The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significa...The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significant security challenges,including impersonation threats,data manipulation,distributed denial of service(DDoS)attacks,and privacy breaches.Traditional security measures are inadequate due to the decentralized and dynamic nature of next-generation networks.This survey provides a comprehensive review of how Federated Learning(FL),Blockchain,and Digital Twin(DT)technologies can collectively enhance the security of 5G and 6G systems.Blockchain offers decentralized,immutable,and transparent mechanisms for securing network transactions,while FL enables privacy-preserving collaborative learning without sharing raw data.Digital Twins create virtual replicas of network components,enabling real-time monitoring,anomaly detection,and predictive threat analysis.The survey examines major security issues in emerging wireless architectures and analyzes recent advancements that integrate FL,Blockchain,and DT to mitigate these threats.Additionally,it presents practical use cases,synthesizes key lessons learned,and identifies ongoing research challenges.Finally,the survey outlines future research directions to support the development of scalable,intelligent,and robust security frameworks for next-generation wireless networks.展开更多
The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubi...The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubiquitous connectivity.However,existing research reveals significant gaps in dynamic resource allocation,joint optimization,and equitable service provisioning under varying channel conditions,limiting practical deployment of these technologies.This paper addresses these challenges by proposing a novel Fairness-Aware Deep Q-Learning(FAIRDQL)framework for joint resource management and phase configuration in HAPS-RIS systems.Our methodology employs a comprehensive three-tier algorithmic architecture integrating adaptive power control,priority-based user scheduling,and dynamic learning mechanisms.The FAIR-DQL approach utilizes advanced reinforcement learning with experience replay and fairness-aware reward functions to balance competing objectives while adapting to dynamic environments.Key findings demonstrate substantial improvements:9.15 dB SINR gain,12.5 bps/Hz capacity,78%power efficiency,and 0.82 fairness index.The framework achieves rapid 40-episode convergence with consistent delay performance.These contributions establish new benchmarks for fairness-aware resource allocation in aerial communications,enabling practical HAPS-RIS deployments in rural connectivity,emergency communications,and urban networks.展开更多
The i4sea research project provides effective and efficient big data integration,processing,and analysis technologies to deliver both real-time and historical operational snapshots of fishing vessels activity in natio...The i4sea research project provides effective and efficient big data integration,processing,and analysis technologies to deliver both real-time and historical operational snapshots of fishing vessels activity in national sea areas.This paper presents the architecture of the i4sea big data platform for sea area monitoring and analysis of fishing vessels activity and demonstrates the operation of some use-case pilot scenarios.展开更多
Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Man...Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Many real-world applications rely on image captioning,such as helping people with visual impairments to see their surroundings.To formulate a coherent and relevant textual description,computer vision techniques are utilized to comprehend the visual content within an image,followed by natural language processing methods.Numerous approaches and models have been developed to deal with this multifaceted problem.Several models prove to be stateof-the-art solutions in this field.This work offers an exclusive perspective emphasizing the most critical strategies and techniques for enhancing image caption generation.Rather than reviewing all previous image captioning work,we analyze various techniques that significantly improve image caption generation and achieve significant performance improvements,including encompassing image captioning with visual attention methods,exploring semantic information types in captions,and employing multi-caption generation techniques.Further,advancements such as neural architecture search,few-shot learning,multi-phase learning,and cross-modal embedding within image caption networks are examined for their transformative effects.The comprehensive quantitative analysis conducted in this study identifies cutting-edgemethodologies and sheds light on their profound impact,driving forward the forefront of image captioning technology.展开更多
Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variati...Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variations emphasize the importance of reliable diagnostic technologies that support clinicians in detecting skin malignancies with higher accuracy.Traditional diagnostic methods often rely on subjective visual assessments,which can lead to misdiagnosis.This study addresses these challenges by developing HybridFusionNet,a novel model that integrates Convolutional Neural Networks(CNN)with 1D feature extraction techniques to enhance diagnostic accuracy.Utilizing two extensive datasets,BCN20000 and HAM10000,the methodology includes data preprocessing,application of Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors(SMOTEENN)for data balancing,and optimization of feature selection using the Tree-based Pipeline Optimization Tool(TPOT).The results demonstrate significant performance improvements over traditional CNN models,achieving an accuracy of 0.9693 on the BCN20000 dataset and 0.9909 on the HAM10000 dataset.The HybridFusionNet model not only outperforms conventionalmethods but also effectively addresses class imbalance.To enhance transparency,it integrates post-hoc explanation techniques such as LIME,which highlight the features influencing predictions.These findings highlight the potential of HybridFusionNet to support real-world applications,including physician-assist systems,teledermatology,and large-scale skin cancer screening programs.By improving diagnostic efficiency and enabling access to expert-level analysis,the modelmay enhance patient outcomes and foster greater trust in artificial intelligence(AI)-assisted clinical decision-making.展开更多
Image captioning,the task of generating descriptive sentences for images,has advanced significantly with the integration of semantic information.However,traditional models still rely on static visual features that do ...Image captioning,the task of generating descriptive sentences for images,has advanced significantly with the integration of semantic information.However,traditional models still rely on static visual features that do not evolve with the changing linguistic context,which can hinder the ability to form meaningful connections between the image and the generated captions.This limitation often leads to captions that are less accurate or descriptive.In this paper,we propose a novel approach to enhance image captioning by introducing dynamic interactions where visual features continuously adapt to the evolving linguistic context.Our model strengthens the alignment between visual and linguistic elements,resulting in more coherent and contextually appropriate captions.Specifically,we introduce two innovative modules:the Visual Weighting Module(VWM)and the Enhanced Features Attention Module(EFAM).The VWM adjusts visual features using partial attention,enabling dynamic reweighting of the visual inputs,while the EFAM further refines these features to improve their relevance to the generated caption.By continuously adjusting visual features in response to the linguistic context,our model bridges the gap between static visual features and dynamic language generation.We demonstrate the effectiveness of our approach through experiments on the MS-COCO dataset,where our method outperforms state-of-the-art techniques in terms of caption quality and contextual relevance.Our results show that dynamic visual-linguistic alignment significantly enhances image captioning performance.展开更多
The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in che...The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in cheating during online exams highlights the need for efficient,adaptable detection models to uphold academic credibility.This paper presents a comprehensive analysis of various deep learning models for cheating detection in online proctoring systems,evaluating their accuracy,efficiency,and adaptability.We benchmark several advanced architectures,including EfficientNet,MobileNetV2,ResNet variants and more,using two specialized datasets(OEP and OP)tailored for online proctoring contexts.Our findings reveal that EfficientNetB1 and YOLOv5 achieve top performance on the OP dataset,with EfficientNetB1 attaining a peak accuracy of 94.59% and YOLOv5 reaching a mean average precision(mAP@0.5)of 98.3%.For the OEP dataset,ResNet50-CBAM,YOLOv5 and EfficientNetB0 stand out,with ResNet50-CBAMachieving an accuracy of 93.61% and EfficientNetB0 showing robust detection performance with balanced accuracy and computational efficiency.These results underscore the importance of selectingmodels that balance accuracy and efficiency,supporting scalable,effective cheating detection in online assessments.展开更多
Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by r...Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by resulting in suboptimal performance.To address these challenges,we propose a novel Squid Game OptimizationDimension Reduction-based Ensemble(SGO-DRE)method for the precise diagnosis of skin diseases.Our approach begins by selecting pre-trained models named MobileNetV1,DenseNet201,and Xception for robust feature extraction.These models are enhanced with dimension reduction blocks to improve efficiency.To tackle the aggregation problem of various models,we leverage the Squid Game Optimization(SGO)algorithm,which iteratively searches for the optimal weightage set to assign the appropriate weightage to each individual model within the proposed weighted average aggregation ensemble approach.The proposed ensemble method effectively utilizes the strengths of each model.We evaluated the proposed method using an 8-class skin disease dataset,a 6-class MSLD dataset,and a 4-class MSID dataset,achieving accuracies of 98.71%,96.34%,and 93.46%,respectively.Additionally,we employed visual tools like Grad-CAM,ROC curves,and Precision-Recall curves to interpret the decision making of models and assess its performance.These evaluations ensure that the proposed method not only provides robust results but also enhances interpretability and reliability in clinical decision-making.展开更多
A geodemographic classification aims to describe the most salient characteristics of a small area zonal geography.However,such representations are influenced by the methodological choices made during their constructio...A geodemographic classification aims to describe the most salient characteristics of a small area zonal geography.However,such representations are influenced by the methodological choices made during their construction.Of particular debate are the choice and specification of input variables,with the objective of identifying inputs that add value but also aim for model parsimony.Within this context,our paper introduces a principal component analysis(PCA)-based automated variable selection methodology that has the objective of identifying candidate inputs to a geodemographic classification from a collection of variables.The proposed methodology is exemplified in the context of variables from the UK 2011 Census,and its output compared to the Office for National Statistics 2011 Output Area Classification(2011 OAC).Through the implementation of the proposed methodology,the quality of the cluster assignment was improved relative to 2011 OAC,manifested by a lower total withincluster sum of square score.Across the UK,more than 70.2%of the Output Areas(OAs)occupied by the newly created classification(i.e.AVS-OAC)outperform the 2011 OAC,with particularly strong performance within Scotland and Wales.展开更多
Over-fertilization has caused significant phosphorus(P)accumulation in Chinese greenhouse vegetable production(GVP)soils.This study,for the first time,quantified profile P accumulation directly from soil P measurement...Over-fertilization has caused significant phosphorus(P)accumulation in Chinese greenhouse vegetable production(GVP)soils.This study,for the first time,quantified profile P accumulation directly from soil P measurements,as well as subsoil P immobilization,in three alkaline coarse-textured GVP soil profiles with 5(S5),15(S15),and 30(S30)years of cultivation in Tongshan,Southeast China.For each profile,soil samples were collected at depths of 0-10(topsoil),10-20,20-40,40-60,60-80,and 80-100 cm.Phosphorus accumulation was estimated from the difference in P contents between topsoil and parent material(60-100 cm subsoil).Phosphorus mobility was assessed from measurements of water-soluble P concentration(P_(Sol)).Finally,P sorption isotherms were produced using a batch sorption experiment and fitted using a modified Langmuir model.High total P contents of 1980(S5),3190(S15),and 2330(S30)mg kg^(-1) were measured in the topsoils versus lower total P content of approximately 600 mg kg^(-1) in the 80-100 cm subsoils.Likewise,topsoil PSol values were very high,varying from 6.4 to 17.0 mg L^(-1).The estimated annual P accumulations in the topsoils were 397(S5),212(S15),and 78(S30)kg ha^(-1) year^(-1).Sorption isotherms demonstrated the dominance of P desorption in highly P-saturated topsoils,whereas the amount of adsorbed P increased in the 80-100 cm subsoils with slightly larger P adsorption capacity.The total P adsorption capacity of the 80-100 cm subsoils at a solution P concentration of0.5 mg L^(-1) was 15.7(S5),8.7(S15),and 6.5(S30)kg ha^(-1),demonstrating that subsoils were unable to secure P concentrations in leaching water below 0.5 mg L^(-1) because of their insufficient P-binding capacity.展开更多
The increase in China’s skilled labor force has drawn much attention from policymakers,national and international firms and media.Understanding how educated talent locates and re-locates across the country can guide ...The increase in China’s skilled labor force has drawn much attention from policymakers,national and international firms and media.Understanding how educated talent locates and re-locates across the country can guide future policy discussions of equality,firm localization and service allocation.Prior studies have tended to adopt a static cross-national approach providing valuable insights into the relative importance of economic and amenity differentials driving the distribution of talent in China.Yet,few adopt longitudinal analysis to examine the temporal dynamics in the stregnth of existing associations.Recently released official statistical data now enables space-time analysis of the geographic distribution of talent and its determinants in China.Using four-year city-level data from national population censuses and 1%population sample surveys conducted every five years between 2000 and 2015,we examine the spatial patterns of talent across Chinese cities and their underpinning drivers evolve over time.Results reveal that the spatial distribution of talent in China is persistently unequal and spatially concentrated between 2000 and 2015.It also shows gradually strengthened and significantly positive spatial autocorrelation in the distribution of talent.An eigenvector spatial filtering negative binomial panel is employed to model the spatial determinants of talent distribution.Results indicate the influences of both economic opportunities and urban amenities,particularly urban public services and greening rate,on the distribution of talent.These results highlight that urban economic-and amenity-related factors have simultaneously driven China’s talent’s settlement patterns over the first fifteen years of the 21st century.展开更多
The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant par...The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant parts,including flowers,leaves,and roots,have been acknowledged for their healing properties and employed in plant identification.Leaf images,however,stand out as the preferred and easily accessible source of information.Manual plant identification by plant taxonomists is intricate,time-consuming,and prone to errors,relying heavily on human perception.Artificial intelligence(AI)techniques offer a solution by automating plant recognition processes.This study thoroughly examines cutting-edge AI approaches for leaf image-based plant identification,drawing insights from literature across renowned repositories.This paper critically summarizes relevant literature based on AI algorithms,extracted features,and results achieved.Additionally,it analyzes extensively used datasets in automated plant classification research.It also offers deep insights into implemented techniques and methods employed for medicinal plant recognition.Moreover,this rigorous review study discusses opportunities and challenges in employing these AI-based approaches.Furthermore,in-depth statistical findings and lessons learned from this survey are highlighted with novel research areas with the aim of offering insights to the readers and motivating new research directions.This review is expected to serve as a foundational resource for future researchers in the field of AI-based identification of medicinal plants.展开更多
High-Speed Rail(HSR)has increasingly become an important mode of inter-city transportation between large cities.Inter-city interaction facilitated by HSR tends to play a more prominent role in promoting urban and regi...High-Speed Rail(HSR)has increasingly become an important mode of inter-city transportation between large cities.Inter-city interaction facilitated by HSR tends to play a more prominent role in promoting urban and regional economic integration and development.Quantifying the impact of HSR’s interaction on cities and people is therefore crucial for long-term urban and regional development planning and policy making.We develop an evaluation framework using toponym information from social media as a proxy to estimate the dynamics of such impact.This paper adopts two types of spatial information:toponyms from social media posts,and the geographical location information embedded in social media posts.The framework highlights the asymmetric nature of social interaction among cities,and proposes a series of metrics to quantify such impact from multiple perspectives-including interaction strength,spatial decay,and channel effect.The results show that HSRs not only greatly expand the uneven distribution of inter-city connections,but also significantly reshape the interactions that occur along HSR routes through the channel effect.展开更多
The software development process mostly depends on accurately identifying both essential and optional features.Initially,user needs are typically expressed in free-form language,requiring significant time and human re...The software development process mostly depends on accurately identifying both essential and optional features.Initially,user needs are typically expressed in free-form language,requiring significant time and human resources to translate these into clear functional and non-functional requirements.To address this challenge,various machine learning(ML)methods have been explored to automate the understanding of these requirements,aiming to reduce time and human effort.However,existing techniques often struggle with complex instructions and large-scale projects.In our study,we introduce an innovative approach known as the Functional and Non-functional Requirements Classifier(FNRC).By combining the traditional random forest algorithm with the Accuracy Sliding Window(ASW)technique,we develop optimal sub-ensembles that surpass the initial classifier’s accuracy while using fewer trees.Experimental results demonstrate that our FNRC methodology performs robustly across different datasets,achieving a balanced Precision of 75%on the PROMISE dataset and an impressive Recall of 85%on the CCHIT dataset.Both datasets consistently maintain an F-measure around 64%,highlighting FNRC’s ability to effectively balance precision and recall in diverse scenarios.These findings contribute to more accurate and efficient software development processes,increasing the probability of achieving successful project outcomes.展开更多
Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms...Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption generation.However,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these features.Consequently,this leads to enhanced captioning network performance.In light of this,we present an image captioning framework that efficiently exploits the extracted representations of the image.Our framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language model.The VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features matrix.Subsequently,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative description.Integrating the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s performance.Using the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve performance.The implementation code can be found here:https://github.com/althobhani/VFDICM(accessed on 30 July 2024).展开更多
“Each place has its own way of supporting its own inhabitants[1].”As the Chinese proverb indicates,geographic environments have great influences on human behavior,and humans are also gradually adapting to these envi...“Each place has its own way of supporting its own inhabitants[1].”As the Chinese proverb indicates,geographic environments have great influences on human behavior,and humans are also gradually adapting to these environments.This relationship is even more prominent in the rapidly changing present world(e.g.,urbanization,climate change,and interregional communication).展开更多
Building,as an integral aspect of human life,is vital in the domains of urban management and urban analysis.To facilitate large-scale urban planning applications,the acquisition of complete and reliable building data ...Building,as an integral aspect of human life,is vital in the domains of urban management and urban analysis.To facilitate large-scale urban planning applications,the acquisition of complete and reliable building data becomes imperative.There are a few publicly available products that provide a lot of building data,such as Microsoft and Open Street Map.However,in East Asia,due to the more complex distribution of buildings and the scarcity of auxiliary data,there is a lack of building data in these regions,hindering the large-scale application in East Asia.Some studies attempt to simulate large-scale building distribution information using incomplete local buildings footprints data through regression.However,the reliance on inaccurate buildings data introduces cumulative errors,rendering this simulation data highly unreliable,leading to limitations in achieving precise research in East Asian region.Therefore,we proposed a comprehensive large-scale buildings mapping framework in view of the complexity of buildings in East Asia,and conducted buildings footprints extraction in 2,897 cities across 5 countries in East Asia and yielded a substantial dataset of 281,093,433 buildings.The evaluation shows the validity of our building product,with an average overall accuracy of 89.63%and an F1 score of 82.55%.In addition,a comparison with existing products further shows the high quality and completeness of our building data.Finally,we conduct spatial analysis of our building data,revealing its value in supporting urban-related research.The data for this article can be downloaded from https://doi.org/10.5281/zenodo.8174931.展开更多
With the development of highways,new technologies should be continuously introduced to improve highway traffic safety.Digital twin(DT)has been an emerging field of research in recent years.To develop a digital twin ma...With the development of highways,new technologies should be continuously introduced to improve highway traffic safety.Digital twin(DT)has been an emerging field of research in recent years.To develop a digital twin management system,a data model is essential.In the field of highway operational risk management(HORM),however,the development of data models is still in its infancy.Motivated by the concept of linked data,in this paper,we attempt to propose an information model for HORM.The main achievements of this paper include data architecture,identification and classification code methods,data interaction method,and the developed system.Based on data needs analysis,the highway information model architecture for risk management is defined as five layers:basic highway products,traffic sensors and equipment,traffic rules,traffic flow,and weather.Furthermore,according to the concepts of semantic data,these five layers can be classified into three categories:highway product data,topology data,and sensor data.Although the Industry Foundation Classes(IFC)standard and Brick schema were first proposed and applied in the building domain,some of their entities and relationships can also be applied to highways.To this end,we defined some new classes,a specific ontology,and an integrated framework for HORM.Finally,a case study was carried out.Applying such information model to highways has broad potential.It changes the file-based exchange method to the data-based one,which can promote highway data exchange and applications.The proposed information model could be of great significance for HORM.展开更多
Enviromics refers to the characterization of micro-and macroenvironments based on large-scale environmental datasets.By providing genotypic recommendations with predictive extrapolation at a site-specific level,enviro...Enviromics refers to the characterization of micro-and macroenvironments based on large-scale environmental datasets.By providing genotypic recommendations with predictive extrapolation at a site-specific level,enviromics could inform plant breeding decisions across varying conditions and anticipate productivity in a changing climate.Enviromics-based integration of statistics,envirotyping(i.e.,determining environmental factors),and remote sensing could help unravel the complex interplay of genetics,environment,and management.To support this goal,exhaustive envirotyping to generate precise environmental profiles would significantly improve predictions of genotype performance and genetic gain in crops.Already,informatics management platforms aggregate diverse environmental datasets obtained using optical,thermal,radar,and light detection and ranging(LiDAR)sensors that capture detailed information about vegetation,surface structure,and terrain.This wealth of information,coupled with freely available climate data,fuels innovative enviromics research.While enviromics holds immense potential for breeding,a few obstacles remain,such as the need for(1)integrative methodologies to systematically collect field data to scale and expand observations across the landscape with satellite data;(2)state-of-the-art AI models for data integration,simulation,and prediction;(3)cyberinfrastructure for processing big data across scales and providing seamless interfaces to deliver forecasts to stakeholders;and(4)collaboration and data sharing among farmers,breeders,physiologists,geoinformatics experts,and programmers across research institutions.Overcoming these challenges is essential for leveraging the full potential of big data captured by satellites to transform 21st century agriculture and crop improvement through enviromics.展开更多
基金derived from a research grant“Cybersecurity Research and Innovation Pioneers Grants Initiative”funded by The National Program for RDI in Cybersecurity(National Cybersecurity Authority)-Kingdom of Saudi Arabia-with grant number(CRPG-25-3168)supported by EIAS Data Science and Blockchain Lab,CCIS,Prince Sultan University.
文摘The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significant security challenges,including impersonation threats,data manipulation,distributed denial of service(DDoS)attacks,and privacy breaches.Traditional security measures are inadequate due to the decentralized and dynamic nature of next-generation networks.This survey provides a comprehensive review of how Federated Learning(FL),Blockchain,and Digital Twin(DT)technologies can collectively enhance the security of 5G and 6G systems.Blockchain offers decentralized,immutable,and transparent mechanisms for securing network transactions,while FL enables privacy-preserving collaborative learning without sharing raw data.Digital Twins create virtual replicas of network components,enabling real-time monitoring,anomaly detection,and predictive threat analysis.The survey examines major security issues in emerging wireless architectures and analyzes recent advancements that integrate FL,Blockchain,and DT to mitigate these threats.Additionally,it presents practical use cases,synthesizes key lessons learned,and identifies ongoing research challenges.Finally,the survey outlines future research directions to support the development of scalable,intelligent,and robust security frameworks for next-generation wireless networks.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project,number PNURSP2025R757Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubiquitous connectivity.However,existing research reveals significant gaps in dynamic resource allocation,joint optimization,and equitable service provisioning under varying channel conditions,limiting practical deployment of these technologies.This paper addresses these challenges by proposing a novel Fairness-Aware Deep Q-Learning(FAIRDQL)framework for joint resource management and phase configuration in HAPS-RIS systems.Our methodology employs a comprehensive three-tier algorithmic architecture integrating adaptive power control,priority-based user scheduling,and dynamic learning mechanisms.The FAIR-DQL approach utilizes advanced reinforcement learning with experience replay and fairness-aware reward functions to balance competing objectives while adapting to dynamic environments.Key findings demonstrate substantial improvements:9.15 dB SINR gain,12.5 bps/Hz capacity,78%power efficiency,and 0.82 fairness index.The framework achieves rapid 40-episode convergence with consistent delay performance.These contributions establish new benchmarks for fairness-aware resource allocation in aerial communications,enabling practical HAPS-RIS deployments in rural connectivity,emergency communications,and urban networks.
基金supported by the Greek Ministry of Development and Investment,General Secretariat of Research and Technology,under the Operational Programme Competitiveness,Entrepreneurship and Innovation 2014-2020[grant T1EDK-03268,i4sea].
文摘The i4sea research project provides effective and efficient big data integration,processing,and analysis technologies to deliver both real-time and historical operational snapshots of fishing vessels activity in national sea areas.This paper presents the architecture of the i4sea big data platform for sea area monitoring and analysis of fishing vessels activity and demonstrates the operation of some use-case pilot scenarios.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Many real-world applications rely on image captioning,such as helping people with visual impairments to see their surroundings.To formulate a coherent and relevant textual description,computer vision techniques are utilized to comprehend the visual content within an image,followed by natural language processing methods.Numerous approaches and models have been developed to deal with this multifaceted problem.Several models prove to be stateof-the-art solutions in this field.This work offers an exclusive perspective emphasizing the most critical strategies and techniques for enhancing image caption generation.Rather than reviewing all previous image captioning work,we analyze various techniques that significantly improve image caption generation and achieve significant performance improvements,including encompassing image captioning with visual attention methods,exploring semantic information types in captions,and employing multi-caption generation techniques.Further,advancements such as neural architecture search,few-shot learning,multi-phase learning,and cross-modal embedding within image caption networks are examined for their transformative effects.The comprehensive quantitative analysis conducted in this study identifies cutting-edgemethodologies and sheds light on their profound impact,driving forward the forefront of image captioning technology.
文摘Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variations emphasize the importance of reliable diagnostic technologies that support clinicians in detecting skin malignancies with higher accuracy.Traditional diagnostic methods often rely on subjective visual assessments,which can lead to misdiagnosis.This study addresses these challenges by developing HybridFusionNet,a novel model that integrates Convolutional Neural Networks(CNN)with 1D feature extraction techniques to enhance diagnostic accuracy.Utilizing two extensive datasets,BCN20000 and HAM10000,the methodology includes data preprocessing,application of Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors(SMOTEENN)for data balancing,and optimization of feature selection using the Tree-based Pipeline Optimization Tool(TPOT).The results demonstrate significant performance improvements over traditional CNN models,achieving an accuracy of 0.9693 on the BCN20000 dataset and 0.9909 on the HAM10000 dataset.The HybridFusionNet model not only outperforms conventionalmethods but also effectively addresses class imbalance.To enhance transparency,it integrates post-hoc explanation techniques such as LIME,which highlight the features influencing predictions.These findings highlight the potential of HybridFusionNet to support real-world applications,including physician-assist systems,teledermatology,and large-scale skin cancer screening programs.By improving diagnostic efficiency and enabling access to expert-level analysis,the modelmay enhance patient outcomes and foster greater trust in artificial intelligence(AI)-assisted clinical decision-making.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Image captioning,the task of generating descriptive sentences for images,has advanced significantly with the integration of semantic information.However,traditional models still rely on static visual features that do not evolve with the changing linguistic context,which can hinder the ability to form meaningful connections between the image and the generated captions.This limitation often leads to captions that are less accurate or descriptive.In this paper,we propose a novel approach to enhance image captioning by introducing dynamic interactions where visual features continuously adapt to the evolving linguistic context.Our model strengthens the alignment between visual and linguistic elements,resulting in more coherent and contextually appropriate captions.Specifically,we introduce two innovative modules:the Visual Weighting Module(VWM)and the Enhanced Features Attention Module(EFAM).The VWM adjusts visual features using partial attention,enabling dynamic reweighting of the visual inputs,while the EFAM further refines these features to improve their relevance to the generated caption.By continuously adjusting visual features in response to the linguistic context,our model bridges the gap between static visual features and dynamic language generation.We demonstrate the effectiveness of our approach through experiments on the MS-COCO dataset,where our method outperforms state-of-the-art techniques in terms of caption quality and contextual relevance.Our results show that dynamic visual-linguistic alignment significantly enhances image captioning performance.
基金funded by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R752),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in cheating during online exams highlights the need for efficient,adaptable detection models to uphold academic credibility.This paper presents a comprehensive analysis of various deep learning models for cheating detection in online proctoring systems,evaluating their accuracy,efficiency,and adaptability.We benchmark several advanced architectures,including EfficientNet,MobileNetV2,ResNet variants and more,using two specialized datasets(OEP and OP)tailored for online proctoring contexts.Our findings reveal that EfficientNetB1 and YOLOv5 achieve top performance on the OP dataset,with EfficientNetB1 attaining a peak accuracy of 94.59% and YOLOv5 reaching a mean average precision(mAP@0.5)of 98.3%.For the OEP dataset,ResNet50-CBAM,YOLOv5 and EfficientNetB0 stand out,with ResNet50-CBAMachieving an accuracy of 93.61% and EfficientNetB0 showing robust detection performance with balanced accuracy and computational efficiency.These results underscore the importance of selectingmodels that balance accuracy and efficiency,supporting scalable,effective cheating detection in online assessments.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R749)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by resulting in suboptimal performance.To address these challenges,we propose a novel Squid Game OptimizationDimension Reduction-based Ensemble(SGO-DRE)method for the precise diagnosis of skin diseases.Our approach begins by selecting pre-trained models named MobileNetV1,DenseNet201,and Xception for robust feature extraction.These models are enhanced with dimension reduction blocks to improve efficiency.To tackle the aggregation problem of various models,we leverage the Squid Game Optimization(SGO)algorithm,which iteratively searches for the optimal weightage set to assign the appropriate weightage to each individual model within the proposed weighted average aggregation ensemble approach.The proposed ensemble method effectively utilizes the strengths of each model.We evaluated the proposed method using an 8-class skin disease dataset,a 6-class MSLD dataset,and a 4-class MSID dataset,achieving accuracies of 98.71%,96.34%,and 93.46%,respectively.Additionally,we employed visual tools like Grad-CAM,ROC curves,and Precision-Recall curves to interpret the decision making of models and assess its performance.These evaluations ensure that the proposed method not only provides robust results but also enhances interpretability and reliability in clinical decision-making.
文摘A geodemographic classification aims to describe the most salient characteristics of a small area zonal geography.However,such representations are influenced by the methodological choices made during their construction.Of particular debate are the choice and specification of input variables,with the objective of identifying inputs that add value but also aim for model parsimony.Within this context,our paper introduces a principal component analysis(PCA)-based automated variable selection methodology that has the objective of identifying candidate inputs to a geodemographic classification from a collection of variables.The proposed methodology is exemplified in the context of variables from the UK 2011 Census,and its output compared to the Office for National Statistics 2011 Output Area Classification(2011 OAC).Through the implementation of the proposed methodology,the quality of the cluster assignment was improved relative to 2011 OAC,manifested by a lower total withincluster sum of square score.Across the UK,more than 70.2%of the Output Areas(OAs)occupied by the newly created classification(i.e.AVS-OAC)outperform the 2011 OAC,with particularly strong performance within Scotland and Wales.
基金the financial support from the Sino-Danish Center for Education and Research(SDC)the financial support of the Special Research Foundation of the Public Natural Resource Management Department from the Ministry of Environmental Protection of China(No.201409044)the National Natural Science Foundation of China(No.41473073)。
文摘Over-fertilization has caused significant phosphorus(P)accumulation in Chinese greenhouse vegetable production(GVP)soils.This study,for the first time,quantified profile P accumulation directly from soil P measurements,as well as subsoil P immobilization,in three alkaline coarse-textured GVP soil profiles with 5(S5),15(S15),and 30(S30)years of cultivation in Tongshan,Southeast China.For each profile,soil samples were collected at depths of 0-10(topsoil),10-20,20-40,40-60,60-80,and 80-100 cm.Phosphorus accumulation was estimated from the difference in P contents between topsoil and parent material(60-100 cm subsoil).Phosphorus mobility was assessed from measurements of water-soluble P concentration(P_(Sol)).Finally,P sorption isotherms were produced using a batch sorption experiment and fitted using a modified Langmuir model.High total P contents of 1980(S5),3190(S15),and 2330(S30)mg kg^(-1) were measured in the topsoils versus lower total P content of approximately 600 mg kg^(-1) in the 80-100 cm subsoils.Likewise,topsoil PSol values were very high,varying from 6.4 to 17.0 mg L^(-1).The estimated annual P accumulations in the topsoils were 397(S5),212(S15),and 78(S30)kg ha^(-1) year^(-1).Sorption isotherms demonstrated the dominance of P desorption in highly P-saturated topsoils,whereas the amount of adsorbed P increased in the 80-100 cm subsoils with slightly larger P adsorption capacity.The total P adsorption capacity of the 80-100 cm subsoils at a solution P concentration of0.5 mg L^(-1) was 15.7(S5),8.7(S15),and 6.5(S30)kg ha^(-1),demonstrating that subsoils were unable to secure P concentrations in leaching water below 0.5 mg L^(-1) because of their insufficient P-binding capacity.
基金Under the auspices of the National Social Science Foundation of China(No.17ZDA055).
文摘The increase in China’s skilled labor force has drawn much attention from policymakers,national and international firms and media.Understanding how educated talent locates and re-locates across the country can guide future policy discussions of equality,firm localization and service allocation.Prior studies have tended to adopt a static cross-national approach providing valuable insights into the relative importance of economic and amenity differentials driving the distribution of talent in China.Yet,few adopt longitudinal analysis to examine the temporal dynamics in the stregnth of existing associations.Recently released official statistical data now enables space-time analysis of the geographic distribution of talent and its determinants in China.Using four-year city-level data from national population censuses and 1%population sample surveys conducted every five years between 2000 and 2015,we examine the spatial patterns of talent across Chinese cities and their underpinning drivers evolve over time.Results reveal that the spatial distribution of talent in China is persistently unequal and spatially concentrated between 2000 and 2015.It also shows gradually strengthened and significantly positive spatial autocorrelation in the distribution of talent.An eigenvector spatial filtering negative binomial panel is employed to model the spatial determinants of talent distribution.Results indicate the influences of both economic opportunities and urban amenities,particularly urban public services and greening rate,on the distribution of talent.These results highlight that urban economic-and amenity-related factors have simultaneously driven China’s talent’s settlement patterns over the first fifteen years of the 21st century.
文摘The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant parts,including flowers,leaves,and roots,have been acknowledged for their healing properties and employed in plant identification.Leaf images,however,stand out as the preferred and easily accessible source of information.Manual plant identification by plant taxonomists is intricate,time-consuming,and prone to errors,relying heavily on human perception.Artificial intelligence(AI)techniques offer a solution by automating plant recognition processes.This study thoroughly examines cutting-edge AI approaches for leaf image-based plant identification,drawing insights from literature across renowned repositories.This paper critically summarizes relevant literature based on AI algorithms,extracted features,and results achieved.Additionally,it analyzes extensively used datasets in automated plant classification research.It also offers deep insights into implemented techniques and methods employed for medicinal plant recognition.Moreover,this rigorous review study discusses opportunities and challenges in employing these AI-based approaches.Furthermore,in-depth statistical findings and lessons learned from this survey are highlighted with novel research areas with the aim of offering insights to the readers and motivating new research directions.This review is expected to serve as a foundational resource for future researchers in the field of AI-based identification of medicinal plants.
基金This work is supported by the National Natural Science Foundation of China[grant numbers 41801378,42071382].
文摘High-Speed Rail(HSR)has increasingly become an important mode of inter-city transportation between large cities.Inter-city interaction facilitated by HSR tends to play a more prominent role in promoting urban and regional economic integration and development.Quantifying the impact of HSR’s interaction on cities and people is therefore crucial for long-term urban and regional development planning and policy making.We develop an evaluation framework using toponym information from social media as a proxy to estimate the dynamics of such impact.This paper adopts two types of spatial information:toponyms from social media posts,and the geographical location information embedded in social media posts.The framework highlights the asymmetric nature of social interaction among cities,and proposes a series of metrics to quantify such impact from multiple perspectives-including interaction strength,spatial decay,and channel effect.The results show that HSRs not only greatly expand the uneven distribution of inter-city connections,but also significantly reshape the interactions that occur along HSR routes through the channel effect.
基金This work is supported by EIAS(Emerging Intelligent Autonomous Systems)Data Science Lab,Prince Sultan University,Kingdom of Saudi Arabia,by paying the APC.
文摘The software development process mostly depends on accurately identifying both essential and optional features.Initially,user needs are typically expressed in free-form language,requiring significant time and human resources to translate these into clear functional and non-functional requirements.To address this challenge,various machine learning(ML)methods have been explored to automate the understanding of these requirements,aiming to reduce time and human effort.However,existing techniques often struggle with complex instructions and large-scale projects.In our study,we introduce an innovative approach known as the Functional and Non-functional Requirements Classifier(FNRC).By combining the traditional random forest algorithm with the Accuracy Sliding Window(ASW)technique,we develop optimal sub-ensembles that surpass the initial classifier’s accuracy while using fewer trees.Experimental results demonstrate that our FNRC methodology performs robustly across different datasets,achieving a balanced Precision of 75%on the PROMISE dataset and an impressive Recall of 85%on the CCHIT dataset.Both datasets consistently maintain an F-measure around 64%,highlighting FNRC’s ability to effectively balance precision and recall in diverse scenarios.These findings contribute to more accurate and efficient software development processes,increasing the probability of achieving successful project outcomes.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption generation.However,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these features.Consequently,this leads to enhanced captioning network performance.In light of this,we present an image captioning framework that efficiently exploits the extracted representations of the image.Our framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language model.The VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features matrix.Subsequently,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative description.Integrating the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s performance.Using the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve performance.The implementation code can be found here:https://github.com/althobhani/VFDICM(accessed on 30 July 2024).
基金supported by the National Natural Science Foundation of China(42242102).
文摘“Each place has its own way of supporting its own inhabitants[1].”As the Chinese proverb indicates,geographic environments have great influences on human behavior,and humans are also gradually adapting to these environments.This relationship is even more prominent in the rapidly changing present world(e.g.,urbanization,climate change,and interregional communication).
基金supported in part by the National Key R&D Program of China under Grant 2022YFB3903402National Natural Science Foundation of China under Grant 42222106+1 种基金National Natural Science Foun-dation of China under Grant 61976234Fundamental Research Funds for the Central Universities,Sun Yat-sen University under Grant 22lgqb12.
文摘Building,as an integral aspect of human life,is vital in the domains of urban management and urban analysis.To facilitate large-scale urban planning applications,the acquisition of complete and reliable building data becomes imperative.There are a few publicly available products that provide a lot of building data,such as Microsoft and Open Street Map.However,in East Asia,due to the more complex distribution of buildings and the scarcity of auxiliary data,there is a lack of building data in these regions,hindering the large-scale application in East Asia.Some studies attempt to simulate large-scale building distribution information using incomplete local buildings footprints data through regression.However,the reliance on inaccurate buildings data introduces cumulative errors,rendering this simulation data highly unreliable,leading to limitations in achieving precise research in East Asian region.Therefore,we proposed a comprehensive large-scale buildings mapping framework in view of the complexity of buildings in East Asia,and conducted buildings footprints extraction in 2,897 cities across 5 countries in East Asia and yielded a substantial dataset of 281,093,433 buildings.The evaluation shows the validity of our building product,with an average overall accuracy of 89.63%and an F1 score of 82.55%.In addition,a comparison with existing products further shows the high quality and completeness of our building data.Finally,we conduct spatial analysis of our building data,revealing its value in supporting urban-related research.The data for this article can be downloaded from https://doi.org/10.5281/zenodo.8174931.
基金supported by the Science and Technology Project of Shandong Provincial Department of Transportation(grant no.2019B32)the Key Science and Technology Projects of the Ministry of Transport of the People’s Republic of China(2019-ZD7-051).
文摘With the development of highways,new technologies should be continuously introduced to improve highway traffic safety.Digital twin(DT)has been an emerging field of research in recent years.To develop a digital twin management system,a data model is essential.In the field of highway operational risk management(HORM),however,the development of data models is still in its infancy.Motivated by the concept of linked data,in this paper,we attempt to propose an information model for HORM.The main achievements of this paper include data architecture,identification and classification code methods,data interaction method,and the developed system.Based on data needs analysis,the highway information model architecture for risk management is defined as five layers:basic highway products,traffic sensors and equipment,traffic rules,traffic flow,and weather.Furthermore,according to the concepts of semantic data,these five layers can be classified into three categories:highway product data,topology data,and sensor data.Although the Industry Foundation Classes(IFC)standard and Brick schema were first proposed and applied in the building domain,some of their entities and relationships can also be applied to highways.To this end,we defined some new classes,a specific ontology,and an integrated framework for HORM.Finally,a case study was carried out.Applying such information model to highways has broad potential.It changes the file-based exchange method to the data-based one,which can promote highway data exchange and applications.The proposed information model could be of great significance for HORM.
基金R.T.R.,L.L.P.,and G.E.M.thank the Brazilian agencies Coordenac¸ao de Aperfeic¸oamento de Pessoal de Nıvel Superior(CAPES)and Conselho Nacional de Desenvolvimento Cientıfico e Tecnologico(CNPq)for the financial support,which was instrumental in the successful execution of this project.L.H.was supported through an ARC Future Fellowship(FT220100350)from the Australian Research Council.C.H.A.was supported by The University of Colorado Boulder Grand ChallengeCIRES Earth Lab.Y.X.was supported by the Agricultural Science and Technology Innovation Program(ASTIP)of the Chinese Academy of Agricultural Sciences,Shenzhen Science and Technology Program(KQTD202303010928390070)Hebei Science and Technology Program(215A7612D),and the Provincial Technology Innovation Program of Shandong,China.
文摘Enviromics refers to the characterization of micro-and macroenvironments based on large-scale environmental datasets.By providing genotypic recommendations with predictive extrapolation at a site-specific level,enviromics could inform plant breeding decisions across varying conditions and anticipate productivity in a changing climate.Enviromics-based integration of statistics,envirotyping(i.e.,determining environmental factors),and remote sensing could help unravel the complex interplay of genetics,environment,and management.To support this goal,exhaustive envirotyping to generate precise environmental profiles would significantly improve predictions of genotype performance and genetic gain in crops.Already,informatics management platforms aggregate diverse environmental datasets obtained using optical,thermal,radar,and light detection and ranging(LiDAR)sensors that capture detailed information about vegetation,surface structure,and terrain.This wealth of information,coupled with freely available climate data,fuels innovative enviromics research.While enviromics holds immense potential for breeding,a few obstacles remain,such as the need for(1)integrative methodologies to systematically collect field data to scale and expand observations across the landscape with satellite data;(2)state-of-the-art AI models for data integration,simulation,and prediction;(3)cyberinfrastructure for processing big data across scales and providing seamless interfaces to deliver forecasts to stakeholders;and(4)collaboration and data sharing among farmers,breeders,physiologists,geoinformatics experts,and programmers across research institutions.Overcoming these challenges is essential for leveraging the full potential of big data captured by satellites to transform 21st century agriculture and crop improvement through enviromics.
