An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyram...An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.展开更多
The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image segmentation.However,their ability to learn local,contextual relationships ...The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image segmentation.However,their ability to learn local,contextual relationships between pixels requires further improvement.Previous methods face challenges in efficiently managing multi-scale fea-tures of different granularities from the encoder backbone,leaving room for improvement in their global representation and feature extraction capabilities.To address these challenges,we propose a novel Decoder with Multi-Head Feature Receptors(DMHFR),which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities:coarse,fine-grained,and full set.These groups are subsequently processed by Multi-Head Feature Receptors(MHFRs)after feature capture and modeling operations.MHFRs include two Three-Head Feature Receptors(THFRs)and one Four-Head Feature Receptor(FHFR).Each group of features is passed through these MHFRs and then fed into axial transformers,which help the model capture long-range dependencies within the features.The three MHFRs produce three distinct feature outputs.The output from the FHFR serves as auxiliary auxiliary features in the prediction head,and the prediction output and their losses will eventually be aggregated.Experimental results show that the Transformer using DMHFR outperforms 15 state of the arts(SOTA)methods on five public datasets.Specifically,it achieved significant improvements in mean DICE scores over the classic Parallel Reverse Attention Network(PraNet)method,with gains of 4.1%,2.2%,1.4%,8.9%,and 16.3%on the CVC-ClinicDB,Kvasir-SEG,CVC-T,CVC-ColonDB,and ETIS-LaribPolypDB datasets,respectively.展开更多
Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure p...Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective treatment.Deep learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and treatment.However,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic level.On the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological features.To address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual representation.Specifically,our model incorporates global features for extracting high-level contextual information from retinal images.Concurrently,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR diagnosis.These global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR classification.Our model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.展开更多
Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely us...Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.展开更多
Anomaly Detection (AD) has been extensively adopted in industrial settings to facilitate quality control of products. It is critical to industrial production, especially to areas such as aircraft manufacturing, which ...Anomaly Detection (AD) has been extensively adopted in industrial settings to facilitate quality control of products. It is critical to industrial production, especially to areas such as aircraft manufacturing, which require strict part qualification rates. Although being more efficient and practical, few-shot AD has not been well explored. The existing AD methods only extract features in a single frequency while defects exist in multiple frequency domains. Moreover, current methods have not fully leveraged the few-shot support samples to extract input-related normal patterns. To address these issues, we propose an industrial few-shot AD method, Feature Extender for Anomaly Detection (FEAD), which extracts normal patterns in multiple frequency domains from few-shot samples under the guidance of the input sample. Firstly, to achieve better coverage of normal patterns in the input sample, we introduce a Sample-Conditioned Transformation Module (SCTM), which transforms support features under the guidance of the input sample to obtain extra normal patterns. Secondly, to effectively distinguish and localize anomaly patterns in multiple frequency domains, we devise an Adaptive Descriptor Construction Module (ADCM) to build and select pattern descriptors in a series of frequencies adaptively. Finally, an auxiliary task for SCTM is designed to ensure the diversity of transformations and include more normal patterns into support features. Extensive experiments on two widely used industrial AD datasets (MVTec-AD and VisA) demonstrate the effectiveness of the proposed FEAD.展开更多
In order to address the challenges encountered in visual navigation for asteroid landing using traditional point features,such as significant recognition and extraction errors,low computational efficiency,and limited ...In order to address the challenges encountered in visual navigation for asteroid landing using traditional point features,such as significant recognition and extraction errors,low computational efficiency,and limited navigation accuracy,a novel approach for multi-type fusion visual navigation is proposed.This method aims to overcome the limitations of single-type features and enhance navigation accuracy.Analytical criteria for selecting multi-type features are introduced,which simultaneously improve computational efficiency and system navigation accuracy.Concerning pose estimation,both absolute and relative pose estimation methods based on multi-type feature fusion are proposed,and multi-type feature normalization is established,which significantly improves system navigation accuracy and lays the groundwork for flexible application of joint absolute-relative estimation.The feasibility and effectiveness of the proposed method are validated through simulation experiments through 4769 Castalia.展开更多
Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework...Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is proposed.In the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and MobileNetV2.Both models are selected based on the top-5 accuracy and less number of parameters.Later,both models are trained through deep transfer learning and extracted deep features fused using a voting scheme.In the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best features.The selected features are classified using several supervised learning methods.The CASIA-B publicly available dataset has been employed for the experimental process.On this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.展开更多
Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certai...Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certain models,they do not invariably guarantee the extraction of the most critical or impactful features.Prior literature underscores the significance of equitable FS practices and has proposed diverse methodologies for the identification of appropriate features.However,the challenge of discerning the most relevant and influential features persists,particularly in the context of the exponential growth and heterogeneity of big data—a challenge that is increasingly salient in modern artificial intelligence(AI)applications.In response,this study introduces an innovative,automated statistical method termed Farea Similarity for Feature Selection(FSFS).The FSFS approach computes a similarity metric for each feature by benchmarking it against the record-wise mean,thereby finding feature dependencies and mitigating the influence of outliers that could potentially distort evaluation outcomes.Features are subsequently ranked according to their similarity scores,with the threshold established at the average similarity score.Notably,lower FSFS values indicate higher similarity and stronger data correlations,whereas higher values suggest lower similarity.The FSFS method is designed not only to yield reliable evaluation metrics but also to reduce data complexity without compromising model performance.Comparative analyses were performed against several established techniques,including Chi-squared(CS),Correlation Coefficient(CC),Genetic Algorithm(GA),Exhaustive Approach,Greedy Stepwise Approach,Gain Ratio,and Filtered Subset Eval,using a variety of datasets such as the Experimental Dataset,Breast Cancer Wisconsin(Original),KDD CUP 1999,NSL-KDD,UNSW-NB15,and Edge-IIoT.In the absence of the FSFS method,the highest classifier accuracies observed were 60.00%,95.13%,97.02%,98.17%,95.86%,and 94.62%for the respective datasets.When the FSFS technique was integrated with data normalization,encoding,balancing,and feature importance selection processes,accuracies improved to 100.00%,97.81%,98.63%,98.94%,94.27%,and 98.46%,respectively.The FSFS method,with a computational complexity of O(fn log n),demonstrates robust scalability and is well-suited for datasets of large size,ensuring efficient processing even when the number of features is substantial.By automatically eliminating outliers and redundant data,FSFS reduces computational overhead,resulting in faster training and improved model performance.Overall,the FSFS framework not only optimizes performance but also enhances the interpretability and explainability of data-driven models,thereby facilitating more trustworthy decision-making in AI applications.展开更多
The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor env...The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.展开更多
Shield attitudes,essentially governed by intricate mechanisms,impact the segment assembly quality and tunnel axis deviation.In data-driven prediction,however,existing methods using the original driving parameters fail...Shield attitudes,essentially governed by intricate mechanisms,impact the segment assembly quality and tunnel axis deviation.In data-driven prediction,however,existing methods using the original driving parameters fail to present convincing performance due to insufficient consideration of complicated interactions among the parameters.Therefore,a multi-dimensional feature synthesizing and screening method is proposed to explore the optimal features that can better reflect the physical mechanism in predicting shield tunneling attitudes.Features embedded with physical knowledge were synthesized from seven dimensions,which were validated by the clustering quality of Shapley Additive Explanations(SHAP)values.Subsequently,a novel index,Expected Impact Index(EII),has been proposed for screening the optimal features reliably.Finally,a Bayesian-optimized deep learning model was established to validate the proposed method in a case study.Results show that the proposed method effectively identifies the optimal parameters for shield attitude prediction,with an average Mean Squared Error(MSE)deduction of 27.3%.The proposed method realized effective assimilation of shield driving data with physical mechanism,providing a valuable reference for shield deviation control.展开更多
Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world appli...Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.展开更多
Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vi...Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.展开更多
Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attack...Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attacks on smart contracts often cause huge economic losses.Since it is difficult to repair and update smart contracts,it is necessary to find the vulnerabilities before they are deployed.However,code analysis,which requires traversal paths,and learning methods,which require many features to be trained,are too time-consuming to detect large-scale on-chain contracts.Learning-based methods will obtain detection models from a feature space compared to code analysis methods such as symbol execution.But the existing features lack the interpretability of the detection results and training model,even worse,the large-scale feature space also affects the efficiency of detection.This paper focuses on improving the detection efficiency by reducing the dimension of the features,combined with expert knowledge.In this paper,a feature extraction model Block-gram is proposed to form low-dimensional knowledge-based features from bytecode.First,the metadata is separated and the runtime code is converted into a sequence of opcodes,which are divided into segments based on some instructions(jumps,etc.).Then,scalable Block-gram features,including 4-dimensional block features and 8-dimensional attribute features,are mined for the learning-based model training.Finally,feature contributions are calculated from SHAP values to measure the relationship between our features and the results of the detection model.In addition,six types of vulnerability labels are made on a dataset containing 33,885 contracts,and these knowledge-based features are evaluated using seven state-of-the-art learning algorithms,which show that the average detection latency speeds up 25×to 650×,compared with the features extracted by N-gram,and also can enhance the interpretability of the detection model.展开更多
Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the ...Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the challenges of image noise,anatomical complexity,and the stringent real-time requirements.The BLFM-Net enhances bronchoscopic image processing by integrating several functional modules.The FFA-Net preprocessing module mitigates image fogging and improves visual clarity for subsequent processing.The feature extraction module derives multi-dimensional features,such as centroids,area,and shape descriptors,from dehazed images.The Faster RCNN Object detection module detects bronchial regions of interest and generates bounding boxes to localize key areas.The feature matching module accelerates the process by combining detection boxes,extracted features,and a KD-Tree(K-Dimensional Tree)-based algorithm,ensuring efficient and accurate regional feature associations.The BLFM-Net was evaluated on 5212 bronchoscopic images,demonstrating superior performance compared to traditional and other deep learning-based image matching methods.It achieved real-time matching with an average frame time of 6 ms,with a matching accuracy of over 96%.The method remained robust under challenging conditions including frame dropping(0,5,10,20),shadowed regions,and variable lighting,maintaining accuracy of above 94%even with the frame dropping of 20.This study presents BLFM-Net,a deep learning-based matching network designed to enhance and match bronchial features in bronchoscopic images.The BLFM-Net shows improved accuracy,real-time performance,and reliability,making a valuable tool for bronchoscopic surgeries.展开更多
Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,ther...Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.展开更多
The success of robot-assisted pelvic fracture reduction surgery heavily relies on the accuracy of 3D/3D feature-based registration.This process involves extracting anatomical feature points from pre-operative 3D image...The success of robot-assisted pelvic fracture reduction surgery heavily relies on the accuracy of 3D/3D feature-based registration.This process involves extracting anatomical feature points from pre-operative 3D images which can be challenging because of the complex and variable structure of the pelvis.PointMLP_RegNet,a modified PointMLP,was introduced to address this issue.It retains the feature extraction module of PointMLP but replaces the classification layer with a regression layer to predict the coordinates of feature points instead of conducting regular classification.A flowchart for an automatic feature points extraction method was presented,and a series of experiments was conducted on a clinical pelvic dataset to confirm the accuracy and effectiveness of the method.PointMLP_RegNet extracted feature points more accurately,with 8 out of 10 points showing less than 4 mm errors and the remaining two less than 5 mm.Compared to PointNettt and PointNet,it exhibited higher accuracy,robustness and space efficiency.The proposed method will improve the accuracy of anatomical feature points extraction,enhance intra-operative registration precision and facilitate the widespread clinical application of robot-assisted pelvic fracture reduction.展开更多
Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis...Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis of this malignancy;however,manual observation of the blood smear is very time-consuming and requires labor and expertise.Transfer learning in deep neural networks is of growing importance to intricate medical tasks such as medical imaging.Our work proposes an application of a novel ensemble architecture that puts together Vision Transformer and EfficientNetV2.This approach fuses deep and spatial features to optimize discriminative power by selecting features accurately,reducing redundancy,and promoting sparsity.Besides the architecture of the ensemble,the advanced feature selection is performed by the Frog-Snake Prey-Predation Relationship Optimization(FSRO)algorithm.FSRO prioritizes the most relevant features while dynamically reducing redundant and noisy data,hence improving the efficiency and accuracy of the classification model.We have compared our method for feature selection against state-of-the-art techniques and recorded an accuracy of 94.88%,a recall of 94.38%,a precision of 96.18%,and an F1-score of 95.63%.These figures are therefore better than the classical methods for deep learning.Though our dataset,collected from four different hospitals,is non-standard and heterogeneous,making the analysis more challenging,although computationally expensive,our approach proves diagnostically superior in cancer detection.Source codes and datasets are available on GitHub.展开更多
Lunar Laser Ranging has extremely high requirements for the pointing accuracy of the telescopes used.To improve its pointing accuracy and solve the problem of insufficiently accurate telescope pointing correction achi...Lunar Laser Ranging has extremely high requirements for the pointing accuracy of the telescopes used.To improve its pointing accuracy and solve the problem of insufficiently accurate telescope pointing correction achieved by tracking stars in the all-sky region,we propose a processing scheme to select larger-sized lunar craters near the Lunar Corner Cube Retroreflector as reference features for telescope pointing bias computation.Accurately determining the position of the craters in the images is crucial for calculating the pointing bias;therefore,we propose a method for accurately calculating the crater position based on lunar surface feature matching.This method uses matched feature points obtained from image feature matching,using a deep learning method to solve the image transformation matrix.The known position of a crater in a reference image is mapped using this matrix to calculate the crater position in the target image.We validate this method using craters near the Lunar Corner Cube Retroreflectors of Apollo 15 and Luna 17 and find that the calculated position of a crater on the target image falls on the center of the crater,even for image features with large distortion near the lunar limb.The maximum image matching error is approximately 1″,and the minimum is only 0.47″,which meets the pointing requirements of Lunar Laser Ranging.This method provides a new technical means for the high-precision pointing bias calculation of the Lunar Laser Ranging system.展开更多
Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,...Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,and interference from contamination.To address these challenges,this paper proposes the Real-time Cable Defect Detection Network(RC2DNet),which achieves an optimal balance between detection accuracy and computational efficiency.Unlike conventional approaches,RC2DNet introduces a small object feature extraction module that enhances the semantic representation of small targets through feature pyramids,multi-level feature fusion,and an adaptive weighting mechanism.Additionally,a boundary feature enhancement module is designed,incorporating boundary-aware convolution,a novel boundary attention mechanism,and an improved loss function to significantly enhance boundary localization accuracy.Experimental results demonstrate that RC2DNet outperforms state-of-the-art methods in precision,recall,F1-score,mean Intersection over Union(mIoU),and frame rate,enabling real-time and highly accurate cable defect detection in complex backgrounds.展开更多
Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learni...Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.展开更多
基金supported by the National Natural Science Foundation of China(No.62241109)the Tianjin Science and Technology Commissioner Project(No.20YDTPJC01110)。
文摘An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.
基金supported by Xiamen Medical and Health Guidance Project in 2021(No.3502Z20214ZD1070)supported by a grant from Guangxi Key Laboratory of Machine Vision and Intelligent Control,China(No.2023B02).
文摘The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image segmentation.However,their ability to learn local,contextual relationships between pixels requires further improvement.Previous methods face challenges in efficiently managing multi-scale fea-tures of different granularities from the encoder backbone,leaving room for improvement in their global representation and feature extraction capabilities.To address these challenges,we propose a novel Decoder with Multi-Head Feature Receptors(DMHFR),which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities:coarse,fine-grained,and full set.These groups are subsequently processed by Multi-Head Feature Receptors(MHFRs)after feature capture and modeling operations.MHFRs include two Three-Head Feature Receptors(THFRs)and one Four-Head Feature Receptor(FHFR).Each group of features is passed through these MHFRs and then fed into axial transformers,which help the model capture long-range dependencies within the features.The three MHFRs produce three distinct feature outputs.The output from the FHFR serves as auxiliary auxiliary features in the prediction head,and the prediction output and their losses will eventually be aggregated.Experimental results show that the Transformer using DMHFR outperforms 15 state of the arts(SOTA)methods on five public datasets.Specifically,it achieved significant improvements in mean DICE scores over the classic Parallel Reverse Attention Network(PraNet)method,with gains of 4.1%,2.2%,1.4%,8.9%,and 16.3%on the CVC-ClinicDB,Kvasir-SEG,CVC-T,CVC-ColonDB,and ETIS-LaribPolypDB datasets,respectively.
基金supported by the National Natural Science Foundation of China(No.62376287)the International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province(2021CB1013)the Natural Science Foundation of Hunan Province(Nos.2022JJ30762,2023JJ70016).
文摘Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective treatment.Deep learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and treatment.However,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic level.On the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological features.To address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual representation.Specifically,our model incorporates global features for extracting high-level contextual information from retinal images.Concurrently,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR diagnosis.These global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR classification.Our model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(62276092,62303167)the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation(GZC20230707)+3 种基金the Key Science and Technology Program of Henan Province,China(242102211051,242102211042,212102310084)Key Scientiffc Research Projects of Colleges and Universities in Henan Province,China(25A520009)the China Postdoctoral Science Foundation(2024M760808)the Henan Province medical science and technology research plan joint construction project(LHGJ2024069).
文摘Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.
基金supported by the National Natural Science Foundation of China(No.52188102).
文摘Anomaly Detection (AD) has been extensively adopted in industrial settings to facilitate quality control of products. It is critical to industrial production, especially to areas such as aircraft manufacturing, which require strict part qualification rates. Although being more efficient and practical, few-shot AD has not been well explored. The existing AD methods only extract features in a single frequency while defects exist in multiple frequency domains. Moreover, current methods have not fully leveraged the few-shot support samples to extract input-related normal patterns. To address these issues, we propose an industrial few-shot AD method, Feature Extender for Anomaly Detection (FEAD), which extracts normal patterns in multiple frequency domains from few-shot samples under the guidance of the input sample. Firstly, to achieve better coverage of normal patterns in the input sample, we introduce a Sample-Conditioned Transformation Module (SCTM), which transforms support features under the guidance of the input sample to obtain extra normal patterns. Secondly, to effectively distinguish and localize anomaly patterns in multiple frequency domains, we devise an Adaptive Descriptor Construction Module (ADCM) to build and select pattern descriptors in a series of frequencies adaptively. Finally, an auxiliary task for SCTM is designed to ensure the diversity of transformations and include more normal patterns into support features. Extensive experiments on two widely used industrial AD datasets (MVTec-AD and VisA) demonstrate the effectiveness of the proposed FEAD.
基金supported by the National Natural Science Foundation of China(No.U2037602)。
文摘In order to address the challenges encountered in visual navigation for asteroid landing using traditional point features,such as significant recognition and extraction errors,low computational efficiency,and limited navigation accuracy,a novel approach for multi-type fusion visual navigation is proposed.This method aims to overcome the limitations of single-type features and enhance navigation accuracy.Analytical criteria for selecting multi-type features are introduced,which simultaneously improve computational efficiency and system navigation accuracy.Concerning pose estimation,both absolute and relative pose estimation methods based on multi-type feature fusion are proposed,and multi-type feature normalization is established,which significantly improves system navigation accuracy and lays the groundwork for flexible application of joint absolute-relative estimation.The feasibility and effectiveness of the proposed method are validated through simulation experiments through 4769 Castalia.
基金King Saud University,Grant/Award Number:RSP2024R157。
文摘Biometric characteristics are playing a vital role in security for the last few years.Human gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is proposed.In the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and MobileNetV2.Both models are selected based on the top-5 accuracy and less number of parameters.Later,both models are trained through deep transfer learning and extracted deep features fused using a voting scheme.In the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best features.The selected features are classified using several supervised learning methods.The CASIA-B publicly available dataset has been employed for the experimental process.On this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.
文摘Feature selection(FS)is a pivotal pre-processing step in developing data-driven models,influencing reliability,performance and optimization.Although existing FS techniques can yield high-performance metrics for certain models,they do not invariably guarantee the extraction of the most critical or impactful features.Prior literature underscores the significance of equitable FS practices and has proposed diverse methodologies for the identification of appropriate features.However,the challenge of discerning the most relevant and influential features persists,particularly in the context of the exponential growth and heterogeneity of big data—a challenge that is increasingly salient in modern artificial intelligence(AI)applications.In response,this study introduces an innovative,automated statistical method termed Farea Similarity for Feature Selection(FSFS).The FSFS approach computes a similarity metric for each feature by benchmarking it against the record-wise mean,thereby finding feature dependencies and mitigating the influence of outliers that could potentially distort evaluation outcomes.Features are subsequently ranked according to their similarity scores,with the threshold established at the average similarity score.Notably,lower FSFS values indicate higher similarity and stronger data correlations,whereas higher values suggest lower similarity.The FSFS method is designed not only to yield reliable evaluation metrics but also to reduce data complexity without compromising model performance.Comparative analyses were performed against several established techniques,including Chi-squared(CS),Correlation Coefficient(CC),Genetic Algorithm(GA),Exhaustive Approach,Greedy Stepwise Approach,Gain Ratio,and Filtered Subset Eval,using a variety of datasets such as the Experimental Dataset,Breast Cancer Wisconsin(Original),KDD CUP 1999,NSL-KDD,UNSW-NB15,and Edge-IIoT.In the absence of the FSFS method,the highest classifier accuracies observed were 60.00%,95.13%,97.02%,98.17%,95.86%,and 94.62%for the respective datasets.When the FSFS technique was integrated with data normalization,encoding,balancing,and feature importance selection processes,accuracies improved to 100.00%,97.81%,98.63%,98.94%,94.27%,and 98.46%,respectively.The FSFS method,with a computational complexity of O(fn log n),demonstrates robust scalability and is well-suited for datasets of large size,ensuring efficient processing even when the number of features is substantial.By automatically eliminating outliers and redundant data,FSFS reduces computational overhead,resulting in faster training and improved model performance.Overall,the FSFS framework not only optimizes performance but also enhances the interpretability and explainability of data-driven models,thereby facilitating more trustworthy decision-making in AI applications.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+1 种基金the Open Research Fund of National Mobile Communications Research Laboratory in Southeast University(No.2023D07)the Fundamental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.
文摘Shield attitudes,essentially governed by intricate mechanisms,impact the segment assembly quality and tunnel axis deviation.In data-driven prediction,however,existing methods using the original driving parameters fail to present convincing performance due to insufficient consideration of complicated interactions among the parameters.Therefore,a multi-dimensional feature synthesizing and screening method is proposed to explore the optimal features that can better reflect the physical mechanism in predicting shield tunneling attitudes.Features embedded with physical knowledge were synthesized from seven dimensions,which were validated by the clustering quality of Shapley Additive Explanations(SHAP)values.Subsequently,a novel index,Expected Impact Index(EII),has been proposed for screening the optimal features reliably.Finally,a Bayesian-optimized deep learning model was established to validate the proposed method in a case study.Results show that the proposed method effectively identifies the optimal parameters for shield attitude prediction,with an average Mean Squared Error(MSE)deduction of 27.3%.The proposed method realized effective assimilation of shield driving data with physical mechanism,providing a valuable reference for shield deviation control.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers CSTB2024TIAD-CYKJCXX0009,CSTB2024NSCQ-LZX0043,CSTB2022NSCQ-MSX0288Chongqing Municipal Commission of Housing and Urban-Rural Development,grant number CKZ2024-87+3 种基金the Chongqing University of Technology Graduate Education High-Quality Development Project,grant number gzlsz202401the Chongqing University of Technology—Chongqing LINGLUE Technology Co.,Ltd.Electronic Information(Artificial Intelligence)Graduate Joint Training Basethe Postgraduate Education and Teaching Reform Research Project in Chongqing,grant number yjg213116the Chongqing University of Technology-CISDI Chongqing Information Technology Co.,Ltd.Computer Technology Graduate Joint Training Base.
文摘Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.
基金supported by the Fundamental Research Funds for the Provincial Universities of Zhejiang (No.GK249909299001-036)National Key Research and Development Program of China (No. 2023YFB4502803)Zhejiang Provincial Natural Science Foundation of China (No.LDT23F01014F01)。
文摘Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.
基金partially supported by the National Natural Science Foundation (62272248)the Open Project Fund of State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences (CARCHA202108,CARCH201905)+1 种基金the Natural Science Foundation of Tianjin (20JCZDJC00610)Sponsored by Zhejiang Lab (2021KF0AB04)。
文摘Smart contracts are widely used on the blockchain to implement complex transactions,such as decentralized applications on Ethereum.Effective vulnerability detection of large-scale smart contracts is critical,as attacks on smart contracts often cause huge economic losses.Since it is difficult to repair and update smart contracts,it is necessary to find the vulnerabilities before they are deployed.However,code analysis,which requires traversal paths,and learning methods,which require many features to be trained,are too time-consuming to detect large-scale on-chain contracts.Learning-based methods will obtain detection models from a feature space compared to code analysis methods such as symbol execution.But the existing features lack the interpretability of the detection results and training model,even worse,the large-scale feature space also affects the efficiency of detection.This paper focuses on improving the detection efficiency by reducing the dimension of the features,combined with expert knowledge.In this paper,a feature extraction model Block-gram is proposed to form low-dimensional knowledge-based features from bytecode.First,the metadata is separated and the runtime code is converted into a sequence of opcodes,which are divided into segments based on some instructions(jumps,etc.).Then,scalable Block-gram features,including 4-dimensional block features and 8-dimensional attribute features,are mined for the learning-based model training.Finally,feature contributions are calculated from SHAP values to measure the relationship between our features and the results of the detection model.In addition,six types of vulnerability labels are made on a dataset containing 33,885 contracts,and these knowledge-based features are evaluated using seven state-of-the-art learning algorithms,which show that the average detection latency speeds up 25×to 650×,compared with the features extracted by N-gram,and also can enhance the interpretability of the detection model.
基金funded by the National Natural Science Foundation of China(Grant No.52175028).
文摘Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries.This study purposes a bronchoscopic lumen feature matching network(BLFM-Net)based on deep learning to address the challenges of image noise,anatomical complexity,and the stringent real-time requirements.The BLFM-Net enhances bronchoscopic image processing by integrating several functional modules.The FFA-Net preprocessing module mitigates image fogging and improves visual clarity for subsequent processing.The feature extraction module derives multi-dimensional features,such as centroids,area,and shape descriptors,from dehazed images.The Faster RCNN Object detection module detects bronchial regions of interest and generates bounding boxes to localize key areas.The feature matching module accelerates the process by combining detection boxes,extracted features,and a KD-Tree(K-Dimensional Tree)-based algorithm,ensuring efficient and accurate regional feature associations.The BLFM-Net was evaluated on 5212 bronchoscopic images,demonstrating superior performance compared to traditional and other deep learning-based image matching methods.It achieved real-time matching with an average frame time of 6 ms,with a matching accuracy of over 96%.The method remained robust under challenging conditions including frame dropping(0,5,10,20),shadowed regions,and variable lighting,maintaining accuracy of above 94%even with the frame dropping of 20.This study presents BLFM-Net,a deep learning-based matching network designed to enhance and match bronchial features in bronchoscopic images.The BLFM-Net shows improved accuracy,real-time performance,and reliability,making a valuable tool for bronchoscopic surgeries.
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd.(Grant No.H20230317).
文摘Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.
基金supported by the National Key Research and Development Program of China(Grant No.2020YFB1313800)the National Science Foundation of China(Grant No.NSFC62373259)+1 种基金the Natural Science Foundation of Top Talent of SZTU(Grant No.GDRC202303)the Education Promotion Foundation of Guangdong Province(Grant No.2022ZDJS115).
文摘The success of robot-assisted pelvic fracture reduction surgery heavily relies on the accuracy of 3D/3D feature-based registration.This process involves extracting anatomical feature points from pre-operative 3D images which can be challenging because of the complex and variable structure of the pelvis.PointMLP_RegNet,a modified PointMLP,was introduced to address this issue.It retains the feature extraction module of PointMLP but replaces the classification layer with a regression layer to predict the coordinates of feature points instead of conducting regular classification.A flowchart for an automatic feature points extraction method was presented,and a series of experiments was conducted on a clinical pelvic dataset to confirm the accuracy and effectiveness of the method.PointMLP_RegNet extracted feature points more accurately,with 8 out of 10 points showing less than 4 mm errors and the remaining two less than 5 mm.Compared to PointNettt and PointNet,it exhibited higher accuracy,robustness and space efficiency.The proposed method will improve the accuracy of anatomical feature points extraction,enhance intra-operative registration precision and facilitate the widespread clinical application of robot-assisted pelvic fracture reduction.
文摘Acute lymphoblastic leukemia(ALL)is characterized by overgrowth of immature lymphoid cells in the bone marrow at the expense of normal hematopoiesis.One of the most prioritized tasks is the early and correct diagnosis of this malignancy;however,manual observation of the blood smear is very time-consuming and requires labor and expertise.Transfer learning in deep neural networks is of growing importance to intricate medical tasks such as medical imaging.Our work proposes an application of a novel ensemble architecture that puts together Vision Transformer and EfficientNetV2.This approach fuses deep and spatial features to optimize discriminative power by selecting features accurately,reducing redundancy,and promoting sparsity.Besides the architecture of the ensemble,the advanced feature selection is performed by the Frog-Snake Prey-Predation Relationship Optimization(FSRO)algorithm.FSRO prioritizes the most relevant features while dynamically reducing redundant and noisy data,hence improving the efficiency and accuracy of the classification model.We have compared our method for feature selection against state-of-the-art techniques and recorded an accuracy of 94.88%,a recall of 94.38%,a precision of 96.18%,and an F1-score of 95.63%.These figures are therefore better than the classical methods for deep learning.Though our dataset,collected from four different hospitals,is non-standard and heterogeneous,making the analysis more challenging,although computationally expensive,our approach proves diagnostically superior in cancer detection.Source codes and datasets are available on GitHub.
基金funded by Natural Science Foundation of Jilin Province(20220101125JC)the National Natural Science Foundation of China(12273079).
文摘Lunar Laser Ranging has extremely high requirements for the pointing accuracy of the telescopes used.To improve its pointing accuracy and solve the problem of insufficiently accurate telescope pointing correction achieved by tracking stars in the all-sky region,we propose a processing scheme to select larger-sized lunar craters near the Lunar Corner Cube Retroreflector as reference features for telescope pointing bias computation.Accurately determining the position of the craters in the images is crucial for calculating the pointing bias;therefore,we propose a method for accurately calculating the crater position based on lunar surface feature matching.This method uses matched feature points obtained from image feature matching,using a deep learning method to solve the image transformation matrix.The known position of a crater in a reference image is mapped using this matrix to calculate the crater position in the target image.We validate this method using craters near the Lunar Corner Cube Retroreflectors of Apollo 15 and Luna 17 and find that the calculated position of a crater on the target image falls on the center of the crater,even for image features with large distortion near the lunar limb.The maximum image matching error is approximately 1″,and the minimum is only 0.47″,which meets the pointing requirements of Lunar Laser Ranging.This method provides a new technical means for the high-precision pointing bias calculation of the Lunar Laser Ranging system.
基金supported by the National Natural Science Foundation of China under Grant 62306128the Basic Science Research Project of Jiangsu Provincial Department of Education under Grant 23KJD520003the Leading Innovation Project of Changzhou Science and Technology Bureau under Grant CQ20230072.
文摘Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems.However,existing methods struggle with small target sizes,complex backgrounds,low-quality image acquisition,and interference from contamination.To address these challenges,this paper proposes the Real-time Cable Defect Detection Network(RC2DNet),which achieves an optimal balance between detection accuracy and computational efficiency.Unlike conventional approaches,RC2DNet introduces a small object feature extraction module that enhances the semantic representation of small targets through feature pyramids,multi-level feature fusion,and an adaptive weighting mechanism.Additionally,a boundary feature enhancement module is designed,incorporating boundary-aware convolution,a novel boundary attention mechanism,and an improved loss function to significantly enhance boundary localization accuracy.Experimental results demonstrate that RC2DNet outperforms state-of-the-art methods in precision,recall,F1-score,mean Intersection over Union(mIoU),and frame rate,enabling real-time and highly accurate cable defect detection in complex backgrounds.
文摘Recognizing road scene context from a single image remains a critical challenge for intelligent autonomous driving systems,particularly in dynamic and unstructured environments.While recent advancements in deep learning have significantly enhanced road scene classification,simultaneously achieving high accuracy,computational efficiency,and adaptability across diverse conditions continues to be difficult.To address these challenges,this study proposes HybridLSTM,a novel and efficient framework that integrates deep learning-based,object-based,and handcrafted feature extraction methods within a unified architecture.HybridLSTM is designed to classify four distinct road scene categories—crosswalk(CW),highway(HW),overpass/tunnel(OP/T),and parking(P)—by leveraging multiple publicly available datasets,including Places-365,BDD100K,LabelMe,and KITTI,thereby promoting domain generalization.The framework fuses object-level features extracted using YOLOv5 and VGG19,scene-level global representations obtained from a modified VGG19,and fine-grained texture features captured through eight handcrafted descriptors.This hybrid feature fusion enables the model to capture both semantic context and low-level visual cues,which are critical for robust scene understanding.To model spatial arrangements and latent sequential dependencies present even in static imagery,the combined features are processed through a Long Short-Term Memory(LSTM)network,allowing the extraction of discriminative patterns across heterogeneous feature spaces.Extensive experiments conducted on 2725 annotated road scene images,with an 80:20 training-to-testing split,validate the effectiveness of the proposed model.HybridLSTM achieves a classification accuracy of 96.3%,a precision of 95.8%,a recall of 96.1%,and an F1-score of 96.0%,outperforming several existing state-of-the-art methods.These results demonstrate the robustness,scalability,and generalization capability of HybridLSTM across varying environments and scene complexities.Moreover,the framework is optimized to balance classification performance with computational efficiency,making it highly suitable for real-time deployment in embedded autonomous driving systems.Future work will focus on extending the model to multi-class detection within a single frame and optimizing it further for edge-device deployments to reduce computational overhead in practical applications.
