Single-Shot Direct Transmission Terahertz Imaging Based on Intense Broadband Terahertz Radiation.

There are numerous applications of terahertz (THz) imaging in many fields. However, current THz imaging is generally based on scanning technique due to the limited intensity of the THz sources. Thus, it takes a long time to obtain a frame image of the target and cannot meet the requirement of fast THz imaging. Here, we demonstrate a single-shot direct THz imaging strategy based on a broadband intense THz source with a frequency range of 0.1~23 THz and a THz camera with a frequency response range of 1~7 THz. This THz source was generated from the laser-plasma interaction, with its central frequency at ~12 THz. The frame rate of this imaging system was 8.5 frames per second. The imaging resolution reached 146.2 µm. With this imaging system, a single-shot THz image for a target object with a size of more than 7 cm was routinely obtained, showing a potential application for fast THz imaging. Furthermore, we proposed and tested an image enhancement algorithm based on an improved dark channel prior (DCP) theory and multi-scale retinex (MSR) theory to optimize the image brightness, contrast, entropy and peak signal-to-noise ratio (PSNR).

An Improved U-Net Infrared Small Target Detection Algorithm Based on Multi-Scale Feature Decomposition and Fusion and Attention Mechanism.

Infrared small target detection technology plays a crucial role in various fields such as military reconnaissance, power patrol, medical diagnosis, and security. The advancement of deep learning has led to the success of convolutional neural networks in target segmentation. However, due to challenges like small target scales, weak signals, and strong background interference in infrared images, convolutional neural networks often face issues like leakage and misdetection in small target segmentation tasks. To address this, an enhanced U-Net method called MST-UNet is proposed, the method combines multi-scale feature decomposition and fusion and attention mechanisms. The method involves using Haar wavelet transform instead of maximum pooling for downsampling in the encoder to minimize feature loss and enhance feature utilization. Additionally, a multi-scale residual unit is introduced to extract contextual information at different scales, improving sensory field and feature expression. The inclusion of a triple attention mechanism in the encoder structure further enhances multidimensional information utilization and feature recovery by the decoder. Experimental analysis on the NUDT-SIRST dataset demonstrates that the proposed method significantly improves target contour accuracy and segmentation precision, achieving IoU and nIoU values of 80.09% and 80.19%, respectively.

A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials.

With the development of data mining technology, the analysis of event-related potential (ERP) data has evolved from statistical analysis of time-domain features to data-driven techniques based on supervised and unsupervised learning. However, there are still many challenges in understanding the relationship between ERP components and the representation of familiar and unfamiliar faces. To address this, this paper proposes a model based on Dynamic Multi-Scale Convolution for group recognition of familiar and unfamiliar faces. This approach uses generated weight masks for cross-subject familiar/unfamiliar face recognition using a multi-scale model. The model employs a variable-length filter generator to dynamically determine the optimal filter length for time-series samples, thereby capturing features at different time scales. Comparative experiments are conducted to evaluate the model's performance against SOTA models. The results demonstrate that our model achieves impressive outcomes, with a balanced accuracy rate of 93.20% and an F1 score of 88.54%, outperforming the methods used for comparison. The ERP data extracted from different time regions in the model can also provide data-driven technical support for research based on the representation of different ERP components.

Multi-scale object equalization learning network for intracerebral hemorrhage region segmentation.

Segmentation and the subsequent quantitative assessment of the target object in computed tomography (CT) images provide valuable information for the analysis of intracerebral hemorrhage (ICH) pathology. However, most existing methods lack a reasonable strategy to explore the discriminative semantics of multi-scale ICH regions, making it difficult to address the challenge of complex morphology in clinical data. In this paper, we propose a novel multi-scale object equalization learning network (MOEL-Net) for accurate ICH region segmentation. Specifically, we first introduce a shallow feature extraction module (SFEM) for obtaining shallow semantic representations to maintain sufficient and effective detailed location information. Then, a deep feature extraction module (DFEM) is leveraged to extract the deep semantic information of the ICH region from the combination of SFEM and original image features. To further achieve equalization learning in different scales of ICH regions, we introduce a multi-level semantic feature equalization fusion module (MSFEFM), which explores the equalized fusion features of the described objects with the assistance of shallow and deep semantic information provided by SFEM and DFEM. Driven by the above three designs, MOEL-Net shows a solid capacity to capture more discriminative features in various ICH region segmentation. To promote the research of clinical automatic ICH region segmentation, we collect two datasets, VMICH and FRICH (divided into Test A and Test B) for evaluation. Experimental results show that the proposed model achieves the Dice scores of 88.28%, 90.92%, and 90.95% on the VMICH, FRICH Test A, and Test B, respectively, which outperform fourteen competing methods.

Multi-Scale Study of a Phase Change Material on a Tropical Island for Evaluating Its Impact on Human Comfort in the Building Sector.

Our study explores the utilization of a phase change material (PCM) to optimize energy efficiency and thermal comfort in buildings in tropical climates. Employing a comprehensive multi-scale approach, this research encompasses both microscopic and macroscopic analyses to rigorously evaluate the PCM's performance under various environmental conditions. It evaluates the effect of PCMs on ambient conditions in the face of temperature variations and high humidity, utilizing experimental methods at different scales (microscopic and macroscopic). Microscopic analyses reveal the composite structure of the PCM, consisting of microencapsulated paraffin within a cellulose fiber matrix. At a macroscopic scale, experiments using two real-scale test cells evaluated thermal performance and its influence on thermal comfort. Temperature and humidity data were meticulously collected over an extended period to assess the PCM's impact on indoor regulation. We employed type T thermocouples and flux meters to monitor thermal dynamics and energy flux across the building walls. This setup facilitated a detailed comparison of temperature variations and thermal comfort metrics between the PCM-equipped test cell and a control cell. The results indicate a seasonal duality of the PCM: beneficial in winter for thermal regulation but problematic in summer due to excessive heat retention. The conclusions highlight the importance of carefully selecting and adapting PCMs for tropical climates, thus providing valuable insights for designing sustainable buildings in regions facing similar climatic challenges.

Improvement of the YOLOv8 Model in the Optimization of the Weed Recognition Algorithm in Cotton Field.

Due to the existence of cotton weeds in a complex cotton field environment with many different species, dense distribution, partial occlusion, and small target phenomena, the use of the YOLO algorithm is prone to problems such as low detection accuracy, serious misdetection, etc. In this study, we propose a YOLOv8-DMAS model for the detection of cotton weeds in complex environments based on the YOLOv8 detection algorithm. To enhance the ability of the model to capture multi-scale features of different weeds, all the BottleNeck are replaced by the Dilation-wise Residual Module (DWR) in the C2f network, and the Multi-Scale module (MSBlock) is added in the last layer of the backbone. Additionally, a small-target detection layer is added to the head structure to avoid the omission of small-target weed detection, and the Adaptively Spatial Feature Fusion mechanism (ASFF) is used to improve the detection head to solve the spatial inconsistency problem of feature fusion. Finally, the original Non-maximum suppression (NMS) method is replaced with SoftNMS to improve the accuracy under dense weed detection. In comparison to YOLO v8s, the experimental results show that the improved YOLOv8-DMAS improves accuracy, recall, mAP0.5, and mAP0.5:0.95 by 1.7%, 3.8%, 2.1%, and 3.7%, respectively. Furthermore, compared to the mature target detection algorithms YOLOv5s, YOLOv7, and SSD, it improves 4.8%, 4.5%, and 5.9% on mAP0.5:0.95, respectively. The results show that the improved model could accurately detect cotton weeds in complex field environments in real time and provide technical support for intelligent weeding research.

Texture characterization of 3D printed fibrous whey protein-starch composite emulsion gels as dysphagia food: A comparative study on starch type.

Texture-modified, multi-nutrient composite foods are essential in clinical treatment for dysphagia individuals. Herein, fibrous whey protein-stabilized emulsion and different crystalline starches (wheat, corn, rice, potato, sweet potato, cassava, mung bean and pea) were used to structure composite emulsion gels (CEGs). These CEGs then underwent 3D printing to explore the feasibility of developing a dysphagia diet. The network of molded CEGs was mainly maintained by hydrophobic interactions and hydrogen bonds. Rice and cassava starches were better suited for structuring soft-textured CEGs. Compared with molded CEGs, 3D printing decreased hydrogen bonds and the compactness of the nano-aggregate structure within the gel system, forming a looser gel network and softening the CEGs. Interestingly, these effects were more pronounced for the CEGs with high initial hardness. This study provided new strategy to fabricate CEGs as dysphagia diet using fibrous whey protein and starch, and to design texture-modified foods for patients using 3D printing.

Improved YOLO-FastestV2 wheat spike detection model based on a multi-stage attention mechanism with a LightFPN detection head.

The number of wheat spikes has an important influence on wheat yield, and the rapid and accurate detection of wheat spike numbers is of great significance for wheat yield estimation and food security. Computer vision and machine learning have been widely studied as potential alternatives to human detection. However, models with high accuracy are computationally intensive and time consuming, and lightweight models tend to have lower precision. To address these concerns, YOLO-FastestV2 was selected as the base model for the comprehensive study and analysis of wheat sheaf detection. In this study, we constructed a wheat target detection dataset comprising 11,451 images and 496,974 bounding boxes. The dataset for this study was constructed based on the Global Wheat Detection Dataset and the Wheat Sheaf Detection Dataset, which was published by PP Flying Paddle. We selected three attention mechanisms, Large Separable Kernel Attention (LSKA), Efficient Channel Attention (ECA), and Efficient Multi-Scale Attention (EMA), to enhance the feature extraction capability of the backbone network and improve the accuracy of the underlying model. First, the attention mechanism was added after the base and output phases of the backbone network. Second, the attention mechanism that further improved the model accuracy after the base and output phases was selected to construct the model with a two-phase added attention mechanism. On the other hand, we constructed SimLightFPN to improve the model accuracy by introducing SimConv to improve the LightFPN module. The results of the study showed that the YOLO-FastestV2-SimLightFPN-ECA-EMA hybrid model, which incorporates the ECA attention mechanism in the base stage and introduces the EMA attention mechanism and the combination of SimLightFPN modules in the output stage, has the best overall performance. The accuracy of the model was P=83.91%, R=78.35%, AP= 81.52%, and F1 = 81.03%, and it ranked first in the GPI (0.84) in the overall evaluation. The research examines the deployment of wheat ear detection and counting models on devices with constrained resources, delivering novel solutions for the evolution of agricultural automation and precision agriculture.

SB-Net: Synergizing CNN and LSTM networks for uncovering retrosynthetic pathways in organic synthesis.

Retrosynthesis is vital in synthesizing target products, guiding reaction pathway design crucial for drug and material discovery. Current models often neglect multi-scale feature extraction, limiting efficacy in leveraging molecular descriptors. Our proposed SB-Net model, a deep-learning architecture tailored for retrosynthesis prediction, addresses this gap. SB-Net combines CNN and Bi-LSTM architectures, excelling in capturing multi-scale molecular features. It integrates parallel branches for processing one-hot encoded descriptors and ECFP, merging through dense layers. Experimental results demonstrate SB-Net's superiority, achieving 73.6 % top-1 and 94.6 % top-10 accuracy on USPTO-50k data. Versatility is validated on MetaNetX, with rates of 52.8 % top-1, 74.3 % top-3, 79.8 % top-5, and 83.5 % top-10. SB-Net's success in bioretrosynthesis prediction tasks indicates its efficacy. This research advances computational chemistry, offering a robust deep-learning model for retrosynthesis prediction. With implications for drug discovery and synthesis planning, SB-Net promises innovative and efficient pathways.

Multi-scale variational autoencoder for imputation of missing values in untargeted metabolomics using whole-genome sequencing data.

BACKGROUND: Missing data is a common challenge in mass spectrometry-based metabolomics, which can lead to biased and incomplete analyses. The integration of whole-genome sequencing (WGS) data with metabolomics data has emerged as a promising approach to enhance the accuracy of data imputation in metabolomics studies. METHOD: In this study, we propose a novel method that leverages the information from WGS data and reference metabolites to impute unknown metabolites. Our approach utilizes a multi-scale variational autoencoder to jointly model the burden score, polygenetic risk score (PGS), and linkage disequilibrium (LD) pruned single nucleotide polymorphisms (SNPs) for feature extraction and missing metabolomics data imputation. By learning the latent representations of both omics data, our method can effectively impute missing metabolomics values based on genomic information. RESULTS: We evaluate the performance of our method on empirical metabolomics datasets with missing values and demonstrate its superiority compared to conventional imputation techniques. Using 35 template metabolites derived burden scores, PGS and LD-pruned SNPs, the proposed methods achieved R2-scores > 0.01 for 71.55 % of metabolites. CONCLUSION: The integration of WGS data in metabolomics imputation not only improves data completeness but also enhances downstream analyses, paving the way for more comprehensive and accurate investigations of metabolic pathways and disease associations. Our findings offer valuable insights into the potential benefits of utilizing WGS data for metabolomics data imputation and underscore the importance of leveraging multi-modal data integration in precision medicine research.

Application of physics encoded neural networks to improve predictability of properties of complex multi-scale systems.

Predicting physical properties of complex multi-scale systems is a common challenge and demands analysis of various temporal and spatial scales. However, physics alone is often not sufficient due to lack of knowledge on certain details of the system. With sufficient data, however, machine learning techniques may aid. If data are yet relatively cumbersome to obtain, hybrid methods may come to the rescue. We focus in this report on using various types of neural networks (NN) including NN's into which physics information is encoded (PeNN's) and also studied effects of NN's hyperparameters. We apply the networks to predict the viscosity of an emulsion as a function of shear rate. We show that using various network performance metrics as the mean squared error and the coefficient of determination ( R 2 ) that the PeNN's always perform better than the NN's, as also confirmed by a Friedman test with a p-value smaller than 0.0002. The PeNN's capture extrapolation and interpolation very well, contrary to the NN's. In addition, we have found that the NN's hyperparameters including network complexity and optimization methods do not have any effect on the above conclusions. We suggest that encoding NN's with any disciplinary system based information yields promise to better predict properties of complex systems than NN's alone, which will be in particular advantageous for small numbers of data. Such encoding would also be scalable, allowing different properties to be combined, without repetitive training of the NN's.

An Improved Archimedes Optimization-aided Multi-scale Deep Learning Segmentation with dilated ensemble CNN classification for detecting lung cancer using CT images.

Early detection of lung cancer is necessary to prevent deaths caused by lung cancer. But, the identification of cancer in lungs using Computed Tomography (CT) scan based on some deep learning algorithms does not provide accurate results. A novel adaptive deep learning is developed with heuristic improvement. The proposed framework constitutes three sections as (a) Image acquisition, (b) Segmentation of Lung nodule, and (c) Classifying lung cancer. The raw CT images are congregated through standard data sources. It is then followed by nodule segmentation process, which is conducted by Adaptive Multi-Scale Dilated Trans-Unet3+. For increasing the segmentation accuracy, the parameters in this model is optimized by proposing Modified Transfer Operator-based Archimedes Optimization (MTO-AO). At the end, the segmented images are subjected to classification procedure, namely, Advanced Dilated Ensemble Convolutional Neural Networks (ADECNN), in which it is constructed with Inception, ResNet and MobileNet, where the hyper parameters is tuned by MTO-AO. From the three networks, the final result is estimated by high ranking-based classification. Hence, the performance is investigated using multiple measures and compared among different approaches. Thus, the findings of model demonstrate to prove the system's efficiency of detecting cancer and help the patient to get the appropriate treatment.

Multi-scale assessment of rainwater harvesting availability across the continental U.S.

Addressing resilience, sustainability, and water resource conservation has become increasingly important in the modern world. Challenges arise due to periodic droughts, climate change, and seasonal variability in areas with limited freshwater availability. Therefore, implementing and promoting water reuse is essential. Rainwater harvesting (RWH) is one such alternative, offering benefits in conserving water resources and mitigating droughts while reducing urban flooding and costs by generating alternative lower-cost water sources. Providing users with knowledge of available volumes for harvesting, including homeowners and governmental entities, is key to encouraging this practice. Hydrological data and geographic information systems are fundamental for managing, designing, and projecting rainwater harvesting practices. However, no tools currently integrate this information at multiple scales with current and future climate scenarios. This research aimed to develop a multi-scale assessment tool named H2O HARVEST, for evaluating the availability and potential of rainwater harvesting. Additional benefits of the H2O HARVEST app include aiding decision-making by national governmental entities and analyzing potential future scenarios for homeowner users. The app also provides regulatory policy information at the state level. We offer an app with the necessary capabilities to bridge the technology gap and promote rainwater harvesting practices. Our research demonstrated that RWH has the potential to be a sustainable water reuse practice. For more than 50% of the states, the RWH could supply at least 50% of the water demand. The regions of the US with the greatest potential are the Central and East.

Eigen-entropy based time series signatures to support multivariate time series classification.

Most current algorithms for multivariate time series classification tend to overlook the correlations between time series of different variables. In this research, we propose a framework that leverages Eigen-entropy along with a cumulative moving window to derive time series signatures to support the classification task. These signatures are enumerations of correlations among different time series considering the temporal nature of the dataset. To manage dataset's dynamic nature, we employ preprocessing with dense multi scale entropy. Consequently, the proposed framework, Eigen-entropy-based Time Series Signatures, captures correlations among multivariate time series without losing its temporal and dynamic aspects. The efficacy of our algorithm is assessed using six binary datasets sourced from the University of East Anglia, in addition to a publicly available gait dataset and an institutional sepsis dataset from the Mayo Clinic. We use recall as the evaluation metric to compare our approach against baseline algorithms, including dependent dynamic time warping with 1 nearest neighbor and multivariate multi-scale permutation entropy. Our method demonstrates superior performance in terms of recall for seven out of the eight datasets.

Fishers (Pekania pennanti) are forest structure specialists when resting and generalists when moving: behavior influences resource selection in a northern Rocky Mountain fisher population.

BACKGROUND: Studies of animal habitat selection are important to identify and preserve the resources species depend on, yet often little attention is paid to how habitat needs vary depending on behavioral state. Fishers (Pekania pennanti) are known to be dependent on large, mature trees for resting and denning, but less is known about their habitat use when foraging or moving within a home range. METHODS: We used GPS locations collected during the energetically costly pre-denning season from 12 female fishers to determine fisher habitat selection during two critical behavioral activities: foraging (moving) or resting, with a focus on response to forest structure related to past forest management actions since this is a primary driver of fisher habitat configuration. We characterized behavior based on high-resolution GPS and collar accelerometer data and modeled fisher selection for these two behaviors within a home range (third-order selection). Additionally, we investigated whether fisher use of elements of forest structure or other important environmental characteristics changed as their availability changed, i.e., a functional response, for each behavior type. RESULTS: We found that fishers exhibited specialist selection when resting and generalist selection when moving, with resting habitat characterized by riparian drainages with dense canopy cover and moving habitat primarily influenced by the presence of mesic montane mixed conifer forest. Fishers were more tolerant of forest openings and other early succession elements when moving than resting. CONCLUSIONS: Our results emphasize the importance of considering the differing habitat needs of animals based on their movement behavior when performing habitat selection analyses. We found that resting fishers are more specialist in their habitat needs, while foraging fishers are more generalist and will tolerate greater forest heterogeneity from past disturbance.

Multi-scale brain attributes contribute to the distribution of diffuse glioma subtypes.

Gliomas are primary brain tumors and are among the most malignant types. Adult-type diffuse gliomas can be classified based on their histological and molecular signatures as IDH-wildtype glioblastoma, IDH-mutant astrocytoma, and IDH-mutant and 1p/19q-codeleted oligodendroglioma. Recent studies have shown that each subtype of glioma has its own specific distribution pattern. However, the mechanisms underlying the specific distributions of glioma subtypes are not entirely clear despite partial explanations such as cell origin. To investigate the impact of multi-scale brain attributes on glioma distribution, we constructed cumulative frequency maps for diffuse glioma subtypes based on T1w structural images and evaluated the spatial correlation between tumor frequency and diverse brain attributes, including postmortem gene expression, functional connectivity metrics, cerebral perfusion, glucose metabolism, and neurotransmitter signaling. Regression models were constructed to evaluate the contribution of these factors to the anatomic distribution of different glioma subtypes. Our findings revealed that the three different subtypes of gliomas had distinct distribution patterns, showing spatial preferences toward different brain environmental attributes. Glioblastomas were especially likely to occur in regions enriched with synapse-related pathways and diverse neurotransmitter receptors. Astrocytomas and oligodendrogliomas preferentially occurred in areas enriched with genes associated with neutrophil-mediated immune responses. The functional network characteristics and neurotransmitter distribution also contributed to oligodendroglioma distribution. Our results suggest that different brain transcriptomic, neurotransmitter, and connectomic attributes are the factors that determine the specific distributions of glioma subtypes. These findings highlight the importance of bridging diverse scales of biological organization when studying neurological dysfunction.

TransMVAN: Multi-view Aggregation Network with Transformer for Pneumonia Diagnosis.

Automated and accurate classification of pneumonia plays a crucial role in improving the performance of computer-aided diagnosis systems for chest X-ray images. Nevertheless, it is a challenging task due to the difficulty of learning the complex structure information of lung abnormality from chest X-ray images. In this paper, we propose a multi-view aggregation network with Transformer (TransMVAN) for pneumonia classification in chest X-ray images. Specifically, we propose to incorporate the knowledge from glance and focus views to enrich the feature representation of lung abnormality. Moreover, to capture the complex relationships among different lung regions, we propose a bi-directional multi-scale vision Transformer (biMSVT), with which the informative messages between different lung regions are propagated through two directions. In addition, we also propose a gated multi-view aggregation (GMVA) to adaptively select the feature information from glance and focus views for further performance enhancement of pneumonia diagnosis. Our proposed method achieves AUCs of 0.9645 and 0.9550 for pneumonia classification on two different chest X-ray image datasets. In addition, it achieves an AUC of 0.9761 for evaluating positive and negative polymerase chain reaction (PCR). Furthermore, our proposed method also attains an AUC of 0.9741 for classifying non-COVID-19 pneumonia, COVID-19 pneumonia, and normal cases. Experimental results demonstrate the effectiveness of our method over other methods used for comparison in pneumonia diagnosis from chest X-ray images.

Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images.

BACKGROUND: Ultrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD. METHOD: We propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images. RESULT AND CONCLUSION: Our proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.

Prediction of drug-target binding affinity based on multi-scale feature fusion.

Accurate prediction of drug-target binding affinity (DTA) plays a pivotal role in drug discovery and repositioning. Although deep learning methods are widely used in DTA prediction, two significant challenges persist: (i) how to effectively represent the complex structural information of proteins and drugs; (ii) how to precisely model the mutual interactions between protein binding sites and key drug substructures. To address these challenges, we propose a MSFFDTA (Multi-scale feature fusion for predicting drug target affinity) model, in which multi-scale encoders effectively capture multi-level structural information of drugs and proteins are designed. And then a Selective Cross Attention (SCA) mechanism is developed to filter out the trivial interactions between drug-protein substructure pairs and retain the important ones, which will make the proposed model better focusing on these key interactions and offering insights into their underlying mechanism. Experimental results on two benchmark datasets demonstrate that MSFFDTA is superior to several state-of-the-art methods across almost all comparison metrics. Finally, we provide the ablation and case studies with visualizations to verify the effectiveness and the interpretability of MSFFDTA. The source code is freely available at https://github.com/whitehat32/MSFF-DTA/.

Coreference Resolution Based on High-Dimensional Multi-Scale Information.

Coreference resolution is a key task in Natural Language Processing. It is difficult to evaluate the similarity of long-span texts, which makes text-level encoding somewhat challenging. This paper first compares the impact of commonly used methods to improve the global information collection ability of the model on the BERT encoding performance. Based on this, a multi-scale context information module is designed to improve the applicability of the BERT encoding model under different text spans. In addition, improving linear separability through dimension expansion. Finally, cross-entropy loss is used as the loss function. After adding BERT and span BERT to the module designed in this article, F1 increased by 0.5% and 0.2%, respectively.