检索结果-南通市图书馆

维普期刊数据库

Improving the Segmentation of Arabic Handwriting Using Ligature Detection Technique

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2015-2034页

作者： Husam Ahmad Al Hamad Mohammad Shehab college of Computer Sciences and Informatics Amman Arab UniversityAmman11953Jordan

Recognizing handwritten characters remains a critical and formidable challenge within the realm of computervision. Although considerable strides have been made in enhancing English handwritten character recognitionthrough various techniques, deciphering Arabic handwritten characters is particularly intricate. This complexityarises from the diverse array of writing styles among individuals, coupled with the various shapes that a singlecharacter can take when positioned differently within document images, rendering the task more perplexing. Inthis study, a novel segmentation method for Arabic handwritten scripts is suggested. This work aims to locatethe local minima of the vertical and diagonal word image densities to precisely identify the segmentation pointsbetween the cursive letters. The proposed method starts with pre-processing the word image without affectingits main features, then calculates the directions pixel density of the word image by scanning it vertically and fromangles 30° to 90° to count the pixel density fromall directions and address the problem of overlapping letters, whichis a commonly attitude in writing Arabic texts by many people. Local minima and thresholds are also determinedto identify the ideal segmentation area. The proposed technique is tested on samples obtained fromtwo datasets: Aself-curated image dataset and the IFN/ENIT dataset. The results demonstrate that the proposed method achievesa significant improvement in the proportions of cursive segmentation of 92.96% on our dataset, as well as 89.37%on the IFN/ENIT dataset.

关键词： Arabic handwritten segmentation image processing ligature detection technique intelligent recognition

Chinese Clinical Named Entity Recognition Using Multi-Feature Fusion and Multi-Scale Local Context Enhancement

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第8期80卷 2283-2299页

作者： Meijing Li Runqing Huang Xianxian Qi college of Information Engineering Shanghai Maritime UniversityShanghai200306China

Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical ***,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity *** address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context *** model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity ***,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the ***,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s *** obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,*** results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall *** can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.

关键词： CNER multi-feature fusion BiLSTM CNN MHA

Enhancing CO_(2)capture of an aminoethylethanolamine-based non-aqueous absorbent by using tertiary amine as a proton-transfer mediator:From performance to mechanism

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第6期140卷 146-156页

作者： Xiaobin Zhou DanWang Chao Liu Guohua Jing Bihong Lv Dunqiu Wang college of Environmental Science and Engineering Guilin University of TechnologyGuilin 541004China The Guangxi Key Laboratory of Theory and Technology for Environmental Pollution Control Guilin University of TechnologyGuilin 541004China college of Chemical Engineering Huaqiao UniversityXiamen 361021China

Non-aqueous absorbents(NAAs)have attracted increasing attention for CO_(2)capture because of their great energy-saving *** diamines which can provide high CO_(2)absorption loading are promising candidates for formulating NAAs but suffer disadvantages in *** this study,a promising strategy that using tertiary amines(TAs)as proton-transfer mediators was proposed to enhance the regenerability of an aminoethylethanolamine(AEEA,diamine)/dimethyl sulfoxide(DMSO)(A/D)***,some employed TAs such as N,N-diethylaminoethanol(DEEA),N,N,N’,N’’,N’’-pentamethyldiethylenetriamine(PMDETA),3-dimethylamino-1-propanol(3DMA1P),and N,N-dimethylethanolamine(DMEA)enhanced not only the regenerability of the A/D NAA but also the CO_(2)absorption ***,the CO_(2)absorption loading and cyclic loading were increased by about 12.7%and 15.5%-22.7%,*** TA-enhanced CO_(2)capture mechanism was comprehensively explored via nuclear magnetic resonance technique and quantum chemical *** CO_(2)absorption,the TA acted as an ultimate proton acceptor for AEEA-zwitterion and enabled more AEEA to form carbamate species(AEEACOO-)to store CO_(2),thus enhancing CO_(2)*** CO_(2)desorption,the TA first provided protons directly to AEEACOO-as a proton donor;moreover,it functioned as a proton carrier and facilitated the low-energy step-wise proton transfer from protonated AEEA to AEEACOO-.Consequently,the presence of TA made it easier for AEEACOO-to obtain protons to decompose,resulting in enhanced CO_(2)*** a word,introducing the TA as a proton-transfer mediator into the A/D NAA enhanced both the CO_(2)absorption performance and the regenerability,which was an efficient way to“kill two birds with one stone”.

关键词： Carbon dioxide capture Non-aqueous absorbent Tertiary amine Proton-transfer mediator Enhanced mechanism

维普期刊数据库

Sensitivity of ghost imaging compared to conventional imaging [Invited]

在线全文

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第6期22卷 15-32页

作者： Long-Kun Du Shuai Sun Yao-Kun Xu Hui-Zu Lin Ning-Yi Leng Wei-Tao Liu Institute for Quantum Science and Technology College of ScienceNational University of Defense TechnologyChangsha 410073China Interdisciplinary Center of Quantum Information National University of Defense TechnologyChangsha 410073China Hunan Key Laboratory of Mechanism and Technology of Quantum Information Changsha 410073China college of Electronic Science and Technology National University of Defense TechnologyChangsha 410073China Department of Mathematics College of ScienceNational University of Defense TechnologyChangsha 410073China

Ghost imaging has been attracting more and more attention, which provides a way to obtain images of objects with only a single-pixel detector. Considering possible applications, it becomes urgent to clarify the sensitivity of ghost imaging. Due to the unique characteristics of single-pixel detectors, which collect photons without distributing them to multiple pixels,often outperforming array sensors, ghost imaging is believed to be more sensitive than conventional imaging. However,a systematic analysis on the sensitivity of ghost imaging is yet to be completed. In this paper, we present a method for quantitatively assessing the sensitivity of ghost imaging. A detailed comparison is provided between ghost imaging and conventional imaging, taking into account the particle nature of photons and the noise of detection. With the settings of the two imaging methods being the same to the most extent, the minimal required number of detected photons for images of a certain quality is considered. For the thermal source version, ghost imaging demonstrates enhanced sensitivity under practical situations, with noise *** an entangled source, ghost imaging surpasses conventional imaging techniques in terms of sensitivity obviously. In one word, ghost imaging promises higher sensitivity at low photon flux and noisy situations.

关键词： sensitivity ghost imaging conventional imaging

维普期刊数据库

Knowledge enhanced graph inference network based entity-relation extraction and knowledge graph construction for industrial domain

在线全文

学校读者我要写书评

暂无评论

Frontiers of Engineering Management 2024年第1期11卷 143-158页

作者： Zhulin HAN Jian WANG college of Electronic and Information Engineering Tongji UniversityShanghai 200092China

With the escalating complexity in production scenarios, vast amounts of production information are retained within enterprises in the industrial domain. Probing questions of how to meticulously excavate value from complex document information and establish coherent information links arise. In this work, we present a framework for knowledge graph construction in the industrial domain, predicated on knowledge-enhanced document-level entity and relation extraction. This approach alleviates the shortage of annotated data in the industrial domain and models the interplay of industrial documents. To augment the accuracy of named entity recognition, domain-specific knowledge is incorporated into the initialization of the word embedding matrix within the bidirectional long short-term memory conditional random field (BiLSTM-CRF) framework. For relation extraction, this paper introduces the knowledge-enhanced graph inference (KEGI) network, a pioneering method designed for long paragraphs in the industrial domain. This method discerns intricate interactions among entities by constructing a document graph and innovatively integrates knowledge representation into both node construction and path inference through TransR. On the application stratum, BiLSTM-CRF and KEGI are utilized to craft a knowledge graph from a knowledge representation model and Chinese fault reports for a steel production line, specifically SPOnto and SPFRDoc. The F1 value for entity and relation extraction has been enhanced by 2% to 6%. The quality of the extracted knowledge graph complies with the requirements of real-world production environment applications. The results demonstrate that KEGI can profoundly delve into production reports, extracting a wealth of knowledge and patterns, thereby providing a comprehensive solution for production management.

关键词： knowledge graph construction industrial BiLSTM-CRF document-level relation extraction graph inference

Comparison of cytokine levels in prostatic secretion between the Ⅲa and Ⅲb subtypes of prostatitis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Asian Journal of Andrology 2024年第1期26卷 77-84页

作者： Cheng-Lin Han Yu-Xuan Deng Peng Hu Bin-Tao Hu Tao Wang Ji-Hong Liu Ming-Chao Li Department of Urology Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430000China

Chronic prostatitis/chronic pelvic pain syndrome(CP/CPPS),also known as National Institutes of Health(NIH)type Ⅲ prostatitis,is a common disorder with an unclear etiology and no known curative *** on the presence or absence of leukocytes in expressed prostatic secretion(EPS),CP/CPPS is classifiedfurther into Illa(inflammatory)and Illb(noninflammatory)***,the severity of symptoms is not entirely consistent with the white blood cell(WBC)*** the preliminary finding of a link between inflammatory cytokines and CP/CPPS,we performed this clinical study with the aim of identifying cytokines that are differentially expressed according to whether the prostatitis subtype is Ⅲa or Ⅲ*** found that granulocyte colony-stimulating factor(G-CSF),interleukin-18(IL-18),and monocyte chemoattractant protein-1(MCP-1)levels were significantly elevated and interferon-inducible protein-10(IP-10)and platelet-derived growth factor-BB(PDGF-BB)levels were downregulated in the EPS of patients with type Ⅲa *** a word,it is a meaningful study in which we investigate the levels of various cytokines in EPS according to whether prostatitis is the Ⅲa or Ⅲb *** combination of G-CSF,IL-18,MCP-1,IP-10,and PDGF-BB expression levels could form a basis for classification,diagnosis,and therapeutic targets in clinical P/CPPS.

关键词： chronic prostatitis/chronic pelvic pain syndrome(CP/CPPS) cytokines NIH-Ⅲa NIH-ⅢB

Fake News Detection Based on Cross-Modal Message Aggregation and Gated Fusion Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 1521-1542页

作者： Fangfang Shan Mengyao Liu Menghan Zhang Zhenyu Wang college of Computer Zhongyuan University of TechnologyZhengzhou450007China Henan Key Laboratory of Cyberspace Situation Awareness Zhengzhou450001China

Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion and daily *** to pure text content,multmodal content significantly increases the visibility and share ability of *** has made the search for efficient modality representations and cross-modal information interaction methods a key focus in the field of multimodal fake news *** effectively address the critical challenge of accurately detecting fake news on social media,this paper proposes a fake news detection model based on crossmodal message aggregation and a gated fusion network(MAGF).MAGF first uses BERT to extract cumulative textual feature representations and word-level features,applies Faster Region-based ConvolutionalNeuralNetwork(Faster R-CNN)to obtain image objects,and leverages ResNet-50 and Visual Geometry Group-19(VGG-19)to obtain image region features and global *** image region features and word-level text features are then projected into a low-dimensional space to calculate a text-image affinity matrix for cross-modal message *** gated fusion network combines text and image region features to obtain adaptively aggregated *** interaction matrix is derived through an attention mechanism and further integrated with global image features using a co-attention mechanism to producemultimodal ***,these fused features are fed into a classifier for news *** were conducted on two public datasets,Twitter and *** show that the proposed model achieves accuracy rates of 91.8%and 88.7%on the two datasets,respectively,significantly outperforming traditional unimodal and existing multimodal models.

关键词： Fake news detection cross-modalmessage aggregation gate fusion network co-attention mechanism multi-modal representation

DeBERTa-GRU: Sentiment Analysis for Large Language Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4219-4236页

作者： Adel Assiri Abdu Gumaei Faisal Mehmood Touqeer Abbas Sami Ullah Department of Informatics for Business College of BusinessKing Khalid UniversityAbha61421Saudi Arabia Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China Department of Computer Science and Technology Beijing University of Chemical TechnologyBeijing100029China Department of Computer Science Government College University FaisalabadFaisalabadPunjab38000Pakistan

Modern technological advancements have made social media an essential component of daily *** media allow individuals to share thoughts,emotions,and *** analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the *** analysis is essential in business and society because it impacts strategic *** analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance *** execution time increases due to the sequential processing of the sequence ***,the calculation times for the Transformer models are reduced because of the parallel *** study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their *** particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment *** the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics *** proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.

关键词： DeBERTa GRU Naive Bayes LSTM sentiment analysis large language model

Constructing the Impossible Differential of Type-II GFN with Boolean Function and Its Application to WARP

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 80-89页

作者： Jiali SHI Guoqiang LIU Chao LI college of Liberal Arts and Sciences National University of Defense Technology Hunan Engineering Research Center of Commercial Cryptography Theory and Technology Innovation State Key Laboratory of Information Security Institute of Information Engineering

Type-Ⅱ generalized Feist el network(GFN) has attracted a lot of attention for its simplicity and high *** differential attack is one of the powerful cryptanalytic approaches for word-oriented block ciphers such as Feistel-like *** deduce the impossible differential of Type-Ⅱ GFN by analyzing the Boolean function in the middle *** main idea is to investigate the expression with the variable representing the plaintext(ciphertext) difference words for the internal state *** adopting the miss-in-the-middle approach,we can construct the impossible differential of Type-Ⅱ *** an illustration,we apply this approach to WARP,a lightweight 128-bit block cipher with a 128-bit key which was presented by Banik et *** SAC *** structure of WARP is a 32-branch Type-Ⅱ ***,we find two 21-round truncated impossible differentials and implement a 32-round key recovery attack on *** the 32-round key recovery attack on WARP,some observations are used to mount an effective *** the advantage of the early abort technique,the data,time,and memory complexities are 2125.69chosen plaintexts,2126.6832-round encryptions,and 2100-bit,*** the best of our knowledge,this is the best attack on WARP in the single-key scenario.

关键词： Ciphers Boolean functions Parallel processing Complexity theory