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

为您找到了以下机构：

共找到9,339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：
Intrusion Detection and Security Attacks Mitigation in Smart Cities with Integration of Human-Computer Interaction 认领 引用 被引量：1
1
作者 Abeer Alnuaim 《Computers, Materials & Continua》 SCIE EI 2026年第1期711-743,共33页
The rapid digitalization of urban infrastructure has made smart cities increasingly vulnerable to sophisticated cyber threats.In the evolving landscape of cybersecurity,the efficacy of Intrusion Detection Systems(IDS)... The rapid digitalization of urban infrastructure has made smart cities increasingly vulnerable to sophisticated cyber threats.In the evolving landscape of cybersecurity,the efficacy of Intrusion Detection Systems(IDS)is increasingly measured by technical performance,operational usability,and adaptability.This study introduces and rigorously evaluates a Human-Computer Interaction(HCI)-Integrated IDS with the utilization of Convolutional Neural Network(CNN),CNN-Long Short Term Memory(LSTM),and Random Forest(RF)against both a Baseline Machine Learning(ML)and a Traditional IDS model,through an extensive experimental framework encompassing many performance metrics,including detection latency,accuracy,alert prioritization,classification errors,system throughput,usability,ROC-AUC,precision-recall,confusion matrix analysis,and statistical accuracy measures.Our findings consistently demonstrate the superiority of the HCI-Integrated approach utilizing three major datasets(CICIDS 2017,KDD Cup 1999,and UNSW-NB15).Experimental results indicate that the HCI-Integrated model outperforms its counterparts,achieving an AUC-ROC of 0.99,a precision of 0.93,and a recall of 0.96,while maintaining the lowest false positive rate(0.03)and the fastest detection time(~1.5 s).These findings validate the efficacy of incorporating HCI to enhance anomaly detection capabilities,improve responsiveness,and reduce alert fatigue in critical smart city applications.It achieves markedly lower detection times,higher accuracy across all threat categories,reduced false positive and false negative rates,and enhanced system throughput under concurrent load conditions.The HCIIntegrated IDS excels in alert contextualization and prioritization,offering more actionable insights while minimizing analyst fatigue.Usability feedback underscores increased analyst confidence and operational clarity,reinforcing the importance of user-centered design.These results collectively position the HCI-Integrated IDS as a highly effective,scalable,and human-aligned solution for modern threat detection environments. 展开更多
关键词 Anomaly detection smart cities Internet of Things(IoT) HCI CNN LSTM random forest intelligent secure solutions
暂未订购 下载PDF
Integration of Computer Vision and Physicochemical Parameters for Post-Harvest Ripeness Classification of TomEJC Mango 认领 引用
2
作者 Savindi Thathsarani Ashan Lakshitha +4 位作者 Pasindu Pramodya Praveen Perera Rasanjali Samarakoon Shagufta Henna Upaka Rathnayake 《Phyton-International Journal of Experimental Botany》 SCIE 2026年第4期352-370,共19页
Accurately determining the optimal post-harvest storage period is still a major challenge in mango processing,especially for the Tom EJC(TEJC)variety,due to reliance on subjective visual evaluations,leading to inconsi... Accurately determining the optimal post-harvest storage period is still a major challenge in mango processing,especially for the Tom EJC(TEJC)variety,due to reliance on subjective visual evaluations,leading to inconsistent product quality and increased post-harvest losses.This study presents an artificial intelligence-based framework combining computer vision and physicochemical analysis to objectively predict the optimal post-harvest storage period of TEJC mango before processing.TEJC mangoes of grade one were stored for eight days at 24-28℃ temperature and 66.4-80%relative humidity.Daily measurements of pH,Total Soluble Solids(TSS),firmness,and peel color parameters(L*,a*,b*)were evaluated along with an image dataset of 5760 photos taken under variable lighting.Image data were then combined with numerical quality parameters to train and evaluate a deep learning model based on a fine-tuning architecture of ResNet50V2 for the classification of multi-class ripeness stages.The model achieved 66.96%of training and 62%testing accuracy,demonstrating the feasibility of integrating computer vision and physicochemical parameters for preliminary multi-class ripeness classification under non-uniform real-world conditions.The ripening trends were reflected in increasing TSS and pH values and declining fruit firmness.Among peel colour parameters,a*was strongly associated with ripening advancement.The findings underscore the potential of deep learning tools as non-destructive decision-support systems for post-harvest mango processing.The proposed framework serves as a proof-of-concept demonstrating its potential applicability in real-world scenarios.Nevertheless,the dataset used in this study enabled proof-of-concept evaluation;it represents a potential limitation for deep learning models,which typically benefit from larger and more diverse training sets. 展开更多
关键词 Artificial Intelligence(AI) CNN model deep learning smart post-harvest management TEJC mango
暂未订购 下载PDF
Integration of data science with the intelligent IoT(IIoT):Current challenges and future perspectives 认领 引用 被引量：7
3
作者 Inam Ullah Deepak Adhikari +3 位作者 Xin Su Francesco Palmieri Celimuge Wu Chang Choi 《Digital Communications and Networks》 SCIE EI CSCD 2025年第2期280-298,共19页
The Intelligent Internet of Things(IIoT)involves real-world things that communicate or interact with each other through networking technologies by collecting data from these“things”and using intelligent approaches,s... The Intelligent Internet of Things(IIoT)involves real-world things that communicate or interact with each other through networking technologies by collecting data from these“things”and using intelligent approaches,such as Artificial Intelligence(AI)and machine learning,to make accurate decisions.Data science is the science of dealing with data and its relationships through intelligent approaches.Most state-of-the-art research focuses independently on either data science or IIoT,rather than exploring their integration.Therefore,to address the gap,this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT)system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics.The paper analyzes the data science or big data security and privacy features,including network architecture,data protection,and continuous monitoring of data,which face challenges in various IoT-based systems.Extensive insights into IoT data security,privacy,and challenges are visualized in the context of data science for IoT.In addition,this study reveals the current opportunities to enhance data science and IoT market development.The current gap and challenges faced in the integration of data science and IoT are comprehensively presented,followed by the future outlook and possible solutions. 展开更多
关键词 Data science Internet of things(IoT) Big data Communication systems Networks Security Data science analytics
暂未订购 下载PDF
Complex adaptive systems science in the era of global sustainability crisis 认领 引用 被引量：1
4
作者 Li An B.L.Turner II +4 位作者 Jianguo Liu Volker Grimm Qi Zhang Zhangyang Wang Ruihong Huang 《Geography and Sustainability》 CSCD 2025年第1期14-24,共11页
A significant number and range of challenges besetting sustainability can be traced to the actions and inter actions of multiple autonomous agents(people mostly)and the entities they create(e.g.,institutions,policies,... A significant number and range of challenges besetting sustainability can be traced to the actions and inter actions of multiple autonomous agents(people mostly)and the entities they create(e.g.,institutions,policies,social network)in the corresponding social-environmental systems(SES).To address these challenges,we need to understand decisions made and actions taken by agents,the outcomes of their actions,including the feedbacks on the corresponding agents and environment.The science of complex adaptive systems-complex adaptive sys tems(CAS)science-has a significant potential to handle such challenges.We address the advantages of CAS science for sustainability by identifying the key elements and challenges in sustainability science,the generic features of CAS,and the key advances and challenges in modeling CAS.Artificial intelligence and data science combined with agent-based modeling promise to improve understanding of agents’behaviors,detect SES struc tures,and formulate SES mechanisms. 展开更多
关键词 Social-environmental systems Complex adaptive systems Sustainability science Agent-based models Artificial intelligence Data science
暂未订购 下载PDF
Multimodal Signal Processing of ECG Signals with Time-Frequency Representations for Arrhythmia Classification 认领 引用 被引量：1
5
作者 Yu Zhou Jiawei Tian Kyungtae Kang 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第2期990-1017,共28页
Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conductin... Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification. 展开更多
关键词 Electrocardiogram arrhythmia classification multimodal time-frequency representation
暂未订购 下载PDF
Celebrating three years of Science in One Health:shaping a transdisciplinary community 认领 引用
6
作者 Hanqing Zhao Lorne Babiuk +11 位作者 Robin Gasser Yvon Le Maho Jianguo Xu Jianzhong Shen Hualan Chen Qingming Luo Jiming Liu Xiaokui Guo Junshi Chen Renhe Zhang Marcel Tanner Xiao-Nong Zhou 《Science in One Health》 2025年第1期1-7,共7页
The journal Science in One Health(SOH)has served as a platform for advancing One Health knowledge and practice since 2022.Guided by the vision of"One World,One Health",SOH is committed to exploring health is... The journal Science in One Health(SOH)has served as a platform for advancing One Health knowledge and practice since 2022.Guided by the vision of"One World,One Health",SOH is committed to exploring health issues at the human-animal-environment interface.Over the past three years,SOH has built an ambitious and dynamic editorial board across diverse disciplines,expanding its global influence and establishing itself as a global One Health community of authors and readers.So far,SOH has published 4 volumes,featuring 90 influential articles.Among them,11 articles have garnered 1782 citations,and 10 have achieved 270012,000 downloads.The third anniversary is considered a significant milestone,which marks a solid foundation for sustained growth.Moving forward,we expect to shape the future of One Health in collaboration with authors,readers,reviewers,and editorial board members of SOH. 展开更多
关键词 One Health One Health approach Human-animal-environment interface Cross-sectors Multiple disciplines
暂未订购 下载PDF
E2ETCA:End-to-end training of CNN and attention ensembles for rice disease diagnosis 认领 引用
7
作者 Md.Zasim Uddin Md.Nadim Mahamood +3 位作者 Ausrukona Ray Md.Ileas Pramanik Fady Alnajjar Md Atiqur Rahman Ahad 《Journal of Integrative Agriculture》 SCIE CAS CSCD 2026年第2期756-768,共13页
Rice is one of the most important staple crops globally.Rice plant diseases can severely reduce crop yields and,in extreme cases,lead to total production loss.Early diagnosis enables timely intervention,mitigates dise... Rice is one of the most important staple crops globally.Rice plant diseases can severely reduce crop yields and,in extreme cases,lead to total production loss.Early diagnosis enables timely intervention,mitigates disease severity,supports effective treatment strategies,and reduces reliance on excessive pesticide use.Traditional machine learning approaches have been applied for automated rice disease diagnosis;however,these methods depend heavily on manual image preprocessing and handcrafted feature extraction,which are labor-intensive and time-consuming and often require domain expertise.Recently,end-to-end deep learning(DL) models have been introduced for this task,but they often lack robustness and generalizability across diverse datasets.To address these limitations,we propose a novel end-toend training framework for convolutional neural network(CNN) and attention-based model ensembles(E2ETCA).This framework integrates features from two state-of-the-art(SOTA) CNN models,Inception V3 and DenseNet-201,and an attention-based vision transformer(ViT) model.The fused features are passed through an additional fully connected layer with softmax activation for final classification.The entire process is trained end-to-end,enhancing its suitability for realworld deployment.Furthermore,we extract and analyze the learned features using a support vector machine(SVM),a traditional machine learning classifier,to provide comparative insights.We evaluate the proposed E2ETCA framework on three publicly available datasets,the Mendeley Rice Leaf Disease Image Samples dataset,the Kaggle Rice Diseases Image dataset,the Bangladesh Rice Research Institute dataset,and a combined version of all three.Using standard evaluation metrics(accuracy,precision,recall,and F1-score),our framework demonstrates superior performance compared to existing SOTA methods in rice disease diagnosis,with potential applicability to other agricultural disease detection tasks. 展开更多
关键词 rice disease diagnosis ensemble method CNN-based model end-to-end model Inception model DenseNet model vision transformer model attention-based model support vector machine
暂未订购 下载PDF
Transforming Healthcare with State-of-the-Art Medical-LLMs:A Comprehensive Evaluation of Current Advances Using Benchmarking Framework 认领 引用
8
作者 Himadri Nath Saha Dipanwita Chakraborty Bhattacharya +5 位作者 Sancharita Dutta Arnab Bera Srutorshi Basuray Satyasaran Changdar Saptarshi Banerjee Jon Turdiev 《Computers, Materials & Continua》 SCIE EI 2026年第2期234-289,共56页
The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decis... The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decision support,documentation,and diagnostics.This evaluation examines the performance of leading Med-LLMs,including GPT-4Med,Med-PaLM,MEDITRON,PubMedGPT,and MedAlpaca,across diverse medical datasets.It provides graphical comparisons of their effectiveness in distinct healthcare domains.The study introduces a domain-specific categorization system that aligns these models with optimal applications in clinical decision-making,documentation,drug discovery,research,patient interaction,and public health.The paper addresses deployment challenges of Medical-LLMs,emphasizing trustworthiness and explainability as essential requirements for healthcare AI.It presents current evaluation techniques that improve model transparency in high-stakes medical contexts and analyzes regulatory frameworks using benchmarking datasets such asMedQA,MedMCQA,PubMedQA,and MIMIC.By identifying ongoing challenges in biasmitigation,reliability,and ethical compliance,thiswork serves as a resource for selecting appropriate Med-LLMs and outlines future directions in the field.This analysis offers a roadmap for developing Med-LLMs that balance technological innovation with the trust and transparency required for clinical integration,a perspective often overlooked in existing literature. 展开更多
关键词 Medical large language models(Med-LLM) AI in healthcare natural language processing(NLP)in medicine fine-tuning medical LLMs retrieval-augmented generation(RAG)in medicine multi-modal learning in healthcare explainability and transparency in medical AI FDA regulations for AI in medicine evaluation and benchmarking of medical large language models
暂未订购 下载PDF
Data clustering:a fundamental method in data science and management 认领 引用
9
作者 Tai Dinh Hauchi Wong +4 位作者 Daniil Lisik Michal Koren Dat Tran Philip S.Yu Joaquín Torres-Sospedra 《Data Science and Management》 EI CSCD 2026年第1期136-161,共26页
This study investigates the pivotal role of data clustering in both data science and management,focusing on core methodologies,tools,and diverse applications.It examines traditional clustering techniques such as parti... This study investigates the pivotal role of data clustering in both data science and management,focusing on core methodologies,tools,and diverse applications.It examines traditional clustering techniques such as partitional and hierarchical methods,alongside more advanced approaches,including data stream,density-based,graphbased,and model-based clustering,which are essential for processing complex and structured datasets.The study highlights fundamental principles,presents commonly adapted tools and frameworks,outlines the clustering workflow within data science,and discusses major implementation challenges.Beyond technical applications,this study emphasizes how clustering supports managerial tasks and decision-making through a comprehensive survey of recent literature.By bridging analytical techniques with real-world business needs,clustering remains an essential tool in both data science and management.The study concludes by outlining future research directions,underscoring the role of clustering in driving innovation and enabling informed strategic and operational decisions. 展开更多
关键词 Data mining Cluster analysis Data science Management Artificial intelligence Machine learning
暂未订购 下载PDF
Theory Evolution Optimization:A Metaheuristic Algorithm BaSed on Evolution Process of Theory 认领 引用
10
作者 Jiacong Liu Jiaze Tu +5 位作者 Chunguang Bi Huiling Chen Ali Asghar Heidari Hao Xie Lei Liu Yi Chen 《Journal of Bionic Engineering》 SCIE EI CSCD 2026年第2期1015-1060,共46页
Metaheuristic algorithms have emerged as indispensable tools for solving NP-hard optimization problems that defy traditional methods.To advance the field’s focus on algorithmic performance,this study introduces the T... Metaheuristic algorithms have emerged as indispensable tools for solving NP-hard optimization problems that defy traditional methods.To advance the field’s focus on algorithmic performance,this study introduces the Theory Evolution Optimization(TEO)–an efficient metaheuristic inspired by the evolution of scientific theory.TEO simulates the competitive,accumulative,and replacement processes among scientific hypotheses,mirroring the evolution from a hypothesis to an established scientific theory.The performance of TEO is validated through extensive experimental simulations and benchmarked against 28 popular algorithms,including highly competitive champions such as EBOwithCMAR,LSHADE_cnEpSi,and LSHADE.Pairwise comparisons between TEO and the latest algorithms are conducted using the Wilcoxon signed-rank test,with multiple comparisons managed by the Friedman test.Initially,TEO is tested on the classical IEEE CEC2017 and the latest IEEE CEC2022 benchmark functions.TEO successfully addresses four prominent engineering design problems in constrained continuous space for practical applications.Additionally,a binary TEO(BTEO)variant is introduced and applied to feature selection tasks in discrete space.Experimental results consistently demonstrate that TEO proposes highly competitive outcomes in optimization problems.The source codes for this research are accessible to the public at http://gffzze767f4cc5ce545d8s606pq5vbbnvq6kbk.ffgz.tsg.suse.edu.cn/TEO.html. 展开更多
关键词 Optimization,metaheuristic algorithms Evolution of scientific theory Theory evolution optimizers Engineering design optimization Feature selection
A Comprehensive Literature Review of AI-Driven Application Mapping and Scheduling Techniques for Network-on-Chip Systems 认领 引用
11
作者 Naveed Ahmad Muhammad Kaleem +5 位作者 Mourad Elloumi Muhammad Azhar Mushtaq Ahlem Fatnassi Mohd Fazil Anas Bilal Abdulbasit A.Darem 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第1期118-155,共38页
Network-on-Chip(NoC)systems are progressively deployed in connecting massively parallel megacore systems in the new computing architecture.As a result,application mapping has become an important aspect of performance ... Network-on-Chip(NoC)systems are progressively deployed in connecting massively parallel megacore systems in the new computing architecture.As a result,application mapping has become an important aspect of performance and scalability,as current trends require the distribution of computation across network nodes/points.In this paper,we survey a large number of mapping and scheduling techniques designed for NoC architectures.This time,we concentrated on 3D systems.We take a systematic literature review approach to analyze existing methods across static,dynamic,hybrid,and machine-learning-based approaches,alongside preliminary AI-based dynamic models in recent works.We classify them into several main aspects covering power-aware mapping,fault tolerance,load-balancing,and adaptive for dynamic workloads.Also,we assess the efficacy of each method against performance parameters,such as latency,throughput,response time,and error rate.Key challenges,including energy efficiency,real-time adaptability,and reinforcement learning integration,are highlighted as well.To the best of our knowledge,this is one of the recent reviews that identifies both traditional and AI-based algorithms for mapping over a modern NoC,and opens research challenges.Finally,we provide directions for future work toward improved adaptability and scalability via lightweight learned models and hierarchical mapping frameworks. 展开更多
关键词 Application mapping mapping techniques network-on-chip system on chip optimisation
暂未订购 下载PDF
Dynamics of Kawasaki Disease Pathogenesis under Stochastic Perturbations and Time-Delay Effects 认领 引用
12
作者 Ali Raza Umar Shafique +3 位作者 Marek Lampart Dumitru Baleanu Emad Fadhal Hadil Alhazmi 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期821-857,共37页
Kawasaki disease(KD)is an acute,self-limited pediatric vasculitis of unknown etiology and is one of the leading causes of acquired coronary artery complications in children.Endothelial dysfunction,vascular endothelial... Kawasaki disease(KD)is an acute,self-limited pediatric vasculitis of unknown etiology and is one of the leading causes of acquired coronary artery complications in children.Endothelial dysfunction,vascular endothelial growth factor(VEGF)activity,adhesion molecule/chemokine activation,and inflammatory cytokine responses play important roles in its pathogenesis.This paper presents a delay differential equation model with stochastic perturbations to study lesion-level inflammatory mechanisms involved in Kawasaki disease pathogenesis.The model describes interactions among healthy endothelial cells,vascular endothelial growth factor(VEGF),adhesion molecules/chemokines,and inflammatory cytokine activity.Mathematically,endothelial-cell injury promotes VEGF production,VEGF contributes to adhesion molecule and chemokine activation,and the combined adhesion molecule/chemokine activity stimulates inflammatory cytokine production after a time delay.The variables are interpreted as aggregated biological activities,not as individual molecular species.The model is not designed to represent the acute,subacute,and convalescent clinical phases of Kawasaki disease separately,and coronary artery inflammation is not included as an independent state variable.Instead,endothelial dysfunction and inflammatory cytokine activity are used as indirect mechanistic indicators of vascular inflammatory progression.The model is shown to preserve positivity and boundedness under suitable dissipativity assumptions.Equilibrium points and an inflammatory feedback threshold quantity are discussed,and local stability is analyzed through the characteristic equations of the delayed system.Reported incidence data from 2020–2025 are used only as qualitative motivation for considering variability and delayed biological responses.A stochastic extension is then formulated to represent random biological and environmental fluctuations,and a stochastic nonstandard finite difference scheme is proposed to preserve positivity and boundedness in numerical simulations.The results provide a mathematical framework for studying delayed stochastic inflammatory interactions in Kawasaki disease,while highlighting that explicit modeling of clinical phases and coronary artery involvement remains an important direction for future work. 展开更多
关键词 Kawasaki disease stochastic delay differential equations inflammatory feedback threshold stability analysis NSFD scheme real data analysis graphical analysis
暂未订购 下载PDF
Analysis and Application of a Discrete-Time Neurodynamic Approach for Fast Constrained l_1-Norm Minimization 认领 引用
13
作者 Youshen Xia Jun Wang Changyin Sun 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期597-610,共14页
Discrete-time neurodynamic approaches(also called recurrent neural networks(RNNs))are easily implemented on software and simulated on digital circuits.First,this paper proposes two modified discrete-time RNNs for quic... Discrete-time neurodynamic approaches(also called recurrent neural networks(RNNs))are easily implemented on software and simulated on digital circuits.First,this paper proposes two modified discrete-time RNNs for quickly dealing with constrained l 1-norm minimization problems.Next,the two modified discrete-time RNNs are proven to be globally convergent to an optimal solution under a large step size.Finally,we apply the obtained results for image recovery.Two convergent discrete-time RNN based algorithms for non-blind image restoration are presented.Due to having a low complexity,the two discrete-time RNNs are more computationally efficient than the existing discrete-time RNN for image restoration.Computed results with application examples show that the two discrete-time RNN-based algorithms are indeed superior to the existing discrete-time RNNbased algorithms with regards to computation time. 展开更多
关键词 Index Terms—Constrained the l1-norm minimization convergence analysis discrete-time neurodynamic approach fixed step length image recovery
暂未订购 下载PDF
A Comprehensive Review of Complex Logical Reasoning in Large Vision-Language Models 认领 引用
14
作者 Weiqiang Jin Yang Liu +9 位作者 Yang Gao Shixiang Tang Yanghao Zhou Jinhu Qi Wentao Zhang Junli Wang Jing Gao Yue Ma Ziwei Zhang Biao Zhao 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期1-51,共51页
relational reasoning,and cross-modal evidence integration.Reasoning abilities such as deductive,inductive,abductive,multi-hop,and causal inference are fundamental to robust decision making,trustworthy interaction,and ... relational reasoning,and cross-modal evidence integration.Reasoning abilities such as deductive,inductive,abductive,multi-hop,and causal inference are fundamental to robust decision making,trustworthy interaction,and real-world deployment,yet they have not been systematically examined in the LVLM literature.Existing surveys mainly discuss mathematical reasoning,general multimodal intelligence,or benchmark progress,but they do not provide a unified account of complex logical reasoning in LVLMs,including its definition,reasoning types,modeling paradigms,evaluation protocols,and unresolved limitations.To address this gap,this survey develops a unified analytical framework for complex logical reasoning in LVLMs.This survey provides a structured review of this emerging area.We first formalize complex logical reasoning in multimodal settings and organize the literature into five recurrent reasoning families:deductive,inductive,abductive,multi-hop,and causal reasoning.We then review reasoning-oriented LVLM architectures,including unified,modular,and tool-augmented paradigms,and summarize major reasoning mechanisms such as chain-of-thought,program-based reasoning,self-correction,and interpretability-oriented analysis.We further examine representative benchmarks and evaluation protocols,with particular attention to the mismatch between final-answer accuracy and genuine reasoning validity.Based on empirical evidence from representative LVLMs and datasets,we identify common capability trends,recurring failure modes,and key open challenges.Our analysis shows that current LVLMs still struggle with reasoning faithfulness,long-horizon inference,cross-modal grounding,hallucination control,and process-aware evaluation.Finally,we outline future directions in reasoning-oriented data construction,model design,training strategies,evaluation methodology,and deployment.Overall,this survey offers a unified conceptual framework and technical roadmap for advancing LVLMs from strong perceptual systems toward reliable multimodal reasoning agents. 展开更多
关键词 **:Large vision-language model complex logical reasoning multimodal reasoning chain-of-thought evaluation benchmark reasoning faithfulness
暂未订购 下载PDF
Advancing Large Language Models for Low-Resource Languages:A Systematic Review of Pretraining,Adaptation,and Ethical Challenges 认领 引用
15
作者 Ismail Hossain Mridul Banik +2 位作者 Fahmid Al Farid Jia Uddin Hezerul bin Abdul Karim 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期122-159,共38页
In recent years,the rapid advancement of Large Language Models(LLMs)has significantly transformed natural language processing(NLP),enabling impressive performance across a wide range of tasks.However,these development... In recent years,the rapid advancement of Large Language Models(LLMs)has significantly transformed natural language processing(NLP),enabling impressive performance across a wide range of tasks.However,these developments have largely benefited high-resource languages,leaving many low-resource and underrepresented languages at risk of further digital marginalization.Addressing this imbalance is crucial to building more inclusive and culturally sustainable AI systems,which is motivating growing research interest in adapting LLMs for linguistically diverse and resource-scarce communities.This systematic review examines recent progress(2020–2025)in the pretraining and adaptation of LLMs for Low-Resource Languages(LRLs).Analysed 812 records obtained in the large databases and using PRISMA criteria,140 core studies were identified.The innovations in data augmentation and parameter-efficient fine-tuning approaches can be outlined in this selection process.It combines major innovations on data-driven augmentation,parameter-efficient fine-tuning and morphologically rich and underrepresented language script-sensitive tokenization.The results highlight the growing effectiveness of culturally aware standards such as IrokoBench and BLEnD and show that approaches to lightweight adaptation eliminate high computational costs while maintaining language accuracy.The review focuses on the ethics in AI practice,the development of corpora through communities,and interdisciplinary research collaboration among computational linguists,social scientists,and digital humanists.The task of generating a diversified dataset,typology-conscious modelling strategies,and open-source multilingual benchmarks should be prioritized in future research as one possible solution to the existing digital language gap worldwide. 展开更多
关键词 LLMs low-resource languages(LRLs) parameter-efficient fine-tuning(PEFT) tokenization cross-lingual transfer multilingual benchmarks
暂未订购 下载PDF
Sentinel 1A data-based glacier facies identification,mass balance and its response to climate change:A focus on benchmark glaciers of the North Western Himalaya 认领 引用
16
作者 Ajay Kumar Taloor Gurnam Parsad +6 位作者 Akash Basotra Sanchayita Das Shiwalika Sambyal Varun Khajuria Girish Ch Kothyari Ashutosh Tiwari Mehnaz 《Research in Cold and Arid Regions》 CAS CSCD 2026年第3期208-225,共18页
This study presents an eight-year(2016–2023)analysis of Northwestern Himalayan benchmark glaciers using Sentinel-1A dual-polarized Synthetic Aperture Radar(SAR)data and a refined linear decision rule-based classifica... This study presents an eight-year(2016–2023)analysis of Northwestern Himalayan benchmark glaciers using Sentinel-1A dual-polarized Synthetic Aperture Radar(SAR)data and a refined linear decision rule-based classification model to delineate glacial zones during ablation periods,enabling transient snowline detection and empirical Glacier Mass Balance(GMB)estimation.The average GMB for the Gangotri glacier was found to be-0.77 m water equivalent(m w.e.),Baspa-0.71 m w.e.Yamnotri-0.69 m w.e.,Bara Shigri-0.07 m w.e.,Thajwas-0.09 m w.e.,and Durung-Drung-0.0049 m w.e.for the 2016–2023 period.The Equilibrium Line Altitudes(ELAs)were derived from the snowlines,upto to the end of ablation period,and further used to compute GMB alongside Accumulation Area Ratios(AARs),with associated uncertainties quantified.Correlation analysis incorporating land surface temperature during ablation and annual precipitation provided insights into the climatic drivers of GMB variability across the region. 展开更多
关键词 SAR imaging Glacial regions Equilibrium line altitude Glacier mass balance Effects of climate change
暂未订购 下载PDF
Smart Offloading of IoT Big Data for Network Resources Optimization 认领 引用
17
作者 Afzal Badshah Mona Eisa +3 位作者 Omar Alghushairy Riad Alharbey Manal Linjawi Ali Daud 《Computers, Materials & Continua》 SCIE EI 2026年第7期1671-1693,共23页
The Internet of Things(IoT)devices generate massive data that leads to network congestion,propagation delays,and suboptimal resource allocation.Traditional Cloud Computing(CC)offers scalable resources required for tha... The Internet of Things(IoT)devices generate massive data that leads to network congestion,propagation delays,and suboptimal resource allocation.Traditional Cloud Computing(CC)offers scalable resources required for that data;however,it has a long delay and communication overhead.On the other hand,Edge Computing(EC)guarantees low latency but has limited computational capacity.In this paper,we propose an intermediate paradigm,Regional Computing(RC),combined with a Fuzzy Logic System(FLS)for dynamic,multi-criteria offloading across edge,regional,and cloud.The FLS takes task size,cost,and computational demand as input metrics.It uses a rule-based inference engine to select the optimal offloading tier for each task.We created real-time data using an Arduino UNO R4 and ran it in our Python custom-built simulator,RegionalEdgeSimPy.It is specially designed to simulate IoT environments.Experimentation results show that the proposed strategy reduces average network latency by 50%as compared to CC offloading.The model also reduces costs by 30%in comparison with EC or CC.The framework enhances scalability and responsiveness in IoT big data applications and is representative of a practical solution for real-world deployment. 展开更多
关键词 Internet of Things computer networks offloading cloud computing edge computing regional computing
暂未订购 下载PDF
IoT-Driven Intelligent Transportation System in the Era of 6G and AI:A Review 认领 引用
18
作者 Muhammet Ali Karabulut A.F.M.Shahen Shah +1 位作者 Al-Sakib Khan Pathan Phillip G.Bradford 《Computers, Materials & Continua》 SCIE EI 2026年第7期120-148,共29页
Today,technological progress is broad and deep.The next generation networks and systems will integrate features,technologies,and models requiring smooth cooperation between new and old technologies.This survey’s uniq... Today,technological progress is broad and deep.The next generation networks and systems will integrate features,technologies,and models requiring smooth cooperation between new and old technologies.This survey’s uniqueness is that it considers an integrated,hybrid and heterogeneous future where Internet of Things(IoT),Sixth-Generation(6G)mobile communications technology,and Artificial Intelligence(AI)will work together,providing a smart and connected Intelligent Transportation System(ITS).This smart ITS will give better road safety and optimized travel.Currently,there is a scarcity of surveys focusing particularly on smart ITS that is expected soon.In this work,we investigate 6G technology and its enhanced features,then provide an overview of how AI systems will work.We also consider the effectiveness and security of ITS for autonomous driving,traffic management,route optimization,and accident prevention.We discuss how AI techniques evaluate data produced by IoT devices to improve ITS performance.Moreover,a performance analysis is conducted considering different system parameters for secure IoT-based ITS.Before concluding the paper,we outline the potential advantages and drawbacks of 6G and AI-enabled ITS and then offer suggestions for future research. 展开更多
关键词 6G AI intelligent transportation systems IoT privacy security
暂未订购 下载PDF
A Review of the Application of Machine Learning in Additive Manufacturing 认领 引用
19
作者 Yuyin Ma Yufang Liu +3 位作者 Yijun Lu Zhen Tian Fujiang Yuan Yanhong Peng 《Computers, Materials & Continua》 SCIE EI 2026年第8期35-58,共24页
Additive manufacturing(AM)has emerged as a transformative technology in modern manufacturing,offering unprecedented capabilities for producing complex geometries and customized components.However,the widespread adopti... Additive manufacturing(AM)has emerged as a transformative technology in modern manufacturing,offering unprecedented capabilities for producing complex geometries and customized components.However,the widespread adoption of AM is hindered by insufficient quality control,stemming from the multi-factor coupling characteristics of the manufacturing process.Machine learning(ML)presents a promising solution by enabling data-driven approaches to process optimization,quality prediction,and defect detection.This review examines the application landscape of ML techniques in AM through comprehensive analysis of recent literature.The study categorizes ML applications into four primary domains:real-time process monitoring and control,process parameter optimization and prediction,material property prediction,and quality inspection and defect identification.Random Forest(RF),neural networks(NN),and Support Vector Machines(SVM)emerge as the most widely adopted algorithms,demonstrating strong performance in handling high-dimensional,nonlinear relationships between process parameters and product quality.The analysis reveals that while ML methods have achieved significant success in offline prediction tasks,most research remains at the supervised learning stage,lacking cross-material adaptability,real-time feedback control capabilities,and model interpretability.The review identifies critical gaps in current research,including the need for closed-loop autonomous control systems,transfer learning across different materials and machines,and physics-informed ML models that integrate domain knowledge.This work provides a comprehensive reference for researchers and practitioners,highlighting both the achievements and limitations of ML applications in AM,and proposing future directions toward intelligent,autonomous,and high-reliability AM systems. 展开更多
关键词 Additive manufacturing machine learning quality control process optimization
暂未订购 下载PDF
Performance Evaluation of Malicious Node Detection and Mitigation of IoT-Based Trust Model for Wireless Sensor Network 认领 引用
20
作者 Anil Kumar Abhay Bhatia +3 位作者 Amit Singh Preeti Rani Vincent Omollo Nyangaresi Mahendihasan S.Heera 《Computers, Materials & Continua》 SCIE EI 2026年第7期1921-1947,共27页
The Internet of Things(IoT)enables seamless real-time monitoring and data exchange across distributed and heterogeneous environments with wireless sensor networks(WSNs).The open architecture and resource constraints o... The Internet of Things(IoT)enables seamless real-time monitoring and data exchange across distributed and heterogeneous environments with wireless sensor networks(WSNs).The open architecture and resource constraints of wireless sensor networks(WSNs)make them highly vulnerable to internal security threats caused by malicious or compromised nodes,particularly in Internet of Things(IoT)environments.To address this issue,we proposed Dynamic Trust Evaluation Model(DTEM),designed to provide a secure,scalable,and efficient framework for IoT-based WSNs.The proposed model identifies the role of trust management in routing,data aggregation,and intrusion detection,including trust-based protocols.DTEM incorporates a lightweight elliptic curve cryptography(ECC)mechanism to ensure secure communication,protect trust information from manipulation,and enhance overall system reliability.In addition,machine learning techniques are employed to improve malicious node classification accuracy.Component-wise analysis demonstrates that the dynamic trust evaluation forms the core detection mechanism,while ECC enhances communication security and machine learning improves malicious node classification accuracy.A large-scale network simulation is conducted to evaluate DTEM’s performance under various attack scenarios.Results demonstrate improved malicious node detection accuracy,higher packet delivery ratios,reduced energy consumption,and lower communication overheads.The proposed DTEM framework proves to be a robust and scalable solution for securing IoT-based wireless sensor networks,making it suitable for real-world applications. 展开更多
关键词 Internet of Things node detection security threats security and protocols wireless sensor 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