期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到597篇文章
< 1 2 … 30 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Landslide susceptibility assessment integrating deep transfer learning and physical models in the Baihetan reservoir area,China 认领 引用 被引量：1
1
作者 Ming Peng Yue Wang +5 位作者 Chenyi Ma Haojie Wang Shaoqiang Meng Zhenming Shi Weijiang Chu Jianrong Xu 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第6期4382-4401,共20页
Reservoir landslides pose significant risks to hydropower projects,potentially leading to catastrophic disasters that threaten downstream lives and properties.Landslide susceptibility assessments are critical for effe... Reservoir landslides pose significant risks to hydropower projects,potentially leading to catastrophic disasters that threaten downstream lives and properties.Landslide susceptibility assessments are critical for effective regional disaster prevention and mitigation.However,the complexity,model uninterpretability,and data scarcity related to reservoir landslides,particularly when adapting models across diverse geographic regions,present significant challenges.This study proposes an interpretable Deep Transfer Learning model coupled with multi-source data and Physical methods(DTLP).The model is trained on multi-source data from the Three Gorges Reservoir Area(TGRA)and Lower Jinsha River Basin(LJRB),tested in Baihetan Reservoir Area(BHT),addressing the issues of limited data and cross-regional generalization.The physical method captures the effect of dynamic water level changes on slope stability.SHAP values are used to interpret the model,providing clear insights into its internal mechanisms.Results demonstrate that DTLP outperforms TrAdaBoost in data-scarce regions,achieving higher accuracy(AUC=0.953,Accuracy=0.941)with better feature generalization and susceptibility zone identification.Incorporating dynamic water level changes into the physical model enhances identification of high-susceptibility areas and reduces misclassifications.SHAP analysis indicates that elevation,lithology,and distance to river significantly influence the model decisions.Using TGRA as the source domain further validates the superiority of DTLP framework.However,due to the initial discrepancies between TGRA and the target domain,the transferability is constrained to some extent,resulting in models trained on LJRB data outperforming those trained on TGRA data. 展开更多
关键词 Landslide susceptibility assessment Deep transfer learning Reservoir landslides Infiniteslope model SHAP values
暂未订购 下载PDF
State Estimation With Model Uncertainty Using Structure Variational Bayesian and Transfer Learning 认领 引用
2
作者 Shuang Gao Xiaoli Luan +2 位作者 Biao Huang Shunyi Zhao Fei Liu 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期715-727,共13页
This paper proposes a novel approach to address parameter uncertainties for state estimation in Markovian jump linear systems by leveraging transfer learning.Assume that the source domain model is available and reliab... This paper proposes a novel approach to address parameter uncertainties for state estimation in Markovian jump linear systems by leveraging transfer learning.Assume that the source domain model is available and reliable,and the target domain model has significant model parameter uncertainties.To enhance estimation performance in the target domain,the proposed method transfers model knowledge from the source domain and adjusts it using a tuning factor before incorporating it into the target domain estimator.More specifically,this approach involves transferring the modified probability density functions of state prediction from the source domain to the target domain and determining the tuning factor via structure variational Bayesian inference using measurements in the target domain.Using numerical examples and a 1-DOF torsion system,we showcase the competitiveness of the proposed state estimator compared to the existing robust state estimation methods when dealing with parameter uncertainties.The results highlight its capability to improve estimation accuracy in practical scenarios,showcasing its potential for real-world applications. 展开更多
关键词 Markovian jump linear systems parameter uncertainty state estimation structure variational inference transfer learning
暂未订购 下载PDF
An Isothermal Surface Imaging and Transfer Learning Framework for Fast Isothermal Surface Prediction and 3D Temperature Field Reconstruction in Metal Additive Manufacturing 认领 引用
3
作者 Zhidong Wang Yanping Lian +2 位作者 Mingjian Li Jiawei Chen Ruxin Gao 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第3期1-28,共28页
Metal additive manufacturing(AM)technology has promising applications across many fields due to its near-net-shape advantages.The quality of the as-built component is closely linked to the temperature evolution during... Metal additive manufacturing(AM)technology has promising applications across many fields due to its near-net-shape advantages.The quality of the as-built component is closely linked to the temperature evolution during the metal AM process,which exhibits strong nonlinearities,localized high gradients,and rapid cooling rates.Therefore,real-time prediction of the temperature field is essential for effective online process control to achieve high fabrication quality,which poses surprising challenges for numerical methods,as traditional methods suffer from the inherent time-consuming nature of fine time-space discretizations.In this study,we proposed an isothermal surface imaging and transfer learning framework for fast prediction of isothermal surfaces,which are further used to reconstruct the high-dimensional,nonlinear temperature field.It consists of three key parts:physics-guided isothermal surface imaging to reduce the problem dimensionality by transforming the unstructured temperature field into a series of structured grayscale images,a pre-trained hybrid parameter-to-image generative neural network for the isothermal surface prediction in favor of small training samples,and a transfer learning strategy leveraging physical similarity of these isothermal surfaces in the metal AM process to obtain the 3D temperature field.The training samples are generated using a high-fidelity numerical model,which is validated against experimental data.The predicted results from the proposed framework agree well with those from the high-fidelity numerical simulation for a given combination of process parameters,achieving a computational cost measured in seconds.It is expected that the proposed framework could serve as a powerful tool for predicting the temperature field and further facilitating online control of process parameters. 展开更多
关键词 Metal additive manufacturing temperature field neural network transfer learning feature engineering
暂未订购 下载PDF
Intelligent segment typesetting in shield tunneling based on artificial neural networks and transfer learning 认领 引用
4
作者 Rui LIU Quanyong ZENG +1 位作者 Haibo XIE Guoli ZHU 《Journal of Zhejiang University-SCIENCE A》 SCIE EI CAS CSCD 2026年第3期200-214,共15页
Shield tunneling is the method most commonly used for underground projects.Segment typesetting,which involves determining the optimal assembly point for each segment ring and sequentially assembling them into a comple... Shield tunneling is the method most commonly used for underground projects.Segment typesetting,which involves determining the optimal assembly point for each segment ring and sequentially assembling them into a complete tunnel,is a critical step in shield tunneling.Currently,this typesetting process relies heavily on the operator’s experience at construction sites,which does not guarantee quality.Furthermore,research focuses mainly on the commonly used 16-point segment typesetting,largely ignoring other segment types.In addition,the reliability of these studies in site applications remains unsatisfactory.To address these issues,we propose an intelligent method for segment typesetting using an artificial neural network(ANN)and transfer learning.Due to insufficient historical data for ANN training,a dataset creation method was devised based on the Monte Carlo method and manual annotation.An ANN model was then developed to typeset 16-point segments,with its hyperparameters optimized through Bayesian optimization.Subsequently,the trained model was adapted to other segment types via transfer learning,using 10-point segments as a case study.Based on the test set established in this study,our proposed method showed superior performance compared with several commonly used machine learning methods and a representative and well-validated segment typesetting method.It was also validated using real data collected from construction sites,achieving an accuracy of 93.75%for 16-point segments and 91.43%for 10-point segments,both of which significantly surpass the results from manual typesetting on-site.The proposed method achieves accurate,rapid,and intelligent segment typesetting,which is adaptable to various segment types. 展开更多
关键词 Shield tunneling Segment typesetting Assembly points Artificial neural network(ANN) Bayesian optimization Transfer learning
暂未订购 下载PDF
Landslide image recognition based on residual networks with transfer learning and spatial-channel dual attention mechanism 认领 引用
5
作者 ZHAO Cheng YU Jiacheng +3 位作者 XIE Yongfei CHEN Huiguan XING Jinquan NIU Jialun 《Journal of Mountain Science》 SCIE CSCD 2026年第7期3155-3169,共15页
Landslides are one of the most significant types of geological disasters worldwide.However,current landslide disaster recognition models generally face issues such as low training efficiency,reliance on large amounts ... Landslides are one of the most significant types of geological disasters worldwide.However,current landslide disaster recognition models generally face issues such as low training efficiency,reliance on large amounts of samples,and vague feature extraction.To address these problems,this paper proposes an enhanced intelligent recognition model based on an improved residual network.Taking remote sensing images from landslide-prone areas in Bijie City,Guizhou Province,China as the research subject,we implemented data augmentation techniques to expand the datasets,subsequently partitioning it into training and validation subsets at a73:27 ratio.During model training,a transfer learning strategy was employed to improve training efficiency through the utilization of ImageNet pre-trained weights.The Res Net50 network architecture was enhanced through the integration of channel attention and spatial attention mechanisms,enabling more effective extraction of critical landslide features.Comparative analysis indicates that after introducing the attention mechanisms,the enhanced model achieved an increase of 1.49% in accuracy,0.45% in precision,1.52% in F1 score,and 0.0297 in Kappa coefficient on the validation set.Notably,recall improved by 2.59%,indicating that the improved model has enhanced landslide disaster recognition capability and overall performance.This study successfully coupled the transfer learning strategy with a dual-attention mechanism into the ResNet50 architecture,allowing the rapid construction of an efficient recognition model under limited sample conditions,significantly improving the comprehensive performance and generalisation ability of the landslide recognition model. 展开更多
关键词 Attention mechanism Convolutional neural network Transfer Learning Landslide disaster identification
暂未订购 下载PDF
Enhanced Scene Recognition via Multi-Model Transfer Learning with Limited Labeled Data 认领 引用
6
作者 Samia Allaoua Chelloug Ahmed A.Abd El-Latif +1 位作者 Samah Al Shathri Mohamed Hammad 《Computers, Materials & Continua》 SCIE EI 2026年第5期1191-1211,共21页
Scene recognition is a critical component of computer vision,powering applications from autonomous vehicles to surveillance systems.However,its development is often constrained by a heavy reliance on large,expensively... Scene recognition is a critical component of computer vision,powering applications from autonomous vehicles to surveillance systems.However,its development is often constrained by a heavy reliance on large,expensively annotated datasets.This research presents a novel,efficient approach that leveragesmulti-model transfer learning from pre-trained deep neural networks—specifically DenseNet201 and Visual Geometry Group(VGG)—to overcome this limitation.Ourmethod significantly reduces dependency on vast labeled data while achieving high accuracy.Evaluated on the Aerial Image Dataset(AID)dataset,the model attained a validation accuracy of 93.6%with a loss of 0.35,demonstrating robust performance with minimal training data.These results underscore the viability of our approach for real-time,data-efficient scene recognition,offering a practical and cost-effective advancement for the field. 展开更多
关键词 Scene recognition transfer learning pre-trained deep models DenseNet201 VGG
暂未订购 下载PDF
Fine-Tune Transfer Learning Model for Deepfake Audio Detection Using Hybrid Features and Data Augmentation 认领 引用
7
作者 Rashid Jahangir Nazik Alturki Muhammad Zubair Khan 《Computers, Materials & Continua》 SCIE EI 2026年第9期1316-1334,共19页
Deepfake audio created with sophisticated speech synthesis and voice cloning technologies is a threat to the credibility of digital communication.Its realism has raised serious concerns in different applications such ... Deepfake audio created with sophisticated speech synthesis and voice cloning technologies is a threat to the credibility of digital communication.Its realism has raised serious concerns in different applications such as digital forensics,cybersecurity,media authentication and voice-based security systems.However,deepfake audio detection still remains difficult.Synthetic speech tends to have subtle artifacts that can mimic the natural vocal pattern very closely.Variations in speakers,recording conditions and background noise make the task more complex.In addition,dataset imbalance and low diversity in training samples could lead to low robustness in the model.To overcome these limitations,the present study aims to propose a framework of transfer learning-based methods based on a combination of fine-tuned pre-trained models,as well as systematic data augmentation.Augmentation methods are introduced to increase the variability and mimic real acoustic conditions.This approach supports the learning of more stable and generalizable representations for both genuine and manipulated speech.The framework employs three DL models:ResNet50 to capture global spectro-temporal structures,VGGish to extract mid-level semantic audio embeddings and YAMNet to identify fine-grained temporal irregularities associated with synthetic speech artifacts.Features from these models are fused through concatenation to construct a unified hybrid feature space.A feature selection stage then reduces redundancy before classification using a lightweight model.Experimental results demonstrate the superiority of the proposed hybrid approach and achieved an accuracy of 99.7%.This performance significantly outperformed individual baseline models and achieved strong generalization across diverse acoustic conditions. 展开更多
关键词 Deepfake audio detection transfer learning hybrid feature fusion data augmentation audio forensics synthetic speech detection
暂未订购 下载PDF
A transfer learning framework for the real-time detection of atmospheric gravity waves from All-Sky Airglow Imager 认领 引用 被引量：1
8
作者 YuBin He QingChen Xu +6 位作者 YaJun Zhu QinZeng Li Cui Tu Bing Cai Wei Yuan XinYing Wang Feng Wei 《Earth and Planetary Physics》 EI CSCD 2026年第3期454-462,共9页
Atmospheric gravity waves(AGWs)observed by the All-Sky Airglow Imager(ASAI)require accurate identification for the study of atmospheric coupling mechanisms and space weather prediction.However,the traditional manual s... Atmospheric gravity waves(AGWs)observed by the All-Sky Airglow Imager(ASAI)require accurate identification for the study of atmospheric coupling mechanisms and space weather prediction.However,the traditional manual screening methods and existing machine learning approaches do not meet the demands of practical station monitoring,which has significantly impeded climatological statistical research based on AGWs.Therefore,a real-time detection framework for ground-based airglow gravity waves that integrates transfer learning with adaptive image preprocessing has been proposed.By employing wavelength-adaptive median filtering and multiscale fusion,the framework effectively suppresses stellar noise while preserving weak gravity wave features.The model utilizes an EfficientNet-B3(convolutional neural network)backbone enhanced with a deformable convolutional layer,trained via a two-stage strategy:A frozen phase prevents overfitting by locking the lower level feature extractor,and a fine-tuning phase optimizes the deformable convolution through cosine annealing and layered optimization.This approach improves both feature transfer efficiency and gravity wave detection sensitivity.The resulting lightweight model achieves 91.2%accuracy with millisecond-level inference speed(23 ms per frame). 展开更多
关键词 atmospheric gravity waves All-Sky Airglow Imager real-time detection multiscale fusion transfer learning EfficientNet-B3 deformable convolution
暂未订购 下载PDF
Transfer Learning for Deep Reinforcement Learning-Based Path Following of Autonomous Surface Vessels 认领 引用 被引量：1
9
作者 Aniket Malviya Suresh Rajendran Xueqian Zhou 《哈尔滨工程大学学报（英文版）》 CSCD 2026年第3期728-744,共17页
Deep Reinforcement Learning(DRL)offers a powerful,model-free,and data-driven approach for the navigation and control of Autonomous Surface Vessels(ASVs).The primary challenge,however,lies in the extensive training req... Deep Reinforcement Learning(DRL)offers a powerful,model-free,and data-driven approach for the navigation and control of Autonomous Surface Vessels(ASVs).The primary challenge,however,lies in the extensive training required for an agent to converge to an effective policy within a complex simulation,leading to significant computational overhead.This paper presents a multi-stage training framework that uses Transfer Learning to pass knowledge between different simulation models,resulting in a highly robust DRL controller for ASVs.The proposed framework utilizes the Deep Deterministic Policy Gradient(DDPG)algorithm to develop the data-driven controller.First,a foundational policy is efficiently learned using a simplified first-order Nomoto dynamics and second-order Nomoto dynamics,which captures the fundamental vessel dynamics.This pre-trained policy is then transferred to a complex,nonlinear Manoeuvring Modelling Group(MMG)model,significantly accelerating training convergence.Subsequently,the agent is fine-tuned within the MMG simulation with environmental disturbances.The models are evaluated on various trajectories during testing to ensure robust performance.The accuracy of the DRL controller is assessed by measuring heading error(eψ)and cross-track error(ye).A traditional Proportional-Integral-Derivative(PID)controller is implemented and compared to benchmark the DRL controller's effectiveness,to highlight the relative advantages and limitations of each approach. 展开更多
关键词 Deep reinforcement learning(DRL) Autonomous surface vessels(ASVs) Deep deterministic policy gradient(DDPG) Transfer learning Proportional-integral-derivative(PID)controller Line of sight(LOS)guidance algorithm
暂未订购 下载PDF
Multi-waveform transfer learning for predicting electromagnetic sensitivity of integrated modular avionics power modules in complex environment 认领 引用
10
作者 Yuntao JIN Fei DAI +2 位作者 Xingye CHEN Lingnan SONG Aixin CHEN 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第4期494-510,共17页
Understanding the electromagnetic compatibility of power modules in complex electromagnetic environments is critical for the safety of integrated modular avionics.However,fully testing the module against various Elect... Understanding the electromagnetic compatibility of power modules in complex electromagnetic environments is critical for the safety of integrated modular avionics.However,fully testing the module against various Electro Magnetic Interference(EMI)waveforms is time-consuming and labor-intensive.To address this challenge,we propose a deep-learning-based approach,termed Multi-waveform Transfer Learning(MWTL),building a unified model to predict module responses across multiple interference waveforms.MWTL utilizes a Convolutional Neural Network-Long Short-Term Memory(CNN-LSTM)architecture to effectively extract the temporal features and build the relation between the interference signals and the response signals.In addition,by leveraging shared features across different scenarios,a Transfer Learning(TL)strategy is applied,generalizing the model into unseen interference waveforms,thereby reducing the need for extensive training data in new tasks.The experimental results show that the proposed method delivers excellent predictive performance across various types of interference,maintaining high accuracy even with limited data.In particular,by transferring shared features from multitask learning to new tasks,the approach significantly reduces data requirements for new scenarios while preserving prediction accuracy. 展开更多
关键词 Electromagnetic compatibility Integrated modular avionics Power module Deep learning Transfer learning
暂未订购 下载PDF
Collaboration Better Than Integration:A Novel Time-Frequency-Assisted Deep Feature Enhancement Mechanism for Few-Shot Transfer Learning in Anomaly Detection 认领 引用
11
作者 Wentao Mao Jianing Wu +2 位作者 Shubin Du Ke Feng Zidong Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期366-382,共17页
Deep transfer learning has achieved significant success in anomaly detection over the past decade,but data acquisition challenges in practical engineering hinder high-quality feature representation for few-shot learni... Deep transfer learning has achieved significant success in anomaly detection over the past decade,but data acquisition challenges in practical engineering hinder high-quality feature representation for few-shot learning tasks.To address this issue,a novel time-frequency-assisted deep feature enhancement(TFE)mechanism is proposed.Unlike traditional methods that integrate time-frequency analysis with deep neural networks,TFE employs a wavelet scattering transform to establish a parallel time-frequency feature space,where a dual interaction strategy facilitates collaboration between deep feature and time-frequency spaces through two operations:1)Enhancement,where a frequency-importance-driven contrastive learning(FICL)network transfers physically-aware information from wavelet scattering features to deep features,and 2)Feedback,which uses a detection rule adaptation module to minimize bias in wavelet scattering features based on deep feature performance.TFE is applied to a domain-adversarial anomaly detection framework and,through alternating training,significantly enhances both deep feature discriminative power and few-shot anomaly detection.Theoretical analysis confirms that the proposed dual interaction strategy reduces the upper bound of classification error.Experiments on benchmark datasets and a real-world industrial dataset from a large steel factory demonstrate TFE's superior performance and highlight the importance of frequency saliency in transfer learning.Thus,collaboration is shown to outperform integration for few-shot transfer learning in anomaly detection. 展开更多
关键词 Anomaly detection feature enhancement few-shot learning time frequency analysis transfer learning
暂未订购 下载PDF
Transfer learning-enabled performance prediction of metallic materials:Methods,applications and prospects 认领 引用
12
作者 Yufan Liu Dexin Zhu +7 位作者 Zhihao Tian Jiayi Liu Xing Ran Zhe Wang Chengjiang Tang Lifei Wang Wei Xu Xin Lu 《International Journal of Minerals,Metallurgy and Materials》 SCIE EI CAS CSCD 2026年第3期749-767,共19页
In the era of materials genome engineering,data-driven machine learning has become a powerful tool for accelerating the re-search and development of metallic materials.However,the predictive accuracy and generalizatio... In the era of materials genome engineering,data-driven machine learning has become a powerful tool for accelerating the re-search and development of metallic materials.However,the predictive accuracy and generalization ability of traditional machine learning models are often limited by the scarcity and heterogeneity of available data,especially in small-sample scenarios.To address these chal-lenges,transfer learning has emerged as an effective strategy to leverage knowledge from related domains,thereby enhancing model per-formance with limited target data.This review systematically summarizes the fundamental concepts,methodologies,and representative applications of transfer learning in the prediction of metallic materials'properties.Transfer learning can be categorized into feature-based,instance-based,parameter-based,and knowledge-based methods.This work discusses their respective mechanisms,advantages,and limit-ations.Case studies demonstrate that transfer learning can significantly improve prediction accuracy,data efficiency,and model inter-pretability in tasks such as mechanical property prediction and alloy design.Furthermore,this work highlights emerging trends including hybrid,multi-task,meta,and adaptive transfer learning,which further expand the applicability of these techniques.Finally,this work out-lines future research directions,emphasizing the need for data standardization,algorithmic innovation,multimodal data fusion,and the in-tegration of physical principles to achieve robust,interpretable,and generalizable models.The perspectives presented aim to advance the intelligent design and discovery of metallic materials,promoting efficient knowledge transfer and collaborative innovation in materials science. 展开更多
关键词 small-sample data machine learning transfer learning performance prediction
暂未订购 下载PDF
Transfer learning empowers material Z classification with muon tomography 认领 引用
13
作者 Hao-Chen Wang Zhao Zhang +12 位作者 Pei Yu Yu-Xin Bao Jia-Jia Zhai Yu Xu Li Deng Sa Xiao Xue-Heng Zhang Yu-Hong Yu Wei-Bo He Liang-Wen Chen Yu Zhang Lei Yang Zhi-Yu Sun 《Nuclear Science and Techniques》 SCIE EI CAS CSCD 2026年第5期298-314,共17页
Cosmic-ray muon sources exhibit distinct scattering angle distributions when interacting with materials of different atomic numbers(Z values),facilitating the identification of various Z-class materials,particularly r... Cosmic-ray muon sources exhibit distinct scattering angle distributions when interacting with materials of different atomic numbers(Z values),facilitating the identification of various Z-class materials,particularly radioactive high-Z nuclear elements.Most traditional identification methods are based on complex statistical iterative reconstruction or simple trajectory approximation.Supervised machine learning methods offer some improvement but rely heavily on prior knowledge of the target materials,significantly limiting their practical applicability in detecting concealed materials.To the best of our knowledge,this is the first study to introduce transfer learning into muon tomography.We propose two lightweight neural network models for fine-tuning and adversarial transfer learning,utilizing muon scattering data of bare materials to predict the Z-class of materials coated by typical shieldings(e.g.,aluminum or polyethylene),simulating practical scenarios such as cargo inspection and arms control.By introducing a novel inverse cumulative distribution-based sampling method,more accurate scattering angle distributions could be obtained from the data,leading to an improvement of nearly 4% in prediction accuracy compared with the traditional random sampling-based training.When applied to coated materials with limited labeled or even unlabeled muon tomography data,the proposed method achieved an overall prediction accuracy exceeding 96%,with high-Z materials reaching nearly 99%.The simulation results indicate that transfer learning improves the prediction accuracy by approximately 10% compared to direct prediction without transfer.This study demonstrates the effectiveness of transfer learning in overcoming the physical challenges associated with limited labeled/unlabeled data and highlights the promising potential of transfer learning in the field of muon tomography. 展开更多
关键词 Transfer learning Muon scattering Z-class identification Neural network
暂未订购 下载PDF
Fatigue Detection with Multimodal Physiological Signals via Uncertainty-Aware Deep Transfer Learning 认领 引用
14
作者 Kourosh Kakhi Hamzeh Asgharnezhad +2 位作者 Abbas Khosravi Roohallah Alizadehsani U.Rajendra Acharya 《Journal of Bionic Engineering》 SCIE EI CSCD 2026年第1期472-487,共16页
Accurate detection of driver fatigue is essential for improving road safety.This study investigates the effectiveness of using multimodal physiological signals for fatigue detection while incorporating uncertainty qua... Accurate detection of driver fatigue is essential for improving road safety.This study investigates the effectiveness of using multimodal physiological signals for fatigue detection while incorporating uncertainty quantification to enhance the reliability of predictions.Physiological signals,including Electrocardiogram(ECG),Galvanic Skin Response(GSR),and Electroencephalogram(EEG),were transformed into image representations and analyzed using pretrained deep neu-ral networks.The extracted features were classified through a feedforward neural network,and prediction reliability was assessed using uncertainty quantification techniques such as Monte Carlo Dropout(MCD),model ensembles,and combined approaches.Evaluation metrics included standard measures(sensitivity,specificity,precision,and accuracy)along with uncertainty-aware metrics such as uncertainty sensitivity and uncertainty precision.Across all evaluations,ECG-based models consistently demonstrated strong performance.The findings indicate that combining multimodal physi-ological signals,Transfer Learning(TL),and uncertainty quantification can significantly improve both the accuracy and trustworthiness of fatigue detection systems.This approach supports the development of more reliable driver assistance technologies aimed at preventing fatigue-related accidents. 展开更多
关键词 Fatigue detection Multimodal physiological signals Deep transfer learning Uncertainty-aware learning Driver monitoring
CALoRA:Content-Aware Low-Rank Adaptation for UAV Transfer Learning 认领 引用
15
作者 Kiseok Kim Taehoon Yoo +1 位作者 Sangmin Lee Hwangnam Kim 《Computers, Materials & Continua》 SCIE EI 2026年第6期1580-1595,共16页
Conventional Low-Rank Adaptation(LoRA)constrains weight updates to a static linear low-rank manifold,which is inherently limited when applied to Reinforcement Learning(RL)tasks for Unmanned Aerial Vehicle(UAV)applicat... Conventional Low-Rank Adaptation(LoRA)constrains weight updates to a static linear low-rank manifold,which is inherently limited when applied to Reinforcement Learning(RL)tasks for Unmanned Aerial Vehicle(UAV)applications.UAVs operate in highly dynamic and nonstationary environments where rapid variations in sensing and state transitions lead to complex,nonlinear input-output relationships.Such environmental complexity cannot be adequately modeled by a static Low-rank approximation,making conventional LoRA approaches insufficient for the high-dimensional dynamics required in UAV applications.To overcome these limitations,we propose an attention-enhanced LoRA that constructs an input-dependent and intrinsically nonlinear adaptation manifold.By integrating a nonstandard attention mechanism into the vanilla LoRA,our method enables the model to dynamically reshape its weight subspace in response to changing environmental conditions.This allows the policy and value networks to capture diverse local patterns as well as global contextual structure during adaptation,ultimately improving robustness under domain shift and nonstationary data distributions.We evaluate the proposed method in UAV adaptation scenario based on the AirSim simulator,where a multi-agent training is conducted with internally collected datasets,including multi-sensor observations and UAV physical state information,and policies are transferred from obstacle-free to cluttered environments.Compared to vanilla LoRA,the proposed method reduces initial reward variance by over 70%,leading to earlier adaptation and more stable generalization,and exhibits richer nonlinear expressive power,allowing the model to accommodate the complex,high-dimensional characteristic of UAV tasks. 展开更多
关键词 Low-rank adaptation transfer learning reinforcement learning unmanned aerial vehicle content-aware
暂未订购 下载PDF
Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits 认领 引用
16
作者 Daniel Martín-Pérez Francesc Rodríguez-Díaz +2 位作者 David Gutiérrez-Avilés Alicia Troncoso Francisco Martínez-Álvarez 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期773-802,共30页
Hybrid classical-quantum architectures have emerged as a practical response to the data and compute demands of modern deep learning,since a pretrained classical backbone can carry the feature extraction while a compac... Hybrid classical-quantum architectures have emerged as a practical response to the data and compute demands of modern deep learning,since a pretrained classical backbone can carry the feature extraction while a compact quantum head provides the trainable component.Quantum transfer learning is the most active instance of this idea.However,existing quantum transfer learning pipelines have been evaluated in isolation,typically on a single software framework and without a structured treatment of noise or statistical significance,which makes it difficult to assess how this paradigm contributes over fair classical baselines.A methodological benchmark for quantum transfer learning is proposed in this paper.The benchmark couples a common set of frozen pretrained convolutional backbones to several classical and quantum classification heads,implemented in both PennyLane and Qiskit,so that the contribution of nonlinearity,software framework,and quantum component can be analyzed separately.The benchmark has been applied to heterogeneous image datasets covering medical,biological,industrial,and general-vision domains,and most configurations have been executed in three environments:ideal simulation,noisy emulation calibrated on IBM Heron r2 and real IBM quantum hardware.Complementary analyses isolate the contribution of individual noise channels,examine scalability with qubit count and circuit depth and assess the presence of barren plateaus.Statistical reliability is ensured through multiple random seeds and pairwise Wilcoxon signed-rank tests,providing the first controlled cross-framework assessment of quantum transfer learning under calibrated noise and on real hardware. 展开更多
关键词 Quantum computing transfer learning hybrid neural networks variational circuits
暂未订购 下载PDF
AiCareNeonates:artificial intelligence powered adaptation of transfer learning models to classify neonate’s sleep-wake states for pediatricians in the loop 认领 引用
17
作者 Muhammad Awais Hemant Ghayvat +2 位作者 Rebakah Geddam Lewis Nkenyereye Kapal Dev 《Digital Communications and Networks》 SCIE EI CSCD 2026年第5期755-764,共10页
This study monitors neonatal sleep patterns using artificial intelligence through an innovative transfer learning approach integrating video and Electroencephalogram(EEG)data.Leveraging non-intrusive,camera-based tech... This study monitors neonatal sleep patterns using artificial intelligence through an innovative transfer learning approach integrating video and Electroencephalogram(EEG)data.Leveraging non-intrusive,camera-based technology,this method offers healthcare professionals an effective tool to evaluate and understand sleep quality in newborns.Such monitoring is essential for pediatricians,providing critical insights into the health and development of infants.Automated sleep/wake staging tools aid healthcare professionals in analyzing infant sleep patterns.Among these methods,camera-based approaches have gained prominence due to their non-intrusive and user-friendly characteristics,making them applicable for home monitoring.This study introduces a novel transfer learning technique for classifying neonatal sleep/wake stages.Our approach utilizes multiple color palettes,such as thermal,amber,grayscale,high contrast,hot metal,and red-blue,captured through a Fluke®(TiX 580)camera system.Continuous monitoring of neonatal sleep is essential for pediatricians to assess neonatal sleep quality comprehensively.Automated sleep/wake staging tools assist healthcare professionals in evaluating infant sleep patterns.Camera-based approaches have garnered significant attention among the various methods due to their non-intrusive and user-friendly nature,making them suitable for home use.In this paper,we propose a novel transfer learning approach for classifying neonatal sleep/wake staging using a combination of multiple color palettes,including thermal,amber,grayscale,high contrast,hot metal,and red-blue,recorded through a Fluke®(TiX 580)camera.The proposed method leverages the retraining of the last fully connected layer of well-established deep neural networks such as Visual Geometry Group 16 and 19,AlexNet,Inception-V3,ResNet-18,ResNet-50,and GoogLeNet to perform accurate sleep and wake stage classification.To enhance the precision of our approach,we integrate EEG data with video data obtained from neonatal subjects.The performance of transfer learning networks is validated using a leave-one-subject-out cross-validation strategy,ensuring robustness in classifying wake and sleep stages.In particular,the Inception-V3 model,when applied to the red-blue color palette video frames,demonstrates an impressive classification accuracy rate of 85.9%.Furthermore,we assessed the impact of including EEG data alongside video data,and even in this context,our approach maintains the same high accuracy of 85.9%.These findings underscore the robustness and effectiveness of our proposed method for neonatal sleep/wake staging classification,which is suitable for home-based monitoring and enhances its practicality and accessibility for pediatricians and caregivers. 展开更多
关键词 Deep convolutional neural network Neonatal sleep classification Transfer learning Neonatal Red-Green-Blue(RGB)face database Quadrupole exciton Polariton
暂未订购 下载PDF
Deep transfer learning for three-dimensional aerodynamic pressure prediction under data scarcity 认领 引用 被引量：3
18
作者 Hao Zhang Yang Shen +2 位作者 Wei Huang Zan Xie Yao-Bin Niu 《Theoretical & Applied Mechanics Letters》 EI CAS CSCD 2025年第2期131-140,共10页
Aerodynamic evaluation under multi-condition is indispensable for the design of aircraft,and the requirement for mass data still means a high cost.To address this problem,we propose a novel point-cloud multi-condition... Aerodynamic evaluation under multi-condition is indispensable for the design of aircraft,and the requirement for mass data still means a high cost.To address this problem,we propose a novel point-cloud multi-condition aerodynamics transfer learning(PCMCA-TL)framework that enables aerodynamic prediction in data-scarce sce-narios by transferring knowledge from well-learned scenarios.We modified the PointNeXt segmentation archi-tecture to a PointNeXtReg+regression model,including a working condition input module.The model is first pre-trained on a public dataset with 2000 shapes but only one working condition and then fine-tuned on a multi-condition small-scale spaceplane dataset.The effectiveness of the PCMCA-TL framework is verified by comparing the pressure coefficients predicted by direct training,pre-training,and TL models.Furthermore,by comparing the aerodynamic force coefficients calculated by predicted pressure coefficients in seconds with the correspond-ing CFD results obtained in hours,the accuracy highlights the development potential of deep transfer learning in aerodynamic evaluation. 展开更多
关键词 Aerodynamic prediction Deep transfer learning Point cloud Multi-condition scenarios Small-scale dataset
暂未订购 下载PDF
A deep transfer learning model for the deformation of braced excavations with limited monitoring data 认领 引用 被引量：3
19
作者 Yuanqin Tao Shaoxiang Zeng +3 位作者 Tiantian Ying Honglei Sun Sunjuexu Pan Yuanqiang Cai 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2025年第3期1555-1568,共14页
The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To addres... The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(S2SCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded.In the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism.To illustrate the proposed methodology,an excavation project in Hangzhou,China is adopted.The proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning model.Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations.The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project. 展开更多
关键词 Braced excavation Wall deflections Transfer learning Deep learning Finite element simulation
暂未订购 下载PDF
Microseismic Event Recognition and Transfer Learning Based on Convolutional Neural Network and Attention Mechanisms 认领 引用 被引量：2
20
作者 Jin Shu Zhang Shichao +2 位作者 Gao Ya Yu Benli Zhen Shenglai 《Applied Geophysics》 SCIE CSCD 2025年第4期1220-1232,1497,共13页
Microseismic monitoring technology is widely used in tunnel and coal mine safety production.For signals generated by ultra-weak microseismic events,traditional sensors encounter limitations in terms of detection sensi... Microseismic monitoring technology is widely used in tunnel and coal mine safety production.For signals generated by ultra-weak microseismic events,traditional sensors encounter limitations in terms of detection sensitivity.Given the complex engineering environment,automatic multi-classification of microseismic data is highly required.In this study,we use acceleration sensors to collect signals and combine the improved Visual Geometry Group with a convolutional block attention module to obtain a new network structure,termed CNN_BAM,for automatic classification and identification of microseismic events.We use the dataset collected from the Hanjiang-to-Weihe River Diversion Project to train and validate the network model.Results show that the CNN_BAM model exhibits good feature extraction ability,achieving a recognition accuracy of 99.29%,surpassing all its counterparts.The stability and accuracy of the classification algorithm improve remarkably.In addition,through fine-tuning and migration to the Pan Ⅱ Mine Project,the network demonstrates reliable generalization performance.This outcome reflects its adaptability across different projects and promising application prospects. 展开更多
关键词 Microseismic Convolutional Neural Networks Multi-classification Attentional mechanism Transfer learning
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 30 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈