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.

Highly selective extraction of aromatics from aliphatics by using metal chloride-based ionic liquids

The separation of aromatics from aliphatics is essential for achieving maximum exploitation of oil resources in the petrochemical industry.In this study,a series of metal chloride-based ionic liquids were prepared and their performances in the separation of 1,2,3,4-tetrahydronaphthalene(tetralin)/dodecane and tetralin/decalin systems were studied.Among these ionic liquids,1-ethyl-3-methylimidazolium tetrachloroferrate([EMIM][FeCl_(4)])with the highest selectivity was used as the extractant.Density functional theory calculations showed that[EMIM][FeCl_(4)]interacted more strongly with tetralin than with dodecane and decalin.Energy decomposition analysis of[EMIM][FeCl_(4)]-tetralin indicated that electrostatics and dispersion played essential roles,and induction cannot be neglected.The van der Waals forces was a main effect in[EMIM][FeCl_(4)]-tetralin by independent gradient model analysis.The tetralin distribution coefficient and selectivity were 0.8 and 110,respectively,with 10%(mol)tetralin in the initial tetralin/dodecane system,and 0.67 and 19.5,respectively,with 10%(mol)tetralin in the initial tetralin/decalin system.The selectivity increased with decreasing alkyl chain length of the extractant.The influence of the extraction temperature,extractant dosage,and initial concentrations of the system components on the separation performance were studied.Recycling experiments showed that the regenerated[EMIM][FeCl_(4)]could be used repeatedly.

Insight into the experiment and extraction mechanism for separating carbazole from anthracene oil with quaternary ammonium-based deep eutectic solvents

Carbazole is an irreplaceable basic organic chemical raw material and intermediate in industry.The separation of carbazole from anthracene oil by environmental benign solvents is important but still a challenge in chemical engineering.Deep eutectic solvents (DESs) as a sustainable green separation solvent have been proposed for the separation of carbazole from model anthracene oil.In this research,three quaternary ammonium-based DESs were prepared using ethylene glycol (EG) as hydrogen bond donor and tetrabutylammonium chloride (TBAC),tetrabutylammonium bromide or choline chloride as hydrogen bond acceptors.To explore their extraction performance of carbazole,the conductor-like screening model for real solvents (COSMO-RS) model was used to predict the activity coefficient at infinite dilution (γ^(∞)) of carbazole in DESs,and the result indicated TBAC:EG (1:2) had the stronger extraction ability for carbazole due to the higher capacity at infinite dilution (C^(∞)) value.Then,the separation performance of these three DESs was evaluated by experiments,and the experimental results were in good agreement with the COSMO-RS prediction results.The TBAC:EG (1:2) was determined as the most promising solvent.Additionally,the extraction conditions of TBAC:EG (1:2) were optimized,and the extraction efficiency,distribution coefficient and selectivity of carbazole could reach up to 85.74%,30.18 and 66.10%,respectively.Moreover,the TBAC:EG (1:2) could be recycled by using environmentally friendly water as antisolvent.In addition,the separation performance of TBAC:EG (1:2) was also evaluated by real crude anthracene,the carbazole was obtained with purity and yield of 85.32%,60.27%,respectively.Lastly,the extraction mechanism was elucidated byσ-profiles and interaction energy analysis.Theoretical calculation results showed that the main driving force for the extraction process was the hydrogen bonding ((N–H...Cl) and van der Waals interactions (C–H...O and C–H...π),which corresponding to the blue and green isosurfaces in IGMH analysis.This work presented a novel method for separating carbazole from crude anthracene oil,and will provide an important reference for the separation of other high value-added products from coal tar.

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.

A three-dimensional feature extraction-based method for coal cleat characterization using X-ray μCT and its application to a Bowen Basin coal specimen

Cleats are the dominant micro-fracture network controlling the macro-mechanical behavior of coal.Improved understanding of the spatial characteristics of cleat networks is therefore important to the coal mining industry.Discrete fracture networks(DFNs)are increasingly used in engineering analyses to spatially model fractures at various scales.The reliability of coal DFNs largely depends on the confidence in the input cleat statistics.Estimates of these parameters can be made from image-based three-dimensional(3D)characterization of coal cleats using X-ray micro-computed tomography(m CT).One key step in this process,after cleat extraction,is the separation of individual cleats,without which the cleats are a connected network and statistics for different cleat sets cannot be measured.In this paper,a feature extraction-based image processing method is introduced to identify and separate distinct cleat groups from 3D X-ray m CT images.Kernels(filters)representing explicit cleat features of coal are built and cleat separation is successfully achieved by convolutional operations on 3D coal images.The new method is applied to a coal specimen with 80 mm in diameter and 100 mm in length acquired from an Anglo American Steelmaking Coal mine in the Bowen Basin,Queensland,Australia.It is demonstrated that the new method produces reliable cleat separation capable of defining individual cleats and preserving 3D topology after separation.Bedding-parallel fractures are also identified and separated,which has his-torically been challenging to delineate and rarely reported.A variety of cleat/fracture statistics is measured which not only can quantitatively characterize the cleat/fracture system but also can be used for DFN modeling.Finally,variability and heterogeneity with respect to the core axis are investigated.Significant heterogeneity is observed and suggests that the representative elementary volume(REV)of the cleat groups for engineering purposes may be a complex problem requiring careful consideration.

Intelligent extraction of road cracks based on vehicle laser point cloud and panoramic sequence images

In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strategy for extracting road cracks.This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images.The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously.A convolutional neural network is utilized to extract cracks from the panoramic sequence image.The extracted sequence image is then aligned with the laser point cloud,enabling the assignment of RGB information to the vehicle-mounted three dimensional(3D)point cloud and location information to the two dimensional(2D)panoramic image.Additionally,a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud.The three-dimensional data pertaining to the cracks can be acquired.The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks.The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks.This approach exhibits superior accuracy when compared to conventional methods.Moreover,it facilitates rapid and accurate identification and localization of road cracks,thereby playing a crucial role in ensuring road maintenance and traffic safety.Consequently,this technique finds extensive application in the domains of intelligent transportation and urbanization development.The technology exhibits significant promise for use in the domains of intelligent transportation and city development.

Mechanism of Rosae Rugosae Flos fl avonoids in the treatment of hyperlipidemia and optimization of extraction process based on network pharmacology

This study aims to identify a natural plant chemical with hypolipidemic effects that can be used to treat high cholesterol without adverse reactions.Through network pharmacology screening,it was found that Rosae Rugosae Flos(RF)flavonoids had potential therapeutic effects on hyperlipidemia and its mechanism of action was discussed.TCMSP and GeneCards databases were used to obtain active ingredients and disease targets.Venn diagrams were drawn to illustrate the findings.The interaction network diagram was created using Cytoscape 3.8.0 software.The PPI protein network was constructed using String.GO and KEGG enrichment analysis was performed using Metascape.The results revealed 2 active flavonoid ingredients and 60 potential targets in RF.The key targets,including CCL2,PPARG,and PPARA,were found to play a role in multiple pathways such as the AGE-RAGE signaling pathway,lipid and atherosclerosis,and cancer pathway in diabetic complications.The solvent extraction method was optimized for efficient flavonoid extraction based on network pharmacology prediction results.This was achieved through a single factor and orthogonal test,resulting in an optimum process with a reflux time of 1.5 h,a solid-liquid ratio of 1:13 g/mL,and an ethanol concentration of 50%.

A Two-Phase Paradigm for Joint Entity-Relation Extraction

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task.However,these models sample a large number of negative entities and negative relations during the model training,which are essential but result in grossly imbalanced data distributions and in turn cause suboptimal model performance.In order to address the above issues,we propose a two-phase paradigm for the span-based joint entity and relation extraction,which involves classifying the entities and relations in the first phase,and predicting the types of these entities and relations in the second phase.The two-phase paradigm enables our model to significantly reduce the data distribution gap,including the gap between negative entities and other entities,aswell as the gap between negative relations and other relations.In addition,we make the first attempt at combining entity type and entity distance as global features,which has proven effective,especially for the relation extraction.Experimental results on several datasets demonstrate that the span-based joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-ofthe-art span-based models for the joint extraction task,establishing a new standard benchmark.Qualitative and quantitative analyses further validate the effectiveness the proposed paradigm and the global features.

Efficient and selective extraction of uranium from seawater based on a novel pulsed liquid chromatography radionuclide separation method

The novel pulsed liquid chromatography radionuclide separation method presented here provides a new and promising strategy for the extraction of uranium from seawater.In this study,a new chromatographic separation method was proposed,and a pulsed nuclide automated separation device was developed,alongside a new chromatographic column.The length of this chromatographic column was 10 m,with an internal warp of 3 mm and a packing size of 1 mm,while the total separation units of the column reached 12,250.The most favorable conditions for the separation of nuclides were then obtained through optimizing the separation conditions of the device:Sample pH in the column=2,sample injection flow rate=5.698 mL/min,chromatographic column heating temperature=60℃.Separation experiments were also carried out for uranium,europium,and sodium ions in mixed solutions;uranium and sodium ions in water samples from the Ganjiang River;and uranium,sodium,and magnesium ions from seawater samples.The separation factors between the different nuclei were then calculated based on the experimental data,and a formula for the separation level was derived.The experimental results showed that the separation factor in the mixed solution of uranium and europium(1:1)was 1.088,while achieving the initial separation of uranium and europium theoretically required a 47-stage separation.Considering the separation factor of 1.50for the uranium and sodium ions in water samples from the Ganjiang River,achieving the initial separation of uranium and sodium ions would have theoretically required at least a 21-stage separation.Furthermore,for the seawater sample separation experiments,the separation factor of uranium and sodium ions was 1.2885;therefore,more than 28 stages of sample separation would be required to achieve uranium extraction from seawater.The novel pulsed liquid chromatography method proposed in this study was innovative in terms of uranium separation and enrichment,while expanding the possibilities of extracting uranium from seawater through chromatography.

Small incision lenticule extraction and femtosecond-assisted laser in situ keratomileusis in patients with deep corneal opacity:case series

AIM:To report the safety,efficacy,and accuracy of small-incision lenticule extraction(SMILE)or femtosecondassisted laser in situ keratomileusis(FS-LASIK)for the correction of myopia or myopic astigmatism in patients with deep corneal opacity denoted by anterior segment optical coherence tomography(AS-OCT).METHODS:Four patients with monocular corneal opacity(3 due to mechanical injury,1 due to a firecracker wound)were recruited and treated with refractive surgery(3 for SMILE,1 for FS-LASIK combined with limbal relaxing incision(LRI).Preoperative ocular manifestations,surgical details,postoperative visual outcomes,corneal opacity parameters,and corneal topography were analyzed.RESULTS:Preoperatively,spherical diopter ranged from-3.0 D to-4.75 D with cylinder ranging from-0.75 to-5.0 D,and corrected distance visual acuity(CDVA)ranging from 20/25 to 20/20.One eye’s corneal opacity was located in the central zone and three were in the mid-peripheral optical zone.Three patients underwent uneventful SMILE in both eyes,whilst one patient underwent FS-LASIK for high astigmatism in both eyes and LRI in the right eye.CDVA of the eye with corneal opacity ranged from 20/22to 20/20 one to six weeks postoperatively.Two patients achieved better CDVA and no patients lost Snellen lines.The postoperative diopter was within±0.75 D for all eyes.Significant edema existed above the corneal opacity in one eye and dissipated soon.No eccentric corneal topography or morphological anomaly of the corneal cap or flap was observed.CONCLUSION:The cases demonstrate that SMILE or FS-LASIK is safe and effective to treat myopic astigmatism combined with deep corneal opacity lesions after comprehensive preoperative evaluation and appropriate candidate selection.FS-LASIK combined with LRI is also sufficient for correcting high astigmatism due to corneal scarring.

Solid-phase microextraction of endogenous metabolites from intact tissue validated using a Biocrates standard reference method kit

Improved analytical methods for the metabolomic profiling of tissue samples are constantly needed.Currently,conventional sample preparation methods often involve tissue biopsy and/or homogenization,which disrupts the endogenous metabolome.In this study,solid-phase microextraction(SPME)fibers were used to monitor changes in endogenous compounds in homogenized and intact ovine lung tissue.Following SPME,a Biocrates AbsoluteIDQ assay was applied to make a downstream targeted metabolomics analysis and confirm the advantages of in vivo SPME metabolomics.The AbsoluteIDQ kit enabled the targeted analysis of over 100 metabolites via solid-liquid extraction and SPME.Statistical analysis revealed significant differences between conventional liquid extractions from homogenized tissue and SPME results for both homogenized and intact tissue samples.In addition,principal component analysis revealed separated clustering among all the three sample groups,indicating changes in the metabolome due to tissue homogenization and the chosen sample preparation method.Furthermore,clear differences in free metabolites were observed when extractions were performed on the intact and homogenized tissue using identical SPME procedures.Specifically,a direct comparison showed that 47 statistically distinct metabolites were detected between the homogenized and intact lung tissue samples(P<0.05)using mixed-mode SPME fibers.These changes were probably due to the disruptive homogenization of the tissue.This study's findings highlight both the importance of sample preparation in tissue-based metabolomics studies and SPME's unique ability to perform minimally invasive extractions without tissue biopsy or homogenization while providing broad metabolite coverage.

Engineering Multi‑field‑coupled Synergistic Ion Transport System Based on the Heterogeneous Nanofluidic Membrane for High‑Efficient Lithium Extraction

The global carbon neutrality strategy brings a wave of rechargeable lithium‐ion batteries technique development and induces an ever-growing consumption and demand for lithium(Li).Among all the Li exploitation,extracting Li from spent LIBs would be a strategic and perspective approach,especially with the low energy consumption and eco-friendly membrane separation method.However,current membrane separation systems mainly focus on monotonous membrane design and structure optimization,and rarely further consider the coordination of inherent structure and applied external field,resulting in limited ion transport.Here,we propose a heterogeneous nanofluidic membrane as a platform for coupling multi-external fields(i.e.,lightinduced heat,electrical,and concentration gradient fields)to construct the multi-field-coupled synergistic ion transport system(MSITS)for Li-ion extraction from spent LIBs.The Li flux of the MSITS reaches 367.4 mmol m^(−2)h^(−1),even higher than the sum flux of those applied individual fields,reflecting synergistic enhancement for ion transport of the multi-field-coupled effect.Benefiting from the adaptation of membrane structure and multi-external fields,the proposed system exhibits ultrahigh selectivity with a Li^(+)/Co^(2+)factor of 216,412,outperforming previous reports.MSITS based on nanofluidic membrane proves to be a promising ion transport strategy,as it could accelerate ion transmembrane transport and alleviate the ion concentration polarization effect.This work demonstrated a collaborative system equipped with an optimized membrane for high-efficient Li extraction,providing an expanded strategy to investigate the other membrane-based applications of their common similarities in core concepts.

Deep Learning-Based Semantic Feature Extraction:A Literature Review and Future Directions

Semantic communication,as a critical component of artificial intelligence(AI),has gained increasing attention in recent years due to its significant impact on various fields.In this paper,we focus on the applications of semantic feature extraction,a key step in the semantic communication,in several areas of artificial intelligence,including natural language processing,medical imaging,remote sensing,autonomous driving,and other image-related applications.Specifically,we discuss how semantic feature extraction can enhance the accuracy and efficiency of natural language processing tasks,such as text classification,sentiment analysis,and topic modeling.In the medical imaging field,we explore how semantic feature extraction can be used for disease diagnosis,drug development,and treatment planning.In addition,we investigate the applications of semantic feature extraction in remote sensing and autonomous driving,where it can facilitate object detection,scene understanding,and other tasks.By providing an overview of the applications of semantic feature extraction in various fields,this paper aims to provide insights into the potential of this technology to advance the development of artificial intelligence.

Comparative study of functional optical zone:small incision lenticule extraction versus femtosecond laser assisted excimer laser keratomileusis

AIM:To investigate the size of functional optical zone(FOZ)after small incision lenticule extraction(SMILE)versus femtosecond laser assisted excimer laser keratomileusis(FS-LASIK)for myopia correction and potential associated factors for FOZ.METHODS:A total of 133 patients who received corneal refractive surgery in our hospital between November 2018 and July 2021 were retrospectively enrolled.There were 63 patients(123 eyes)in SMILE group and 70patients(139 eyes)in FS-LASIK group.The size of FOZ was measured using Pentacam 3-dementional anterior segment analyzer before and 3mo after surgery,so as to analyze postoperative achieved functional optical zone(AFOZ)and its contributing parameters.RESULTS:When planned functional optical zone(PFOZ)was 6.5 mm for both groups,AFOZ was 1.45±0.27 and 1.67±0.25 mm smaller than preoperative FOZ in SMILE group and FS-LASIK group 3mo after surgery.AFOZ in SMILE group was significantly larger than that in FS-LASIK group(P<0.001).Variation of FOZ was negatively correlated with preoperative spherical equivalent(SE)and positively correlated with variation of mean keratometry value(△Km),variation of spherical aberration(△SA),and variation of Q-value(△Q,all P<0.001)in both groups.Multiple variable linear regression equations were△FOZ=1.354-0.1×pre-SE+0.336×△Q+1.462×△SA in SMILE group and△FOZ=1.512+0.137×△Q+0.468×△SA in FS-LASIK group.CONCLUSION:AFOZ is significantly smaller than preoperative FOZ in both SMILE and FS-LASIK groups.With the same PFOZ,larger AFOZ is achieved in SMILE group than in FS-LASIK group.

基于PIPEPHASE的苏南采出水外输系统模拟研究

采出水外输是各大气田生产过程中保证气田产量和完善气田开发效果的重要途径。苏南气田采出水外输系统是一个复杂的流体网络系统,系统需要在不同状态下对外输方式进行调整。基于集气站、输水阀室、输水管线、处理厂的空间分布和拓扑结构关系,利用PIPEPHASE稳态多相流模拟计算软件,建立包含管网设施和参数的气田采出水外输系统模型;通过黏密度检测分析、阴阳离子色谱实验等明确了外输系统中的介质组分,进而开展仿真模拟;通过误差修正后的模型开展模拟计算,得出不同状态下各节点单元的压力和流量。结果表明:外部气温变化造成的介质温度改变会对外输系统产生小幅影响,通过对比不同分配分输方式的模拟计算结果与现场生产数据,验证了模型的合理性。研究结果可以为苏南气田现场生产提供参考。

Fusion of Region Extraction and Cross-Entropy SVM Models for Wheat Rust Diseases Classification

Wheat rust diseases are one of the major types of fungal diseases that cause substantial yield quality losses of 15%–20%every year.The wheat rust diseases are identified either through experienced evaluators or computerassisted techniques.The experienced evaluators take time to identify the disease which is highly laborious and too costly.If wheat rust diseases are predicted at the development stages,then fungicides are sprayed earlier which helps to increase wheat yield quality.To solve the experienced evaluator issues,a combined region extraction and cross-entropy support vector machine(CE-SVM)model is proposed for wheat rust disease identification.In the proposed system,a total of 2300 secondary source images were augmented through flipping,cropping,and rotation techniques.The augmented images are preprocessed by histogram equalization.As a result,preprocessed images have been applied to region extraction convolutional neural networks(RCNN);Fast-RCNN,Faster-RCNN,and Mask-RCNN models for wheat plant patch extraction.Different layers of region extraction models construct a feature vector that is later passed to the CE-SVM model.As a result,the Gaussian kernel function in CE-SVM achieves high F1-score(88.43%)and accuracy(93.60%)for wheat stripe rust disease classification.

Biomaterials-based anti-inflammatory treatment strategies for Alzheimer's disease

The current therapeutic drugs for Alzheimer's disease only improve symptoms,they do not delay disease progression.Therefo re,there is an urgent need for new effective drugs.The underlying pathogenic factors of Alzheimer's disease are not clear,but neuroinflammation can link various hypotheses of Alzheimer's disease;hence,targeting neuroinflammation may be a new hope for Alzheimer's disease treatment.Inhibiting inflammation can restore neuronal function,promote neuro regeneration,reduce the pathological burden of Alzheimer's disease,and improve or even reverse symptoms of Alzheimer's disease.This review focuses on the relationship between inflammation and various pathological hypotheses of Alzheimer's disease;reports the mechanisms and characteristics of small-molecule drugs(e.g.,nonsteroidal anti-inflammatory drugs,neurosteroids,and plant extracts);macromolecule drugs(e.g.,peptides,proteins,and gene therapeutics);and nanocarriers(e.g.,lipid-based nanoparticles,polymeric nanoparticles,nanoemulsions,and inorganic nanoparticles)in the treatment of Alzheimer's disease.The review also makes recommendations for the prospective development of anti-inflammatory strategies based on nanocarriers for the treatment of Alzheimer's disease.

Peak extraction and classification from digital elevation models based on the relationship between morphological characteristics and spatial position

A peak is an important topographic feature crucial in quantitative geomorphic feature analysis,digital geomorphological mapping,and other fields.Most peak extraction methods are based on the maximum elevation in a local area but ignore the morphological characteristics of the peak area.This paper proposes three indices based on the morphological characteristics of peaks and their spatial relationship with ridge lines:convexity mean index(CM-index),convexity standard deviation(CSD-index),and convexity imbalance index(CIBindex).We develop computation methods to extract peaks from digital elevation model(DEM).Subsequently,the initial peaks extracted by neighborhood statistics are classified using the proposed indices.The method is evaluated in the Qinghai Tibet Plateau and the Loess Plateau in China.An ASTER Global DEM(ASTGTM2 DEM)with a grid size of 30 m is chosen to assess the suitability of the proposed mountain peak extraction and classification method in different geomorphic regions.DEM data with grid sizes of 30 m and 5 m are used for the Loess Plateau.The mountain peak extraction and classification results obtained from the different resolution DEM are compared.The experimental results show that:(1)The CM-index and the CSDindex accurately reflect the concave or convex morphology of the surface and can be used as supplements to existing surface morphological indices.(2)The three indices can identify pseudo mountain peaks and classify the remaining peaks into single ridge peak(SR-Peak)and multiple ridge intersection peak(MRI-Peak).The visual inspection results show that the classification accuracy in the different study areas exceeds 75%.(3)The number of peaks is significantly higher for the 5 m DEM than for the 30 m DEM because more peaks can be detected at a finer resolution.

Multi-Modal Military Event Extraction Based on Knowledge Fusion

Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured text.Extracting event elements from multi-modal data remains a challenging task due to the presence of a large number of images and overlapping event elements in the data.Although researchers have proposed various methods to accomplish this task,most existing event extraction models cannot address these challenges because they are only applicable to text scenarios.To solve the above issues,this paper proposes a multi-modal event extraction method based on knowledge fusion.Specifically,for event-type recognition,we use a meticulous pipeline approach that integrates multiple pre-trained models.This approach enables a more comprehensive capture of the multidimensional event semantic features present in military texts,thereby enhancing the interconnectedness of information between trigger words and events.For event element extraction,we propose a method for constructing a priori templates that combine event types with corresponding trigger words.This approach facilitates the acquisition of fine-grained input samples containing event trigger words,thus enabling the model to understand the semantic relationships between elements in greater depth.Furthermore,a fusion method for spatial mapping of textual event elements and image elements is proposed to reduce the category number overload and effectively achieve multi-modal knowledge fusion.The experimental results based on the CCKS 2022 dataset show that our method has achieved competitive results,with a comprehensive evaluation value F1-score of 53.4%for the model.These results validate the effectiveness of our method in extracting event elements from multi-modal data.

Feature Extraction and Classification of Photovoltaic Panels Based on Convolutional Neural Network

Photovoltaic(PV)boards are a perfect way to create eco-friendly power from daylight.The defects in the PV panels are caused by various conditions;such defective PV panels need continuous monitoring.The recent development of PV panel monitoring systems provides a modest and viable approach to monitoring and managing the condition of the PV plants.In general,conventional procedures are used to identify the faulty modules earlier and to avoid declines in power generation.The existing deep learning architectures provide the required output to predict the faulty PV panels with less accuracy and a more time-consuming process.To increase the accuracy and to reduce the processing time,a new Convolutional Neural Network(CNN)architecture is required.Hence,in the present work,a new Real-time Multi Variant Deep learning Model(RMVDM)architecture is proposed,and it extracts the image features and classifies the defects in PV panels quickly with high accuracy.The defects that arise in the PV panels are identified by the CNN based RMVDM using RGB images.The biggest difference between CNN and its predecessors is that CNN automatically extracts the image features without any help from a person.The technique is quantitatively assessed and compared with existing faulty PV board identification approaches on the large real-time dataset.The results show that 98%of the accuracy and recall values in the fault detection and classification process.