期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到43篇文章
< 1 2 3 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
基于CNN-Transformer encoder-BiLSTM模型的轴承剩余寿命预测 认领 引用 被引量：7
1
作者 张代林 孔康 +1 位作者 朱晨曦 杨奕婷 《华中科技大学学报（自然科学版）》 EI CAS CSCD 北大核心 2026年第5期1-8,共8页
针对复杂工况下轴承退化过程非线性强且长期依赖关系难以有效建模的问题,提出一种基于改进的CNNTransformer encoder-BiLSTM模型的剩余寿命预测方法.在该方法中,卷积神经网络(CNN)关注局部信息以更好地提取特征;改进的Transformer enco... 针对复杂工况下轴承退化过程非线性强且长期依赖关系难以有效建模的问题,提出一种基于改进的CNNTransformer encoder-BiLSTM模型的剩余寿命预测方法.在该方法中,卷积神经网络(CNN)关注局部信息以更好地提取特征;改进的Transformer encoder引入三种不同的注意力掩码机制,计算过程仅关注长期信息中重要的部分;使用双向长短期记忆网络(BiLSTM)关注所有信息的长期依赖关系.在C-MAPSS和XJTU-SY数据集上验证了模型的精度,实验结果表明:在加入高斯噪声后,该模型的估计效果优于其他方法,具有更好的稳定性. 展开更多
关键词 剩余寿命预测 注意力掩码机制 卷积神经网络 Transformer encoder 双向长短期记忆网络
暂未订购 下载PDF
Remaining Useful Life Prediction of Rail Based on Improved Pulse Separable Convolution Enhanced Transformer Encoder 认领 引用
2
作者 Zhongmei Wang Min Li +2 位作者 Jing He Jianhua Liu Lin Jia 《Journal of Transportation Technologies》 2024年第2期137-160,共24页
In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is di... In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set. 展开更多
关键词 Equipment Health Prognostics Remaining Useful Life Prediction Pulse Separable Convolution Attention Mechanism Transformer Encoder
暂未订购 下载PDF
Natural Language Processing for Chest X-Ray Reports in the Transformer Era:BERT-Like Encoders for Comprehension and GPT-Like Decoders for Generation 认领 引用 被引量：2
3
作者 Han Yuan 《iRADIOLOGY》 CSCD 2025年第4期295-301,共7页
1|Transformer for Chest X-Ray Report Analysis Natural language processing(NLP)has gained widespread use in computer-assisted chest X-ray(CXR)report analysis,particularly since the renaissance of deep learning(DL)in th... 1|Transformer for Chest X-Ray Report Analysis Natural language processing(NLP)has gained widespread use in computer-assisted chest X-ray(CXR)report analysis,particularly since the renaissance of deep learning(DL)in the 2012 ImageNet challenge.While early endeavors predominantly employed recurrent neural networks(RNN)and convolutional neural networks(CNN)[1]. 展开更多
关键词 bidirectional encoder representations from transformers chest X-ray report generative pre-trained transformer large language model natural language processing
暂未订购 下载PDF
Optimized Quantum Autoencoder 认领 引用
4
作者 Yibin Huang Muchun Yang D.L.Zhou 《Chinese Physics Letters》 SCIE EI CAS CSCD 2026年第2期117-130,共14页
Quantum autoencoder(QAE)compresses a bipartite quantum state into its subsystem using a self-checking mechanism.How to characterize and minimize the lost information in this process is essential for understanding the ... Quantum autoencoder(QAE)compresses a bipartite quantum state into its subsystem using a self-checking mechanism.How to characterize and minimize the lost information in this process is essential for understanding the compression mechanism of QAE.Here,we investigate how to minimize the lost information in QAE for any input mixed state.We theoretically show that the lost information is the quantum mutual information between the remaining subsystem and the discarded one;the encoding unitary transformation is designed to minimize this mutual information.Furthermore,we show that the optimized unitary transformation can be decomposed as the product of a permutation unitary transformation and a disentanglement unitary transformation,and the permutation unitary transformation can be searched by a regular Young tableau algorithm.When the search can be made exhaustive in lower-dimensional systems,the lost information is minimized numerically,which is shown theoretically to be a global minimum.When the dimension of the system becomes larger such that an exhaustive search is impossible,we adopt an approximate search algorithm to numerically identify that our compression scheme gives lower lost information than that from the quantum variational circuit-based QAE. 展开更多
关键词 quantum autoencoder qae compresses bipartite quantum state quantum autoencoder characterize minimize lost information quantum mutual information encoding unitary transformation compression mechanism permutation unitary transformation
暂未订购 下载PDF
基于机器视觉的电梯轿厢平层准确度检测系统研究 认领 引用
5
作者 郭春雨 《机电产品开发与创新》 2026年第4期86-88,共3页
针对电梯平层精度不准可能带来的事故风险,提出了一种基于深度学习的电梯平层精度检测系统,该系统通过在电梯停留时电梯井道的相应位置和对应楼层安装刻度尺,并且在电梯轿厢底部安装激光发射器、工业相机和光源,来获取电梯到达指定楼层... 针对电梯平层精度不准可能带来的事故风险,提出了一种基于深度学习的电梯平层精度检测系统,该系统通过在电梯停留时电梯井道的相应位置和对应楼层安装刻度尺,并且在电梯轿厢底部安装激光发射器、工业相机和光源,来获取电梯到达指定楼层后激光在对应楼层刻度尺上的位置图片并通过图像增强,数值数据增强,图形数据增强等方法来制作为数据集和测试集,并针对数据集中激光线的细小不明显等问题,提出了一种基于YOLOv5算法改进模型,该模型通过使用Transformer encoder模块替换了YOLOv5中的一些卷积块和CSP bottleneck blocks来达到对小目标的高精度检测。最后实验中随机指定楼层进行模型进行测试,结果证明该模型的最大检测误差为0.03mm。 展开更多
关键词 层精度检测 深度学习 Transformer encoder模块 YOLOv5
暂未订购 下载PDF
Text Augmentation-Based Model for Emotion Recognition Using Transformers 认领 引用
6
作者 Fida Mohammad Mukhtaj Khan +4 位作者 Safdar Nawaz Khan Marwat Naveed Jan Neelam Gohar Muhammad Bilal Amal Al-Rasheed 《Computers, Materials & Continua》 SCIE EI 2023年第9期3523-3547,共25页
Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally intelligentmachines.Graph-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC tasks.However,their... Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally intelligentmachines.Graph-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC tasks.However,their limited ability to collect and acquire contextual information hinders their effectiveness.We propose a Text Augmentation-based computational model for recognizing emotions using transformers(TA-MERT)to address this.The proposed model uses the Multimodal Emotion Lines Dataset(MELD),which ensures a balanced representation for recognizing human emotions.Themodel used text augmentation techniques to producemore training data,improving the proposed model’s accuracy.Transformer encoders train the deep neural network(DNN)model,especially Bidirectional Encoder(BE)representations that capture both forward and backward contextual information.This integration improves the accuracy and robustness of the proposed model.Furthermore,we present a method for balancing the training dataset by creating enhanced samples from the original dataset.By balancing the dataset across all emotion categories,we can lessen the adverse effects of data imbalance on the accuracy of the proposed model.Experimental results on the MELD dataset show that TA-MERT outperforms earlier methods,achieving a weighted F1 score of 62.60%and an accuracy of 64.36%.Overall,the proposed TA-MERT model solves the GBN models’weaknesses in obtaining contextual data for ERC.TA-MERT model recognizes human emotions more accurately by employing text augmentation and transformer-based encoding.The balanced dataset and the additional training samples also enhance its resilience.These findings highlight the significance of transformer-based approaches for special emotion recognition in conversations. 展开更多
关键词 Emotion recognition in conversation graph-based network text augmentation-basedmodel multimodal emotion lines dataset bidirectional encoder representation for transformer
暂未订购 下载PDF
Enhancing Arabic Cyberbullying Detection with End-to-End Transformer Model 认领 引用 被引量：1
7
作者 Mohamed A.Mahdi Suliman Mohamed Fati +2 位作者 Mohamed A.G.Hazber Shahanawaj Ahamad Sawsan A.Saad 《Computer Modeling in Engineering & Sciences》 SCIE EI 2024年第11期1651-1671,共21页
Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online spaces.To tackle this challenge,our study introduces a ... Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online spaces.To tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in English.This model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection methods.Our model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing methods.Experimental results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities. 展开更多
关键词 Cyberbullying offensive detection Bidirectional Encoder Representations from the Transformers(BERT) continuous bag of words Social Media natural language processing
暂未订购 下载PDF
基于VMD-MPE和并行双支路的变压器局部放电模式识别方法 认领 引用 被引量：1
8
作者 陈康裕 王飞 +1 位作者 曾龙兴 陈尔佳 《电工电能新技术》 CSCD 北大核心 2025年第9期100-110,共11页
针对变压器局部放电信号的非平稳性和非线性特点,本文提出了一种基于变分模态分解(VMD)和多尺度排列熵(MPE)以及并行双支路的变压器局部放电模式识别方法。首先,利用VMD技术对局部放电波形进行层次分解,分离出若干带限本征模态函数(IMF)... 针对变压器局部放电信号的非平稳性和非线性特点,本文提出了一种基于变分模态分解(VMD)和多尺度排列熵(MPE)以及并行双支路的变压器局部放电模式识别方法。首先,利用VMD技术对局部放电波形进行层次分解,分离出若干带限本征模态函数(IMF),并基于MPE提取各阶IMF分量的深层特征信息,构建特征向量样本集。接着,设计了一个并行双支路模型,其中支路一通过Transformer Encoder的多头注意力机制提取全局特征,支路二利用堆叠的一维卷积神经网络(1D-CNN)结合挤压与激励网络(SENet)进一步提取局部特征信息。通过特征融合拼接策略,将双支路提取的全局与局部特征信息有效融合,从而增强模式识别的表现力。实验结果表明,本文所提出的方法在变压器局部放电模式识别中的准确率达到96.37%,且具有较高的识别效率,能够有效提升变压器局部放电故障的诊断性能,为变压器设备的维护工作提供了坚实的技术保障。 展开更多
关键词 变压器局部放电 变分模态分解 多尺度排列熵 Transformer Encoder 一维卷积神经网络 挤压与激励网络 故障诊断
暂未订购 下载PDF
Analysis and estimation of wave-induced Doppler shift from low-incidence-angle RAR based on sea state parameters 认领 引用
9
作者 Jing Ye Yong Wan +3 位作者 Chenqing Fan Yongshou Dai Yisen Yang Xiangying Miao 《Acta Oceanologica Sinica》 SCIE CAS CSCD 2025年第9期169-182,共14页
The research on ocean dynamics information plays a crucial role in understanding ocean phenomena, assessing marine environmental impacts, and guiding engineering designs. The Doppler information observed by radars ref... The research on ocean dynamics information plays a crucial role in understanding ocean phenomena, assessing marine environmental impacts, and guiding engineering designs. The Doppler information observed by radars reflects sea surface dynamics, to which ocean waves make important contributions. Low-incidence-angle real aperture radar(RAR)demonstrates great potential for independently observing vectorial Doppler information on the ocean surface. To systematically characterize and accurately estimate the wave-induced Doppler frequency shift(WVF) from lowincidence-angle RAR, this study conducts comprehensive influencing factor analysis and establishes sea-stateparameterized WVF models. First, a simulated WVF dataset is generated under a rotating low-incidence-angle RAR.The feature parameters of WVF are then determined by analysing contributing factors including wind waves, swells,and sea state parameters. Furthermore, two WVF models(WVF_Ku P9 with 9 inputs and WVF_Ku P4 with 4 inputs) are constructed by the Transformer encoder for different application scenarios. Both models achieve high accuracy for WVF estimation with root mean square errors(RMSE) of 1.874 Hz and 2.716 Hz, respectively. The reliability and superiority of the proposed models are validated through comparisons with the Ka DOP, which is a typical geophysical model function(GMF). The findings in this paper advance the understanding of WVF characteristics and generation mechanisms. The proposed estimation models can provide reliable estimates, offering critical references for lowincidence-angle RAR applications such as ocean surface current retrieval. 展开更多
关键词 wave-induced Doppler shift parameter estimation low-incidence-angle real aperture radar sea state parameters Transformer encoder
暂未订购 下载PDF
基于机器学习的槽型结构动态变形场重构 认领 引用
10
作者 白金川 胡高波 +2 位作者 陈三桂 肖汉林 张涛 《舰船科学技术》 北大核心 2025年第22期38-45,共8页
针对目前多数重构位移场的方法在实际工程应用中存在测点数量多、位置要求高等问题,引入机器学习建立了应变与位移之间的关系,实现了位移场的重构。分析LSTM、Transformer Encoder在动态变形重构中的精度和鲁棒性;然后设计加工槽型结构... 针对目前多数重构位移场的方法在实际工程应用中存在测点数量多、位置要求高等问题,引入机器学习建立了应变与位移之间的关系,实现了位移场的重构。分析LSTM、Transformer Encoder在动态变形重构中的精度和鲁棒性;然后设计加工槽型结构搭建实验平台,对槽道侧壁进行动态加载,通过采集系统和激光位移传感器对应变、位移信息进行采集,对比分析测试集的动态预测结果与传感器的测试结果;最后,融合LSTM和Transformer Encoder这2种神经网络,提出一种新的LSTM-Transformer Encoder(LTE)网络。结果表明:测试集上LSTM网络重构的节点最大平均误差为0.610%,Transformer Encoder重构的节点最大平均相对误差为1.010%。LSTM网络相比Transformer Encoder网络具有更好鲁棒性的同时重构精度更高,提出的LTE网络在测试集上具有更小的MSE(均方误差)及更大的R2(模型拟合系数),在整体的表现上优于LSTM和Transformer Encoder。 展开更多
关键词 结构健康监测 位移场重构 LSTM Transformer Encoder
暂未订购 下载PDF
Leveraging Unlabeled Corpus for Arabic Dialect Identification 认领 引用
11
作者 Mohammed Abdelmajeed Jiangbin Zheng +3 位作者 Ahmed Murtadha Youcef Nafa Mohammed Abaker Muhammad Pervez Akhter 《Computers, Materials & Continua》 SCIE EI 2025年第5期3471-3491,共21页
Arabic Dialect Identification(DID)is a task in Natural Language Processing(NLP)that involves determining the dialect of a given piece of text in Arabic.The state-of-the-art solutions for DID are built on various deep ... Arabic Dialect Identification(DID)is a task in Natural Language Processing(NLP)that involves determining the dialect of a given piece of text in Arabic.The state-of-the-art solutions for DID are built on various deep neural networks that commonly learn the representation of sentences in response to a given dialect.Despite the effectiveness of these solutions,the performance heavily relies on the amount of labeled examples,which is labor-intensive to atain and may not be readily available in real-world scenarios.To alleviate the burden of labeling data,this paper introduces a novel solution that leverages unlabeled corpora to boost performance on the DID task.Specifically,we design an architecture that enables learning the shared information between labeled and unlabeled texts through a gradient reversal layer.The key idea is to penalize the model for learning source dataset specific features and thus enable it to capture common knowledge regardless of the label.Finally,we evaluate the proposed solution on benchmark datasets for DID.Our extensive experiments show that it performs signifcantly better,especially,with sparse labeled data.By comparing our approach with existing Pre-trained Language Models(PLMs),we achieve a new state-of-the-art performance in the DID field.The code will be available on GitHub upon the paper's acceptance. 展开更多
关键词 Arabic dialect identification natural language processing bidirectional encoder representations from transformers pre-trained language models gradient reversal layer
暂未订购 下载PDF
Semi-Supervised New Intention Discovery for Syntactic Elimination and Fusion in Elastic Neighborhoods 认领 引用
12
作者 Di Wu Liming Feng Xiaoyu Wang 《Computers, Materials & Continua》 SCIE EI 2025年第4期977-999,共23页
Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit informati... Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit information,a Semi-supervised New Intent Discovery for Elastic Neighborhood Syntactic Elimination and Fusion model(SNID-ENSEF)is proposed.Syntactic elimination contrast learning leverages verb-dominant syntactic features,systematically replacing specific words to enhance data diversity.The radius of the positive sample neighborhood is elastically adjusted to eliminate invalid samples and improve training efficiency.A neighborhood sample fusion strategy,based on sample distribution patterns,dynamically adjusts neighborhood size and fuses sample vectors to reduce noise and improve implicit information utilization and discovery accuracy.Experimental results show that SNID-ENSEF achieves average improvements of 0.88%,1.27%,and 1.30%in Normalized Mutual Information(NMI),Accuracy(ACC),and Adjusted Rand Index(ARI),respectively,outperforming PTJN,DPN,MTP-CLNN,and DWG models on the Banking77,StackOverflow,and Clinc150 datasets.The code is available at http://gffzz188fe103f8f1460as0xuwb695ppqn6cx0.ffgz.tsg.suse.edu.cn/qsdesz/SNID-ENSEF,accessed on 16 January 2025. 展开更多
关键词 Natural language understanding semi-supervised new intent discovery syntactic elimination contrast learning neighborhood sample fusion strategies bidirectional encoder representations from transformers(BERT)
暂未订购 下载PDF
基于BERT-TENER的服装质量抽检通告命名实体识别 认领 引用 被引量：2
13
作者 陈进东 胡超 +1 位作者 郝凌霄 曹丽娜 《科学技术与工程》 北大核心 2024年第34期14754-14764,共11页
识别服装质量抽检通告中的实体信息,对于评估不同区域的服装质量状况以及制定宏观政策具有重要意义。针对质量抽检通告命名实体识别存在的长文本序列信息丢失、小类样本特征学习不全等问题,以注意力机制为核心,提出了基于BERT(bidirecti... 识别服装质量抽检通告中的实体信息,对于评估不同区域的服装质量状况以及制定宏观政策具有重要意义。针对质量抽检通告命名实体识别存在的长文本序列信息丢失、小类样本特征学习不全等问题,以注意力机制为核心,提出了基于BERT(bidirectional encoder representations from transformers)和TENER(transformer encoder for NER)模型的领域命名实体识别模型。BERT-TENER模型通过预训练模型BERT获得字符的动态字向量;将字向量输入TENER模块中,基于注意力机制使得同样的字符拥有不同的学习过程,基于改进的Transformer模型进一步捕捉字符与字符之间的距离和方向信息,增强模型对不同长度、小类别文本内容的理解,并采用条件随机场模型获得每个字符对应的实体标签。在领域数据集上,BERT-TENER模型针对服装抽检领域的实体识别F_1达到92.45%,相较传统方法有效提升了命名实体识别率,并且在长文本以及非均衡的实体类别中也表现出较好的性能。 展开更多
关键词 命名实体识别 服装质量抽检通告 BERT(Bidirectional encoder representations from transformers) TENER(transformer encoder for NER)
暂未订购 下载PDF
基于BE-MCNN模型的新闻评论情感分析方法 认领 引用 被引量：3
14
作者 李文书 管平 《软件导刊》 2024年第3期1-7,共7页
实时新闻评论具有文本短、信息丰富、结构复杂等特点,情感分析难以准确捕捉其真实的情感倾向。为增强语义的特征信息,减少模型过拟合问题,提高新闻评论情感分析的准确性,提出一种融合BERT模型、Transformer En⁃coder与多尺度CNN模型的... 实时新闻评论具有文本短、信息丰富、结构复杂等特点,情感分析难以准确捕捉其真实的情感倾向。为增强语义的特征信息,减少模型过拟合问题,提高新闻评论情感分析的准确性,提出一种融合BERT模型、Transformer En⁃coder与多尺度CNN模型的新闻评论情感分析算法。首先,针对新闻评论长度较短、表达情绪观点内容较多的特点,使用BERT模型对新闻评论文本进行预训练,获得具有上下文信息的特征向量;其次,为解决模型过拟合问题,在BERT模型下游添加一层Transformer编码器;最后使用四通道双层CNN模型,通过组合不同大小尺寸的卷积核来提升模型分析新闻评论情感的性能。实验结果表明,该方法在两个新闻评论数据集上的准确率分别达到93.0%与96.4%;与不同模型的比较实验进一步证明了所提方法的有效性。 展开更多
关键词 情感分析 BERT模型 Transformer Encoder 多尺度CNN 新闻评论
暂未订购 下载PDF
基于融合策略的突发公共卫生事件网络舆情多模态负面情感识别 认领 引用 被引量：32
15
作者 曾子明 孙守强 李青青 《情报学报》 CSSCI CSCD 北大核心 2023年第5期611-622,共12页
突发公共卫生事件以社交媒体为阵地进行线下舆情的线上映射,而图文并茂的多模态信息成为公众情感表达的主要方式。为充分利用不同模态间的关联性和互补性,提升突发公共卫生事件网络舆情多模态负面情感识别精准度,本文构建了两阶段混合... 突发公共卫生事件以社交媒体为阵地进行线下舆情的线上映射,而图文并茂的多模态信息成为公众情感表达的主要方式。为充分利用不同模态间的关联性和互补性,提升突发公共卫生事件网络舆情多模态负面情感识别精准度,本文构建了两阶段混合融合策略驱动的多模态细粒度负面情感识别模型(two-stage,hybrid fusion strategy-driven multimodal fine-grained negative sentiment recognition model,THFMFNSR)。该模型包括多模态特征表示、特征融合、分类器和决策融合4个部分。本文通过收集新浪微博新冠肺炎的相关图文数据,验证了该模型的有效性,并抽取了最佳情感决策融合规则和分类器配置。研究结果表明,相比于文本、图像、图文特征融合的最优识别模型,本文模型在情感识别方面精确率分别提高了14.48%、12.92%、2.24%;在细粒度负面情感识别方面,精确率分别提高了22.73%、10.85%、3.34%。通过该多模态细粒度负面情感识别模型可感知舆情态势,从而辅助公共卫生部门和舆情管控部门决策。 展开更多
关键词 突发公共卫生事件 网络舆情 多模态 负面情感识别 bidirectional encoder representations from transformers(BERT) vision transformer(ViT)
暂未订购 下载PDF
基于图卷积神经网络的古汉语分词研究 认领 引用 被引量：11
16
作者 唐雪梅 苏祺 +1 位作者 王军 杨浩 《情报学报》 CSSCI CSCD 北大核心 2023年第6期740-750,共11页
古汉语的语法有省略、语序倒置的特点,词法有词类活用、代词名词丰富的特点,这些特点增加了古汉语分词的难度,并带来严重的out-of-vocabulary(OOV)问题。目前,深度学习方法已被广泛地应用在古汉语分词任务中并取得了成功,但是这些研究... 古汉语的语法有省略、语序倒置的特点,词法有词类活用、代词名词丰富的特点,这些特点增加了古汉语分词的难度,并带来严重的out-of-vocabulary(OOV)问题。目前,深度学习方法已被广泛地应用在古汉语分词任务中并取得了成功,但是这些研究更关注的是如何提高分词效果,忽视了分词任务中的一大挑战,即OOV问题。因此,本文提出了一种基于图卷积神经网络的古汉语分词框架,通过结合预训练语言模型和图卷积神经网络,将外部知识融合到神经网络模型中来提高分词性能并缓解OOV问题。在《左传》《战国策》和《儒林外史》3个古汉语分词数据集上的研究结果显示,本文模型提高了3个数据集的分词表现。进一步的研究分析证明,本文模型能够有效地融合词典和N-gram信息;特别是N-gram有助于缓解OOV问题。 展开更多
关键词 古汉语 汉语分词 图卷积神经网络 预训练语言模型 BERT(bidirectional encoder representations from transformers)
暂未订购 下载PDF
A Novel Named Entity Recognition Scheme for Steel E-Commerce Platforms Using a Lite BERT 认领 引用 被引量：4
17
作者 Maojian Chen Xiong Luo +2 位作者 Hailun Shen Ziyang Huang Qiaojuan Peng 《Computer Modeling in Engineering & Sciences》 SCIE EI 2021年第10期47-63,共17页
In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive position.However,it is very difficult to choose satisfactory steel raw materials from diverse s... In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive position.However,it is very difficult to choose satisfactory steel raw materials from diverse steel commodities online on steel E-commerce platforms in the purchase of staffs.In order to improve the efficiency of purchasers searching for commodities on the steel E-commerce platforms,we propose a novel deep learning-based loss function for named entity recognition(NER).Considering the impacts of small sample and imbalanced data,in our NER scheme,the focal loss,the label smoothing,and the cross entropy are incorporated into a lite bidirectional encoder representations from transformers(BERT)model to avoid the over-fitting.Moreover,through the analysis of different classic annotation techniques used to tag data,an ideal one is chosen for the training model in our proposed scheme.Experiments are conducted on Chinese steel E-commerce datasets.The experimental results show that the training time of a lite BERT(ALBERT)-based method is much shorter than that of BERT-based models,while achieving the similar computational performance in terms of metrics precision,recall,and F1 with BERT-based models.Meanwhile,our proposed approach performs much better than that of combining Word2Vec,bidirectional long short-term memory(Bi-LSTM),and conditional random field(CRF)models,in consideration of training time and F1. 展开更多
关键词 Named entity recognition bidirectional encoder representations from transformers steel E-commerce platform annotation technique
暂未订购 下载PDF
BSTFNet:An Encrypted Malicious Traffic Classification Method Integrating Global Semantic and Spatiotemporal Features 认领 引用 被引量：4
18
作者 Hong Huang Xingxing Zhang +2 位作者 Ye Lu Ze Li Shaohua Zhou 《Computers, Materials & Continua》 SCIE EI 2024年第3期3929-3951,共23页
While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning me... While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning methods relying on expert experience and the insufficient representation capabilities of existing deep learning methods for encrypted malicious traffic,we propose an encrypted malicious traffic classification method that integrates global semantic features with local spatiotemporal features,called BERT-based Spatio-Temporal Features Network(BSTFNet).At the packet-level granularity,the model captures the global semantic features of packets through the attention mechanism of the Bidirectional Encoder Representations from Transformers(BERT)model.At the byte-level granularity,we initially employ the Bidirectional Gated Recurrent Unit(BiGRU)model to extract temporal features from bytes,followed by the utilization of the Text Convolutional Neural Network(TextCNN)model with multi-sized convolution kernels to extract local multi-receptive field spatial features.The fusion of features from both granularities serves as the ultimate multidimensional representation of malicious traffic.Our approach achieves accuracy and F1-score of 99.39%and 99.40%,respectively,on the publicly available USTC-TFC2016 dataset,and effectively reduces sample confusion within the Neris and Virut categories.The experimental results demonstrate that our method has outstanding representation and classification capabilities for encrypted malicious traffic. 展开更多
关键词 Encrypted malicious traffic classification bidirectional encoder representations from transformers text convolutional neural network bidirectional gated recurrent unit
暂未订购 下载PDF
Effective short text classification via the fusion of hybrid features for IoT social data 认领 引用 被引量：5
19
作者 Xiong Luo Zhijian Yu +2 位作者 Zhigang Zhao Wenbing Zhao Jenq-Haur Wang 《Digital Communications and Networks》 SCIE CSCD 2022年第6期942-954,共13页
Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Prev... Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Previous studies mainly tackle these problems by enhancing the semantic information or the statistical information individually. However, the improvement achieved by a single type of information is limited, while fusing various information may help to improve the classification accuracy more effectively. To fuse various information for short text classification, this article proposes a feature fusion method that integrates the statistical feature and the comprehensive semantic feature together by using the weighting mechanism and deep learning models. In the proposed method, we apply Bidirectional Encoder Representations from Transformers (BERT) to generate word vectors on the sentence level automatically, and then obtain the statistical feature, the local semantic feature and the overall semantic feature using Term Frequency-Inverse Document Frequency (TF-IDF) weighting approach, Convolutional Neural Network (CNN) and Bidirectional Gate Recurrent Unit (BiGRU). Then, the fusion feature is accordingly obtained for classification. Experiments are conducted on five popular short text classification datasets and a 5G-enabled IoT social dataset and the results show that our proposed method effectively improves the classification performance. 展开更多
关键词 Information fusion Short text classi fication BERT Bidirectional encoder representations fr 0om transformers Deep learning Social data
暂未订购 下载PDF
Deep-BERT:Transfer Learning for Classifying Multilingual Offensive Texts on Social Media 认领 引用 被引量：5
20
作者 Md.Anwar Hussen Wadud M.F.Mridha +2 位作者 Jungpil Shin Kamruddin Nur Aloke Kumar Saha 《Computer Systems Science & Engineering》 SCIE EI 2023年第2期1775-1791,共17页
Offensive messages on social media,have recently been frequently used to harass and criticize people.In recent studies,many promising algorithms have been developed to identify offensive texts.Most algorithms analyze ... Offensive messages on social media,have recently been frequently used to harass and criticize people.In recent studies,many promising algorithms have been developed to identify offensive texts.Most algorithms analyze text in a unidirectional manner,where a bidirectional method can maximize performance results and capture semantic and contextual information in sentences.In addition,there are many separate models for identifying offensive texts based on monolin-gual and multilingual,but there are a few models that can detect both monolingual and multilingual-based offensive texts.In this study,a detection system has been developed for both monolingual and multilingual offensive texts by combining deep convolutional neural network and bidirectional encoder representations from transformers(Deep-BERT)to identify offensive posts on social media that are used to harass others.This paper explores a variety of ways to deal with multilin-gualism,including collaborative multilingual and translation-based approaches.Then,the Deep-BERT is tested on the Bengali and English datasets,including the different bidirectional encoder representations from transformers(BERT)pre-trained word-embedding techniques,and found that the proposed Deep-BERT’s efficacy outperformed all existing offensive text classification algorithms reaching an accuracy of 91.83%.The proposed model is a state-of-the-art model that can classify both monolingual-based and multilingual-based offensive texts. 展开更多
关键词 Offensive text classification deep convolutional neural network(DCNN) bidirectional encoder representations from transformers(BERT) natural language processing(NLP)
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 3 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈