From text to image:challenges in integrating vision into ChatGPT for medical image interpretation

Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive text data.Their potential integration into clinical settings offers a promising avenue that could transform clinical diagnosis and decision-making processes in the future(Thirunavukarasu et al.,2023).This article aims to provide an in-depth analysis of LLMs’current and potential impact on clinical practices.Their ability to generate differential diagnosis lists underscores their potential as invaluable tools in medical practice and education(Hirosawa et al.,2023;Koga et al.,2023).

基于改进TextRank的科技文本关键词抽取方法

针对科技文本关键词抽取任务中抽取出现次数少但能较好表达文本主旨的词语效果差的问题,提出一种基于改进TextRank的关键词抽取方法。首先,利用词语的词频-逆文档频率(TF-IDF)统计特征和位置特征优化共现图中词语间的概率转移矩阵,通过迭代计算得到词语的初始得分;然后,利用K-Core(K-Core decomposition)算法挖掘KCore子图得到词语的层级特征,利用平均信息熵特征衡量词语的主题表征能力;最后,在词语初始得分的基础上融合层级特征和平均信息熵特征,从而确定关键词。实验结果表明,在公开数据集上,与TextRank方法和OTextRank(Optimized TextRank)方法相比,所提方法在抽取不同关键词数量的实验中,F1均值分别提高了6.5和3.3个百分点;在科技服务项目数据集上,与TextRank方法和OTextRank方法相比,所提方法在抽取不同关键词数量的实验中,F1均值分别提高了7.4和3.2个百分点。实验结果验证了所提方法抽取出现频率低但较好表达文本主旨关键词的有效性。

Context Information and Fragments Based Cross-Domain Word Segmentation

A new joint decoding strategy that combines the character-based and word-based conditional random field model is proposed.In this segmentation framework,fragments are used to generate candidate Out-of-Vocabularies(OOVs).After the initial segmentation,the segmentation fragments are divided into two classes as "combination"(combining several fragments as an unknown word) and "segregation"(segregating to some words).So,more OOVs can be recalled.Moreover,for the characteristics of the cross-domain segmentation,context information is reasonably used to guide Chinese Word Segmentation(CWS).This method is proved to be effective through several experiments on the test data from Sighan Bakeoffs 2007 and Bakeoffs 2010.The rates of OOV recall obtain better performance and the overall segmentation performances achieve a good effect.

基于DAN与FastText的藏文短文本分类研究

随着藏文信息不断融入社会生活,越来越多的藏文短文本数据存在网络平台上。针对传统分类方法在藏文短文本上分类性能低的问题,文中提出了一种基于DAN-FastText的藏文短文本分类模型。该模型使用FastText网络在较大规模的藏文语料上进行无监督训练获得预训练的藏文音节向量集,使用预训练的音节向量集将藏文短文本信息转化为音节向量,把音节向量送入DAN(Deep Averaging Networks)网络并在输出阶段融合经过FastText网络训练的句向量特征,最后通过全连接层和softmax层完成分类。在公开的TNCC(Tibetan News Classification Corpus)新闻标题数据集上所提模型的Macro-F1是64.53%,比目前最好评测结果TiBERT模型的Macro-F1得分高出2.81%,比GCN模型的Macro-F1得分高出6.14%,融合模型具有较好的藏文短文本分类效果。

一种利用词典扩展数据库模式信息的Text2SQL方法

现有Text2SQL方法严重依赖表名和列名在自然语言查询中的显式提及,在同物异名的实际应用场景中准确率急剧下降.此外,这些方法仅仅依赖数据库模式捕捉数据库建模的领域知识,而数据库模式作为结构化的元数据,其表达领域知识的能力是非常有限的,即使有经验的程序员也很难仅从数据库模式完全领会该数据库建模的领域知识,因此程序员必须依赖详细的数据库设计文档才能构造SQL语句以正确地表达特定的查询.为此,本文提出一种利用词典扩展数据库模式信息的Text2SQL方法,该方法从数据库表名和列名解析出其中的单词或短语,查询词典获取这些单词或短语的语义解释,将这些解释看成是相应表名或列名的扩展内容,与表名、列名及其他数据库模式信息(主键、外键等)相结合,作为模型的输入,从而使模型能够更全面地学习数据库建模的应用领域知识.在Spider-syn和Spider数据集上进行的实验说明了所提出方法的有效性,即使自然语言查询中使用的表名和列名与数据库模式中对应的表名和列名完全不同,本文方法也能够得到较好的SQL翻译结果,明显优于最新提出的抗同义词替换攻击的方法.

多视图融合DJ-TextRCNN的古籍文本主题推荐研究

传统编目分类和规则匹配方法存在工作效能低、过度依赖专家知识、缺乏对古籍文本自身语义的深层次挖掘、编目主题边界模糊、较难实现对古籍文本领域主题的精准推荐等问题。为此,本文结合古籍语料特征探究如何实现精准推荐符合研究者需求的文本主题内容的方法,以推动数字人文研究的进一步发展。首先,选取本课题组前期标注的古籍语料数据进行主题类别标注和视图分类;其次,构建融合BERT(bidirectional encoder representation from transformers)预训练模型、改进卷积神经网络、循环神经网络和多头注意力机制的语义挖掘模型;最后,融入“主体-关系-客体”多视图的语义增强模型,构建DJ-TextRCNN(DianJi-recurrent convolutional neural networks for text classification)模型实现对典籍文本更细粒度、更深层次、更多维度的语义挖掘。研究结果发现,DJ-TextRCNN模型在不同视图下的古籍主题推荐任务的准确率均为最优。在“主体-关系-客体”视图下,精确率达到88.54%,初步实现了对古籍文本的精准主题推荐,对中华文化深层次、细粒度的语义挖掘具有一定的指导意义。

基于SWPF2vec和DJ-TextRCNN的古籍文本主题分类研究

以编目分类和规则匹配为主的古籍文本主题分类方法存在工作效能低、专家知识依赖性强、分类依据单一化、古籍文本主题自动分类难等问题。对此,本文结合古籍文本内容和文字特征,尝试从古籍内容分类得到符合研究者需求的主题,推动数字人文研究范式的转型。首先,参照东汉古籍《说文解字》对文字的分析方式,以前期标注的古籍语料数据集为基础,构建全新的“字音(说)-原文(文)-结构(解)-字形(字)”四维特征数据集。其次,设计四维特征向量提取模型(speaking,word,pattern,and font to vector,SWPF2vec),并结合预训练模型实现对古籍文本细粒度的特征表示。再其次,构建融合卷积神经网络、循环神经网络和多头注意力机制的古籍文本主题分类模型(dianji-recurrent convolutional neural networks for text classification,DJ-TextRCNN)。最后,融入四维语义特征,实现对古籍文本多维度、深层次、细粒度的语义挖掘。在古籍文本主题分类任务上,DJ-TextRCNN模型在不同维度特征下的主题分类准确率均为最优,在“说文解字”四维特征下达到76.23%的准确率,初步实现了对古籍文本的精准主题分类。

基于BERT和TextCNN的智能制造成熟度评估方法

随着智能制造2025目标的临近,企业为了解自身能力水平纷纷加入到智能制造成熟度评估的行列中。然而,由于智能制造成熟度评估标准的复杂性,企业缺乏其对行业水平的了解,导致企业贸然申请,浪费自身时间的同时又占用大量评估资源。鉴于此,设计了一种新的评估流程,采用文本处理算法对整个评估过程进行了重构,通过利用国标文件中智能制造成熟度评估标准,将其作为训练集,采用基于预训练语言模型与文本神经网络(BERT+TextCNN)相结合的智能评估算法代替人工评估。在真实的企业智能制造数据集上的验证表明,当BERT+TextCNN评估模型在卷积核为[2,3,4]、迭代次数为6次、学习率为3e-5时,对智能制造成熟度进行评估,准确率达到85.32%。这表明所设计的评估方法能够较准确地帮助企业完成智能制造成熟度自评估,有助于企业了解自身智能制造能力水平,制定正确的发展方向。

树立行业发展新方向——Techtextil&Texprocess 2024亮点回顾

为期4天的法兰克福国际产业用纺织品及非织造布展览会及国际纺织品及柔性材料缝制加工展览会(Techtextil&Texprocess 2024)吸引了来自全球53个国家和地区的1700家领先企业参展和来自102个国家和地区的38000名观众,展会规模再创新高,充分彰显了纺织行业蓬勃的生命力与持续的创新力。

Identifying multidisciplinary problems from scientific publications based on a text generation method

Purpose:A text generation based multidisciplinary problem identification method is proposed,which does not rely on a large amount of data annotation.Design/methodology/approach:The proposed method first identifies the research objective types and disciplinary labels of papers using a text classification technique;second,it generates abstractive titles for each paper based on abstract and research objective types using a generative pre-trained language model;third,it extracts problem phrases from generated titles according to regular expression rules;fourth,it creates problem relation networks and identifies the same problems by exploiting a weighted community detection algorithm;finally,it identifies multidisciplinary problems based on the disciplinary labels of papers.Findings:Experiments in the“Carbon Peaking and Carbon Neutrality”field show that the proposed method can effectively identify multidisciplinary research problems.The disciplinary distribution of the identified problems is consistent with our understanding of multidisciplinary collaboration in the field.Research limitations:It is necessary to use the proposed method in other multidisciplinary fields to validate its effectiveness.Practical implications:Multidisciplinary problem identification helps to gather multidisciplinary forces to solve complex real-world problems for the governments,fund valuable multidisciplinary problems for research management authorities,and borrow ideas from other disciplines for researchers.Originality/value:This approach proposes a novel multidisciplinary problem identification method based on text generation,which identifies multidisciplinary problems based on generative abstractive titles of papers without data annotation required by standard sequence labeling techniques.

CVTD: A Robust Car-Mounted Video Text Detector

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.

Blockchain-Based Certificateless Cross-Domain Authentication Scheme in the Industrial Internet of Things

The Industrial Internet of Things(IIoT)consists of massive devices in different management domains,and the lack of trust among cross-domain entities leads to risks of data security and privacy leakage during information exchange.To address the above challenges,a viable solution that combines Certificateless Public Key Cryptography(CL-PKC)with blockchain technology can be utilized.However,as many existing schemes rely on a single Key Generation Center(KGC),they are prone to problems such as single points of failure and high computational overhead.In this case,this paper proposes a novel blockchain-based certificateless cross-domain authentication scheme,that integrates the threshold secret sharing mechanism without a trusted center,meanwhile,adopts blockchain technology to enable cross-domain entities to authenticate with each other and to negotiate session keys securely.This scheme also supports the dynamic joining and removing of multiple KGCs,ensuring secure and efficient cross-domain authentication and key negotiation.Comparative analysiswith other protocols demonstrates that the proposed cross-domain authentication protocol can achieve high security with relatively lowcomputational overhead.Moreover,this paper evaluates the scheme based on Hyperledger Fabric blockchain environment and simulates the performance of the certificateless scheme under different threshold parameters,and the simulation results show that the scheme has high performance.

A Blockchain-Based Efficient Cross-Domain Authentication Scheme for Internet of Vehicles

The Internet of Vehicles(IoV)is extensively deployed in outdoor and open environments to effectively address traffic efficiency and safety issues by connecting vehicles to the network.However,due to the open and variable nature of its network topology,vehicles frequently engage in cross-domain interactions.During such processes,directly uploading sensitive information to roadside units for interaction may expose it to malicious tampering or interception by attackers,thus compromising the security of the cross-domain authentication process.Additionally,IoV imposes high real-time requirements,and existing cross-domain authentication schemes for IoV often encounter efficiency issues.To mitigate these challenges,we propose CAIoV,a blockchain-based efficient cross-domain authentication scheme for IoV.This scheme comprehensively integrates technologies such as zero-knowledge proofs,smart contracts,and Merkle hash tree structures.It divides the cross-domain process into anonymous cross-domain authentication and safe cross-domain authentication phases to ensure efficiency while maintaining a balance between efficiency and security.Finally,we evaluate the performance of CAIoV.Experimental results demonstrate that our proposed scheme reduces computational overhead by approximately 20%,communication overhead by around 10%,and storage overhead by nearly 30%.

J-TEXT动态扰动磁场线圈电磁结构分析

为了研究J-TEXT装置的动态扰动磁场线圈在放电破裂时刻的受力情况,使用TSC程序对J-TEXT装置进行等离子体放电模拟,得到了放电破裂期间等离子体电流及极向场线圈电流等数据,模拟结果与实验数据吻合。利用有限元分析软件ANSYS建立J-TEXT仿真模型,并导入模拟得到的破裂放电数据,将电流数据作为载荷施加在等离子体电流丝、极向场线圈等仿真模型中,对动态扰动磁场线圈进行电磁结构耦合分析,得到扰动磁场线圈受力情况。

A Post-Quantum Cross-Domain Authentication Scheme Based on Multi-Chain Architecture

Due to the rapid advancements in network technology,blockchain is being employed for distributed data storage.In the Internet of Things(IoT)scenario,different participants manage multiple blockchains located in different trust domains,which has resulted in the extensive development of cross-domain authentication techniques.However,the emergence of many attackers equipped with quantum computers has the potential to launch quantum computing attacks against cross-domain authentication schemes based on traditional cryptography,posing a significant security threat.In response to the aforementioned challenges,our paper demonstrates a post-quantum cross-domain identity authentication scheme to negotiate the session key used in the cross-chain asset exchange process.Firstly,our paper designs the hiding and recovery process of user identity index based on lattice cryptography and introduces the identity-based signature from lattice to construct a post-quantum cross-domain authentication scheme.Secondly,our paper utilizes the hashed time-locked contract to achieves the cross-chain asset exchange of blockchain nodes in different trust domains.Furthermore,the security analysis reduces the security of the identity index and signature to Learning With Errors(LWE)and Short Integer Solution(SIS)assumption,respectively,indicating that our scheme has post-quantum security.Last but not least,through comparison analysis,we display that our scheme is efficient compared with the cross-domain authentication scheme based on traditional cryptography.

Method to Remove Handwritten Texts Using Smart Phone

To remove handwritten texts from an image of a document taken by smart phone,an intelligent removal method was proposed that combines dewarping and Fully Convolutional Network with Atrous Convolutional and Atrous Spatial Pyramid Pooling(FCN-AC-ASPP).For a picture taken by a smart phone,firstly,the image is transformed into a regular image by the dewarping algorithm.Secondly,the FCN-AC-ASPP is used to classify printed texts and handwritten texts.Lastly,handwritten texts can be removed by a simple algorithm.Experiments show that the classification accuracy of the FCN-AC-ASPP is better than FCN,DeeplabV3+,FCN-AC.For handwritten texts removal effect,the method of combining dewarping and FCN-AC-ASPP is superior to FCN-AC-ASP alone.

CINO-TextGCN:融合CINO与TextGCN的藏文文本分类模型研究

为提高藏文新闻文本分类准确性,文章提出一种融合少数民族语言预训练模型(Chinese Minority Pr-etrained Language Model,CINO)和图卷积神经网络模型(Text Graph Convolutional Networks,TextGCN)的方法,即CINO-TextGCN模型。为有效评测该模型对藏文文本的分类性能,自建了较大规模和较高质量的藏文新闻文本公开数据集TNEWS(https://github.com/LG2016/CINO-TextGCN),通过实验发现,CINO-Text-GCN在公开数据集TNCC上的准确率为74.20%,在TNEWS上为83.96%。因此,该融合模型能够较好地捕捉到藏文文本语义,提升藏文文本分类性能。

Introducing MagBERT:A language model for magnesium textual data mining and analysis

Magnesium(Mg)based materials hold immense potential for various applications due to their lightweight and high strength-to-weight ratio.However,to fully harness the potential of Mg alloys,structured analytics are essential to gain valuable insights from centuries of accumulated knowledge.Efficient information extraction from the vast corpus of scientific literature is crucial for this purpose.In this work,we introduce MagBERT,a BERT-based language model specifically trained for Mg-based materials.Utilizing a dataset of approximately 370,000 abstracts focused on Mg and its alloys,MagBERT is designed to understand the intricate details and specialized terminology of this domain.Through rigorous evaluation,we demonstrate the effectiveness of MagBERT for information extraction using a fine-tuned named entity recognition(NER)model,named MagNER.This NER model can extract mechanical,microstructural,and processing properties related to Mg alloys.For instance,we have created an Mg alloy dataset that includes properties such as ductility,yield strength,and ultimate tensile strength(UTS),along with standard alloy names.The introduction of MagBERT is a novel advancement in the development of Mg-specific language models,marking a significant milestone in the discovery of Mg alloys and textual information extraction.By making the pre-trained weights of MagBERT publicly accessible,we aim to accelerate research and innovation in the field of Mg-based materials through efficient information extraction and knowledge discovery.

Text-to-SQL文本信息处理技术研究综述

信号与信息处理的需求日益增加,离不开数据处理技术,数据处理需要数据库的支持,然而没有经过训练的使用者会因为不熟悉数据库操作产生诸多问题。文本转结构化查询语言(Text to Structured Query Language,Text-to-SQL)的出现,使用户无需掌握结构化查询语言(Structured Query Language,SQL)也能够熟练操作数据库。介绍Text-to-SQL的研究背景及面临的挑战;介绍Text-to-SQL关键技术、基准数据集、模型演变及最新研究进展,关键技术包括Transformer等主流技术,用于模型训练的基准数据集包括WikiSQL和Spider;介绍Text-to-SQL不同阶段模型的特点,详细阐述Text-to-SQL最新研究成果的工作原理,包括模型构建、解析器设计及数据集生成;总结Text-to-SQL未来的发展方向及研究重点。

YOLOv5ST:A Lightweight and Fast Scene Text Detector

Scene text detection is an important task in computer vision.In this paper,we present YOLOv5 Scene Text(YOLOv5ST),an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection.Our primary goal is to enhance inference speed without sacrificing significant detection accuracy,thereby enabling robust performance on resource-constrained devices like drones,closed-circuit television cameras,and other embedded systems.To achieve this,we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation,including replacing standard convolution with depth-wise convolution,adopting the C2 sequence module in place of C3,employing Spatial Pyramid Pooling Global(SPPG)instead of Spatial Pyramid Pooling Fast(SPPF)and integrating Bi-directional Feature Pyramid Network(BiFPN)into the neck.Experimental results demonstrate a remarkable 26%improvement in inference speed compared to the baseline,with only marginal reductions of 1.6%and 4.2%in mean average precision(mAP)at the intersection over union(IoU)thresholds of 0.5 and 0.5:0.95,respectively.Our work represents a significant advancement in scene text detection,striking a balance between speed and accuracy,making it well-suited for performance-constrained environments.