检索结果-南通市图书馆

A Transformer-Assisted Cascade Learning Network for Choroidal Vessel Segmentation

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 Computer Science & Technology 2024年第2期39卷 286-304页

作者：温阳吴依林毕磊石武祯刘潇骁许毓鹏许迅曹文明冯大淦 Guangdong Provincial Key Laboratory of Intelligent information Processing School of Electronics and Information EngineeringShenzhen UniversityShenzhen 518060China Institute of Translational medicine Shanghai Jiao Tong UniversityShanghai 200240China Department of Ophthalmology Shanghai General HospitalShanghai Jiao Tong University School of MedicineShanghai 200080China School of information Technologies The University of SydneySydney 2006Australia

As a highly vascular eye part,the choroid is crucial in various eye disease ***,limited research has focused on the inner structure of the choroid due to the challenges in obtaining sufficient accurate label data,particularly for the choroidal ***,the existing direct choroidal vessel segmentation methods for the intelligent diagnosis of vascular assisted ophthalmic diseases are still unsatisfactory due to noise data,while the synergistic segmentation methods compromise vessel segmentation performance for the choroid layer segmentation *** cascaded structures grapple with error propagation during *** address these challenges,we propose a cascade learning segmentation method for the inner vessel structures of the choroid in this ***,we propose TransformerAssisted Cascade Learning Network(TACLNet)for choroidal vessel segmentation,which comprises a two-stage training strategy:pre-training for choroid layer segmentation and joint training for choroid layer and choroidal vessel *** also enhance the skip connection structures by introducing a multi-scale subtraction connection module designated as MSC,capturing differential and detailed information ***,we implement an auxiliary Transformer branch named ATB to integrate global features into the segmentation *** results exhibit that our method achieves the state-of-the-art performance for choroidal vessel ***,we further validate the significant superiority of the proposed method for retinal fluid segmentation in optical coherence tomography(OCT)scans on a publicly available *** these fully prove that our TACLNet contributes to the advancement of choroidal vessel segmentation and is of great significance for ophthalmic research and clinical application.

关键词： choroidal vessel segmentation optical coherence tomography(OCT) Transformer-assisted cascade learning retinal fluid segmentation multi-scale feature extraction

Regulating Effect of Substrate Temperature on Sputteringgrown Ge/Si QDs under Low Ge Deposition

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 Wuhan University of Technology(Materials Science) 2024年第4期39卷 888-894页

作者：舒启江 YANG Linjing LIU Hongxing 黄鹏儒 Institute of information Yunnan University of Chinese MedicineKunming 650500China Guangxi Key Laboratory of information Materials and Guangxi Collaborative Innovation Center of Structure and Property for New Energy and Materials School of Material Science&EngineeringGuilin University of Electronic TechnologyGuilin 541004China

The effect of deposition temperature on the morphology and optoelectronic performance of Ge/Si QDs grown by magnetron sputtering under low Ge deposition(~4 nm)was investigated by atomic force microscopy,Raman spectroscopy,and photoluminescence(PL)*** experimental results indicate that temperatures higher than 750℃effectively increase the crystallization rate and surface smoothness of the Si buffer layer,and temperatures higher than 600℃significantly enhance the migration ability of Ge atoms,thus increasing the probability of Ge atoms meeting and nucleating to form QDs on Si buffer layer,but an excessively high temperature will cause the QDs to undergo an Ostwald ripening process and thus develop into super large *** addition,some PL peaks were observed in samples containing small-sized,high-density Ge QDs,the photoelectric properties reflected by these peaks were in good agreement with the corresponding structural characteristics of the grown *** results demonstrate the viability of preparing high-quality QDs by magnetron sputtering at high deposition rate,and the temperature effect is expected to work in conjunction with other controllable factors to further regulate QD growth,which paves an effective way for the industrial production of QDs that can be used in future devices.

关键词： Ge/Si QDs deposition temperatures evolution law photoelectric performance

Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese medicine

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Integrative medicine 2024年第3期30卷 267-276页

作者： WANG Xin-yu YANG Tao GAO Xiao-yuan HU Kong-fa School of Artificial Intelligence and information Technology Nanjing University of Chinese MedicineNanjing210023China School of information Management Nanjing UniversityNanjing210023China Jiangsu Collaborative Innovation Center of Traditional Chinese medicine in Prevention and Treatment of Tumor Nanjing210023China Jiangsu Province Engineering Research Center of TCM Intelligence Health Service Nanjing210023China

Chinese medicine(CM)diagnosis intellectualization is one of the hotspots in the research of CM *** traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues,however,it is difficult to solve the problems such as excessive or similar *** the development of natural language processing techniques,text generation technique has become increasingly *** this study,we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation *** semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory(BILSTM)with Transformer as the backbone ***,the CM diagnosis generation model Knowledge Graph Enhanced Transformer(KGET)was established by introducing the knowledge in medical field to enhance the inferential *** KGET model was established based on 566 CM case texts,and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence(LSTM-seq2seq),Bidirectional and Auto-Regression Transformer(BART),and Chinese Pre-trained Unbalanced Transformer(CPT),so as to analyze the model ***,the ablation experiments were performed to explore the influence of the optimized part on the KGET *** results of Bilingual Evaluation Understudy(BLEU),Recall-Oriented Understudy for Gisting Evaluation 1(ROUGE1),ROUGE2 and Edit distance of KGET model were 45.85,73.93,54.59 and 7.12,respectively in this *** with LSTM-seq2seq,BART and CPT models,the KGET model was higher in BLEU,ROUGE1 and ROUGE2 by 6.00–17.09,1.65–9.39 and 0.51–17.62,respectively,and lower in Edit distance by 0.47–*** ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model ***,the manual assessment indicated that the CM diagnosis results of the KGET model used

关键词： Chinese medicine diagnosis knowledge graph enhanced transformer text generation

Bioinspired Multifunctional Self-Sensing Actuated Gradient Hydrogel for Soft-Hard Robot Remote Interaction

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2024年第4期16卷 139-152页

作者： He Liu Haoxiang Chu Hailiang Yuan Deliang Li Weisi Deng Zhiwei Fu Ruonan Liu Yiying Liu Yixuan Han Yanpeng Wang Yue Zhao Xiaoyu Cui Ye Tian College of medicine and Biological information Engineering Northeastern UniversityShenyang 110169People’s Republic of China Foshan Graduate School of Innovation Northeastern UniversityFoshan 528300People’s Republic of China

The development of bioinspired gradient hydrogels with self-sensing actuated capabilities for remote interaction with soft-hard robots remains a challenging endeavor. Here, we propose a novel multifunctional self-sensing actuated gradient hydrogel that combines ultrafast actuation and high sensitivity for remote interaction with robotic hand. The gradient network structure, achieved through a wettability difference method involving the rapid precipitation of MoO_(2) nanosheets, introduces hydrophilic disparities between two sides within hydrogel. This distinctive approach bestows the hydrogel with ultrafast thermo-responsive actuation(21° s^(-1)) and enhanced photothermal efficiency(increase by 3.7 ℃ s^(-1) under 808 nm near-infrared). Moreover, the local cross-linking of sodium alginate with Ca^(2+) endows the hydrogel with programmable deformability and information display capabilities. Additionally, the hydrogel exhibits high sensitivity(gauge factor 3.94 within a wide strain range of 600%), fast response times(140 ms) and good cycling stability. Leveraging these exceptional properties, we incorporate the hydrogel into various soft actuators, including soft gripper, artificial iris, and bioinspired jellyfish, as well as wearable electronics capable of precise human motion and physiological signal detection. Furthermore, through the synergistic combination of remarkable actuation and sensitivity, we realize a self-sensing touch bioinspired tongue. Notably, by employing quantitative analysis of actuation-sensing, we realize remote interaction between soft-hard robot via the Internet of Things. The multifunctional self-sensing actuated gradient hydrogel presented in this study provides a new insight for advanced somatosensory materials, self-feedback intelligent soft robots and human–machine interactions.

关键词： Self-sensing Gradient structure Bioinspired actuator Hydrogel sensor Remote interaction

Tracking direct and indirect impact on technology and policy of transformative research via ego citation network

在线全文

学校读者我要写书评

暂无评论

Journal of Data and information Science 2024年第3期9卷 65-87页

作者： Xian Li Xiaojun Hu College of Computer and information Science Southwest UniversityChongqing 400037China Medical information Center Zhejiang University School of MedicineHangzhou 310058China

Purpose:The disseminating of academic knowledge to nonacademic audiences partly relies on the transition of subsequent citing *** study aims to investigate direct and indirect impact on technology and policy originating from transformative research based on ego citation ***/methodology/approach:Key Nobel Prize-winning publications(NPs)in fields of gene engineering and astrophysics are regarded as a proxy for transformative *** this contribution,we introduce a network-structural indicator of citing patents to measure technological impact of a target article and use policy citations as a preliminary tool for policy ***:The results show that the impact on technology and policy of NPs are higher than that of their subsequent citation generations in gene engineering but not in *** limitations:The selection of Nobel Prizes is not balanced and the database used in this study,Dimensions,suffers from incompleteness and inaccuracy of citation *** implications:Our findings provide useful clues to better understand the characteristics of transformative research in technological and policy ***/value:This study proposes a new framework to explore the direct and indirect impact on technology and policy originating from transformative research.

关键词： Transformative research Nobel Prize winning articles Citation networks Technological impact Policy impact

Depressive semantic awareness from vlog facial and vocal streams via spatio-temporal transformer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第3期10卷 577-585页

作者： Yongfeng Tao Minqiang Yang Yushan Wu Kevin Lee Adrienne Kline Bin Hu School of information Science and Engineering Lanzhou UniversityLanzhouChina The School of Accounting Auditing and TaxationBusiness SchoolUNSW SydneyAustralia Department of Preventive medicine Northwestern UniversityChicagoILUnited States

With the rapid growth of information transmission via the Internet,efforts have been made to reduce network load to promote *** such application is semantic computing,which can extract and process semantic *** media has enabled users to share their current emotions,opinions,and life events through their mobile ***,people suffering from mental health problems are more willing to share their feelings on social ***,it is necessary to extract semantic information from social media(vlog data)to identify abnormal emotional states to facilitate early identification and *** studies do not consider spatio-temporal information when fusing multimodal information to identify abnormal emotional states such as *** solve this problem,this paper proposes a spatio-temporal squeeze transformer method for the extraction of semantic features of ***,a module with spatio-temporal data is embedded into the transformer encoder,which is utilized to obtain a representation of spatio-temporal ***,a classifier with a voting mechanism is designed to encourage the model to classify depression and non-depression *** are conducted on the D-Vlog *** results show that the method is effective,and the accuracy rate can reach 70.70%.This work provides scaffolding for future work in the detection of affect recognition in semantic communication based on social media vlog data.

关键词： Emotional computing Semantic awareness Depression recognition Vlog data

Formulation of international standards of Chinese medicine technology:clinical practice guide of Chinese medicine for cough

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 Traditional Chinese medicine 2024年第2期44卷 396-402页

作者： FANG Hanyu HONG Zheng LI Deming ZHANG Hongchun SHI Yihang LI Xiaojuan SUN Zengtao CHEN Wei ZHANG Chuchu ZU Yaqi Beijing University of Chinese medicine Beijing 100029China Department of Traditional Chinese medicine for Pulmonary Diseases Center of Respiratory MedicineChina-Japan Friendship HospitalBeijing 100029 National Center for Respiratory medicine Beijing 100029China Department of Traditional Chinese medicine for Pulmonary Diseases Center of Respiratory MedicineChina-Japan Friendship HospitalBeijing 100029China Tianjin University of Traditional Chinese medicine Tianjin 301617China Second Teaching Hospital of Tianjin University of Traditional Chinese medicine Tianjin 300250China Center for Evidence-based medicine Beijing University of Chinese MedicineBeijing 100029China Institute of information on Traditional Chinese medicine China Academy of Chinese Medical SciencesBeijing 100700China

OBJECTIVE:To formulate the first clinical practice guideline for the treatment of cough using Chinese medicine based on the grading of recommendations assessment,development,and evaluation(GRADE)systematic approach,including clinical evidence,evaluation of ancient literature,and expert ***:In the process of development,the regulation of"evidence-based,consensus-assisted,and empirical"was followed,and a comprehensive systematic approach of recommendation assessment,GRADE,evidence-based evaluation,expert consensus,and the Delphi method was *** the process of guideline development,evidence-based evaluation of ancient literature was included for the first time,and clinical evidence was fully integrated with clinical expert ***:The clinical practice guidelines for the treatment of cough with Chinese herbal medicine were developed after a comprehensive consideration of evidence-based evaluation and expert *** guideline recommendations focused on recommending herbal compound decoctions and Chinese patent medicines for cough in different *** on the GRADE systematic approach,we conducted an evidence-based evaluation of the recommended Chinese patent medicines one by one;meanwhile,the expert consensus method was used to unify the recommendations of ***:Based on clinical evidence,ancient literature evaluation,and expert consensus,a clinical practice guideline for Traditional Chinese medicine(TCM)in the treatment of cough was developed,providing the first current clinical practice guideline for domestic and foreign TCM and Western medicine practitioners,especially respiratory professionals at home and abroad.

关键词： medicine Chinese Traditional clinical practice cough practice guide international standard

RoBGP:A Chinese Nested Biomedical Named Entity Recognition Model Based on RoBERTa and Global Pointer

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3603-3618页

作者： Xiaohui Cui Chao Song Dongmei Li Xiaolong Qu Jiao Long Yu Yang Hanchao Zhang School of information Science and Technology Beijing Forestry UniversityBeijing100083China Engineering Research Center for Forestry-Oriented Intelligent information Processing of National Forestry and Grassland Administration Beijing100083China Division of Biostatistics Department of Population HealthGrossman School of MedicineNew York UniversityNew York10016USA

Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and categorize them into predefined entity *** process can provide basic support for the automatic construction of knowledge *** contrast to general texts,biomedical texts frequently contain numerous nested entities and local dependencies among these entities,presenting significant challenges to prevailing NER *** address these issues,we propose a novel Chinese nested biomedical NER model based on RoBERTa and Global Pointer(RoBGP).Our model initially utilizes the RoBERTa-wwm-ext-large pretrained language model to dynamically generate word-level initial *** then incorporates a Bidirectional Long Short-Term Memory network for capturing bidirectional semantic information,effectively addressing the issue of long-distance ***,the Global Pointer model is employed to comprehensively recognize all nested entities in the *** conduct extensive experiments on the Chinese medical dataset CMeEE and the results demonstrate the superior performance of RoBGP over several baseline *** research confirms the effectiveness of RoBGP in Chinese biomedical NER,providing reliable technical support for biomedical information extraction and knowledge base construction.

关键词： Biomedicine knowledge base named entity recognition pretrained language model global pointer

Jianpi Decoction Combined with Medroxyprogesterone Acetate Alleviates Cancer Cachexia and Prevents Muscle Atrophy by Directly Inhibiting E3 Ubiquitin Ligase

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 Integrative medicine 2024年第6期30卷 499-506页

作者： LI Qi KONG Zhao-di WANG Huan GU Hong-hui CHEN Zhong Li Shi-guang CHEN Yi-qi CAI Yu YANG Zhen-jiang Department of Oncology and Hematology Shenzhen Traditional Chinese Medicine HospitalShenzhenGuangdong Province518033China College of Pharmacy/International Cooperative Laboratory of Traditional Chinese medicine Modernization and Innovative Drug Development of Ministry of Education(MOE)of China Jinan UniversityGuangzhou510632China Guangdong Key Lab of Traditional Chinese medicine information Technology Jinan UniversityGuangzhou510632China

ObjectiveTo provide comprehensive evidence for the anti-cancer cachexia effect of Jianpi Decoction(JP)and to explore its mechanism of anti-cancer *** mouse model of colon cancer(CT26)-induced cancer cachexia(CC)was used to investigate the anti-CC effect of JP combined with medroxyprogesterone acetate(MPA).Thirty-six mice were equally divided into 6 groups:normal control,CC,MPA(100 mg·kg^(−1)·d^(−1)),MPA+low-dose(20 mg·kg^(−1)·d^(−1))JP(L-JP),MPA+medium-dose(30 mg·kg^(−1)·d^(−1))JP(M-JP),and MPA+high-dose(40 mg·kg^(−1)·d^(−1))JP(H-JP)*** successful modeling,the mice were administered by gavage for 11 *** body weight and tumor volume were measured and recorded every 2 d starting on the 8th day after *** liver,heart,spleen,lung,kidney,tumor and gastrocnemius muscle of mice were collected and *** pathological changes of the tumor was observed,and the cross-sectional area of the gastrocnemius muscle was *** protein expressions of STAT3 and E3 ubiquitinase in the gastrocnemius muscle were measured by Western *** addition,an in vitro C2C12 myotube formation model was established to investigate the role of JP in hindering dexamethasone-induced muscle *** vitro experiments were divided into control,model,and JP serum *** 2-d administration,microscopic photographs were taken and myotube diameters were *** blot was performed to measure the protein expressions of STAT3 and E3 *** combined with MPA restored tumor-induced weight loss(P<0.05,***)and muscle fiber size(P<0.01,***).Mechanistically,JP reduced the expression of atrophy-related proteins MuRF1 and MAFbx in tumor-induced muscle atrophy in vivo(P<0.05,***).In addition,JP reduced the expression of atrophy-related proteins MuRF1 and MAFbx and p-STAT3 phosphorylation(P<0.05 or P<0.01 *** group)in C2C12 myotubes treated with dexamethasone in *** of JP combined with MPA restores t

关键词： cancer cachexia muscle atrophy Jianpi Decoction Chinese medicine E3 ubiquitin ligases