Unmanned aerial vehicles(UAVs),especially quadcopters,have become indispensable in numerous industrial and scientific applications due to their flexibility,lowcost,and capability to operate in dynamic environments.Thi...Unmanned aerial vehicles(UAVs),especially quadcopters,have become indispensable in numerous industrial and scientific applications due to their flexibility,lowcost,and capability to operate in dynamic environments.This paper presents a complete design and implementation of a compact autonomous quadcopter capable of trajectory tracking,object detection,precision landing,and real-time telemetry via long-range communication protocols.The system integrates an onboard flight controller running real-time sensor fusion algorithms,a vision-based detection system on a companion single-board computer,and a telemetry unit using Long Range(LoRa)communication.Extensive flight tests were conducted to validate the system’s stability,communication range,and autonomous capabilities.Potential applications in law enforcement,agriculture,search and rescue,and environmental monitoring are also discussed.展开更多
Embedded printing is a highly promising approach for creating complex structures within a yield-stress support bath.However,the accurate prediction and control of printability remain fundamental challenges due to the ...Embedded printing is a highly promising approach for creating complex structures within a yield-stress support bath.However,the accurate prediction and control of printability remain fundamental challenges due to the complex interactions between inks and support baths.Here,we present an artificial intelligence(AI)-driven framework that interprets and predicts embedded printability using rheological data.Using a standardized workflow,we extracted 21 rheological descriptors and established 12 indicators to evaluate structural continuity and geometric fidelity.Interpretable machine learning models revealed that direction-dependent defects are governed by the synergistic interplay among ink yield stress,support bath zero shear viscosity,flow behavior index,and time constant.To enable the prediction of printability in a generalizable manner,we further developed a cascaded neural network,which achieved mean relative prediction errors below 15%across all indicators.Experimental validation using three-dimensional(3 D)-printed constructs and micro-computed tomography(μCT)reconstructions confirmed a strong correlation between predicted and actual fidelity.This work establishes a physics-informed,data-driven paradigm for decoding and optimizing embedded printing,offering broad applicability and providing a robust tool for the rapid pairing of suitable printable ink-support bath combinations.展开更多
With the rapid development of intelligent cyber-physical systems(ICPS),diverse services with varying Quality of Service(QoS)requirements have brought great challenges to traditional network resource allocation.Further...With the rapid development of intelligent cyber-physical systems(ICPS),diverse services with varying Quality of Service(QoS)requirements have brought great challenges to traditional network resource allocation.Furthermore,given the open environment and a multitude of devices,enhancing the security of ICPS is an urgent concern.To address these issues,this paper proposes a novel trusted virtual network embedding(T-VNE)approach for ICPS based combining blockchain and edge computing technologies.Additionally,the proposed algorithm leverages a deep reinforcement learning(DRL)model to optimize decision-making processes.It employs the policygradient-based agent to compute candidate embedding nodes and utilizes a breadth-first search(BFS)algorithm to determine the optimal embedding paths.Finally,through simulation experiments,the efficacy of the proposed method was validated,demonstrating outstanding performance in terms of security,revenue generation,and virtual network request(VNR)acceptance rate.展开更多
Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame...Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame-work that uses Bidirectional Encoder Representations from Transformers(BERT)for contextual feature extraction and a multiple-window Convolutional Neural Network(CNN)for classification.To identify semantic nuances in email content,BERT embeddings are used,and CNN filters extract discriminative n-gram patterns at various levels of detail,enabling accurate spam identification.The proposed model outperformed Word2Vec-based baselines on a sample of 5728 labelled emails,achieving an accuracy of 98.69%,AUC of 0.9981,F1 Score of 0.9724,and MCC of 0.9639.With a medium kernel size of(6,9)and compact multi-window CNN architectures,it improves performance.Cross-validation illustrates stability and generalization across folds.By balancing high recall with minimal false positives,our method provides a reliable and scalable solution for current spam detection in advanced deep learning.By combining contextual embedding and a neural architecture,this study develops a security analysis method.展开更多
Message structure reconstruction is a critical task in protocol reverse engineering,aiming to recover protocol field structures without access to source code.It enables important applications in network security,inclu...Message structure reconstruction is a critical task in protocol reverse engineering,aiming to recover protocol field structures without access to source code.It enables important applications in network security,including malware analysis and protocol fuzzing.However,existing methods suffer from inaccurate field boundary delineation and lack hierarchical relationship recovery,resulting in imprecise and incomplete reconstructions.In this paper,we propose ProRE,a novel method for reconstructing protocol field structures based on program execution slice embedding.ProRE extracts code slices from protocol parsing at runtime,converts them into embedding vectors using a data flow-sensitive assembly language model,and performs hierarchical clustering to recover complete protocol field structures.Evaluation on two datasets containing 12 protocols shows that ProRE achieves an average F1 score of 0.85 and a cophenetic correlation coefficient of 0.189,improving by 19%and 0.126%respectively over state-of-the-art methods(including BinPRE,Tupni,Netlifter,and QwQ-32B-preview),demonstrating significant superiority in both accuracy and completeness of field structure recovery.Case studies further validate the effectiveness of ProRE in practical malware analysis scenarios.展开更多
In recent years,ransomware attacks have become one of the most common and destructive types of cyberattacks.Their impact is significant on the operations,finances and reputation of affected companies.Despite the effor...In recent years,ransomware attacks have become one of the most common and destructive types of cyberattacks.Their impact is significant on the operations,finances and reputation of affected companies.Despite the efforts of researchers and security experts to protect information systems from these attacks,the threat persists and the proposed solutions are not able to significantly stop the spread of ransomware attacks.The latest remarkable achievements of large language models(LLMs)in NLP tasks have caught the attention of cybersecurity researchers to integrate thesemodels into security threat detection.Thesemodels offer high embedding capabilities,able to extract rich semantic representations and paving theway formore accurate and adaptive solutions.In this context,we propose a new approach for ransomware detection based on an ensemblemethod that leverages three distinctLLMembeddingmodels.This ensemble strategy takes advantage of the variety of embedding methods and the strengths of each model.In the proposed solution,each embedding model is associated with an independently trainedMLP classifier.The predictions obtained are then merged using a weighted voting technique,assigning each model an influence proportional to its performance.This approach makes it possible to exploit the complementarity of representations,improve detection accuracy and robustness,and offer a more reliable solution in the face of the growing diversity and complexity of modern ransomware.展开更多
Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with impro...Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with improved efficiency.This study presents the design and implementation of an autonomous radio-controlled(RC)vehicle prototype capable of lane line detection,obstacle avoidance,and navigation through dynamic path planning.The system integrates image processing and ultrasonic sensing,utilizing Raspberry Pi for vision-based tasks and ArduinoNano for real-time control.Lane line detection is achieved through conventional image processing techniques,providing the basis for local path generation,while traffic sign classification employs a You Only Look Once(YOLO)model optimized with TensorFlow Lite to support navigation decisions.Images captured by the onboard camera are processed on the Raspberry Pi to extract lane geometry and calculate steering angles,enabling the vehicle to follow the planned path.In addition,ultrasonic sensors placed in three directions at the front of the vehicle detect obstacles and allow real-time path adjustment for safe navigation.Experimental results demonstrate stable performance under controlled conditions,highlighting the system’s potential for scalable autonomous driving applications.This work confirms that deep learning methods can be efficiently deployed on low-power embedded systems,offering a practical framework for navigation,path planning,and intelligent transportation research.展开更多
Adaptive optics(AO)has significantly advanced high-resolution solar observations by mitigating atmospheric turbulence.However,traditional post-focal AO systems suffer from external configurations that introduce excess...Adaptive optics(AO)has significantly advanced high-resolution solar observations by mitigating atmospheric turbulence.However,traditional post-focal AO systems suffer from external configurations that introduce excessive optical surfaces,reduced light throughput,and instrumental polarization.To address these limitations,we propose an embedded solar adaptive optics telescope(ESAOT)that intrinsically incorporates the solar AO(SAO)subsystem within the telescope's optical train,featuring a co-designed correction chain with a single Hartmann-Shack full-wavefront sensor(HS f-WFS)and a deformable secondary mirror(DSM).The HS f-WFS uses temporal-spatial hybrid sampling technique to simultane-ously resolve tip-tilt and high-order aberrations,while the DSM performs real-time compensation through adaptive modal optimization.This unified architecture achieves symmetrical polarization suppression and high system throughput by min-imizing optical surfaces.A 600 mm ESAOT prototype incorporating a 12×12 micro-lens array HS f-WFS and 61-actuator piezoelectric DSM has been developed and successfully conducted on-sky photospheric observations.Validations in-cluding turbulence simulations,optical bench testing,and practical observations at the Lijiang observatory collectively confirm the system's capability to maintain aboutλ/10 wavefront error during active region tracking.This architectural breakthrough of the ESAOT addresses long-standing SAO integration challenges in solar astronomy and provides scala-bility analyses confirming direct applicability to the existing and future large solar observation facilities.展开更多
Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algeb...Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algebraic subsets of G forms a family of closed sets for another T_(1)topology Z_(G) on G called the Zarski topology.A subgroup H of G is said to be Markov(resp.Zarski)embedded if the equality M_(G|H)=M_(H)(resp.Z_(G|H)=Z_(H))holds.I's proved that an abirary subgroup of a free group is both Zariski and Markov embedded in it.展开更多
Digital watermarking must balance imperceptibility,robustness,complexity,and security.To address the challenge of computational efficiency in trellis-based informed embedding,we propose a modified watermarking framewo...Digital watermarking must balance imperceptibility,robustness,complexity,and security.To address the challenge of computational efficiency in trellis-based informed embedding,we propose a modified watermarking framework that integrates fuzzy c-means(FCM)clustering into the generation off block codewords for labeling trellis arcs.The system incorporates a parallel trellis structure,controllable embedding parameters,and a novel informed embedding algorithm with reduced complexity.Two types of embedding schemes—memoryless and memory-based—are designed to flexibly trade-off between imperceptibility and robustness.Experimental results demonstrate that the proposed method outperforms existing approaches in bit error rate(BER)and computational complexity under various attacks,including additive noise,filtering,JPEG compression,cropping,and rotation.The integration of FCM enhances robustness by increasing the codeword distance,while preserving perceptual quality.Overall,the proposed framework is suitable for real-time and secure watermarking applications.展开更多
A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehens...A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.展开更多
In shale gas reservoir stimulation,proppants are essential for sustaining fracture conductivity.However,increasing closing stress causes proppants to embed into the rock matrix,leading to a progressive decline in frac...In shale gas reservoir stimulation,proppants are essential for sustaining fracture conductivity.However,increasing closing stress causes proppants to embed into the rock matrix,leading to a progressive decline in fracture permeability and conductivity.Furthermore,rock creep contributes to long-term reductions in fracture performance.To elucidate the combined effects of proppant embedding and rock creep on sustained conductivity,this study conducted controlled experiments examining conductivity decay in propped fractures under varying closing stresses,explicitly accounting for both mechanisms.An embedded discrete fracture model was developed to simulate reservoir production under different conductivity decay scenarios,while evaluating the influence of proppant parameters on fracture performance.The results demonstrate that fracture conductivity diminishes rapidly with increasing stress,yet at 50 MPa,the decline becomes less pronounced.Simulated production profiles show strong agreement with actual gas well data,confirming the model’s accuracy and predictive capability.These findings suggest that employing a high proppant concentration with smaller particle size(5 kg/m^(2),70/140 mesh)is effective for maintaining long-term fracture conductivity and enhancing shale gas recovery.This study provides a rigorous framework for optimizing proppant selection and designing stimulation strategies that maximize reservoir performance over time.展开更多
Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to ...Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to Tibetan medicine.However,existing Tibetan MNER methods often struggle to comprehensively capture multi-level semantic information,failing to sufficiently extract multi-granularity features and effectively filter out irrelevant information,which ultimately impacts the accuracy of entity recognition.This paper proposes an improved embedding representation method called syllable-word-sentence embedding.By leveraging features at different granularities and using un-scaled dot-product attention to focus on key features for feature fusion,the syllable-word-sentence embedding is integrated into the transformer,enhancing the specificity and diversity of feature representations.The model leverages multi-level and multi-granularity semantic information,thereby improving the performance of Tibetan MNER.We evaluate our proposed model on datasets from various domains.The results indicate that the model effectively identified three types of entities in the Tibetan news dataset we constructed,achieving an F1 score of 93.59%,which represents an improvement of 1.24%compared to the vanilla FLAT.Additionally,results from the Tibetan medical dataset we developed show that it is effective in identifying five kinds of medical entities,with an F1 score of 71.39%,which is a 1.34%improvement over the vanilla FLAT.展开更多
Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications li...Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.展开更多
Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrat...Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrates the utilization of sparse confocal microscopy layers to interpolate continuous axial resolution.With an embedded system focused on neural network pruning,image scaling,and post-processing,PLayer achieves high-performance metrics with an average structural similarity index of 0.9217 and a peak signal-to-noise ratio of 27.75 dB,all within 20 s.This represents a significant time saving of 85.71%with simplified image processing.By harnessing statistical map estimation in interpolation and incorporating the Vision Transformer–based Restorer,PLayer ensures 2D layer consistency while mitigating heavy computational dependence.As such,PLayer can reconstruct 3D neural organoid confocal data continuously under limited computational power for the wide acceptance of fundamental connectomics and pattern-related research with embedded devices.展开更多
Battery safety has emerged as a critical challenge for achieving carbon neutrality,driven by the increasing frequency of thermal runaway incidents in electric vehicles(EVs)and stationary energy storage systems(ESSs).C...Battery safety has emerged as a critical challenge for achieving carbon neutrality,driven by the increasing frequency of thermal runaway incidents in electric vehicles(EVs)and stationary energy storage systems(ESSs).Conventional battery monitoring technologies struggle to track multiple physicochemical parameters in real time,hindering early hazard detection.Embedded optical fiber sensors have gained prominence as a transformative solution for next-generation smart battery sensing,owing to their micrometer size,multiplexing capability,and electromagnetic immunity.However,comprehensive reviews focusing on their advancements in operando multi-parameter monitoring remain scarce,despite their critical importance for ensuring battery safety.To address this gap,this review first introduces a classification and the fundamental principles of advanced battery-oriented optical fiber sensors.Subsequently,it summarizes recent developments in single-parameter battery monitoring using optical fiber sensors.Building on this foundation,this review presents the first comprehensive analysis of multifunctional optical fiber sensing platforms capable of simultaneously tracking temperature,strain,pressure,refractive index,and monitoring battery aging.Targeted strategies are proposed to facilitate the practical development of this technology,including optimization of sensor integration techniques,minimizing sensor invasiveness,resolving the cross-sensitivity of fiber Bragg grating(FBG)through structural innovation,enhancing techno-economics,and combining with artificial intelligence(AI).By aligning academic research with industry requirements,this review provides a methodological roadmap for developing robust optical sensing systems to ensure battery safety in decarbonization-driven applications.展开更多
The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situati...The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.展开更多
Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the vary...Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.展开更多
In this study,a new linear friction welding(LFW)process,embedded LFW process,was put forward,which was mainly applied to combination manufacturing of long or overlong loadcarrying titanium alloy structural components ...In this study,a new linear friction welding(LFW)process,embedded LFW process,was put forward,which was mainly applied to combination manufacturing of long or overlong loadcarrying titanium alloy structural components in aircraft.The interfacial plastic flow behavior and bonding mechanism of this process were investigated by a developed coupling EulerianLagrangian numerical model using software ABAQUS and a novel thermo-physical simulation method with designed embedded hot compression specimen.In addition,the formation mechanism and control method of welding defects caused by uneven plastic flow were discussed.The results reveal that the plastic flow along oscillating direction of this process is even and sufficient.In the direction perpendicular to oscillation,thermo-plastic metals mainly flow downward along welding interface under coupling of shear stress and interfacial pressure,resulting in the interfacial plastic zone shown as an inverted“V”shape.The upward plastic flow in this direction is relatively weak,and only a small amount of flash is extruded from top of joint.Moreover,the wedge block and welding components at top of joint are always in un-steady friction stage,leading to nonuniform temperature field distribution and un-welded defects.According to the results of numerical simulation,high oscillating frequency combined with low pressure and small amplitude is considered as appropriate parameter selection scheme to improve the upward interfacial plastic flow at top of joint and suppress the un-welded defects.The results of thermo-physical simulation illustrate that continuous dynamic recrystallization(CDRX)induces the bonding of interface,accompanying by intense dislocation movement and creation of many low-angle grain boundaries.In the interfacial bonding area,grain orientation is random with relatively low texture density(5.0 mud)owing to CDRX.展开更多
Network virtualization is the development trend and inevitable requirement of hybrid wireless sensor networks(HWSNs).Low mapping efficiency and service interruption caused by mobility seriously affect the reliability ...Network virtualization is the development trend and inevitable requirement of hybrid wireless sensor networks(HWSNs).Low mapping efficiency and service interruption caused by mobility seriously affect the reliability of sensing tasks and ultimately affect the long-term revenue of the infrastructure providers.In response to these problems,this paper proposes an efficient virtual network embedding algorithm with a reliable service guarantee.Based on the topological attributes of nodes,a method for evaluating the physical network resource importance degree is proposed,and the nodes with rich resources are selected to improve embedding efficiency.Then,a method for evaluating the physical network reliability degree is proposed to predict the probability of mobile sensors providing uninterrupted services.The simulation results show that the proposed algorithm improves the acceptance rate of virtual sensor networks(VSN)embedding requests and the long-term revenue of the infrastructure providers.展开更多
文摘Unmanned aerial vehicles(UAVs),especially quadcopters,have become indispensable in numerous industrial and scientific applications due to their flexibility,lowcost,and capability to operate in dynamic environments.This paper presents a complete design and implementation of a compact autonomous quadcopter capable of trajectory tracking,object detection,precision landing,and real-time telemetry via long-range communication protocols.The system integrates an onboard flight controller running real-time sensor fusion algorithms,a vision-based detection system on a companion single-board computer,and a telemetry unit using Long Range(LoRa)communication.Extensive flight tests were conducted to validate the system’s stability,communication range,and autonomous capabilities.Potential applications in law enforcement,agriculture,search and rescue,and environmental monitoring are also discussed.
基金supported by the National Natural Science Foundation of China(Nos.52305314 and U21A20394)the Beijing Natural Science Foundation(Nos.7252285 and L246001)the National Key Research and Development Program of China(No.2023YFB4605800)。
文摘Embedded printing is a highly promising approach for creating complex structures within a yield-stress support bath.However,the accurate prediction and control of printability remain fundamental challenges due to the complex interactions between inks and support baths.Here,we present an artificial intelligence(AI)-driven framework that interprets and predicts embedded printability using rheological data.Using a standardized workflow,we extracted 21 rheological descriptors and established 12 indicators to evaluate structural continuity and geometric fidelity.Interpretable machine learning models revealed that direction-dependent defects are governed by the synergistic interplay among ink yield stress,support bath zero shear viscosity,flow behavior index,and time constant.To enable the prediction of printability in a generalizable manner,we further developed a cascaded neural network,which achieved mean relative prediction errors below 15%across all indicators.Experimental validation using three-dimensional(3 D)-printed constructs and micro-computed tomography(μCT)reconstructions confirmed a strong correlation between predicted and actual fidelity.This work establishes a physics-informed,data-driven paradigm for decoding and optimizing embedded printing,offering broad applicability and providing a robust tool for the rapid pairing of suitable printable ink-support bath combinations.
基金supported by the National Natural Science Foundation of China under Grant 62471493supported by the Natural Science Foundation of Shandong Province under Grant ZR2023LZH017,ZR2024MF066。
文摘With the rapid development of intelligent cyber-physical systems(ICPS),diverse services with varying Quality of Service(QoS)requirements have brought great challenges to traditional network resource allocation.Furthermore,given the open environment and a multitude of devices,enhancing the security of ICPS is an urgent concern.To address these issues,this paper proposes a novel trusted virtual network embedding(T-VNE)approach for ICPS based combining blockchain and edge computing technologies.Additionally,the proposed algorithm leverages a deep reinforcement learning(DRL)model to optimize decision-making processes.It employs the policygradient-based agent to compute candidate embedding nodes and utilizes a breadth-first search(BFS)algorithm to determine the optimal embedding paths.Finally,through simulation experiments,the efficacy of the proposed method was validated,demonstrating outstanding performance in terms of security,revenue generation,and virtual network request(VNR)acceptance rate.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R234)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame-work that uses Bidirectional Encoder Representations from Transformers(BERT)for contextual feature extraction and a multiple-window Convolutional Neural Network(CNN)for classification.To identify semantic nuances in email content,BERT embeddings are used,and CNN filters extract discriminative n-gram patterns at various levels of detail,enabling accurate spam identification.The proposed model outperformed Word2Vec-based baselines on a sample of 5728 labelled emails,achieving an accuracy of 98.69%,AUC of 0.9981,F1 Score of 0.9724,and MCC of 0.9639.With a medium kernel size of(6,9)and compact multi-window CNN architectures,it improves performance.Cross-validation illustrates stability and generalization across folds.By balancing high recall with minimal false positives,our method provides a reliable and scalable solution for current spam detection in advanced deep learning.By combining contextual embedding and a neural architecture,this study develops a security analysis method.
文摘Message structure reconstruction is a critical task in protocol reverse engineering,aiming to recover protocol field structures without access to source code.It enables important applications in network security,including malware analysis and protocol fuzzing.However,existing methods suffer from inaccurate field boundary delineation and lack hierarchical relationship recovery,resulting in imprecise and incomplete reconstructions.In this paper,we propose ProRE,a novel method for reconstructing protocol field structures based on program execution slice embedding.ProRE extracts code slices from protocol parsing at runtime,converts them into embedding vectors using a data flow-sensitive assembly language model,and performs hierarchical clustering to recover complete protocol field structures.Evaluation on two datasets containing 12 protocols shows that ProRE achieves an average F1 score of 0.85 and a cophenetic correlation coefficient of 0.189,improving by 19%and 0.126%respectively over state-of-the-art methods(including BinPRE,Tupni,Netlifter,and QwQ-32B-preview),demonstrating significant superiority in both accuracy and completeness of field structure recovery.Case studies further validate the effectiveness of ProRE in practical malware analysis scenarios.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01176).
文摘In recent years,ransomware attacks have become one of the most common and destructive types of cyberattacks.Their impact is significant on the operations,finances and reputation of affected companies.Despite the efforts of researchers and security experts to protect information systems from these attacks,the threat persists and the proposed solutions are not able to significantly stop the spread of ransomware attacks.The latest remarkable achievements of large language models(LLMs)in NLP tasks have caught the attention of cybersecurity researchers to integrate thesemodels into security threat detection.Thesemodels offer high embedding capabilities,able to extract rich semantic representations and paving theway formore accurate and adaptive solutions.In this context,we propose a new approach for ransomware detection based on an ensemblemethod that leverages three distinctLLMembeddingmodels.This ensemble strategy takes advantage of the variety of embedding methods and the strengths of each model.In the proposed solution,each embedding model is associated with an independently trainedMLP classifier.The predictions obtained are then merged using a weighted voting technique,assigning each model an influence proportional to its performance.This approach makes it possible to exploit the complementarity of representations,improve detection accuracy and robustness,and offer a more reliable solution in the face of the growing diversity and complexity of modern ransomware.
文摘Recent advancements in autonomous vehicle technologies are transforming intelligent transportation systems.Artificial intelligence enables real-time sensing,decision-making,and control on embedded platforms with improved efficiency.This study presents the design and implementation of an autonomous radio-controlled(RC)vehicle prototype capable of lane line detection,obstacle avoidance,and navigation through dynamic path planning.The system integrates image processing and ultrasonic sensing,utilizing Raspberry Pi for vision-based tasks and ArduinoNano for real-time control.Lane line detection is achieved through conventional image processing techniques,providing the basis for local path generation,while traffic sign classification employs a You Only Look Once(YOLO)model optimized with TensorFlow Lite to support navigation decisions.Images captured by the onboard camera are processed on the Raspberry Pi to extract lane geometry and calculate steering angles,enabling the vehicle to follow the planned path.In addition,ultrasonic sensors placed in three directions at the front of the vehicle detect obstacles and allow real-time path adjustment for safe navigation.Experimental results demonstrate stable performance under controlled conditions,highlighting the system’s potential for scalable autonomous driving applications.This work confirms that deep learning methods can be efficiently deployed on low-power embedded systems,offering a practical framework for navigation,path planning,and intelligent transportation research.
基金support from the National Science Foundation of China(NSFC)(Grants No.12293031 and No.61905252)the National Science Foundation for Distinguished Young Scholars(Grant No.12022308)the National Key R&D Program of China(Grants No.2021YFC2202200 and No.2021YFC2202204).
文摘Adaptive optics(AO)has significantly advanced high-resolution solar observations by mitigating atmospheric turbulence.However,traditional post-focal AO systems suffer from external configurations that introduce excessive optical surfaces,reduced light throughput,and instrumental polarization.To address these limitations,we propose an embedded solar adaptive optics telescope(ESAOT)that intrinsically incorporates the solar AO(SAO)subsystem within the telescope's optical train,featuring a co-designed correction chain with a single Hartmann-Shack full-wavefront sensor(HS f-WFS)and a deformable secondary mirror(DSM).The HS f-WFS uses temporal-spatial hybrid sampling technique to simultane-ously resolve tip-tilt and high-order aberrations,while the DSM performs real-time compensation through adaptive modal optimization.This unified architecture achieves symmetrical polarization suppression and high system throughput by min-imizing optical surfaces.A 600 mm ESAOT prototype incorporating a 12×12 micro-lens array HS f-WFS and 61-actuator piezoelectric DSM has been developed and successfully conducted on-sky photospheric observations.Validations in-cluding turbulence simulations,optical bench testing,and practical observations at the Lijiang observatory collectively confirm the system's capability to maintain aboutλ/10 wavefront error during active region tracking.This architectural breakthrough of the ESAOT addresses long-standing SAO integration challenges in solar astronomy and provides scala-bility analyses confirming direct applicability to the existing and future large solar observation facilities.
基金Supported by the Grant-in-Aid for Scientific Research(C)by the Japan Society for the Promotion of Science(20K03615)。
文摘Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algebraic subsets of G forms a family of closed sets for another T_(1)topology Z_(G) on G called the Zarski topology.A subgroup H of G is said to be Markov(resp.Zarski)embedded if the equality M_(G|H)=M_(H)(resp.Z_(G|H)=Z_(H))holds.I's proved that an abirary subgroup of a free group is both Zariski and Markov embedded in it.
基金funded by the National Science and Technology Council,Taiwan,under grant number NSTC 114-2221-E-167-005-MY3,and NSTC 113-2221-E-167-006-.
文摘Digital watermarking must balance imperceptibility,robustness,complexity,and security.To address the challenge of computational efficiency in trellis-based informed embedding,we propose a modified watermarking framework that integrates fuzzy c-means(FCM)clustering into the generation off block codewords for labeling trellis arcs.The system incorporates a parallel trellis structure,controllable embedding parameters,and a novel informed embedding algorithm with reduced complexity.Two types of embedding schemes—memoryless and memory-based—are designed to flexibly trade-off between imperceptibility and robustness.Experimental results demonstrate that the proposed method outperforms existing approaches in bit error rate(BER)and computational complexity under various attacks,including additive noise,filtering,JPEG compression,cropping,and rotation.The integration of FCM enhances robustness by increasing the codeword distance,while preserving perceptual quality.Overall,the proposed framework is suitable for real-time and secure watermarking applications.
文摘A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.
基金supported by the National Natural Science Foundation of China(Nos.52204051,52304046).
文摘In shale gas reservoir stimulation,proppants are essential for sustaining fracture conductivity.However,increasing closing stress causes proppants to embed into the rock matrix,leading to a progressive decline in fracture permeability and conductivity.Furthermore,rock creep contributes to long-term reductions in fracture performance.To elucidate the combined effects of proppant embedding and rock creep on sustained conductivity,this study conducted controlled experiments examining conductivity decay in propped fractures under varying closing stresses,explicitly accounting for both mechanisms.An embedded discrete fracture model was developed to simulate reservoir production under different conductivity decay scenarios,while evaluating the influence of proppant parameters on fracture performance.The results demonstrate that fracture conductivity diminishes rapidly with increasing stress,yet at 50 MPa,the decline becomes less pronounced.Simulated production profiles show strong agreement with actual gas well data,confirming the model’s accuracy and predictive capability.These findings suggest that employing a high proppant concentration with smaller particle size(5 kg/m^(2),70/140 mesh)is effective for maintaining long-term fracture conductivity and enhancing shale gas recovery.This study provides a rigorous framework for optimizing proppant selection and designing stimulation strategies that maximize reservoir performance over time.
基金supported in part by the National Science and Technology Major Project under(Grant 2022ZD0116100)in part by the National Natural Science Foundation Key Project under(Grant 62436006)+4 种基金in part by the National Natural Science Foundation Youth Fund under(Grant 62406257)in part by the Xizang Autonomous Region Natural Science Foundation General Project under(Grant XZ202401ZR0031)in part by the National Natural Science Foundation of China under(Grant 62276055)in part by the Sichuan Science and Technology Program under(Grant 23ZDYF0755)in part by the Xizang University‘High-Level Talent Training Program’Project under(Grant 2022-GSP-S098).
文摘Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to Tibetan medicine.However,existing Tibetan MNER methods often struggle to comprehensively capture multi-level semantic information,failing to sufficiently extract multi-granularity features and effectively filter out irrelevant information,which ultimately impacts the accuracy of entity recognition.This paper proposes an improved embedding representation method called syllable-word-sentence embedding.By leveraging features at different granularities and using un-scaled dot-product attention to focus on key features for feature fusion,the syllable-word-sentence embedding is integrated into the transformer,enhancing the specificity and diversity of feature representations.The model leverages multi-level and multi-granularity semantic information,thereby improving the performance of Tibetan MNER.We evaluate our proposed model on datasets from various domains.The results indicate that the model effectively identified three types of entities in the Tibetan news dataset we constructed,achieving an F1 score of 93.59%,which represents an improvement of 1.24%compared to the vanilla FLAT.Additionally,results from the Tibetan medical dataset we developed show that it is effective in identifying five kinds of medical entities,with an F1 score of 71.39%,which is a 1.34%improvement over the vanilla FLAT.
基金funded by Advanced Research Project(30209040702).
文摘Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.
基金supported by the National Key R&D Program of China(Grant No.2021YFA1001000)the National Natural Science Foundation of China(Grant Nos.82111530212,U23A20282,and 61971255)+2 种基金the Natural Science Founda-tion of Guangdong Province(Grant No.2021B1515020092)the Shenzhen Bay Laboratory Fund(Grant No.SZBL2020090501014)the Shenzhen Science,Technology and Innovation Commission(Grant Nos.KJZD20231023094659002,JCYJ20220530142809022,and WDZC20220811170401001).
文摘Neural organoids and confocal microscopy have the potential to play an important role in microconnectome research to understand neural patterns.We present PLayer,a plug-and-play embedded neural system,which demonstrates the utilization of sparse confocal microscopy layers to interpolate continuous axial resolution.With an embedded system focused on neural network pruning,image scaling,and post-processing,PLayer achieves high-performance metrics with an average structural similarity index of 0.9217 and a peak signal-to-noise ratio of 27.75 dB,all within 20 s.This represents a significant time saving of 85.71%with simplified image processing.By harnessing statistical map estimation in interpolation and incorporating the Vision Transformer–based Restorer,PLayer ensures 2D layer consistency while mitigating heavy computational dependence.As such,PLayer can reconstruct 3D neural organoid confocal data continuously under limited computational power for the wide acceptance of fundamental connectomics and pattern-related research with embedded devices.
基金the financial supports of the National Natural Science Foundation of China(No.52372200)a project supported by the State Key Laboratory of Mechanics and Control for Aerospace Structures(No.MCAS-S-0324G01)。
文摘Battery safety has emerged as a critical challenge for achieving carbon neutrality,driven by the increasing frequency of thermal runaway incidents in electric vehicles(EVs)and stationary energy storage systems(ESSs).Conventional battery monitoring technologies struggle to track multiple physicochemical parameters in real time,hindering early hazard detection.Embedded optical fiber sensors have gained prominence as a transformative solution for next-generation smart battery sensing,owing to their micrometer size,multiplexing capability,and electromagnetic immunity.However,comprehensive reviews focusing on their advancements in operando multi-parameter monitoring remain scarce,despite their critical importance for ensuring battery safety.To address this gap,this review first introduces a classification and the fundamental principles of advanced battery-oriented optical fiber sensors.Subsequently,it summarizes recent developments in single-parameter battery monitoring using optical fiber sensors.Building on this foundation,this review presents the first comprehensive analysis of multifunctional optical fiber sensing platforms capable of simultaneously tracking temperature,strain,pressure,refractive index,and monitoring battery aging.Targeted strategies are proposed to facilitate the practical development of this technology,including optimization of sensor integration techniques,minimizing sensor invasiveness,resolving the cross-sensitivity of fiber Bragg grating(FBG)through structural innovation,enhancing techno-economics,and combining with artificial intelligence(AI).By aligning academic research with industry requirements,this review provides a methodological roadmap for developing robust optical sensing systems to ensure battery safety in decarbonization-driven applications.
文摘The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.
基金supported by the Collaborative Tackling Project of the Yangtze River Delta SciTech Innovation Community(Nos.2024CSJGG01503,2024CSJGG01500)Guangxi Key Research and Development Program(No.AB24010317)Jiangxi Provincial Key Laboratory of Electronic Data Control and Forensics(Jiangxi Police College)(No.2025JXJYKFJJ002).
文摘Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.
基金co-supported by the National Natural Science Foundation of China(Nos.52105411,52105400and 52305420)the China Postdoctoral Science Foundation(No.2023M742830)Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University(No.CX2023008).
文摘In this study,a new linear friction welding(LFW)process,embedded LFW process,was put forward,which was mainly applied to combination manufacturing of long or overlong loadcarrying titanium alloy structural components in aircraft.The interfacial plastic flow behavior and bonding mechanism of this process were investigated by a developed coupling EulerianLagrangian numerical model using software ABAQUS and a novel thermo-physical simulation method with designed embedded hot compression specimen.In addition,the formation mechanism and control method of welding defects caused by uneven plastic flow were discussed.The results reveal that the plastic flow along oscillating direction of this process is even and sufficient.In the direction perpendicular to oscillation,thermo-plastic metals mainly flow downward along welding interface under coupling of shear stress and interfacial pressure,resulting in the interfacial plastic zone shown as an inverted“V”shape.The upward plastic flow in this direction is relatively weak,and only a small amount of flash is extruded from top of joint.Moreover,the wedge block and welding components at top of joint are always in un-steady friction stage,leading to nonuniform temperature field distribution and un-welded defects.According to the results of numerical simulation,high oscillating frequency combined with low pressure and small amplitude is considered as appropriate parameter selection scheme to improve the upward interfacial plastic flow at top of joint and suppress the un-welded defects.The results of thermo-physical simulation illustrate that continuous dynamic recrystallization(CDRX)induces the bonding of interface,accompanying by intense dislocation movement and creation of many low-angle grain boundaries.In the interfacial bonding area,grain orientation is random with relatively low texture density(5.0 mud)owing to CDRX.
基金supported by National Natural Science Foundation of China(61901071,61871062,61771082,U20A20157)Science and Natural Science Foundation of Chongqing,China(cstc2020jcyjzdxmX0024)+1 种基金University Innovation Research Group of Chongqing(CXQT20017)Scientific and Technological Research Program of Chongqing Municipal Education Commission(No.KJZD-K201901301).
文摘Network virtualization is the development trend and inevitable requirement of hybrid wireless sensor networks(HWSNs).Low mapping efficiency and service interruption caused by mobility seriously affect the reliability of sensing tasks and ultimately affect the long-term revenue of the infrastructure providers.In response to these problems,this paper proposes an efficient virtual network embedding algorithm with a reliable service guarantee.Based on the topological attributes of nodes,a method for evaluating the physical network resource importance degree is proposed,and the nodes with rich resources are selected to improve embedding efficiency.Then,a method for evaluating the physical network reliability degree is proposed to predict the probability of mobile sensors providing uninterrupted services.The simulation results show that the proposed algorithm improves the acceptance rate of virtual sensor networks(VSN)embedding requests and the long-term revenue of the infrastructure providers.
