期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到98,708篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
LLM-KE: An Ontology-Aware LLM Methodology for Military Domain Knowledge Extraction 认领 引用 被引量：2
1
作者 Yu Tao Ruopeng Yang +3 位作者 Yongqi Wen Yihao Zhong Kaige Jiao Xiaolei Gu 《Computers, Materials & Continua》 SCIE EI 2026年第1期2045-2061,共17页
Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representati... Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development. 展开更多
关键词 Knowledge extraction natural language processing knowledge graph large language model
暂未订购 下载PDF
Hybrid knowledge reasoning over knowledge hypergraph:Inductive,deductive,and abductive 认领 引用
2
作者 Ling Tian Lei Gao +3 位作者 Ben Zhang Xiao Liu Yi-Nong Shi Hui Gao 《Journal of Electronic Science and Technology》 EI CAS CSCD 2026年第2期11-26,共16页
Traditional knowledge reasoning methods,which are predominantly reliant on static rules and structured data,often struggle to adapt to the ambiguity and dynamic evolution of real-world scenarios.To overcome these limi... Traditional knowledge reasoning methods,which are predominantly reliant on static rules and structured data,often struggle to adapt to the ambiguity and dynamic evolution of real-world scenarios.To overcome these limitations,this study proposes a novel reasoning framework based on a three-layered knowledge hypergraph.Core innovation lies in the synergy of inductive,deductive,and abductive reasoning mechanisms to enhance both reliability and interpretability.Specifically,hypergraph-based inductive reasoning extracts robust evolutionary patterns by mining the historical subgraph structures.Deductive reasoning ensures transparency by constructing tree-shaped inference paths,whereas abductive reasoning establishes causal traceability by forming evidence chains from historical contexts.Experimental evaluations on the Integrated Crisis Early Warning System(ICEWS)dataset demonstrate that the proposed approach significantly outperforms existing methods in terms of accuracy and interpretability,thereby offering a scalable solution for complex event analysis. 展开更多
关键词 Abductive reasoning Deductive reasoning Inductive reasoning Knowledge hypergraphs Knowledge reasoning
暂未订购 下载PDF
Efficient user scheduling in mm Wave networks:leveraging knowledge transfer with channel knowledge map 认领 引用
3
作者 Chunlong He Peihong He Xingquan Li 《Digital Communications and Networks》 SCIE EI CSCD 2026年第2期319-331,共13页
This paper proposes a Deep Reinforcement Learning(DRL)algorithm for user scheduling in Millimeter Wave(mmWave)networks,which utilizes Channel Knowledge Map(CKM)for knowledge transfer to enhance the learning of schedul... This paper proposes a Deep Reinforcement Learning(DRL)algorithm for user scheduling in Millimeter Wave(mmWave)networks,which utilizes Channel Knowledge Map(CKM)for knowledge transfer to enhance the learning of scheduling strategies.The user scheduling and link configuration problems are modeled as a multiqueue system.Each queue represents the data demand of an individual user.This setup allows the base station to make dynamic scheduling decisions based on changing environmental conditions.This approach facilitates efficient management of user-specific requirements while addressing the challenges posed by dynamic network environments.Our model incorporates relay selection,codebook selection,and beam tracking to support flexible and efficient resource allocation.In contrast to traditional channel model-based optimization,we design algorithms for scheduling policy pre-training using CKMs,which provide information about the channel between specific pairs of locations.Specifically,we assume that the CKM is fully available to allow the complex scheduling network to have a better starting point or follow a more favorable gradient direction through knowledge migration.This integration of CKM with knowledge transfer significantly accelerates DRL convergence and enhances performance stability.Simulation results confirmed the effectiveness of the proposed approach.Relative to the baseline methods,integrating CKM with knowledge transfer accelerated the convergence of the DRL algorithm by approximately 20%,maintained the delay within 30 milliseconds,and reduced the average queue length by nearly 30%. 展开更多
关键词 Millimeter wave User scheduling Knowledge transfer Channel knowledge map Deep reinforcement learning
暂未订购 下载PDF
Knowledge-Enhanced Industrial Question-Answering Using Large Language Models 认领 引用 被引量：2
4
作者 Ronghui Liu Hao Ren +5 位作者 Haojie Ren Wu Rui Wei Cui Xiaojun Liang Chunhua Yang Weihua Gui 《Engineering》 SCIE EI CSCD 2026年第5期142-153,共12页
Modern industrial systems have grown increasingly extensive,complex,and hierarchical,with operations relying on numerous knowledge-based queries.These queries necessitate considerable human resources while also requir... Modern industrial systems have grown increasingly extensive,complex,and hierarchical,with operations relying on numerous knowledge-based queries.These queries necessitate considerable human resources while also requiring high levels of accuracy,subjectivity,and consistency,all of which critically influence operational efficiency.To overcome these challenges,this study proposes an industrial retrieval-augmented generation(RAG)method designed to enhance large language models(LLMs)using domain-specific knowledge,thereby improving the precision of question answering.A comprehensive industrial knowledge base was constructed from diverse sources,including journal articles,theses,books,and patents.A Text classification model based on bidirectional encoder representations from transformers(BERTs)was trained to accurately classify incoming queries.Furthermore,the general text embedding-dense passage retrieval(GTE-DPR)model was employed to perform word embedding and vector similarity retrieval,facilitating the alignment of query vectors with relevant entries in the knowledge base to obtain initial responses.LLMs subsequently refined these initial results to produce accurate final answers.Experimental evaluations confirm the effectiveness of the proposed approach.In particular,when applied to ChatGLM2-6B,the RAG method increased the ROUGE-L score from 32.52%to 55.04%and improved accuracy from 50.52%to 73.92%.Comparable improvements were also observed with LLaMA2-7B,underscoring the RAG framework's capability to significantly enhance the accuracy and relevance of industrial question-answering(QA)systems. 展开更多
关键词 Retrieval augmented generation Knowledge enhancement Question answering Large language models Industrial knowledge automation
暂未订购 下载PDF
A lightweight single stage small object detection network based on knowledge distillation and novel feature networks 认领 引用 被引量：1
5
作者 Miao ZHANG Xuefang ZHOU Junchao HU 《Optoelectronics Letters》 EI 2026年第5期282-288,共7页
With the increasing demand for traffic sign detection,the challenge of small target detection has become particularly prominent.The present study proposes an innovative approach by integrating knowledge distillation,L... With the increasing demand for traffic sign detection,the challenge of small target detection has become particularly prominent.The present study proposes an innovative approach by integrating knowledge distillation,L2 loss function,and convolutional block attention module(CBAM)mechanism to effectively tackle this issue.This series of improvements not only provide a new idea for small target detection,but also bring significant performance improvement in actual traffic scenes.Then,the integration method of the bidirectional feature pyramid network(BiFPN)is used to enhance the flexibility of the neural network to deal with input of different scales,while speeding up and improving the process of feature fusion.The experimental results demonstrate that when processing the Chinese city traffic sign detection benchmark(CCTSDB)dataset and executing the FLOW-IMG small target detection task,the optimized algorithm shows obvious performance improvement,and its accurate recognition rate jumps to 97%and 84.9%,respectively.For the basic algorithm,two datasets achieved improved accuracy by an innovative approach,improving accuracy by 5.8%and 1.3%,respectively.In terms of resource efficiency,compared to the original teacher model,the newly constructed model reduced the number of computing participants by approximately 15%during execution,while successfully reducing the overall computing task load by 14%. 展开更多
关键词 traffic sign detectionthe integration method knowledge distillationl loss functionand L loss function knowledge distillation small target detection small target detectionbut bidirectional feature pyramid network
暂未订购 下载PDF
TSMixerE:Entity Context-Aware Method for Static Knowledge Graph Completion 认领 引用
6
作者 Jianzhong Chen Yunsheng Xu +2 位作者 Zirui Guo Tianmin Liu Ying Pan 《Computers, Materials & Continua》 SCIE EI 2026年第4期2207-2230,共24页
The rapid development of information technology and accelerated digitalization have led to an explosive growth of data across various fields.As a key technology for knowledge representation and sharing,knowledge graph... The rapid development of information technology and accelerated digitalization have led to an explosive growth of data across various fields.As a key technology for knowledge representation and sharing,knowledge graphs play a crucial role by constructing structured networks of relationships among entities.However,data sparsity and numerous unexplored implicit relations result in the widespread incompleteness of knowledge graphs.In static knowledge graph completion,most existing methods rely on linear operations or simple interaction mechanisms for triple encoding,making it difficult to fully capture the deep semantic associations between entities and relations.Moreover,many methods focus only on the local information of individual triples,ignoring the rich semantic dependencies embedded in the neighboring nodes of entities within the graph structure,which leads to incomplete embedding representations.To address these challenges,we propose Two-Stage Mixer Embedding(TSMixerE),a static knowledge graph completion method based on entity context.In the unit semantic extraction stage,TSMixerE leveragesmulti-scale circular convolution to capture local features atmultiple granularities,enhancing the flexibility and robustness of feature interactions.A channel attention mechanism amplifies key channel responses to suppress noise and irrelevant information,thereby improving the discriminative power and semantic depth of feature representations.For contextual information fusion,a multi-layer self-attentionmechanism enables deep interactions among contextual cues,effectively integrating local details with global context.Simultaneously,type embeddings clarify the semantic identities and roles of each component,enhancing the model’s sensitivity and fusion capabilities for diverse information sources.Furthermore,TSMixerE constructs contextual unit sequences for entities,fully exploring neighborhood information within the graph structure to model complex semantic dependencies,thus improving the completeness and generalization of embedding representations. 展开更多
关键词 Knowledge graph knowledge graph complementation convolutional neural network feature interaction context
暂未订购 下载PDF
Constructing a Dynamic Trust Assessment Mechanism Combining Zero Knowledge Proof with Unsupervised Learning 认领 引用 被引量：1
7
作者 Nai-Wei Lo Cheng-I Lin +2 位作者 Chih-Chieh Chang Chi-Yang Chang Tran Thi Luu Ly 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第4期1343-1368,共26页
The growing frequency of malicious attacks on Internet of Things(IoT)devices has rendered conventional approaches with static label-dependent risk assessment models obsolete,especially when coping with unknown and con... The growing frequency of malicious attacks on Internet of Things(IoT)devices has rendered conventional approaches with static label-dependent risk assessment models obsolete,especially when coping with unknown and continuously evolving threats.To mitigate these challenges,a novel dynamic trust evaluation framework approach is proposed in this work.The proposed framework utilized unsupervised learning and zero-knowledge proofs to assess device risks in complex environments adaptively,with an accuracy rate of 98.96%for normal clustering and 95.39%for anomalies.K-means clustering algorithm is leveraged to distinguish risk patterns with an additional Decision Tree classification algorithm to analyze the distinguishing characteristics of the behaviors of normal and anomalous devices.The architecture is evaluated in a simulated environment based on real device interaction,with various malicious attacks proportions.In addition,Zero Trust Architecture is integrated into this novel framework to ensure no implicit trust exists between devices,which enforces trust assessment before any collaboration or data exchange. 展开更多
关键词 Zero knowledge proof zero trust architecture decision tree trust assessment unsupervised learning
暂未订购 下载PDF
Thoughts on the Agricultural Practice of the Party s Governance Strategy for Xinjiang in the New Era:Based on the Traditional Knowledge and Cultural Heritage 认领 引用 被引量：1
8
作者 Zhiguo SUN Dongbing XING +2 位作者 Yulan BAI Jinjin WANG Meng LIU 《Asian Agricultural Research》 2026年第6期1-12,共12页
Traditional knowledge, biological genetic resources and folk literature and art are intellectual property rights of cultural heritage that can be shared by regional groups without time limit. This paper studies the tr... Traditional knowledge, biological genetic resources and folk literature and art are intellectual property rights of cultural heritage that can be shared by regional groups without time limit. This paper studies the traditional knowledge and cultural heritage of Xinjiang agriculture from the aspects of traditional knowledge, important agricultural heritage system, intangible cultural heritage, biological genetic resources, tangible cultural heritage, frontier development and defense culture, and cultural tourism resources. It analyzes the main problems existing in the protection and inheritance of them, and puts forward suggestions such as inheriting and sharing intellectual property rights of cultural heritage, improving the protection system of biological germplasm resources, establishing national-level cultural ecological protection (experimental) zones, promoting agricultural science and technology cultural exchanges, creating Xinjiang's characteristic Great Wall culture, deeply integrating "agriculture+culture+tourism", building national and autonomous region cultural parks, and dynamically inheriting agricultural cultural heritage. 展开更多
关键词 Traditional knowledge Biological genetic resources Agricultural intellectual property Cultural enrichment of Xinjiang The Party's governance strategy for Xinjiang
暂未订购 下载PDF
Changes in knowledge and attitude after communitybased first-aid training:a prospective study with a 12-month follow-up 认领 引用
9
作者 Shijiao Yan Wenning Fu +5 位作者 Ping Tan Chang Su Xuan Deng Jinlong Wang Chuanzhu Lyu Yanhong Yang 《World Journal of Emergency Medicine》 SCIE CAS CSCD 2026年第3期215-222,共8页
BACKGROUND:This study aims to evaluate the immediate and 12-month effects of communitybased first-aid training on public knowledge and attitude,assess satisfaction,and identify factors associated with score changes.ME... BACKGROUND:This study aims to evaluate the immediate and 12-month effects of communitybased first-aid training on public knowledge and attitude,assess satisfaction,and identify factors associated with score changes.METHODS:This was a prospective study.In 2022-2023,a total of 2,010 community residents in Hainan Province received first-aid training and completed structured questionnaires at baseline,immediately after training,and at 3,6,and 12 months after training.First-aid knowledge was assessed through 33 items,with a maximum total score of 33.First-aid attitude was evaluated using seven items,totaling a maximum score of 21.Satisfaction was measured on a 5-point Likert scale.Paired-sample t-tests were used to compare baseline and post-training scores,repeated-measures analysis of variance(ANOVA)was used to examine time effects,and multiple linear regression was used to analyze factors associated with score changes.RESULTS:The satisfaction score with the training was high(mean score>4.3 for all items).The first-aid knowledge and attitude scores increased significantly after training(first-aid knowledge at baseline,14.90±7.63;immediately after training,20.70±5.72,P<0.001;and attitude at baseline,17.52±2.29;immediately after training,17.89±1.54,P<0.001).At 12 months after training,knowledge scores declined slightly compared with those immediately after training but remained above baseline(time effect P<0.001),whereas attitude scores remained stable(time effect P<0.001).Knowledge improvement was greater among middle-income participants and less among participants with lower levels of education,those in professional occupations,widowed individuals,or those who had previously received first-aid training.Attitude improvements were more pronounced among male participants,younger participants,and those in the agriculture or sales/service sectors.CONCLUSION:Community-based first-aid training improved public first-aid knowledge and attitude and was well received by participants.While knowledge levels declined somewhat over time,attitude remained relatively stable,highlighting the importance of continuous reinforcement training.Personalized reinforcement strategies may be particularly beneficial for individuals with lower levels of education,specific professional backgrounds,widowhood,or prior training experience to further enhance training effectiveness. 展开更多
关键词 First aid Knowledge Attitude Practice Training Longitudinal studies
暂未订购 下载PDF
Data-driven iterative calibration method for prior knowledge of earth-rockfilldam wetting model parameters 认领 引用
10
作者 Shaolin Ding Jiajun Pan +4 位作者 Yanli Wang Lin Wang Han Xu Yiwei Lu Xudong Zhao 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第2期1621-1632,共12页
Wetting deformation in earth-rockfill dams is a critical factor influencingdam safety.Although numerous mathematical models have been developed to describe this phenomenon,most of them rely on empirical formulations a... Wetting deformation in earth-rockfill dams is a critical factor influencingdam safety.Although numerous mathematical models have been developed to describe this phenomenon,most of them rely on empirical formulations and lack prior knowledge of model parameters,which is essential for Bayesian parameter inversion to enhance accuracy and reduce uncertainty.This study introduces a datadriven approach to establishing prior knowledge of earth-rockfill dams.Driving factors are utilized to determine the potential range of model parameters,and settlement changes within this range are calculated.The results are iteratively compared with actual monitoring data until the calculated range encompasses the observed data,thereby providing prior knowledge of the model parameters.The proposed method is applied to the right-bank earth-rockfilldam of Danjiangkou.Employing a Gibbs sample size of 30,000,the proposed method effectively calibrates the prior knowledge of the wetting model parameters,achieving a root mean square error(RMSE)of 5.18 mm for the settlement predictions.By comparison,the use of non-informative priors with sample sizes of 30,000 and 50,000 results in significantly larger RMSE values of 11.97 mm and 16.07 mm,respectively.Furthermore,the computational efficiencyof the proposed method is demonstrated by an inversion computation time of 902 s for 30,000 samples,which is notably shorter than the 1026 s and 1558 s required for noninformative priors with 30,000 and 50,000 samples,respectively.These findingsunderscore the superior performance of the proposed approach in terms of both prediction accuracy and computational efficiency.These results demonstrate that the proposed method not only improves the predictive accuracy but also enhances the computational efficiency,enabling optimal parameter identificationwith reduced computational effort.This approach provides a robust and efficientframework for advancing dam safety assessments. 展开更多
关键词 Earth-rockfilldam Wetting deformation Prior knowledge Data-driven Bayesian inversion
暂未订购 下载PDF
Effects of family-based nursing interventions on mothers’knowledge,attitudes,and self-efficacy related to stunting prevention in Indonesia:A quasi-experimental study 认领 引用
11
作者 Agus Setiawan Syamikar Baridwan Syamsir +4 位作者 Dwi Cahya Rahmadiyah Astuti Lasarus Atamou Randy Talilah Shefaly Shorey 《International Journal of Nursing Sciences》 CSCD 2026年第2期113-121,共9页
Objectives:This study aimed to evaluate the effectiveness of family-based nursing interventions in improving mothers’knowledge,attitudes,and self-efficacy to prevent stunting among children under 2 years of age in In... Objectives:This study aimed to evaluate the effectiveness of family-based nursing interventions in improving mothers’knowledge,attitudes,and self-efficacy to prevent stunting among children under 2 years of age in Indonesia.Methods:A quasi-experimental study was conducted from June to December 2024 in Alor District,East Nusa Tenggara,Indonesia.Sixty mothers of children aged 0–24 months were recruited using convenience sampling and assigned to either an intervention group(n=30)or a control group(n=30).The intervention group received seven structured sessions of a family-based nursing intervention grounded in Family-Centered Care and Social Cognitive Theory.In contrast,the control group received routine health education from local community health centers.Knowledge,attitudes,and self-efficacy were measured using validated questionnaires at baseline,post-intervention,and a three-month follow-up.Data were analyzed using independent-sample t-tests and a mixed repeated-measures analysis of variance.Results:All 60 participants completed the study.Independent-sample t-tests revealed no significant differences between the two groups at baseline for knowledge(t=−0.682,P=0.498),attitudes(t=0.655,P=0.515),and self-efficacy(t=1.671,P=0.100).A mixed repeated-measures analysis of variance demonstrated significant group,time,and group×time effects on knowledge,attitudes,and self-efficacy(all P<0.001).Pairwise comparison revealed that the scores at post-intervention and three-month follow-up were significantly higher in the intervention group for all three variables(all P<0.001).Conclusions:The family-based nursing intervention effectively enhanced maternal knowledge,attitudes,and self-efficacy regarding stunting prevention.These findings underscore the importance of incorporating structured,family-centered interventions into community-based public health programs to reduce the risk of stunting. 展开更多
关键词 Attitudes Family nursing Indonesia Knowledge Self-efficacy Stunting
暂未订购 下载PDF
From data to insight:Building a knowledge graph for risk analysis of hazardous chemical accidents 认领 引用
12
作者 Kai Zhao Xilei Lu +7 位作者 Lining Wan Linlin Zhang Yulong Jin Pengtao Wen Jinhao Gao Miao He Qibo Wang Li Zhang 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2026年第3期92-110,共19页
A substantial amount hazardous chemical accident(HCA)data have been accumulated in the form of unstructured textual data,making systematic analysis and utilization challenging.More importantly,manually identifying and... A substantial amount hazardous chemical accident(HCA)data have been accumulated in the form of unstructured textual data,making systematic analysis and utilization challenging.More importantly,manually identifying and analyzing key information from a considerable quantity of accident data is inefficient and highly susceptible to subjective bias.To efficiently unlock the value of HCA investigation reports and uncover underlying accident patterns,a semi-automated method for knowledge graph(KG)construction has been developed to model the HCA data.First,an ontology that accurately expresses key factors of HCAs is established.Second,an automated method is developed for the identification,standardization,and enhancement of accident factors,which combines deep learning(DL)and natural language processing(NLP)techniques.Specifically,the deep neural network model,named interaction region and type information(IRTI)is proposed to extract accident factors and their relationships from lengthy HCA data with complex overlapping issues.Non-standard accident factors are standardized using ChatGPT-4 in combination with the proposed text clustering model,named contrastive learningbased short text clustering(CLSTC).The processed accident factors are used to construct the hazardous chemical accident knowledge graph(HCAKG).Finally,the risk factors in the HCAKG are statistically analyzed,and their internal topological relationships are explored to facilitate quantitative analysis.Data from HCA investigation reports are used to demonstrate the effectiveness of this method.The result shows that it improves the accuracy and efficiency of accident data analysis,promoting better risk assessment and management strategies. 展开更多
关键词 Chemical processes Safety Neural networks Knowledge graph Hazardous chemical accident Risk analysis
暂未订购 下载PDF
A Knowledge-Distilled CharacterBERT-BiLSTM-ATT Framework for Lightweight DGA Detection in IoT Devices 认领 引用
13
作者 Chengqi Liu YongtaoLi +1 位作者 Weiping Zou Deyu Lin 《Computers, Materials & Continua》 SCIE EI 2026年第4期2049-2068,共20页
With the large-scale deployment of the Internet of Things(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random do... With the large-scale deployment of the Internet of Things(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random domain names,hiding the real IP of Command and Control(C&C)servers to build botnets.Due to the randomness and dynamics of DGA,traditional methods struggle to detect them accurately,increasing the difficulty of network defense.This paper proposes a lightweight DGA detection model based on knowledge distillation for resource-constrained IoT environments.Specifically,a teacher model combining CharacterBERT,a bidirectional long short-term memory(BiLSTM)network,and attention mechanism(ATT)is constructed:it extracts character-level semantic features viaCharacterBERT,captures sequence dependencieswith the BiLSTM,and integrates theATT for key feature weighting,formingmulti-granularity feature fusion.An improved knowledge distillation approach transfers the teacher model’s learned knowledge to the simplified DistilBERT student model.Experimental results show the teacher model achieves 98.68%detection accuracy.The student modelmaintains slightly improved accuracy while significantly compressing parameters to approximately 38.4%of the teacher model’s scale,greatly reducing computational overhead for IoT deployment. 展开更多
关键词 IoT security DGA detection knowledge distillation lightweight model edge computing
暂未订购 下载PDF
Analysis of the dissemination and development pathways of Traditional Chinese Medicine health knowledge in China 认领 引用
14
作者 ZHU Min GUO Hua +5 位作者 MA Xuesheng ZHANG Xingping ZHANG Lei SONG Yujiao JIANG Zhuonan YU Feilong 《Journal of Traditional Chinese Medicine》 SCIE CAS CSCD 2026年第3期740-744,共5页
Against the backdrop of China's aging society and under the macro policy of building a Healthy China proposed at the Fifth Plenary Session of the 18th Central Committee of the Communist Party of China,the dissemin... Against the backdrop of China's aging society and under the macro policy of building a Healthy China proposed at the Fifth Plenary Session of the 18th Central Committee of the Communist Party of China,the dissemination of Traditional Chinese Medicine(TCM)health knowledge has emerged as particularly crucial and imperative.This paper systematically examines the current status of TCM health knowledge dissemination in China.It identifies multiple challenges in the dissemination process,including multidimensional constraints related to content dissemination,media channels,and audience characteristics.Drawing on these findings,this paper proposes a strategic framework centered on high-quality content,with standardized media platforms as key hubs and audience empowerment as the ultimate goal. 展开更多
关键词 aging medicine Chinese traditional dissemination of health knowledge analysis of the current situation
暂未订购 下载PDF
MobiIris: Attention-Enhanced Lightweight Iris Recognition with Knowledge Distillation and Quantization 认领 引用
15
作者 Trong-Thua Huynh De-Thu Huynh +2 位作者 Du-Thang Phu Hong-Son Nguyen Quoc HNguyen 《Computers, Materials & Continua》 SCIE EI 2026年第6期623-636,共14页
This paper introduces MobiIris,a lightweight deep network for mobile iris recognition that enhances attention and specifically addresses the balance between accuracy and efficiency on devices with limited resources.Th... This paper introduces MobiIris,a lightweight deep network for mobile iris recognition that enhances attention and specifically addresses the balance between accuracy and efficiency on devices with limited resources.The proposed model is based on the large version of MobileNetV3 and adds more spatial attention blocks and an embedding-based head that was trained using margin-based triplet learning,enabling fine-grained modeling of iris textures in a compact representation.To further improve discriminability,we design a training pipeline that combines dynamic-margin triplet loss,a staged hard/semi-hard negative mining strategy,and feature-level knowledge distillation from a ResNet-50 teacher.Finally,we investigate the use of post-training float16 quantization to reduce memory footprint and latency for deployment on mobile hardware.Experiments on the challenging CASIA-IrisV4-Thousand dataset show that the full-precision MobiIris model requires only 12 MB of storage and 27 ms inference latency,while achieving an EER of 1.409%,VR@FAR=1%of 98.184%,and CMC@1 of 94.785%,closely matching a ResNet-50 baseline that is more than 7×larger and slower.Under post-training quantization,the model shrinks to 5.94 MB with 13 ms latency and maintains a competitive balance between accuracy and efficiency compared to other optimized variants.These results demonstrate that a coherent combination of lightweight architecture design,attention mechanisms,metric-learning objectives,hard negative mining,and knowledge distillation yields a practical iris recognition solution suitable for secure,real-time authentication on mobile and embedded platforms. 展开更多
关键词 Iris recognition lightweight architecture model optimization attention mechanism knowledge distillation model quantization
暂未订购 下载PDF
Few-Shot Knowledge Graph Completion with Structure-Aware Graph Attention Network 认领 引用
16
作者 YANG Rongtai SHAO Yubin +2 位作者 DU Qingzhi ZHANG Feng QI Yuting 《Journal of Shanghai Jiaotong university(Science)》 EI 2026年第4期1024-1033,I0019,共10页
Few-shot knowledge graph completion refers to inferring missing entity using limited instances.A key challenge lies in entity representation,which is complicated by diverse neighbor attributes.Although the entity'... Few-shot knowledge graph completion refers to inferring missing entity using limited instances.A key challenge lies in entity representation,which is complicated by diverse neighbor attributes.Although the entity's neighborhood topology holds potential to address this,its significance is overlooked in current research.In this paper,we propose a structure-aware graph attention network for few-shot knowledge graph completion.Firstly,to enhance entity representations,we design a structure-aware graph attention encoder to capture the graph's structural features of nodes,generating embedding for entity pairs.Secondly,a semantic prototype matching network is employed to compute the prediction score.Experiments on the NELL-One and Wiki-One datasets show that our proposed model outperforms the best baseline models by 0.021,0.026,0.039,0.032 and 0.016,0.064,0.043,0.040 in terms of MRR,Hits@10,Hits@5,and Hits@1 metrics,respectively.This demonstrates that our model can effectively leverage neighborhood topological information to improve the accuracy of knowledge completion,and achieve a better generalization. 展开更多
关键词 knowledge graph completion neighborhood topology structure-aware graph attention entity representations semantic prototype
暂未订购 下载PDF
Intelligent Teaching Scenarios Based on Knowledge Graphs and the Integration of“Teacher-Machine-Student” 认领 引用
17
作者 Yanhang Zhang Xiaohong Su +1 位作者 Yu Zhang Tiantian Wang 《计算机教育》 2026年第3期81-88,共8页
This paper delves into effective pathways for transforming course ecosystems from resource provision to knowledge service and competency development through university-enterprise collaboration in co-building knowledge... This paper delves into effective pathways for transforming course ecosystems from resource provision to knowledge service and competency development through university-enterprise collaboration in co-building knowledge graphs and intelligent shared courses.This approach enables personalized,learning-driven teaching.Based on knowledge graphs and integrated teacher-machine-student smart teaching scenarios,it not only innovates autonomous learning environments and human-computer interaction models while optimizing teaching experiences for both instructors and students,but also effectively addresses the issues of students’“scattered,superficial,and fragmented learning”.This establishes the foundation for personalized teaching tailored to individual aptitudes. 展开更多
关键词 Knowledge graphs Teacher-machine-student Smart teaching
暂未订购 下载PDF
Distribution network data asset protection considering multiple topology and multi-dimensional knowledge graph 认领 引用
18
作者 Junfeng Yang Li Liu +5 位作者 Nawaraj Kumar Mahato Luhan Li Jiaxuan Yang Gangjun Gong Jun Lu Chao Yang 《Global Energy Interconnection》 EI CSCD 2026年第3期585-610,共26页
The proliferation of diverse entities within distribution network has led to an increase in the scale and complexity of data asset interactions,exacerbating security risks,such as unauthorized access,data tampering,an... The proliferation of diverse entities within distribution network has led to an increase in the scale and complexity of data asset interactions,exacerbating security risks,such as unauthorized access,data tampering,and forgery.In response to these challenges,this study introduces a novel framework that enhances the protection of data assets.It incorporates a multi-dimensional knowledge graph(MDKG)to refine access control and overcome current limitations by integrating a comprehensive set of data asset attributes,roles,policies,and permissions.This approach fosters the development of a nuanced and adaptable access-control mechanism.Furthermore,the framework integrates multiple topology(MTP)for holistic security risk detection,leveraging attention mechanisms,and cross-fusion to adapt to the dynamic data security landscape.Empirical evaluations affirm the effectiveness of MDKG-based access control,whereas comparative experiments demonstrate the superiority of the MTP-based security risk model over existing models.The framework was proven to be effective in countering security risks.This study provides innovative perspectives on data asset protection and establishes a solid foundation for the advancement of smart grid technology. 展开更多
关键词 Distribution network Data asset protection Security access control Multi-dimensional knowledge graph Multiple topology Security risk detection
暂未订购 下载PDF
Knowledge-Data Fusion Model for Multivariate Load Short-Term Forecasting of Integrated Energy System 认领 引用
19
作者 WU Lizhen ZHAO Yifan +1 位作者 QIN Wenbin CHEN Wei 《Journal of Shanghai Jiaotong university(Science)》 EI 2026年第2期499-514,共16页
The short-term forecasting of multiple loads is crucial for the optimization and scheduling of integrated energy system(IES).However,the load within the IES exhibits diversified and strongly coupled characteristics,wh... The short-term forecasting of multiple loads is crucial for the optimization and scheduling of integrated energy system(IES).However,the load within the IES exhibits diversified and strongly coupled characteristics,which seriously affects the forecast accuracy.Moreover,only using deep learning forecasting methods cannot analyze the factors that affect the forecast results,which is not conducive to guiding the optimization and scheduling of comprehensive energy systems.Therefore,a multivariate load forecasting model based on knowledge-guided multi-task spatial-temporal synchronous graph convolutional network is proposed.Firstly,the user clusters are classified according to the energy-using characteristics of different buildings.Then,the domain knowledge base is built by combining the dimensionless trends of different groups and expert experience.At the same time,the input features are filtered based on the improved maximum information coefficient method to construct spatialtemporal graph data,forming a more refined and efficient input sample data.Finally,the knowledge-data fusion model for multivariate load forecasting is constructed to predict local fluctuations of the multivariate load series and reconstruct the load ratio.The IES data set of Arizona State University Tempe Campus is taken as a test case.The results show that the proposed method is interpretable,has higher forecast accuracy and has better generalization ability. 展开更多
关键词 integrated energy system(IES) multivariate load forecasting knowledge guide multi-task learning spatial-temporal synchronous graph convolutional network
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈