Wavelet Multi-Resolution Interpolation Galerkin Method for Linear Singularly Perturbed Boundary Value Problems

In this study,a wavelet multi-resolution interpolation Galerkin method(WMIGM)is proposed to solve linear singularly perturbed boundary value problems.Unlike conventional wavelet schemes,the proposed algorithm can be readily extended to special node generation techniques,such as the Shishkin node.Such a wavelet method allows a high degree of local refinement of the nodal distribution to efficiently capture localized steep gradients.All the shape functions possess the Kronecker delta property,making the imposition of boundary conditions as easy as that in the finite element method.Four numerical examples are studied to demonstrate the validity and accuracy of the proposedwavelet method.The results showthat the use ofmodified Shishkin nodes can significantly reduce numerical oscillation near the boundary layer.Compared with many other methods,the proposed method possesses satisfactory accuracy and efficiency.The theoretical and numerical results demonstrate that the order of theε-uniform convergence of this wavelet method can reach 5.

Recognition of Hybrid PQ Disturbances Based on Multi-Resolution S-Transform and Decision Tree

Aiming at the problems of multiple types of power quality composite disturbances,strong feature correlation and high recognition error rate,a method of power quality composite disturbances identification based on multiresolution S-transform and decision tree was proposed.Firstly,according to IEEE standard,the signal models of seven single power quality disturbances and 17 combined power quality disturbances are given,and the disturbance waveform samples are generated in batches.Then,in order to improve the recognition accuracy,the adjustment factor is introduced to obtain the controllable time-frequency resolution through multi-resolution S-transform time-frequency domain analysis.On this basis,five disturbance time-frequency domain features are extracted,which quantitatively reflect the characteristics of the analyzed power quality disturbance signal,which is less than the traditional method based on S-transform.Finally,three classifiers such as K-nearest neighbor,support vector machine and decision tree algorithm are used to effectively complete the identification of power quality composite disturbances.Simulation results showthat the classification accuracy of decision tree algorithmis higher than that of K-nearest neighbor and support vector machine.Finally,the proposed method is compared with other commonly used recognition algorithms.Experimental results show that the proposedmethod is effective in terms of detection accuracy,especially for combined PQ interference.

Efficient Sparse-Grid Implementation of a Fifth-Order Multi-resolution WENO Scheme for Hyperbolic Equations

High-order accurate weighted essentially non-oscillatory(WENO)schemes are a class of broadly applied numerical methods for solving hyperbolic partial differential equations(PDEs).Due to highly nonlinear property of the WENO algorithm,large amount of computational costs are required for solving multidimensional problems.In our previous work(Lu et al.in Pure Appl Math Q 14:57–86,2018;Zhu and Zhang in J Sci Comput 87:44,2021),sparse-grid techniques were applied to the classical finite difference WENO schemes in solving multidimensional hyperbolic equations,and it was shown that significant CPU times were saved,while both accuracy and stability of the classical WENO schemes were maintained for computations on sparse grids.In this technical note,we apply the approach to recently developed finite difference multi-resolution WENO scheme specifically the fifth-order scheme,which has very interesting properties such as its simplicity in linear weights’construction over a classical WENO scheme.Numerical experiments on solving high dimensional hyperbolic equations including Vlasov based kinetic problems are performed to demonstrate that the sparse-grid computations achieve large savings of CPU times,and at the same time preserve comparable accuracy and resolution with those on corresponding regular single grids.

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.

SciCN:A Scientific Dataset for Chinese Named Entity Recognition

Named entity recognition(NER)is a fundamental task of information extraction(IE),and it has attracted considerable research attention in recent years.The abundant annotated English NER datasets have significantly promoted the NER research in the English field.By contrast,much fewer efforts are made to the Chinese NER research,especially in the scientific domain,due to the scarcity of Chinese NER datasets.To alleviate this problem,we present aChinese scientificNER dataset–SciCN,which contains entity annotations of titles and abstracts derived from 3,500 scientific papers.We manually annotate a total of 62,059 entities,and these entities are classified into six types.Compared to English scientific NER datasets,SciCN has a larger scale and is more diverse,for it not only contains more paper abstracts but these abstracts are derived from more research fields.To investigate the properties of SciCN and provide baselines for future research,we adapt a number of previous state-of-theart Chinese NER models to evaluate SciCN.Experimental results show that SciCN is more challenging than other Chinese NER datasets.In addition,previous studies have proven the effectiveness of using lexicons to enhance Chinese NER models.Motivated by this fact,we provide a scientific domain-specific lexicon.Validation results demonstrate that our lexicon delivers better performance gains than lexicons of other domains.We hope that the SciCN dataset and the lexicon will enable us to benchmark the NER task regarding the Chinese scientific domain and make progress for future research.The dataset and lexicon are available at:https://github.com/yangjingla/SciCN.git.

RoBGP:A Chinese Nested Biomedical Named Entity Recognition Model Based on RoBERTa and Global Pointer

Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and categorize them into predefined entity types.This process can provide basic support for the automatic construction of knowledge bases.In contrast to general texts,biomedical texts frequently contain numerous nested entities and local dependencies among these entities,presenting significant challenges to prevailing NER models.To address these issues,we propose a novel Chinese nested biomedical NER model based on RoBERTa and Global Pointer(RoBGP).Our model initially utilizes the RoBERTa-wwm-ext-large pretrained language model to dynamically generate word-level initial vectors.It then incorporates a Bidirectional Long Short-Term Memory network for capturing bidirectional semantic information,effectively addressing the issue of long-distance dependencies.Furthermore,the Global Pointer model is employed to comprehensively recognize all nested entities in the text.We conduct extensive experiments on the Chinese medical dataset CMeEE and the results demonstrate the superior performance of RoBGP over several baseline models.This research confirms the effectiveness of RoBGP in Chinese biomedical NER,providing reliable technical support for biomedical information extraction and knowledge base construction.

SHEL:a semantically enhanced hardware-friendly entity linking method

With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this task.Some researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition model.This paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good performance.Specifically,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling operations.These series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this paper.In terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.

Multi-resolution image segmentation based on Gaussian mixture model

Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.

Winter wheat identification by integrating spectral and temporal information derived from multi-resolution remote sensing data

Timely crop acreage and distribution information are the basic data which drive many agriculture related applications.For identifying crop types based on remote sensing,methods using only a single image type have significant limitations.Current research that integrates fine and coarser spatial resolution images,using techniques such as unmixing methods,regression models,and others,usually results in coarse resolution abundance without sufficient detail within pixels,and limited attention has been paid to the spatial relationship between the pixels from these two kinds of images.Here we propose a new solution to identify winter wheat by integrating spectral and temporal information derived from multi-resolution remote sensing data and determine the spatial distribution of sub-pixels within the coarse resolution pixels.Firstly,the membership of pixels which belong to winter wheat is calculated using a 25-m resolution resampled Landsat Thematic Mapper(TM)image based on the Bayesian equation.Then,the winter wheat abundance(acreage fraction in a pixel)is assessed by using a multiple regression model based on the unique temporal change features from moderate resolution imaging spectroradiometer(MODIS)time series data.Finally,winter wheat is identified by the proposed Abundance-Membership(AM)model based on the spatial relationship between the two types of pixels.Specifically,winter wheat is identified by comparing the spatially corresponding 10×10 membership pixels of each abundance pixel.In other words,this method takes advantage of the relative size of membership in a local space,rather than the absolute size in the entire study area.This method is tested in the major agricultural area of Yiluo Basin,China,and the results show that acreage accuracy(Aa)is 93.01%and sampling accuracy(As)is 91.40%.Confusion matrix shows that overall accuracy(OA)is 91.4%and the kappa coefficient(Kappa)is 0.755.These values are significantly improved compared to the traditional Maximum Likelihood classification(MLC)and Random Forest classification(RFC)which rely on spectral features.The results demonstrate that the identification accuracy can be improved by integrating spectral and temporal information.Since the identification of winter wheat is performed in the space corresponding to each MODIS pixel,the influence of differences of environmental conditions is greatly reduced.This advantage allows the proposed method to be effectively applied in other places.

Application of multi-resolution analysis in sonar image denoising

Sonar images have complex background, low contrast, and deteriorative edges; these characteristics make it difficult for researchers to dispose the sonar objects. The multi-resolution analysis represents the signals in different scales efficiently, which is widely used in image processing. Wavelets are successful in disposing point discontinuities in one dimension, but not in two dimensions. The finite Ridgelet transform （FRIT） deals efficiently with the singularity in high dimension. It presents three improved denoising approaches, which are based on FRIT and used in the sonar image disposal technique. By experiment and comparison with traditional methods, these approaches not only suppress the artifacts, but also obtain good effect in edge keeping and SNR of the sonar image denoising.

Multi-resolution EMD and classscatter matrix extracting of tank sound

The acoustic vibration signal of tank is disassembled into the sum of intrinsic mode function （IMF） by multi-resolution empirical mode decomposition （EMD） method. The instantaneous frequency is obtained, and feature transformation matrix is figured out by class scatter matrix. Multi- dimensional scale energy vector is mapped into low-dimensional eigenvector, and classification extraction is realized. This method sufficiently separates of different sound target features. The test result indicates that it is effective.

Magnetic-resonance image segmentation based on improved variable weight multi-resolution Markov random field in undecimated complex wavelet domain

To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov random field(MRMRF)model.The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales.The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm,and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation.The results are then segmented by the improved MRMRF model.In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model,it is proposed to introduce variable weight parameters in the segmentation process of each scale.Furthermore,the final segmentation results are optimized.We name this algorithm the variable-weight multi-resolution Markov random field(VWMRMRF).The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness,and can accurately and stably achieve low signal-to-noise ratio,weak boundary MR image segmentation.

Convergence to Steady-State Solutions of the New Type of High-Order Multi-resolution WENO Schemes: a Numerical Study

A new type of high-order multi-resolution weighted essentially non-oscillatory(WENO)schemes(Zhu and Shu in J Comput Phys,375:659-683,2018)is applied to solve for steady-state problems on structured meshes.Since the classical WENO schemes(Jiang and Shu in J Comput Phys,126:202-228,1996)might suffer from slight post-shock oscillations(which are responsible for the residue to hang at a truncation error level),this new type of high-order finite-difference and finite-volume multi-resolution WENO schemes is applied to control the slight post-shock oscillations and push the residue to settle down to machine zero in steady-state simulations.This new type of multi-resolution WENO schemes uses the same large stencils as that of the same order classical WENO schemes,could obtain fifth-order,seventh-order,and ninth-order in smooth regions,and could gradually degrade to first-order so as to suppress spurious oscillations near strong discontinuities.The linear weights of such new multi-resolution WENO schemes can be any positive numbers on the condition that their sum is one.This is the first time that a series of unequal-sized hierarchical central spatial stencils are used in designing high-order finitedifference and finite-volume WENO schemes for solving steady-state problems.In comparison with the classical fifth-order finite-difference and finite-volume WENO schemes,the residue of these new high-order multi-resolution WENO schemes can converge to a tiny number close to machine zero for some benchmark steady-state problems.

Conformal Multi-resolution Time-Domain Method for Scattering Curved Dielectric Objects

A conformal multi-resolution time-domain( CMRTD) method is presented for modeling curved objects. The effective dielectric constant and area weighting are used to derive the update equations of CMRTD. The backward scattering bistatic radar cross sections( RCS) of the dielectric cylinder and ellipsoid are used to validate the proposed method. The results show that the proposed conformal method is more accurate to deal with the complex curved objects in electromagnetic simulations.

Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation

Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.

Runge-Kutta Multi-resolution Time-Domain Method for Modeling 3D Dielectric Curved Objects

A conformal Runge-Kutta multi-resolution time-domain(C-RKMRTD)method is present and applied to model and analyze curved objects.Compared with the non-conformal method,the proposed method is more accurate.The scattering analyses of the cylinder and ellipsoid are presented to validate the proposed method.The numerical results demonstrate that the proposed scheme perform better than the MRTD method and other higher order methods with a higher accuracy.

A Federated Named Entity Recognition Model with Explicit Relation for Power Grid

The power grid operation process is complex,and many operation process data involve national security,business secrets,and user privacy.Meanwhile,labeled datasets may exist in many different operation platforms,but they cannot be directly shared since power grid data is highly privacysensitive.How to use these multi-source heterogeneous data as much as possible to build a power grid knowledge map under the premise of protecting privacy security has become an urgent problem in developing smart grid.Therefore,this paper proposes federated learning named entity recognition method for the power grid field,aiming to solve the problem of building a named entity recognition model covering the entire power grid process training by data with different security requirements.We decompose the named entity recognition(NER)model FLAT(Chinese NER Using Flat-Lattice Transformer)in each platform into a global part and a local part.The local part is used to capture the characteristics of the local data in each platform and is updated using locally labeled data.The global part is learned across different operation platforms to capture the shared NER knowledge.Its local gradients fromdifferent platforms are aggregated to update the global model,which is further delivered to each platform to update their global part.Experiments on two publicly available Chinese datasets and one power grid dataset validate the effectiveness of our method.

An image registration method based on multi-resolution morphology contour detection

Combined with the printing application,an image registration method based on the multi-resolution morphology contour detection was proposed.First,a direction based multi-resolution gray morphology in the scheme was proposed to realize the contour extraction.Then,based on the contour features,the subspace image registration was proposed to deal with issues of the computing complexity appeared in the traditional image registration methods.The proposed image registration was efficiently applied in the defect inspection of printing images.

Real-Time Rendering of Dynamic Clouds Using Multi-Resolution Adaptive Grids

The multi-resolution adaptive grids method is proposed to solve the problems of inefficiency in the previous grid-based methods,and it can be used in clouds simulation as well as the interactive simulation between objects and clouds.Oriented bounding box(OBB)hierarchical trees of objects are established,and the resolutions of global and local grids can be selected automatically.The motion equations of fluid dynamics are simplified.Upwind difference is applied to ensure the stability of the simulation process during the discrete process of partial differential equations.To solve the speed problem of existed phase functions,the improved phase function is applied to the illumination calculation of clouds.Experimental results show that the proposed methods can promote the simulation efficiency and meet the need for the simulation of large-scale clouds scene.Real-time rendering of clouds and the interaction between clouds and objects have been realized without preprocessing stage.

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.