检索结果-内蒙古大学图书馆

Credit risk evaluation model with textual features from loan descriptions for P2P lending

ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS 2020年 42卷 100989-100989页

作者： Zhang, Weiguo Wang, Chao Zhang, Yue Wang, Junbo South China Univ Technol Sch Business Adm Guangzhou Guangdong Peoples R China City Univ Hong Kong Dept Econ & Finance Kowloon Hong Kong Peoples R China

Previous studies on the peer-to-peer (P2P) lending market have shown that borrowers' default status is related to textual factors derived from the loan descriptions in loan applications. However, textual loan descriptions have not been fully explored in terms of their possible utility in credit risk evaluation models. In this study, we propose a new approach to construct a credit risk assessment model for the P2P lending market. This approach first utilizes a transformer encoder to extract the textual features from the loan description, and then combines them with the hard features derived from the loan application;together, they comprise the final features of a loan. Finally the combined features are fed into a two-layer feed-forward neural network to predict the loan's default probability. We perform empirical studies on two data sets of real transactions: LendingClub loan data from the American market and Renrendai loan data from the Chinese market. The results show that the model considering the textual loan description outperforms that which does not in terms of loan default prediction. Furthermore, the model is based on the transformer encoder achieving the best performance under the AUC and G-mean metrics.

关键词： Peer-to-peer lending Credit risk model transformer encoder Loan description

来源：评论

学校读者我要写书评

暂无评论

Leverage Boosting and transformer on Text-Image Matching for Cheap Fakes Detection

引用

ALGORITHMS 2022年第11期15卷 423-423页

作者： Tuan-Vinh La Dao, Minh-Son Le, Duy-Dong Thai, Kim-Phung Nguyen, Quoc-Hung Phan-Thi, Thuy-Kieu Univ Informat Technol Ho Chi Minh City 700000 Vietnam Vietnam Natl Univ Ho Chi Minh City 700000 Vietnam Natl Inst Informat & Commun Technol Tokyo 1848795 Japan Univ Econ Ho Chi Minh City 700000 Vietnam

The explosive growth of the social media community has increased many kinds of misinformation and is attracting tremendous attention from the research community. One of the most prevalent ways of misleading news is cheapfakes. Cheapfakes utilize non-AI techniques such as unaltered images with false context news to create false news, which makes it easy and "cheap" to create and leads to an abundant amount in the social media community. Moreover, the development of deep learning also opens and invents many domains relevant to news such as fake news detection, rumour detection, fact-checking, and verification of claimed images. Nevertheless, despite the impact on and harmfulness of cheapfakes for the social community and the real world, there is little research on detecting cheapfakes in the computer science domain. It is challenging to detect misused/false/out-of-context pairs of images and captions, even with human effort, because of the complex correlation between the attached image and the veracity of the caption content. Existing research focuses mostly on training and evaluating on given dataset, which makes the proposal limited in terms of categories, semantics and situations based on the characteristics of the dataset. In this paper, to address these issues, we aimed to leverage textual semantics understanding from the large corpus and integrated with different combinations of text-image matching and image captioning methods via ANN/transformer boosting schema to classify a triple of (image, caption(1), caption(2)) into OOC (out-of-context) and NOOC (no out-of-context) labels. We customized these combinations according to various exceptional cases that we observed during data analysis. We evaluate our approach using the dataset and evaluation metrics provided by the COSMOS baseline. Compared to other methods, including the baseline, our method achieves the highest Accuracy, Recall, and F1 scores.

关键词： deep learning computer vision natural language processing image-text matching cheapfakes misinformation transformer encoder

来源：评论

学校读者我要写书评

暂无评论

ACTION RECOGNITION IMPROVED BY CORRELATIONS AND ATTENTION OF SUBJECTS AND SCENE

ACTION RECOGNITION IMPROVED BY CORRELATIONS AND ATTENTION OF...

引用

IEEE International Conference on Visual Communications and Image Processing (VCIP) - Visual Communications in the Era of AI and Limited Resources

作者： Ha, Manh-Hung Chen, Oscal Tzyh-Chiang Natl Chung Cheng Univ Dept Elect Engn Chiayi Taiwan

ISBN: (纸本)9781728185514

Comprehensive activity understanding of multiple subjects in a video requires subject detection, action identification, and behavior interpretation as well as the interactions among subjects and background. This work develops the action recognition of subject(s) based on the correlations and interactions of the whole scene and subject(s) by using the Deep Neural Network (DNN). The proposed DNN consists of 3D Convolutional Neural Network (CNN), Spatial Attention (SA) generation layer, mapping convolutional fused-depth layer, transformer encoder (TE), and two fully connected layers with late fusion for final classification. Especially, the attention mechanisms in SA and TE are implemented to find out meaningful action information on spatial and temporal domains for enhancing recognition performance, respectively. The experimental results reveal that the proposed DNN shows the superior accuracies of 97.8%, 98.4% and 85.6% in the datasets of traffic police, UCF101-24 and JHMDB-21, respectively. Therefore, our DNN is an outstanding classifier for various action recognitions involving one or multiple subjects.

关键词： Deep neural network convolutional neural network spatiotemporal attention subject detection transformer encoder action recognition

来源：评论

学校读者我要写书评

暂无评论

Plant and Animal Species Recognition Based on Dynamic Vision transformer Architecture

引用

REMOTE SENSING 2022年第20期14卷 5242-5242页

作者： Pan, Hang Xie, Lun Wang, Zhiliang Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

Automatic prediction of the plant and animal species most likely to be observed at a given geo-location is useful for many scenarios related to biodiversity management and conservation. However, the sparseness of aerial images results in small discrepancies in the image appearance of different species categories. In this paper, we propose a novel Dynamic Vision transformer (DViT) architecture to reduce the effect of small image discrepancies for plant and animal species recognition by aerial image and geo-location environment information. We extract the latent representation by sampling a subset of patches with low attention weights in the transformer encoder model with a learnable mask token for multimodal aerial images. At the same time, the geo-location environment information is added to the process of extracting the latent representation from aerial images and fused with the token with high attention weights to improve the distinguishability of representation by the dynamic attention fusion model. The proposed DViT method is evaluated on the GeoLifeCLEF 2021 and 2022 datasets, achieving state-of-the-art performance. The experimental results show that fusing the aerial image and multimodal geo-location environment information contributes to plant and animal species recognition.

关键词： transformer encoder learnable mask token self-attention mechanism dynamic attention fusion plant and animal species recognition

来源：评论

学校读者我要写书评

暂无评论

基于BE-MCNN模型的新闻评论情感分析方法

引用

软件导刊 2024年第3期23卷 1-7页

作者：李文书管平浙江理工大学人工智能学院浙江理工大学信息学院浙江杭州310018

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... 详细信息

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。

关键词：情感分析 BERT模型 transformer encoder 多尺度CNN 新闻评论

来源：评论

学校读者我要写书评

暂无评论

基于硬共享机制的多任务情感分类算法研究

基于硬共享机制的多任务情感分类算法研究

引用

作者：张建中国计量大学

学位级别：硕士

情感分类任务是一种在现实生活中应用广泛,对人们的生活与工作影响较大的任务。该任务的数据中常含有明显的情感词或语气特征,因此该任务的数据中常常含有一定的相似性,进而可以利用多任务学习方法提取多个相似任务数据中的特征,提高每... 详细信息

情感分类任务是一种在现实生活中应用广泛,对人们的生活与工作影响较大的任务。该任务的数据中常含有明显的情感词或语气特征,因此该任务的数据中常常含有一定的相似性,进而可以利用多任务学习方法提取多个相似任务数据中的特征,提高每个任务的效果。但是多任务学习模型常常存在特征提取能力不足或者多任务之间互相干扰的问题。为此,本文针对该问题提出了两种转化共享特征空间干扰的算法,可以有效增强共享特征空间的表示。本文的主要研究内容如下:(1)针对硬共享模式中共享层的特征提取能力不足的问题,本文提出了基于任务识别训练的多任务学习情感分类算法。该算法首先利用多层transformer encoder模型构成共享层,并利用BERT(Bidirectional encoder Representations from transformers)模型中的知识,提高共享层中的表征能力。然后提出了任务识别训练的方法,将多个任务之间的干扰转化为区分不同任务的特征,进而提高模型对不同任务的识别效果。最后在两个多任务情感分类数据集上进行实验。实验结果表明,本文提出的方法有效提高了模型在多任务情感分类中的表现。(2)本文提出了一种基于多层残差连接Bi-LSTM(Bi-directional Long Short-Term Memory)的多任务学习情感分类算法。该算法解决了使用BERT模型带来的问题,如模型参数量增大,计算量增多,运行时间变长,以及多层transformer encoder模型特征提取能力不足等问题。首先利用注意力机制,关注输入句子中的重要词汇。然后搭建多层次残差连接Bi-LSTM神经网络,提取输入句子中多层次的序列特征,并将其与注意力机制的特征整合,作为共享层的输出。最后使用一个简单分类器即可达到较好的结果。本文在多任务多情感类别数据集上进行实验,实验结果表明,该方法较其他多任务学习方法在多情感类别数据上的效果更好。针对不同的数据集可以调整共享层中Bi-LSTM神经网络的层数,以便于提取不同层次的序列特征;该模型具有较强的特征提取能力,即使利用简单神经网络,也可以实现较好的识别效果。

关键词：深度学习多任务学习情感分类硬共享机制 transformer encoder

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Identification Algorithm for Smearing Star Image

引用

REMOTE SENSING 2021年第22期13卷 4541-4541页

作者： Han, Jinliang Yang, Xiubin Xu, Tingting Fu, Zongqiang Chang, Lin Yang, Chunlei Jin, Guang Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Zhuhai Orbita Aerosp Technol Co Ltd Zhuhai 519000 Peoples R China

In the previous study, there were a few direct star identification (star-ID) algorithms for smearing star image. An end-to-end star-ID algorithm is proposed in this article, to directly identify the smearing image from star sensors with fast attitude maneuvering. Combined with convolutional neural networks and the self-attention mechanism of transformer encoder, the algorithm can effectively classify the smearing image and identify the star. Through feature extraction and position encoding, neural networks learn the position of stars to generate semantic information and realize the end-to-end identification for the smearing star image. The algorithm can also solve the problem of low identification rate due to smearing of long exposure time for images. A dataset of dynamic stars is analyzed and constructed based on multiple angular velocities. Experiment results show that, compared with representative algorithms, the identification rate of the proposed algorithm is improved at high angular velocities. When the three-axis angular velocity is 10 & DEG;/s, the rate is still 60.4%. At the same time, the proposed algorithm has good robustness to position noise and magnitude noise.

关键词： star identification end-to-end identification smearing image transformer encoder

来源：评论

学校读者我要写书评

暂无评论

基于视线估计神经网络的教学注意力分析研究

基于视线估计神经网络的教学注意力分析研究

引用

作者：陈沁电子科技大学

学位级别：硕士

随着教育焦虑的蔓延和优质教育资源竞争愈发激烈,教育教学工作呈现出快节奏化的趋势。教师在讲课时还要兼顾观察学生的学习情况,获取反馈信息以改进教学方式方法,这给教师带来很大负担,也不利于学生的整体进步。因此亟需一些辅助手段来... 详细信息

随着教育焦虑的蔓延和优质教育资源竞争愈发激烈,教育教学工作呈现出快节奏化的趋势。教师在讲课时还要兼顾观察学生的学习情况,获取反馈信息以改进教学方式方法,这给教师带来很大负担,也不利于学生的整体进步。因此亟需一些辅助手段来帮助教师判断学生的学习状况,特别是注意力的集中情况。为了解决这一问题,本文利用基于全脸图像的三维视线估计神经网络来估计学生的视线方向,然后计算学生在教学环境中的视线落点位置,之后根据该落点与课堂的相关性来对注意力进行量化分析,主要的工作有以下几点:(1)设计和优化三维视线估计神经网络TFGaze Net和SSRGaze Net。针对人眼图像的低分辨率特性,使用了高分辨率神经网络,在特征融合时分别使用transformer encoder和软式分阶段回归的方法。经过优化与测试,TFGaze Net表现较为优异,对于不同人脸和各种头部姿态情况下的视线估计具有较好的泛化性能和稳定性。与公认的基准视线估计网络相比,TFGaze Net以较小的精度损失为代价有效地降低了模型的参数量。(2)设计了基于视线向量投影的注意力量化分析方法。利用双目摄像头获取人脸图像和深度信息,视线估计神经网络估计出视线方向,结合教室环境信息,计算出学生的视线在教室中落点的位置,依此对学生注意力进行量化,该方法不受相机安装方式限制和教室环境限制,自适应陌生的场景。(3)对注意力分析算法和视线估计神经网络进行边缘计算部署,并开展注意力分析实验。在Atlas 200DK上进行相关算法和模型的部署,设计了模拟场景下的课堂教学注意力分析实验,实际测试了注意力量化分析算法,结果表明算法具备有效性和可行性。

关键词：注意力分析三维视线估计视线落点 transformer encoder 边缘计算

来源：评论

学校读者我要写书评

暂无评论

BERT-BIGRU-CRF: A Novel Entity Relationship Extraction Model 11

BERT-BIGRU-CRF: A Novel Entity Relationship Extraction Model

引用

11th IEEE International Conference on Knowledge Graph (IEEE ICKG)

作者： Lv, Jianghai Du, Junping Zhou, Nan Xue, Zhe Beijing Univ Posts & Telecommun Beijing Key Lab Intelligent Telecommun Software & Sch Comp Sci Beijing Peoples R China

ISBN: (纸本)9781728181561

Entity name recognition and entity relationship extraction are the most critical foundation for building knowledge graph, and it is also the basic task of NPL. The main purpose of entity relationship extraction is to extract the semantic relationship between the pairs of marked entities in the sentence, that is, to determine the relationship categories between entity pairs in unstructured text based on entity identification, and to form structured data for storage and retrieval. This paper proposes a BERT-BIGRU-CRF entity relationship extraction method, which effectively changes the relationship between the pre-training generated word vector and the downstream specific NLP task, and gradually moves the downstream specific NLP task to the pre-training generated word vector. Our method achieves better performance of relationship extraction and entity name recognition, which helps to construct the knowledge graph more accurately.

关键词： Pre-training deep learning transformer encoder Sentence-level representation Masked LM

来源：评论

学校读者我要写书评

暂无评论

Radiomics of PET Using Neural Networks for Prediction of Alzheimer's Disease Diagnosis

引用

Statistics in medicine 2025年第13-14期44卷 e70128页

作者： Yimo Zhang Jon A Steingrimsson Akhil Ambekar Hwamee Oh Ani Eloyan Department of Biostatistics Brown University Providence Rhode Island USA. Department of Psychiatry and Human Behavior & Department of Cognitive Linguistic and Psychological Sciences Brown University Providence Rhode Island USA.

Positron emission tomography (PET) imaging technology is widely used for diagnosing Alzheimer's disease (AD) in people with dementia. Although various computational methods have been proposed for diagnosis of AD using PET images, prediction of disease diagnosis by leveraging longitudinal PET imaging data has not been widely studied. In this paper, we propose novel implementations of deep learning models graph neural network (GNN) and transformer encoder (TE), to leverage longitudinal sequences of PET images in addition to cognitive scores for prediction of AD diagnosis and prediction of conversion from cognitively unimpaired or mild cognitive impairment to AD using data collected in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. In addition, we compare the performance of these two approaches with other methods including simple feed-forward networks (FFN) that only utilize PET images from a single time point and recurrent neural networks (RNN) that model longitudinal images by considering them as sequences, while failing to take into account between visit time variability. We show that GNN and TE have higher predictive performance than FFN and RNN in predicting disease diagnosis, where predictive performance is measured by accuracy, area under receiver operating characteristic (AUC) curve, and the Brier score. Furthermore, we illustrate the potential of PET images in predicting conversion from mild cognitive impairment or cognitively normal to AD.

关键词： cognitive status feed‐forward network positron emission tomography recurrent neural network transformer encoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：