the AG MP-1M anion-exchange resin to purify Cu,Fe,Zn,Cd,and the NOBIAS Chelate-PA1 resin to further extract Ni from the matrix elements.Finally,a multi-collector inductively coupled plasma mass spectroscope(MC-ICPMS)was employed for the isotopic measurements using a doublespike technique or sample-standard bracketing combined with internal normalization.This method exhibited low total procedural blanks(0.04 pg,0.04 pg,0.21 pg,0.15 pg,and 3 pg for Ni,Cu,Fe,Zn,and Cd,respectively)and high extraction efficiencies(100.5%±0.3%,100.2%±0.5%,97.8%±1.4%,99.9%±0.8%,and 100.1%±0.2%for Ni,Cu,Fe,Zn,and Cd,respectively).The external errors and external precisions of this method could be considered negligible.The proposed method was further tested on the seawater samples obtained from the whole vertical profile of a water column during the Chinese GEOTRACES GP09 cruise in the Northwest Pacific,and the results showed good agreement with previous related data.This innovative method will contribute to the advancement of isotope research and enhance our understanding of the marine biogeochemical cycling of Fe,Ni,Cu,Zn,and Cd.

Ten-year observation of corneal densitometry and associated factors following small incision lenticule extraction

●AIM:To investigate the long-term changes of corneal densitometry(CD)and its contributing elements after small incision lenticule extraction(SMILE).●METHODS:Totally 31 eyes of 31 patients with mean spherical equivalent of-6.46±1.50 D and mean age 28.23±7.38y were enrolled.Full-scale examinations were conducted on all patients preoperatively and during followup.Visual acuity,manifest refraction,axial length,corneal thickness,corneal higher-order aberrations,and CD were evaluated.●RESULTS:All surgeries were completed successfully without complications or adverse events.Ten-year safety index was 1.17±0.20 and efficacy 1.04±0.28.CD value of 0–6 mm zones in central layer was statistically significantly lower 10y postoperatively,compared with preoperative values(0–2 mmΔ=-1.62,2–6 mmΔ=-1.24,P<0.01).There were no correlations between CD values and factors evaluated.●CONCLUSION:SMILE is a safe and efficient procedure for myopia on a long-term basis.CD values get lower 10y postoperatively,whose mechanism is to be further discussed.

Online identification and extraction method of regional large-scale adjustable load-aggregation characteristics

This article introduces the concept of load aggregation,which involves a comprehensive analysis of loads to acquire their external characteristics for the purpose of modeling and analyzing power systems.The online identification method is a computer-involved approach for data collection,processing,and system identification,commonly used for adaptive control and prediction.This paper proposes a method for dynamically aggregating large-scale adjustable loads to support high proportions of new energy integration,aiming to study the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction methods.The experiment selected 300 central air conditioners as the research subject and analyzed their regulation characteristics,economic efficiency,and comfort.The experimental results show that as the adjustment time of the air conditioner increases from 5 minutes to 35 minutes,the stable adjustment quantity during the adjustment period decreases from 28.46 to 3.57,indicating that air conditioning loads can be controlled over a long period and have better adjustment effects in the short term.Overall,the experimental results of this paper demonstrate that analyzing the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction algorithms is effective.

Noise‐tolerant matched filter scheme supplemented with neural dynamics algorithm for sea island extraction

Achieving high‐precision extraction of sea islands from high‐resolution satellite remote sensing images is crucial for effective resource development and sustainable management.Unfortunately,achieving such accuracy for sea island extraction presents significant challenges due to the presence of extensive background interference.A more widely applicable noise‐tolerant matched filter(NTMF)scheme is proposed for sea island extraction based on the MF scheme.The NTMF scheme effectively suppresses the background interference,leading to more accurate and robust sea island extraction.To further enhance the accuracy and robustness of the NTMF scheme,a neural dynamics algorithm is supplemented that adds an error integration feedback term to counter noise interference during internal computer operations in practical applications.Several comparative experiments were conducted on various remote sensing images of sea islands under different noisy working conditions to demonstrate the superiority of the proposed neural dynamics algorithm‐assisted NTMF scheme.These experiments confirm the ad-vantages of using the NTMF scheme for sea island extraction with the assistance of neural dynamics algorithm.

Network Configuration Entity Extraction Method Based on Transformer with Multi-Head Attention Mechanism

Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurations.This research paper presents a novel entity extraction method that leverages a combination of active learning and attention mechanisms.Initially,an improved active learning approach is employed to select the most valuable unlabeled samples,which are subsequently submitted for expert labeling.This approach successfully addresses the problems of isolated points and sample redundancy within the network configuration sample set.Then the labeled samples are utilized to train the model for network configuration entity extraction.Furthermore,the multi-head self-attention of the transformer model is enhanced by introducing the Adaptive Weighting method based on the Laplace mixture distribution.This enhancement enables the transformer model to dynamically adapt its focus to words in various positions,displaying exceptional adaptability to abnormal data and further elevating the accuracy of the proposed model.Through comparisons with Random Sampling(RANDOM),Maximum Normalized Log-Probability(MNLP),Least Confidence(LC),Token Entrop(TE),and Entropy Query by Bagging(EQB),the proposed method,Entropy Query by Bagging and Maximum Influence Active Learning(EQBMIAL),achieves comparable performance with only 40% of the samples on both datasets,while other algorithms require 50% of the samples.Furthermore,the entity extraction algorithm with the Adaptive Weighted Multi-head Attention mechanism(AW-MHA)is compared with BILSTM-CRF,Mutil_Attention-Bilstm-Crf,Deep_Neural_Model_NER and BERT_Transformer,achieving precision rates of 75.98% and 98.32% on the two datasets,respectively.Statistical tests demonstrate the statistical significance and effectiveness of the proposed algorithms in this paper.

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.