3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safe...3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.展开更多
The metaverse enables immersive virtual healthcare environments,presenting opportunities for enhanced care delivery.A key challenge lies in effectively combining multimodal healthcare data and generative artificial in...The metaverse enables immersive virtual healthcare environments,presenting opportunities for enhanced care delivery.A key challenge lies in effectively combining multimodal healthcare data and generative artificial intelligence abilities within metaverse-based healthcare applications,which is a problem that needs to be addressed.This paper proposes a novel multimodal learning framework for metaverse healthcare,MMLMH,based on collaborative intra-and intersample representation and adaptive fusion.Our framework introduces a collaborative representation learning approach that captures shared and modality-specific features across text,audio,and visual health data.By combining modality-specific and shared encoders with carefully formulated intrasample and intersample collaboration mechanisms,MMLMH achieves superior feature representation for complex health assessments.The framework’s adaptive fusion approach,utilizing attention mechanisms and gated neural networks,demonstrates robust performance across varying noise levels and data quality conditions.Experiments on metaverse healthcare datasets demonstrate MMLMH’s superior performance over baseline methods across multiple evaluation metrics.Longitudinal studies and visualization further illustrate MMLMH’s adaptability to evolving virtual environments and balanced performance across diagnostic accuracy,patient-system interaction efficacy,and data integration complexity.The proposed framework has a unique advantage in that a similar level of performance is maintained across various patient populations and virtual avatars,which could lead to greater personalization of healthcare experiences in the metaverse.MMLMH’s successful functioning in such complicated circumstances suggests that it can combine and process information streams from several sources.They can be successfully utilized in next-generation healthcare delivery through virtual reality.展开更多
In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address t...In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address these challenges,this paper proposes an improved detection algorithm based on YOLOv11n.First,a Dynamic Multi-Scale Feature Fusion and Adaptive Weighting approach is employed to design an Adaptive Focused Diffusion Pyramid Network(AFDPN),which enhances the feature expression and transmission capability of shallow small targets,thereby reducing the loss of detailed information.Then,combined with an Edge Enhancement(EE)module,the model improves the extraction of infrared small target edge features through low-frequency suppression and high-frequency enhancement strategies.Experimental results on the publicly available HIT-UAV dataset show that the improved model achieves a 3.8%increase in average detection accuracy and a 3.0%improvement in recall rate compared to YOLOv11n,with a computational cost of only 9.1 GFLOPS.In comparison experiments,the detection accuracy and model size balance achieved the optimal solution,meeting the lightweight deployment requirements for drone-based systems.This method provides a high-precision,lightweight solution for small target detection in drone-based infrared imagery.展开更多
The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assem...The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assembly errors,and other imperfections that may arise during the design or manufacturing phases.Conse-quently,these micro-motors might generate anomalous noises during their operation,consequently exerting a substantial adverse influence on the overall comfort of drivers and passengers.Automobile micro-motors exhibit a diverse array of structural variations,consequently leading to the manifestation of a multitude of distinctive auditory irregularities.To address the identification of diverse forms of abnormal noise,this research presents a novel approach rooted in the utilization of vibro-acoustic fusion-convolutional neural network(VAF-CNN).This method entails the deployment of distinct network branches,each serving to capture disparate features from the multi-sensor data,all the while considering the auditory perception traits inherent in the human auditory sys-tem.The intermediary layer integrates the concept of adaptive weighting of multi-sensor features,thus affording a calibration mechanism for the features hailing from multiple sensors,thereby enabling a further refinement of features within the branch network.For optimal model efficacy,a feature fusion mechanism is implemented in the concluding layer.To substantiate the efficacy of the proposed approach,this paper initially employs an augmented data methodology inspired by modified SpecAugment,applied to the dataset of abnormal noise sam-ples,encompassing scenarios both with and without in-vehicle interior noise.This serves to mitigate the issue of limited sample availability.Subsequent comparative evaluations are executed,contrasting the performance of the model founded upon single-sensor data against other feature fusion models reliant on multi-sensor data.The experimental results substantiate that the suggested methodology yields heightened recognition accuracy and greater resilience against interference.Moreover,it holds notable practical significance in the engineering domain,as it furnishes valuable support for the targeted management of noise emanating from vehicle micro-motors.展开更多
The accuracy of Digital Surface Models(DSMs)generated using stereo matching methods varies due to the varying acquisition conditions and configuration parameters of stereo images.It has been a good practice to fuse th...The accuracy of Digital Surface Models(DSMs)generated using stereo matching methods varies due to the varying acquisition conditions and configuration parameters of stereo images.It has been a good practice to fuse these DSMs generated from various stereo pairs to achieve enhanced,in which multiple DSMs are combined through computational approaches into a single,more accurate,and complete DSM.However,accurately characterizing detailed objects and their boundaries still present a challenge since most boundary-ware fusion methods still struggle to achieve sharpened depth discontinuities due to the averaging effects of different DSMs.Therefore,we propose a simple and efficient adaptive image-guided DSM fusion method that applies k-means clustering on small patches of the orthophoto to guide the pixel-level fusion adapted to the most consistent and relevant elevation points.The experiment results show that our proposed method has outperformed comparing methods in accuracy and the ability to preserve sharpened depth edges.展开更多
In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is pro...In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.展开更多
In the normal operation condition, a conventional square-root cubature Kalman filter （SRCKF） gives sufficiently good estimation results. However, if the measurements are not reliable, the SRCKF may give inaccurate r...In the normal operation condition, a conventional square-root cubature Kalman filter （SRCKF） gives sufficiently good estimation results. However, if the measurements are not reliable, the SRCKF may give inaccurate results and diverges by time. This study introduces an adaptive SRCKF algorithm with the filter gain correction for the case of measurement malfunctions. By proposing a switching criterion, an optimal filter is selected from the adaptive and conventional SRCKF according to the measurement quality. A subsystem soft fault detection algorithm is built with the filter residual. Utilizing a clear subsystem fault coefficient, the faulty subsystem is isolated as a result of the system reconstruction. In order to improve the performance of the multi-sensor system, a hybrid fusion algorithm is presented based on the adaptive SRCKF. The state and error covariance matrix are also predicted by the priori fusion estimates, and are updated by the predicted and estimated information of subsystems. The proposed algorithms were applied to the vessel dynamic positioning system simulation. They were compared with normal SRCKF and local estimation weighted fusion algorithm. The simulation results show that the presented adaptive SRCKF improves the robustness of subsystem filtering, and the hybrid fusion algorithm has the better performance. The simulation verifies the effectiveness of the proposed algorithms.展开更多
Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded an...Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded and blurred targets between long-range complex scene frames.More so,its fixed weight fusion strategy does not use the complementary properties of deep and shallow features.In this paper,we propose a new target tracking method,namely ECO++,using deep feature adaptive fusion in a complex scene,in the following two aspects:First,we constructed a new temporal convolution mode and used it to replace the underlying convolution layer in Conformer network to obtain an improved Conformer network.Second,we adaptively fuse the deep features,which output through the improved Conformer network,by combining the Peak to Sidelobe Ratio(PSR),frame smoothness scores and adaptive adjustment weight.Extensive experiments on the OTB-2013,OTB-2015,UAV123,and VOT2019 benchmarks demonstrate that the proposed approach outperforms the state-of-the-art algorithms in tracking accuracy and robustness in complex scenes with occluded,blurred,and fast-moving targets.展开更多
Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which ...Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.展开更多
This paper describes the analysis and design of an assistive device for elderly people under development at the EgyptJapan University of Science and Technology（E-JUST） named E-JUST assistive device（EJAD）.Several e...This paper describes the analysis and design of an assistive device for elderly people under development at the EgyptJapan University of Science and Technology（E-JUST） named E-JUST assistive device（EJAD）.Several experiments were carried out using a motion capture system（VICON） and inertial sensors to identify the human posture during the sit-to-stand motion.The EJAD uses only two inertial measurement units（IMUs） fused through an adaptive neuro-fuzzy inference systems（ANFIS） algorithm to imitate the real motion of the caregiver.The EJAD consists of two main parts,a robot arm and an active walker.The robot arm is a 2-degree-of-freedom（2-DOF） planar manipulator.In addition,a back support with a passive joint is used to support the patient s back.The IMUs on the leg and trunk of the patient are used to compensate for and adapt to the EJAD system motion depending on the obtained patient posture.The ANFIS algorithm is used to train the fuzzy system that converts the IMUs signals to the right posture of the patient.A control scheme is proposed to control the system motion based on practical measurements taken from the experiments.A computer simulation showed a relatively good performance of the EJAD in assisting the patient.展开更多
An integrated navlgation based on the kinematic or dynamic state model and the raw measurements has the advantages of high redundancy, high reliability, as well as high ability of fault tolerance and simplicity in cal...An integrated navlgation based on the kinematic or dynamic state model and the raw measurements has the advantages of high redundancy, high reliability, as well as high ability of fault tolerance and simplicity in calculation. In order to control the influences of measurements outliers and the kinematic model errors on the integrated navigation results, a robust estimation method and an adaptive data fusion method are applied. An integrated navigation example using simulated data is performed and analyzed.展开更多
Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models...Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models achieve speed-accuracy trade-offs via fixed convolution kernels and manual feature fusion,their rigid architectures struggle with multi-scale adaptability,as exemplified by YOLOv8n’s 36.4%mAP and 13.9%small-object AP on VisDrone2019.This paper presents YOLO-LE,a lightweight framework addressing these limitations through three novel designs:(1)We introduce the C2f-Dy and LDown modules to enhance the backbone’s sensitivity to small-object features while reducing backbone parameters,thereby improving model efficiency.(2)An adaptive feature fusion module is designed to dynamically integrate multi-scale feature maps,optimizing the neck structure,reducing neck complexity,and enhancing overall model performance.(3)We replace the original loss function with a distributed focal loss and incorporate a lightweight self-attention mechanism to improve small-object recognition and bounding box regression accuracy.Experimental results demonstrate that YOLO-LE achieves 39.9%mAP@0.5 on VisDrone2019,representing a 9.6%improvement over YOLOv8n,while maintaining 8.5 GFLOPs computational efficiency.This provides an efficient solution for UAV object detection in complex scenarios.展开更多
Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a chall...Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.展开更多
Following publication of the original article[1],the statement of Competing interests has been added.Competing interests Ying Liu is an Associate Editor for Autonomous Intelligent Systems and was not involved in the e...Following publication of the original article[1],the statement of Competing interests has been added.Competing interests Ying Liu is an Associate Editor for Autonomous Intelligent Systems and was not involved in the editorial review or the decision to publish this article.All authors declare that there are no other competing interests.展开更多
Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewpriv...Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.展开更多
The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have ...The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representation;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used Res Net-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(m AP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49%.展开更多
Polarization-based integrated navigation system(PINS)that combines the polarization sensor(PS)and the inertial navigation system(INS)has been widely recognized as an effective solution for acquiring attitude informati...Polarization-based integrated navigation system(PINS)that combines the polarization sensor(PS)and the inertial navigation system(INS)has been widely recognized as an effective solution for acquiring attitude information of unmanned aerial vehicles(UAVs).However,based on the PINS hardware configuration,the accurate acquisition of UAV position information remains a challenge.In this article,we propose an improved PS/INS integrated navigation scheme by incorporating an embedded UAV dynamic model(UDM).Compared with existing PS/INS fusion methods,the presented PINS enables the optimal estimation of the UDM thrust coefficient error along with other system state elements,thus significantly improving the UDM accuracy.On this basis,the UDM and PS are used to fuse with the INS,which improves the estimation accuracy of both the UAV attitude and position.Furthermore,we employ an adaptive fusion strategy to detect the reliability of PS data.Therefore,once the UDM is corrected using reliable PS data,it can further fuse with the INS,thereby improving the environmental adaptability of the PINS.The simulation and flight experiment results verified the effectiveness of the proposed PS/INS/UDM integrated navigation scheme.展开更多
In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the mor...In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for recognition.To further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is proposed.The proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion strategy.First,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature maps.Next,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is proposed.Different from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding space.At last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular regions.Extensive experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.展开更多
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004).
文摘3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.
基金supported by the National Natural Science Foundation of China under Grant No.62202247the National Key R&D Program of China under Grant No.2022ZD0115303.
文摘The metaverse enables immersive virtual healthcare environments,presenting opportunities for enhanced care delivery.A key challenge lies in effectively combining multimodal healthcare data and generative artificial intelligence abilities within metaverse-based healthcare applications,which is a problem that needs to be addressed.This paper proposes a novel multimodal learning framework for metaverse healthcare,MMLMH,based on collaborative intra-and intersample representation and adaptive fusion.Our framework introduces a collaborative representation learning approach that captures shared and modality-specific features across text,audio,and visual health data.By combining modality-specific and shared encoders with carefully formulated intrasample and intersample collaboration mechanisms,MMLMH achieves superior feature representation for complex health assessments.The framework’s adaptive fusion approach,utilizing attention mechanisms and gated neural networks,demonstrates robust performance across varying noise levels and data quality conditions.Experiments on metaverse healthcare datasets demonstrate MMLMH’s superior performance over baseline methods across multiple evaluation metrics.Longitudinal studies and visualization further illustrate MMLMH’s adaptability to evolving virtual environments and balanced performance across diagnostic accuracy,patient-system interaction efficacy,and data integration complexity.The proposed framework has a unique advantage in that a similar level of performance is maintained across various patient populations and virtual avatars,which could lead to greater personalization of healthcare experiences in the metaverse.MMLMH’s successful functioning in such complicated circumstances suggests that it can combine and process information streams from several sources.They can be successfully utilized in next-generation healthcare delivery through virtual reality.
文摘In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address these challenges,this paper proposes an improved detection algorithm based on YOLOv11n.First,a Dynamic Multi-Scale Feature Fusion and Adaptive Weighting approach is employed to design an Adaptive Focused Diffusion Pyramid Network(AFDPN),which enhances the feature expression and transmission capability of shallow small targets,thereby reducing the loss of detailed information.Then,combined with an Edge Enhancement(EE)module,the model improves the extraction of infrared small target edge features through low-frequency suppression and high-frequency enhancement strategies.Experimental results on the publicly available HIT-UAV dataset show that the improved model achieves a 3.8%increase in average detection accuracy and a 3.0%improvement in recall rate compared to YOLOv11n,with a computational cost of only 9.1 GFLOPS.In comparison experiments,the detection accuracy and model size balance achieved the optimal solution,meeting the lightweight deployment requirements for drone-based systems.This method provides a high-precision,lightweight solution for small target detection in drone-based infrared imagery.
基金The author received the funding from Sichuan Natural Science Foundation(2022NSFSC1892).
文摘The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assembly errors,and other imperfections that may arise during the design or manufacturing phases.Conse-quently,these micro-motors might generate anomalous noises during their operation,consequently exerting a substantial adverse influence on the overall comfort of drivers and passengers.Automobile micro-motors exhibit a diverse array of structural variations,consequently leading to the manifestation of a multitude of distinctive auditory irregularities.To address the identification of diverse forms of abnormal noise,this research presents a novel approach rooted in the utilization of vibro-acoustic fusion-convolutional neural network(VAF-CNN).This method entails the deployment of distinct network branches,each serving to capture disparate features from the multi-sensor data,all the while considering the auditory perception traits inherent in the human auditory sys-tem.The intermediary layer integrates the concept of adaptive weighting of multi-sensor features,thus affording a calibration mechanism for the features hailing from multiple sensors,thereby enabling a further refinement of features within the branch network.For optimal model efficacy,a feature fusion mechanism is implemented in the concluding layer.To substantiate the efficacy of the proposed approach,this paper initially employs an augmented data methodology inspired by modified SpecAugment,applied to the dataset of abnormal noise sam-ples,encompassing scenarios both with and without in-vehicle interior noise.This serves to mitigate the issue of limited sample availability.Subsequent comparative evaluations are executed,contrasting the performance of the model founded upon single-sensor data against other feature fusion models reliant on multi-sensor data.The experimental results substantiate that the suggested methodology yields heightened recognition accuracy and greater resilience against interference.Moreover,it holds notable practical significance in the engineering domain,as it furnishes valuable support for the targeted management of noise emanating from vehicle micro-motors.
基金John Hopkins University Applied Physics Lab to support the Imagery of the 2019 DFC datasets
文摘The accuracy of Digital Surface Models(DSMs)generated using stereo matching methods varies due to the varying acquisition conditions and configuration parameters of stereo images.It has been a good practice to fuse these DSMs generated from various stereo pairs to achieve enhanced,in which multiple DSMs are combined through computational approaches into a single,more accurate,and complete DSM.However,accurately characterizing detailed objects and their boundaries still present a challenge since most boundary-ware fusion methods still struggle to achieve sharpened depth discontinuities due to the averaging effects of different DSMs.Therefore,we propose a simple and efficient adaptive image-guided DSM fusion method that applies k-means clustering on small patches of the orthophoto to guide the pixel-level fusion adapted to the most consistent and relevant elevation points.The experiment results show that our proposed method has outperformed comparing methods in accuracy and the ability to preserve sharpened depth edges.
基金National Youth Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Jiangsu University Superior Discipline Construction Project。
文摘In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.
基金Supported by the National Natural Science Foundation of China （50979017, NSFC60775060） the National High Technology Ship Research Project of China （GJCB09001）
文摘In the normal operation condition, a conventional square-root cubature Kalman filter （SRCKF） gives sufficiently good estimation results. However, if the measurements are not reliable, the SRCKF may give inaccurate results and diverges by time. This study introduces an adaptive SRCKF algorithm with the filter gain correction for the case of measurement malfunctions. By proposing a switching criterion, an optimal filter is selected from the adaptive and conventional SRCKF according to the measurement quality. A subsystem soft fault detection algorithm is built with the filter residual. Utilizing a clear subsystem fault coefficient, the faulty subsystem is isolated as a result of the system reconstruction. In order to improve the performance of the multi-sensor system, a hybrid fusion algorithm is presented based on the adaptive SRCKF. The state and error covariance matrix are also predicted by the priori fusion estimates, and are updated by the predicted and estimated information of subsystems. The proposed algorithms were applied to the vessel dynamic positioning system simulation. They were compared with normal SRCKF and local estimation weighted fusion algorithm. The simulation results show that the presented adaptive SRCKF improves the robustness of subsystem filtering, and the hybrid fusion algorithm has the better performance. The simulation verifies the effectiveness of the proposed algorithms.
基金supported by the National Key R&D Plan"Intelligent Robots"Key Project of P.R.China(Grant No.2018YFB1308602)the National Natural Science Foundation of P.R.China(Grant No.61173184)+3 种基金the Chongqing Natural Science Foundation of P.R.China(Grant No.cstc2018jcyj AX0694)Research Project of Chongqing Big Data Application and Development Administration Bureau(No.22-30)Basic and Advanced Research Projects of CSTC(No.cstc2019jcyj-zdxmX0008)the Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.KJZD-K201900605)。
文摘Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded and blurred targets between long-range complex scene frames.More so,its fixed weight fusion strategy does not use the complementary properties of deep and shallow features.In this paper,we propose a new target tracking method,namely ECO++,using deep feature adaptive fusion in a complex scene,in the following two aspects:First,we constructed a new temporal convolution mode and used it to replace the underlying convolution layer in Conformer network to obtain an improved Conformer network.Second,we adaptively fuse the deep features,which output through the improved Conformer network,by combining the Peak to Sidelobe Ratio(PSR),frame smoothness scores and adaptive adjustment weight.Extensive experiments on the OTB-2013,OTB-2015,UAV123,and VOT2019 benchmarks demonstrate that the proposed approach outperforms the state-of-the-art algorithms in tracking accuracy and robustness in complex scenes with occluded,blurred,and fast-moving targets.
基金the National Natural Science Foundation of China(No.61975015)the Research and Innovation Project for Graduate Students at Zhongyuan University of Technology(No.YKY2024ZK14).
文摘Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.
基金supported in part by a scholarship provided by the Mission DepartmentMinistry of Higher Education of the Government of Egypt
文摘This paper describes the analysis and design of an assistive device for elderly people under development at the EgyptJapan University of Science and Technology（E-JUST） named E-JUST assistive device（EJAD）.Several experiments were carried out using a motion capture system（VICON） and inertial sensors to identify the human posture during the sit-to-stand motion.The EJAD uses only two inertial measurement units（IMUs） fused through an adaptive neuro-fuzzy inference systems（ANFIS） algorithm to imitate the real motion of the caregiver.The EJAD consists of two main parts,a robot arm and an active walker.The robot arm is a 2-degree-of-freedom（2-DOF） planar manipulator.In addition,a back support with a passive joint is used to support the patient s back.The IMUs on the leg and trunk of the patient are used to compensate for and adapt to the EJAD system motion depending on the obtained patient posture.The ANFIS algorithm is used to train the fuzzy system that converts the IMUs signals to the right posture of the patient.A control scheme is proposed to control the system motion based on practical measurements taken from the experiments.A computer simulation showed a relatively good performance of the EJAD in assisting the patient.
基金Project supported by the National Outstanding Youth Science Foundation ( No.49825107) and the Natural Science Foundation ( No.40244002 No.40174009) .
文摘An integrated navlgation based on the kinematic or dynamic state model and the raw measurements has the advantages of high redundancy, high reliability, as well as high ability of fault tolerance and simplicity in calculation. In order to control the influences of measurements outliers and the kinematic model errors on the integrated navigation results, a robust estimation method and an adaptive data fusion method are applied. An integrated navigation example using simulated data is performed and analyzed.
文摘Unmanned aerial vehicle(UAV)imagery poses significant challenges for object detection due to extreme scale variations,high-density small targets(68%in VisDrone dataset),and complex backgrounds.While YOLO-series models achieve speed-accuracy trade-offs via fixed convolution kernels and manual feature fusion,their rigid architectures struggle with multi-scale adaptability,as exemplified by YOLOv8n’s 36.4%mAP and 13.9%small-object AP on VisDrone2019.This paper presents YOLO-LE,a lightweight framework addressing these limitations through three novel designs:(1)We introduce the C2f-Dy and LDown modules to enhance the backbone’s sensitivity to small-object features while reducing backbone parameters,thereby improving model efficiency.(2)An adaptive feature fusion module is designed to dynamically integrate multi-scale feature maps,optimizing the neck structure,reducing neck complexity,and enhancing overall model performance.(3)We replace the original loss function with a distributed focal loss and incorporate a lightweight self-attention mechanism to improve small-object recognition and bounding box regression accuracy.Experimental results demonstrate that YOLO-LE achieves 39.9%mAP@0.5 on VisDrone2019,representing a 9.6%improvement over YOLOv8n,while maintaining 8.5 GFLOPs computational efficiency.This provides an efficient solution for UAV object detection in complex scenarios.
基金supported by the STI2030-Major-Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.
文摘Following publication of the original article[1],the statement of Competing interests has been added.Competing interests Ying Liu is an Associate Editor for Autonomous Intelligent Systems and was not involved in the editorial review or the decision to publish this article.All authors declare that there are no other competing interests.
文摘Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.
基金supported in part by the Natural Science Foundation of Xinjiang Uygur Autonomous Region(Grant No.2022D01B186 and No.2022D01B05)。
文摘The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representation;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used Res Net-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(m AP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49%.
基金supported by the National Natural Science Foundation of China(Grant Nos.62388101,62425302,62227813,62373033,62403024)the National Key R&D Program of China(Grant No.2020YFA0711200)。
文摘Polarization-based integrated navigation system(PINS)that combines the polarization sensor(PS)and the inertial navigation system(INS)has been widely recognized as an effective solution for acquiring attitude information of unmanned aerial vehicles(UAVs).However,based on the PINS hardware configuration,the accurate acquisition of UAV position information remains a challenge.In this article,we propose an improved PS/INS integrated navigation scheme by incorporating an embedded UAV dynamic model(UDM).Compared with existing PS/INS fusion methods,the presented PINS enables the optimal estimation of the UDM thrust coefficient error along with other system state elements,thus significantly improving the UDM accuracy.On this basis,the UDM and PS are used to fuse with the INS,which improves the estimation accuracy of both the UAV attitude and position.Furthermore,we employ an adaptive fusion strategy to detect the reliability of PS data.Therefore,once the UDM is corrected using reliable PS data,it can further fuse with the INS,thereby improving the environmental adaptability of the PINS.The simulation and flight experiment results verified the effectiveness of the proposed PS/INS/UDM integrated navigation scheme.
基金This work was supported by National Natural Science Foundation of China(Nos.62006225,61906199 and 62071468)the Strategic Priority Research Program of Chinese Academy of Sciences(CAS),China(No.XDA 27040700)sponsored by The Beijing Nova Program,China(Nos.Z201100006820050 and Z211100002121010).
文摘In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are acquired.As the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for recognition.To further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is proposed.The proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion strategy.First,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature maps.Next,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is proposed.Different from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding space.At last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular regions.Extensive experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.
