检索结果-南通市图书馆

Towards few-shot mixed-type dialogue generation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2025年第2期68卷 120-133页

作者： Zeming LIU Haifeng WANG Zeyang LEI Zheng-Yu NIU Hua WU Wanxiang CHE research center for Social Computing and Information Retrieval Baidu Inc.

Building an agent capable of conducting both open-domain and task-oriented dialogues, known as mixed-type dialogues, has been an enduring challenge for the AI community. Previous approaches have focused on constructing largescale human-annotated datasets for training models. However, annotating these datasets is expensive and hinders the practical application of these models. This paper identifies a novel challenge, few-shot mixed-type dialogue generation. To address this challenge, we first present a pre-trained dialogue generation framework with modular-based architecture and prompttuning component. Additionally, we collect a mixed-type dialogue dataset that combines persona-chat with conversational recommendation or task-oriented dialogues within a single dialogue session. Specifically, the modular-based architecture allows us to easily incorporate more supervised signals and human-annotated information, thereby facilitating the learning of sessionlevel dialogue logic. We pre-train this dialogue generation framework using multiple external datasets and then fine-tune it on the mixed-type dialogue dataset we collected. Experimental results demonstrate that the three key designs — modular-based architecture, prompt-tuning component, and model pre-training — significantly enhance the performance of this framework compared to state-of-the-art baselines.

关键词： mixed-type dialogue dialogue generation PLATO-prompt Mixed-FS few-shot

General Automatic Solution Generation for Social Problems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence research 2025年第1期22卷 145-159页

作者： Tong Niu Haoyu Huang Yu Du Weihao Zhang Luping Shi Rong Zhao center for Brain-Inspired Computing research(CBICR) Optical Memory National Engineering Research Centerand Department of Precision InstrumentTsinghua UniversityBeijing100084China IDG/McGovern Institute for Brain research Tsinghua UniversityBeijing100084China THU-CET HIK Joint research center for Brain-Inspired Computing Beijing100084China

Given the escalating intricacy and multifaceted nature of contemporary social systems,manually generating solutions to address pertinent social issues has become a formidable *** response to this challenge,the rapid development of artificial intelligence has spurred the exploration of computational methodologies aimed at automatically generating ***,current methods for the auto-generation of solutions mainly concentrate on local social regulations that pertain to specific ***,we report an automatic social operating system(ASOS)designed for general social solution generation built upon agent-based models that enables both global and local analyses and regulations of social problems across spatial and temporal *** adopts a hypergraph with extensible social semantics for a comprehensive and structured representation of social *** also incorporates a generalized protocol for standardized hypergraph operations and a symbolic hybrid framework that delivers interpretable solutions,yielding a balance between regulatory efficacy and functional *** demonstrate the effectiveness of the ASOS,we apply it to the domain of averting extreme events within international oil futures *** generating a new trading role supplemented by new mechanisms,ASOS can adeptly discern precarious market conditions and make front-running interventions for nonprofit *** study demonstrated that ASOS provides an efficient and systematic approach for generating solutions for enhancing our society.

关键词： General automatic generation global-local regulation hypergraph social representation symbolic hybrid scheme generalized operation protocol

Congenital anomalies of coronary artery misdiagnosed as coronary dilatations in Kawasaki disease:A clinical predicament

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Pediatrics 2025年第1期14卷 93-100页

作者： Rakesh Kumar Pilania Pallavi L Nadig Suprit Basu Reva Tyagi Abarna Thangaraj Ridhima Aggarwal Munish Arora Arun Sharma Surjit Singh Manphool Singhal Pediatric Allergy Immunology Unit Department of PediatricsAdvanced Pediatrics CenterPost Graduate Institute of Medical Education and ResearchChandigarh 160012ChandīgarhIndia Department of Radiodiagnosis and Imaging Postgraduate Institute of Medical Education and ResearchChandigarh 160012ChandīgarhIndia

BACKGROUND 2D-echocardiography(2DE)has been the primary imaging modality in children with Kawasaki disease(KD)to assess coronary *** To report the presence and implications of incidental congenital coronary artery anomalies that had been misinterpreted as coronary artery abnormalities(CAAs)on *** Records of children diagnosed with KD,who underwent computed tomography coronary angiography(CTCA)at our center between 2013-2023 were *** identified 3 children with congenital coronary artery anomalies in this cohort on *** of CTCA and 2DE were compared in these 3 *** Of the 241 patients with KD who underwent CTCA,3(1.24%)had congenital coronary artery anomalies on CTCA detected *** all 3 patients,baseline 2DE had identified *** was then performed for detailed evaluation as per our unit ***(11-year-boy)amongst the 3 patients had complete KD,while the other two(3.3-year-boy;4-month-girl)had incomplete *** revealed separate origins of left anterior descending artery and left circumflex from left sinus[misinterpreted as dilated left main coronary artery(LCA)on 2DE],single coronary artery(interpreted as dilated LCA on 2DE)and dilated right coronary artery on 2DE in case of anomalous origin of LCA from the main pulmonary *** latter one was subsequently operated *** CTCA is essential for detailed assessment of coronary arteries in children with KD especially in cases where there is suspicion of congenital coronary artery *** solely on 2DE may not be sufficient in such cases,and findings from CTCA can significantly impact therapeutic decision-making.

关键词： Coronary artery abnormalities Congenital coronary artery anomalies Computed tomography coronary angiography Kawasaki disease 2-dimensional echocardiography

Phenanthrene perturbs hematopoietic development and causes hematopoietic defects in zebrafish

维普期刊数据库评论

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 2025年第5期151卷 573-581页

作者： Lingyu Ren Yue Wang Ying Ren Guangke Li Nan Sang College of Environment and Resource Research Center of Environment and HealthShanxi UniversityTaiyuan 030006China

Phenanthrene(Phe)is one of the common polycyclic aromatic hydrocarbons in the environment,and recent studies show that it can cause cardiac developmental toxicity and ***,it is still unknown whether it can affect the hematopoietic development in aquatic *** address this question,zebrafish(Danio rerio)were chronically exposed to Phe at different *** found that Phe caused structural damage to the renal tubules in the kidney,induced malformed erythrocytes in peripheral blood,and decreased the proportion of myeloid cells in adult zebrafish,suggesting possible negative impacts that Phe posed to hematopoietic ***,using in situ hybridization technology,we found that Phe decreased the expression of primitive hematopoietic marker genes,specifically gata1 and pu.1,accompanied by an obstruction of primitive erythrocyte ***,Phe impaired definitive hematopoiesis,increased aberrations of the transient hematopoietic site(PBI),and reduced the generation of hematopoietic stem cells,ultimately influencing the number of erythrocytes and myeloid *** findings suggested that Phe could induce hematopoietic toxicity in zebrafish embryos and pose unknown ecological risks.

关键词： Phenanthrene Zebrafish Hematopoietic development Hematopoietic defect

Managing virus diseases in citrus:Leveraging high-throughput sequencing for versatile applications

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Horticultural Plant Journal 2025年第1期11卷 57-68页

作者： Hongming Chen Zhiyou Xuan Lu Yang Song Zhang Mengji Cao Integrative Science center of Germplasm Creation in Western China(Chongqing)Science City Citrus Research InstituteSouthwest UniversityChongqing 400712China National Citrus Engineering research center Citrus Research InstituteSouthwest UniversityChongqing 400712China

In this review,the advantages and advances in applying high-throughput sequencing(HTS)in the management of viral diseases in citrus,along with some challenges,are discussed to provide perspectives on future *** the initial implementation of HTS in citrus virology,a substantial number of citrus viruses have been identified,with a notable increase in the last 7 *** acquisition of viral genomes and various HTS-based omics analyses serve as crucial pillars for advancing research in the etiology,epidemiology,pathology,evolution,ecology,and biotechnology of citrus *** has notably contributed to disease diagnosis,such as the diagnoses of concave gum and impietratura,as well as to the surveillance of new virus risks and the preparation of virus-free ***,certain inherent defects in HTS and coupled bioinformatics analysis,such as challenges with sequence assembly and the detection of viral dark matter,require improvement to enhance practical *** addition,the utilization of HTS for the systematic management of citrus viral diseases remains limited,and drawing insights from other virus-plant pathosystems while integrating emerging compatible techniques and ideas may broaden its specific applications.

关键词： Deep sequencing Virus epidemics Functional genomics CRISPR/Cas Virus-host interactions

维普期刊数据库

research on the balance optimization algorithm of image recognition accuracy and speed based on autocollimator measurement

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年第2期21卷 121-128页

作者： LI Renpu MA Long CUI Jiwen GUO Junqi Andrei KULIKOV WEN Dandan Chongqing Engineering research center of Intelligent Sensing Technology and Microsystem Chongqing University of Post and TelecommunicationsChongqing 400065China School of Instrumentation Science and Engineering Harbin Institute of TechnologyHarbin 150080China Higher School of Engineering and Technology ITMO UniversitySaint Petersburg 197101Russia

The autocollimator is an important device for achieving precise,small-angle,non-contact *** primarily obtains angular parameters of a plane target mirror indirectly by detecting the position of the imaging *** is limited report on the core algorithmic techniques in current commercial products and recent scientific *** paper addresses the performance requirements of coordinate reading accuracy and operational speed in autocollimator image *** proposes a cross-image center recognition scheme based on the Hough transform and another based on Zernike moments and the least squares *** experimental evaluation of the accuracy and speed of both schemes,the optimal image recognition scheme balancing measurement accuracy and speed for the autocollimator is *** these,the center recognition method based on Zernike moments and the least squares method offers higher measurement accuracy and stability,while the Hough transform-based method provides faster measurement speed.

关键词： image optimization recognition

维普期刊数据库

Synthesis of intermetallic PtCo fuel cell catalysts from bimetallic core@shell structured nanoparticles

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第2期101卷 1-6页

作者： Le Zhang Lei Tong Shuai Li Chang-Song Ma Kun-Ze Xue Hai-Wei Liang Hefei National research center for Physical Sciences at the Microscale Department of Chemistry University of Science and Technology of China

The high activity and stability of intermetallic PtCo nanocatalysts toward oxygen reduction reaction make them a top candidate as low-Pt cathode catalysts in proton exchange membrane fuel cells（PEMFCs）.However,forming intermetallic structures typically requires high-temperature annealing,posing a challenge for achieving well-size control and highly ordered *** we report the design and synthesis of bimetallic co re@shell structured precursors for affording high-performance intermetallic PtCo *** fabrication of the core@shell precursor involves using a molecular ligand containing both sulfur and oxygen donors to selectively bind with Pt colloidal nanoparticles as the core and chelate Co ions as the *** high-temperature annealing,the ligand transforms into carbon coatings around alloy nanoparticles,preventing particle sintering;meanwhile,Co ions in the shell can easily diffuse into the Pt core,which helps to increase the thermodynamic driving force for forming intermetallic *** benefits enable us to obtain the catalyst with finely dispersed nanoparticles（～3.5 nm）and a high ordering degree of 72%.With 0.1 mgPt/cm2cathode loading,the catalyst delivers superior performance and durability in PEMFCs,showing an initial mass activity of 0.56 A/mgPt,an initial power density of 1.05 W/cm2at 0.67 V（H2-air）,and a voltage loss of 26 mV at 0.8 A/cm2after the accelerated durability test.

关键词： Bimetallic structure Fuel cells Intermetallic PtCo Oxygen reduction reaction

Prediction and optimization of flue pressure in sintering process based on SHAP

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第2期32卷 346-359页

作者： Mingyu Wang Jue Tang Mansheng Chu Quan Shi Zhen Zhang School of Metallurgy Northeastern UniversityShenyang 110819China Liaoning Low-Carbon Steelmaking Technology Engineering research center Northeastern UniversityShenyang 110819China Engineering research center of Frontier Technologies for Low-Carbon Steelmaking(Ministry of Education) Shenyang 110819China

Sinter is the core raw material for blast *** pressure,which is an important state parameter,affects sinter *** this paper,flue pressure prediction and optimization were studied based on the shapley additive explanation(SHAP)to predict the flue pressure and take targeted adjustment ***,the sintering process data were collected and processed.A flue pressure prediction model was then constructed after comparing different feature selection methods and model algorithms using SHAP+extremely random-ized trees(ET).The prediction accuracy of the model within the error range of±0.25 kPa was 92.63%.SHAP analysis was employed to improve the interpretability of the prediction *** effects of various sintering operation parameters on flue pressure,the relation-ship between the numerical range of key operation parameters and flue pressure,the effect of operation parameter combinations on flue pressure,and the prediction process of the flue pressure prediction model on a single sample were analyzed.A flue pressure optimization module was also constructed and analyzed when the prediction satisfied the judgment *** operating parameter combination was then *** flue pressure was increased by 5.87%during the verification process,achieving a good optimization effect.

关键词： sintering process flue pressure shapley additive explanation prediction optimization

维普期刊数据库

A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering research center of post Big Data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University Institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms