To improve the theoretical prediction accuracy of static mechanical quantities in MEMS cantilever beams for microwave power detection chips,a distributed static model is proposed based on the deflection equation.An an...To improve the theoretical prediction accuracy of static mechanical quantities in MEMS cantilever beams for microwave power detection chips,a distributed static model is proposed based on the deflection equation.An analytical frame-work is established through the precise characterization of cantilever beam bending.The framework can accurately extract key electromechanical parameters,and the correlation between these parameters and geometric changes is systematically studied.Results show that the pull-in voltage increases with the gap but decreases with the length.The predicted pull-in voltage indi-cates a relative error of only 6.5%between the distributed static model and the simulation,which is significantly lower than that of the other two models.The overload power and sensitivity are also analyzed to facilitate performance trade-offs in chip design.The measured return loss varies between-66.46 and-10.56 dB over the 8-12 GHz frequency band,exhibiting a charac-teristic V-shaped trend.Moreover,the measured sensitivity of 66.5 fF/W closely matches the theoretical value of 69.3 fF/W,show-ing a relative error of 5.6%.These findings confirm that the distributed model outperforms the other two in terms of both accu-racy and physical realism,thereby providing important reference for the design of microwave power detection chips.展开更多
Amazon Web Services(AWS)Cloud Trail auditing service provides detailed records of operational and security events,enabling cloud administrators to monitor user activity and manage compliance.Although signaturebased th...Amazon Web Services(AWS)Cloud Trail auditing service provides detailed records of operational and security events,enabling cloud administrators to monitor user activity and manage compliance.Although signaturebased threat detection methods have been enhanced with machine learning and Large Language Models(LLMs),these approaches remain limited in addressing emerging threats.This study evaluates a two-step Retrieval Augmented Generation(RAG)approach using Gemini 2.5 Pro to enhance threat detection accuracy and contextual relevance.The RAG system integrates external cybersecurity knowledge sources including the MITRE ATT&CK framework,AWS Threat Technique Catalogue,and threat reports to overcome limitations of static pre-trained LLMs.We constructed an evaluation dataset of 200 unique CloudTrail events(122 malicious,78 benign)using the Stratus Red Team adversary emulation framework,covering 9 MITRE ATT&CK techniques across 8 tactics.Events were sampled from 1724 total events using stratified sampling.Ground truth labels were created through systematic expert annotation with 90%inter-annotator agreement.The RAG-enabled model achieved estimated 78%accuracy,85%precision,and 79%F1-score,representing 70.5%accuracy improvement and 76.4%F1-score improvement over baseline Gemini 2.5 Pro(46%accuracy,45%F1-score).Performance are based on evaluation results on 200-event dataset.Cost-latency analysis revealed processing time of 4.1 s and cost of$0.00376 per event,comparable to commercial SIEM solutions while providing superior MITRE ATT&CK attribution.The findings demonstrate that RAG substantially enhances context-aware threat detection,providing actionable insights for cloud security operations.展开更多
Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet th...Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a...To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.展开更多
The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a...The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a crucial research question arises:How can we differentiate between AI-generated and human-authored text?Existing detectors face some challenges,such as operating as black boxes,relying on supervised training,and being vulnerable to manipulation and misinformation.To tackle these challenges,we propose an innovative unsupervised white-box detection method that utilizes a“dual-driven verification mechanism”to achieve high-performance detection,even in the presence of obfuscated attacks in the text content.To be more specific,we initially employ the SpaceInfi strategy to enhance the difficulty of detecting the text content.Subsequently,we randomly select vulnerable spots from the text and perturb them using another pre-trained language model(e.g.,T5).Finally,we apply a dual-driven defense mechanism(D3M)that validates text content with perturbations,whether generated by a model or authored by a human,based on the dimensions of Information TransmissionQuality and Information TransmissionDensity.Through experimental validation,our proposed novelmethod demonstrates state-of-the-art(SOTA)performancewhen exposed to equivalent levels of perturbation intensity across multiple benchmarks,thereby showcasing the effectiveness of our strategies.展开更多
In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds...In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.展开更多
The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integra...The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.展开更多
The use of Unmanned Aerial Vehicles(UAVs)for defect detection on railway slopes is becoming increasingly widespread due to their ability to capture high-resolution images over large,inaccessible,and topographically co...The use of Unmanned Aerial Vehicles(UAVs)for defect detection on railway slopes is becoming increasingly widespread due to their ability to capture high-resolution images over large,inaccessible,and topographically complex areas.However,current UAV-based detection methods face several critical limitations,including constrained deployment frequency,limited availability of annotated defect data,and the lack of mature risk assessment frameworks.To address these challenges,this study introduces a novel approach that integrates diffusion models with Large Language Models(LLMs)to generate highquality synthetic defect images tailored to railway slope scenarios.Furthermore,an improved transformerbased architecture is proposed,incorporating attention mechanisms and LLM-guided diffusion-generated imagery to enhance defect recognition performance under complex environmental conditions.Experimental evaluations conducted on a dataset of 300 field-collected images from high-risk railway slopes demonstrate that the proposed method significantly outperforms existing baselines in terms of precision,recall,and robustness,indicating strong applicability for real-world railway infrastructure monitoring and disaster prevention.展开更多
Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may r...Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.展开更多
With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random dom...With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random domain names,hiding the real IP of Command and Control(C&C)servers to build botnets.Due to the randomness and dynamics of DGA,traditional methods struggle to detect them accurately,increasing the difficulty of network defense.This paper proposes a lightweight DGA detection model based on knowledge distillation for resource-constrained IoT environments.Specifically,a teacher model combining CharacterBERT,a bidirectional long short-term memory(BiLSTM)network,and attention mechanism(ATT)is constructed:it extracts character-level semantic features viaCharacterBERT,captures sequence dependencieswith the BiLSTM,and integrates theATT for key feature weighting,formingmulti-granularity feature fusion.An improved knowledge distillation approach transfers the teacher model’s learned knowledge to the simplified DistilBERT student model.Experimental results show the teacher model achieves 98.68%detection accuracy.The student modelmaintains slightly improved accuracy while significantly compressing parameters to approximately 38.4%of the teacher model’s scale,greatly reducing computational overhead for IoT deployment.展开更多
Phishing email detection represents a critical research challenge in cybersecurity.To address this,this paper proposes a novel Double-S(statistical-semantic)feature model based on three core entities involved in email...Phishing email detection represents a critical research challenge in cybersecurity.To address this,this paper proposes a novel Double-S(statistical-semantic)feature model based on three core entities involved in email communication:the sender,recipient,and email content.We employ strategic game theory to analyze the offensive strategies of phishing attackers and defensive strategies of protectors,extracting statistical features from these entities.We also leverage the Qwen large language model to excavate implicit semantic features(e.g.,emotional manipulation and social engineering tactics)from email content.By integrating statistical and semantic features,our model achieves a robust representation of phishing emails.We introduce a hybrid detection model that integrates a convolutional neural network(CNN)module with the XGBoost(Extreme Gradient Boosting)classifier,effectively capturing local correlations in high-dimensional features.Experimental results on real-world phishing email datasets demonstrate the superiority of our approach,achieving an F1-score of 0.9587,precision of 0.9591,and recall of 0.9583,representing improvements of 1.3%–10.6%compared to state-of-the-art methods.展开更多
The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and ot...The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.展开更多
Asparagus stem blight is a devastating crop disease,and the early detection of its pathogenic spores is essential for effective disease control and prevention.However,spore detection is still hindered by complex backg...Asparagus stem blight is a devastating crop disease,and the early detection of its pathogenic spores is essential for effective disease control and prevention.However,spore detection is still hindered by complex backgrounds,small target sizes,and high annotation costs,which limit its practical application and widespread adoption.To address these issues,a semi-supervised spore detection framework is proposed for use under complex background conditions.Firstly,a difficulty perception scoring function is designed to quantify the detection difficulty of each image region.For regions with higher difficulty scores,a masking strategy is applied,while the remaining regions are adversarial augmentation is applied to encourage the model to learn fromchallenging areasmore effectively.Secondly,a Gaussian Mixture Model is employed to dynamically adjust the allocation threshold for pseudo-labels,thereby reducing the influence of unreliable supervision signals and enhancing the stability of semi-supervised learning.Finally,the Wasserstein distance is introduced for object localization refinement,offering a more robust positioning approach.Experimental results demonstrate that the proposed framework achieves 88.9% mAP50 and 60.7% mAP50-95,surpassing the baseline method by 4.2% and 4.6%,respectively,using only 10% of labeled data.In comparison with other state-of-the-art semi-supervised detection models,the proposed method exhibits superior detection accuracy and robustness.In conclusion,the framework not only offers an efficient and reliable solution for plant pathogen spore detection but also provides strong algorithmic support for real-time spore detection and early disease warning systems,with significant engineering application potential.展开更多
Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on li...Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.展开更多
The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(L...The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.展开更多
Many machine learning-based Android malware detection often suffers from concept drift,where models trained on historical data fail to generalize to evolving threats.This paper proposes SCAN(Structural Clustering with...Many machine learning-based Android malware detection often suffers from concept drift,where models trained on historical data fail to generalize to evolving threats.This paper proposes SCAN(Structural Clustering with Adaptive thresholds for iNtelligent Android malware detection),a hybrid intelligent framework designed to mitigate concept drift without retraining.SCAN integrates Gaussian Mixture Models(GMMs)-based clustering with cluster-wise adaptive thresholding and supervised classifiers tailored to each cluster.A key challenge in clusteringbased malware detection is cluster-wise class imbalance,where clusters contain disproportionate distributions of benign and malicious samples.SCAN addresses this issue through adaptive thresholding,which dynamically adjusts the decision boundary of each cluster according to its malicious-to-benign ratio.In the final training stage,four supervised learning algorithms—Random Forest(RF),Support Vector Machine(SVM),k-NN,and XGBoost—are applied within the GMM-defined clusters.We train SCAN on Android applications collected from 2014-2017 and test it with applications from 2018-2023.Experimental results demonstrate that SCAN combined with RF consistently achieves superior performance,with both average accuracy and average F1-score exceeding 91%.These findings confirm SCAN’s robustness to concept drift and highlight its potential as a sustainable and intelligent solution for long-term Android malware detection in the real world.展开更多
To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints ...To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.展开更多
Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-dr...Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-driven strategy(MDCDS)enhances model transparency and molten iron quality(MIQ)prediction.By zoning the furnace and applying mechanism-based features for material and thermal trends,coupled with a novel stationary broad feature learning system(StaBFLS),interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined.Subsequently,by integrating stationary feature representation with mechanism features,our temporal matching broad learning system(TMBLS)aligns process and quality variables using MIQ as the target.This integration allows us to establish process monitoring statistics using both mechanism and data-driven features,as well as detect modeling deviations.Validated against real-world BFIP data,our MDCDS model demonstrates consistent process alignment,robust feature extraction,and improved MIQ modeling—Yielding better fault detection.Additionally,we offer detailed insights into the validation process,including parameter baselining and optimization.展开更多
To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precis...To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precisely pinpointing misfire faults.In the experiment,we established a total of 11 distinct states,encompassing the engine’s normal state,single-cylinder misfire faults,and dual-cylinder misfire faults for different cylinders.Data collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,840Hz.The collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and prevent overlap between the two sets.The results revealed that,with a vibration acceleration sequence of 1000 time steps(approximately 50 ms)as input,the SENET model achieved a misfire fault detection accuracy of 99.8%.For comparison,we also trained and tested several commonly used models,including Long Short-Term Memory(LSTM),Transformer,and Multi-Scale Residual Networks(MSRESNET),yielding accuracy rates of 84%,79%,and 95%,respectively.This underscores the superior accuracy of the SENET model in detecting engine misfire faults compared to other models.Furthermore,the F1 scores for each type of recognition in the SENET model surpassed 0.98,outperforming the baseline models.Our analysis indicated that the misclassified samples in the LSTM and Transformer models’predictions were primarily due to intra-class misidentifications between single-cylinder and dual-cylinder misfire scenarios.To delve deeper,we conducted a visual analysis of the features extracted by the LSTM and SENET models using T-distributed Stochastic Neighbor Embedding(T-SNE)technology.The findings revealed that,in the LSTMmodel,data points of the same type tended to cluster together with significant overlap.Conversely,in the SENET model,data points of various types were more widely and evenly dispersed,demonstrating its effectiveness in distinguishing between different fault types.展开更多
基金supported by the National Natural Science Foundation of China(61904089)the Province Natural Science Foundation of Jiangsu(BK20190731).
文摘To improve the theoretical prediction accuracy of static mechanical quantities in MEMS cantilever beams for microwave power detection chips,a distributed static model is proposed based on the deflection equation.An analytical frame-work is established through the precise characterization of cantilever beam bending.The framework can accurately extract key electromechanical parameters,and the correlation between these parameters and geometric changes is systematically studied.Results show that the pull-in voltage increases with the gap but decreases with the length.The predicted pull-in voltage indi-cates a relative error of only 6.5%between the distributed static model and the simulation,which is significantly lower than that of the other two models.The overload power and sensitivity are also analyzed to facilitate performance trade-offs in chip design.The measured return loss varies between-66.46 and-10.56 dB over the 8-12 GHz frequency band,exhibiting a charac-teristic V-shaped trend.Moreover,the measured sensitivity of 66.5 fF/W closely matches the theoretical value of 69.3 fF/W,show-ing a relative error of 5.6%.These findings confirm that the distributed model outperforms the other two in terms of both accu-racy and physical realism,thereby providing important reference for the design of microwave power detection chips.
文摘Amazon Web Services(AWS)Cloud Trail auditing service provides detailed records of operational and security events,enabling cloud administrators to monitor user activity and manage compliance.Although signaturebased threat detection methods have been enhanced with machine learning and Large Language Models(LLMs),these approaches remain limited in addressing emerging threats.This study evaluates a two-step Retrieval Augmented Generation(RAG)approach using Gemini 2.5 Pro to enhance threat detection accuracy and contextual relevance.The RAG system integrates external cybersecurity knowledge sources including the MITRE ATT&CK framework,AWS Threat Technique Catalogue,and threat reports to overcome limitations of static pre-trained LLMs.We constructed an evaluation dataset of 200 unique CloudTrail events(122 malicious,78 benign)using the Stratus Red Team adversary emulation framework,covering 9 MITRE ATT&CK techniques across 8 tactics.Events were sampled from 1724 total events using stratified sampling.Ground truth labels were created through systematic expert annotation with 90%inter-annotator agreement.The RAG-enabled model achieved estimated 78%accuracy,85%precision,and 79%F1-score,representing 70.5%accuracy improvement and 76.4%F1-score improvement over baseline Gemini 2.5 Pro(46%accuracy,45%F1-score).Performance are based on evaluation results on 200-event dataset.Cost-latency analysis revealed processing time of 4.1 s and cost of$0.00376 per event,comparable to commercial SIEM solutions while providing superior MITRE ATT&CK attribution.The findings demonstrate that RAG substantially enhances context-aware threat detection,providing actionable insights for cloud security operations.
基金Tianmin Tianyuan Boutique Vegetable Industry Technology Service Station(Grant No.2024120011003081)Development of Environmental Monitoring and Traceability System for Wuqing Agricultural Production Areas(Grant No.2024120011001866)。
文摘Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
基金the Shandong Provincial Key Research and Development Program(Grant No.2024SFGC0201).
文摘To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.
文摘The emergence of large language models(LLMs)has brought about revolutionary social value.However,concerns have arisen regarding the generation of deceptive content by LLMs and their potential for misuse.Consequently,a crucial research question arises:How can we differentiate between AI-generated and human-authored text?Existing detectors face some challenges,such as operating as black boxes,relying on supervised training,and being vulnerable to manipulation and misinformation.To tackle these challenges,we propose an innovative unsupervised white-box detection method that utilizes a“dual-driven verification mechanism”to achieve high-performance detection,even in the presence of obfuscated attacks in the text content.To be more specific,we initially employ the SpaceInfi strategy to enhance the difficulty of detecting the text content.Subsequently,we randomly select vulnerable spots from the text and perturb them using another pre-trained language model(e.g.,T5).Finally,we apply a dual-driven defense mechanism(D3M)that validates text content with perturbations,whether generated by a model or authored by a human,based on the dimensions of Information TransmissionQuality and Information TransmissionDensity.Through experimental validation,our proposed novelmethod demonstrates state-of-the-art(SOTA)performancewhen exposed to equivalent levels of perturbation intensity across multiple benchmarks,thereby showcasing the effectiveness of our strategies.
基金funded by the Joint Funds of the National Natural Science Foundation of China(U2341223)the Beijing Municipal Natural Science Foundation(No.4232067).
文摘In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under Grant No.(GPIP:1074-612-2024).
文摘The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.
基金supported in part by the National Natural Science Foundation of China under Grant 52432012in part by the Shanghai Science and Technology Project with 25ZR1402508。
文摘The use of Unmanned Aerial Vehicles(UAVs)for defect detection on railway slopes is becoming increasingly widespread due to their ability to capture high-resolution images over large,inaccessible,and topographically complex areas.However,current UAV-based detection methods face several critical limitations,including constrained deployment frequency,limited availability of annotated defect data,and the lack of mature risk assessment frameworks.To address these challenges,this study introduces a novel approach that integrates diffusion models with Large Language Models(LLMs)to generate highquality synthetic defect images tailored to railway slope scenarios.Furthermore,an improved transformerbased architecture is proposed,incorporating attention mechanisms and LLM-guided diffusion-generated imagery to enhance defect recognition performance under complex environmental conditions.Experimental evaluations conducted on a dataset of 300 field-collected images from high-risk railway slopes demonstrate that the proposed method significantly outperforms existing baselines in terms of precision,recall,and robustness,indicating strong applicability for real-world railway infrastructure monitoring and disaster prevention.
文摘Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.
基金supported by the following projects:National Natural Science Foundation of China(62461041)Natural Science Foundation of Jiangxi Province China(20242BAB25068).
文摘With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random domain names,hiding the real IP of Command and Control(C&C)servers to build botnets.Due to the randomness and dynamics of DGA,traditional methods struggle to detect them accurately,increasing the difficulty of network defense.This paper proposes a lightweight DGA detection model based on knowledge distillation for resource-constrained IoT environments.Specifically,a teacher model combining CharacterBERT,a bidirectional long short-term memory(BiLSTM)network,and attention mechanism(ATT)is constructed:it extracts character-level semantic features viaCharacterBERT,captures sequence dependencieswith the BiLSTM,and integrates theATT for key feature weighting,formingmulti-granularity feature fusion.An improved knowledge distillation approach transfers the teacher model’s learned knowledge to the simplified DistilBERT student model.Experimental results show the teacher model achieves 98.68%detection accuracy.The student modelmaintains slightly improved accuracy while significantly compressing parameters to approximately 38.4%of the teacher model’s scale,greatly reducing computational overhead for IoT deployment.
基金supported by the National Key Research and Development Program of China(No.2023YFB3105700).
文摘Phishing email detection represents a critical research challenge in cybersecurity.To address this,this paper proposes a novel Double-S(statistical-semantic)feature model based on three core entities involved in email communication:the sender,recipient,and email content.We employ strategic game theory to analyze the offensive strategies of phishing attackers and defensive strategies of protectors,extracting statistical features from these entities.We also leverage the Qwen large language model to excavate implicit semantic features(e.g.,emotional manipulation and social engineering tactics)from email content.By integrating statistical and semantic features,our model achieves a robust representation of phishing emails.We introduce a hybrid detection model that integrates a convolutional neural network(CNN)module with the XGBoost(Extreme Gradient Boosting)classifier,effectively capturing local correlations in high-dimensional features.Experimental results on real-world phishing email datasets demonstrate the superiority of our approach,achieving an F1-score of 0.9587,precision of 0.9591,and recall of 0.9583,representing improvements of 1.3%–10.6%compared to state-of-the-art methods.
基金supported in part by the Science and Technology Innovation Program of Hunan Province under Grant 2025RC3166the National Natural Science Foundation of China under Grant 62572176the National Key R&D Program of China under Grant 2024YFF0618800.
文摘The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.
基金supported by Development of asparagus price database based on agricultural big data(381724).
文摘Asparagus stem blight is a devastating crop disease,and the early detection of its pathogenic spores is essential for effective disease control and prevention.However,spore detection is still hindered by complex backgrounds,small target sizes,and high annotation costs,which limit its practical application and widespread adoption.To address these issues,a semi-supervised spore detection framework is proposed for use under complex background conditions.Firstly,a difficulty perception scoring function is designed to quantify the detection difficulty of each image region.For regions with higher difficulty scores,a masking strategy is applied,while the remaining regions are adversarial augmentation is applied to encourage the model to learn fromchallenging areasmore effectively.Secondly,a Gaussian Mixture Model is employed to dynamically adjust the allocation threshold for pseudo-labels,thereby reducing the influence of unreliable supervision signals and enhancing the stability of semi-supervised learning.Finally,the Wasserstein distance is introduced for object localization refinement,offering a more robust positioning approach.Experimental results demonstrate that the proposed framework achieves 88.9% mAP50 and 60.7% mAP50-95,surpassing the baseline method by 4.2% and 4.6%,respectively,using only 10% of labeled data.In comparison with other state-of-the-art semi-supervised detection models,the proposed method exhibits superior detection accuracy and robustness.In conclusion,the framework not only offers an efficient and reliable solution for plant pathogen spore detection but also provides strong algorithmic support for real-time spore detection and early disease warning systems,with significant engineering application potential.
基金supported in part by the National Natural Science Foundation of China(62573387)the Natural Science Foundation of Zhejiang province,China(LY24F030004)the Fundamental Research Funds of Zhejiang Sci-Tech University(25222139-Y).
文摘Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.
文摘The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.
基金supported in part by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(No.2021R1A2C2012574)in part by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korea government(Ministry of Science and ICT)(IITP-2025-RS-2023-00259967).
文摘Many machine learning-based Android malware detection often suffers from concept drift,where models trained on historical data fail to generalize to evolving threats.This paper proposes SCAN(Structural Clustering with Adaptive thresholds for iNtelligent Android malware detection),a hybrid intelligent framework designed to mitigate concept drift without retraining.SCAN integrates Gaussian Mixture Models(GMMs)-based clustering with cluster-wise adaptive thresholding and supervised classifiers tailored to each cluster.A key challenge in clusteringbased malware detection is cluster-wise class imbalance,where clusters contain disproportionate distributions of benign and malicious samples.SCAN addresses this issue through adaptive thresholding,which dynamically adjusts the decision boundary of each cluster according to its malicious-to-benign ratio.In the final training stage,four supervised learning algorithms—Random Forest(RF),Support Vector Machine(SVM),k-NN,and XGBoost—are applied within the GMM-defined clusters.We train SCAN on Android applications collected from 2014-2017 and test it with applications from 2018-2023.Experimental results demonstrate that SCAN combined with RF consistently achieves superior performance,with both average accuracy and average F1-score exceeding 91%.These findings confirm SCAN’s robustness to concept drift and highlight its potential as a sustainable and intelligent solution for long-term Android malware detection in the real world.
基金supported by the National Key R&D Program of China(No.2023YFC3081200)the National Natural Science Foundation of China(No.42077264)。
文摘To map the rock joints in the underground rock mass,a method was proposed to semiautomatically detect the rock joints from borehole imaging logs using a deep learning algorithm.First,450 images containing rock joints were selected from borehole ZKZ01 in the Rumei hydropower station.These images were labeled to establish ground truth which was subdivided into training,validation,and testing data.Second,the YOLO v2 model with optimal parameter settings was constructed.Third,the training and validation data were used for model training,while the test data was used to generate the precision-recall curve for prediction evaluation.Fourth,the trained model was applied to a new borehole ZKZ02 to verify the feasibility of the model.There were 12 rock joints detected from the selected images in borehole ZKZ02 and four geometric parameters for each rock joint were determined by sinusoidal curve fitting.The average precision of the trained model reached 0.87.
基金supported in part by the National Natural Science Foundation of China(61933015,61703371,62273030)the Central University Basic Research Fund of China(K20200002)(for NGICS Platform,Zhejiang University)the Social Development Project of Zhejiang Provincial Public Technology Research(LGF19F030004,LGG21F030015).
文摘Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-driven strategy(MDCDS)enhances model transparency and molten iron quality(MIQ)prediction.By zoning the furnace and applying mechanism-based features for material and thermal trends,coupled with a novel stationary broad feature learning system(StaBFLS),interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined.Subsequently,by integrating stationary feature representation with mechanism features,our temporal matching broad learning system(TMBLS)aligns process and quality variables using MIQ as the target.This integration allows us to establish process monitoring statistics using both mechanism and data-driven features,as well as detect modeling deviations.Validated against real-world BFIP data,our MDCDS model demonstrates consistent process alignment,robust feature extraction,and improved MIQ modeling—Yielding better fault detection.Additionally,we offer detailed insights into the validation process,including parameter baselining and optimization.
基金Yongxian Huang supported by Projects of Guangzhou Science and Technology Plan(2023A04J0409)。
文摘To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precisely pinpointing misfire faults.In the experiment,we established a total of 11 distinct states,encompassing the engine’s normal state,single-cylinder misfire faults,and dual-cylinder misfire faults for different cylinders.Data collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,840Hz.The collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and prevent overlap between the two sets.The results revealed that,with a vibration acceleration sequence of 1000 time steps(approximately 50 ms)as input,the SENET model achieved a misfire fault detection accuracy of 99.8%.For comparison,we also trained and tested several commonly used models,including Long Short-Term Memory(LSTM),Transformer,and Multi-Scale Residual Networks(MSRESNET),yielding accuracy rates of 84%,79%,and 95%,respectively.This underscores the superior accuracy of the SENET model in detecting engine misfire faults compared to other models.Furthermore,the F1 scores for each type of recognition in the SENET model surpassed 0.98,outperforming the baseline models.Our analysis indicated that the misclassified samples in the LSTM and Transformer models’predictions were primarily due to intra-class misidentifications between single-cylinder and dual-cylinder misfire scenarios.To delve deeper,we conducted a visual analysis of the features extracted by the LSTM and SENET models using T-distributed Stochastic Neighbor Embedding(T-SNE)technology.The findings revealed that,in the LSTMmodel,data points of the same type tended to cluster together with significant overlap.Conversely,in the SENET model,data points of various types were more widely and evenly dispersed,demonstrating its effectiveness in distinguishing between different fault types.
