In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively r...Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively researched for both aerial and underwater navigation applications.However,many TAN systems that rely on recursive Unmanned Aerial Vehicle(UAV)position estimation methods,such as Extended Kalman Filters(EKF),often face challenges with divergence and instability,particularly in highly non-linear systems.To address these issues,this paper proposes and investigates a hybrid two-stage TAN positioning system for UAVs that utilizes Particle Filter.To enhance the system’s robustness against uncertainties caused by noise and to estimate additional system states,a Fuzzy Particle Filter(FPF)is employed in the first stage.This approach introduces a novel terrain composite feature that enables a fuzzy expert system to analyze terrain non-linearities and dynamically adjust the number of particles in real-time.This design allows the UAV to be efficiently localized in GPS-denied environments while also reducing the computational complexity of the particle filter in real-time applications.In the second stage,an Error State Kalman Filter(ESKF)is implemented to estimate the UAV’s altitude.The ESKF is chosen over the conventional EKF method because it is more suitable for non-linear systems.Simulation results demonstrate that the proposed fuzzy-based terrain composite method achieves high positional accuracy while reducing computational time and memory usage.展开更多
To effectively extract multi-scale information from observation data and improve computational efficiency,a multi-scale second-order autoregressive recursive filter(MSRF)method is designed.The second-order autoregress...To effectively extract multi-scale information from observation data and improve computational efficiency,a multi-scale second-order autoregressive recursive filter(MSRF)method is designed.The second-order autoregressive filter used in this study has been attempted to replace the traditional first-order recursive filter used in spatial multi-scale recursive filter(SMRF)method.The experimental results indicate that the MSRF scheme successfully extracts various scale information resolved by observations.Moreover,compared with the SMRF scheme,the MSRF scheme improves computational accuracy and efficiency to some extent.The MSRF scheme can not only propagate to a longer distance without the attenuation of innovation,but also reduce the mean absolute deviation between the reconstructed sea ice concentration results and observations reduced by about 3.2%compared to the SMRF scheme.On the other hand,compared with traditional first-order recursive filters using in the SMRF scheme that multiple filters are executed,the MSRF scheme only needs to perform two filter processes in one iteration,greatly improving filtering efficiency.In the two-dimensional experiment of sea ice concentration,the calculation time of the MSRF scheme is only 1/7 of that of SMRF scheme.This means that the MSRF scheme can achieve better performance with less computational cost,which is of great significance for further application in real-time ocean or sea ice data assimilation systems in the future.展开更多
Filter capacitors play an important role in altern-ating current(AC)-line filtering for stabilizing voltage,sup-pressing harmonics,and improving power quality.However,traditional aluminum electrolytic capacitors(AECs)...Filter capacitors play an important role in altern-ating current(AC)-line filtering for stabilizing voltage,sup-pressing harmonics,and improving power quality.However,traditional aluminum electrolytic capacitors(AECs)suffer from a large size,short lifespan,low power density,and poor reliability,which limits their use.In contrast,ultrafast supercapacitors(SCs)are ideal for replacing commercial AECs because of their extremely high power densities,fast charging and discharging,and excellent high-frequency re-sponse.We review the design principles and key parameters for ultrafast supercapacitors and summarize research pro-gress in recent years from the aspects of electrode materials,electrolytes,and device configurations.The preparation,structures,and frequency response performance of electrode materials mainly consisting of carbon materials such as graphene and carbon nanotubes,conductive polymers,and transition metal compounds,are focused on.Finally,future research directions for ultrafast SCs are suggested.展开更多
Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells an...Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.展开更多
With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of...With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.展开更多
Improving the volumetric energy density of supercapacitors is essential for practical applications,which highly relies on the dense storage of ions in carbon-based electrodes.The functional units of carbon-based elect...Improving the volumetric energy density of supercapacitors is essential for practical applications,which highly relies on the dense storage of ions in carbon-based electrodes.The functional units of carbon-based electrode exhibit multi-scale structural characteristics including macroscopic electrode morphologies,mesoscopic microcrystals and pores,and microscopic defects and dopants in the carbon basal plane.Therefore,the ordered combination of multi-scale structures of carbon electrode is crucial for achieving dense energy storage and high volumetric performance by leveraging the functions of various scale structu re.Considering that previous reviews have focused more on the discussion of specific scale structu re of carbon electrodes,this review takes a multi-scale perspective in which recent progresses regarding the structureperformance relationship,underlying mechanism and directional design of carbon-based multi-scale structures including carbon morphology,pore structure,carbon basal plane micro-environment and electrode technology on dense energy storage and volumetric property of supercapacitors are systematically discussed.We analyzed in detail the effects of the morphology,pore,and micro-environment of carbon electrode materials on ion dense storage,summarized the specific effects of different scale structures on volumetric property and recent research progress,and proposed the mutual influence and trade-off relationship between various scale structures.In addition,the challenges and outlooks for improving the dense storage and volumetric performance of carbon-based supercapacitors are analyzed,which can provide feasible technical reference and guidance for the design and manufacture of dense carbon-based electrode materials.展开更多
This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualiz...This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network mo...To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.展开更多
Soil cement bentonite(SCB)is a common material for constructing vertical cutoff walls to prevent groundwater migration at contaminated industrial sites.However,site contaminants can degrade the durability of the cutof...Soil cement bentonite(SCB)is a common material for constructing vertical cutoff walls to prevent groundwater migration at contaminated industrial sites.However,site contaminants can degrade the durability of the cutoff wall.To enhance its performance,this study developed a silica fume-SCB(SSCB).The macroscopic and microscopic properties of SSCB were assessed by unconfined compressive strength test,variable head permeability test,X-ray diffraction(XRD),scanning electron microscopy(SEM)and nuclear magnetic resonance(NMR)spectroscopy.The correlation between its multi-scale properties was analyzed based on pore characteristics.The results indicate that increasing the silica fume substitution ratio improved SSCB strength,especially in the middle and late curing stages.Moreover,increasing the substitution ratio decreased SSCB permeability coefficient,with a more pronounced effect in earlier curing stages.Silica fume addition also refined SSCB pore structure and reduced its porosity.The fractal dimension was used to quantify SSCB pore structure complexity.Increasing silica fume content reduced small pore fractal dimension in SSCB.Concurrently,SSCB strength increased and SSCB permeability coefficient decreased.The findings of this research will demonstrate the great potential of SSCB backfill for practical applications.展开更多
This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi...This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi-scale encoding significantly enhances the model’s ability to capture both fine-grained and global features,while the dynamic loss function adapts during training to optimize classification accuracy and retrieval performance.Our approach was evaluated on the ISIC-2018 and ChestX-ray14 datasets,yielding notable improvements.Specifically,on the ISIC-2018 dataset,our method achieves an F1-Score improvement of+4.84% compared to the standard ViT,with a precision increase of+5.46% for melanoma(MEL).On the ChestX-ray14 dataset,the method delivers an F1-Score improvement of 5.3%over the conventional ViT,with precision gains of+5.0% for pneumonia(PNEU)and+5.4%for fibrosis(FIB).Experimental results demonstrate that our approach outperforms traditional CNN-based models and existing ViT variants,particularly in retrieving relevant medical cases and enhancing diagnostic accuracy.These findings highlight the potential of the proposedmethod for large-scalemedical image analysis,offering improved tools for clinical decision-making through superior classification and case comparison.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
Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low informatio...Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low information density in dialogues,methods based on trigger enhancement have been proposed,yielding positive results.However,trigger enhancement faces challenges,which cause suboptimal model performance.First,the proportion of annotated triggers is low in DialogRE.Second,feature representations of triggers and arguments often contain conflicting information.In this paper,we propose a novel Multi-Feature Filtering and Fusion trigger enhancement approach to overcome these limitations.We first obtain representations of arguments,and triggers that contain rich semantic information through attention and gate methods.Then,we design a feature filtering mechanism that eliminates conflicting features in the encoding of trigger prototype representations and their corresponding argument pairs.Additionally,we utilize large language models to create prompts based on Chain-of-Thought and In-context Learning for automated trigger extraction.Experiments show that our model increases the average F1 score by 1.3%in the dialogue relation extraction task.Ablation and case studies confirm the effectiveness of our model.Furthermore,the feature filtering method effectively integrates with other trigger enhancement models,enhancing overall performance and demonstrating its ability to resolve feature conflicts.展开更多
Aluminum electrolyte capacitors(AEC)are widely used in AC filtering as traditional filter capacitors.However,their strong rigidity,high hardness,and high-risk factor have hindered the flexible development of filter ca...Aluminum electrolyte capacitors(AEC)are widely used in AC filtering as traditional filter capacitors.However,their strong rigidity,high hardness,and high-risk factor have hindered the flexible development of filter capacitors.Flexible supercapacitors,due to their high energy density and outstanding cycle stability,are becoming one of the main directions for the development of filter capacitors in the future.This paper self-assembles a MnO_(2)-based flexible supercapacitor with high area capacitance and fast frequency response,and preliminarily verifies the feasibility of using the capacitor for AC filtering through simulation tests in Multisim.Finally,the AC filtering test of the flexible supercapacitor using an oscilloscope demonstrates that the ripple factor in the range of 2.7%to 8%,which confirms that the MnO_(2)-based flexible supercapacitor has a great AC filtering function and can replace traditional aluminum electrolyte capacitors in AC filtering,promoting the flexible development of electronic products.展开更多
The multi-scale modeling combined with the cohesive zone model(CZM)and the molecular dynamics(MD)method were preformed to simulate the crack propagation in NiTi shape memory alloys(SMAs).The metallographic microscope ...The multi-scale modeling combined with the cohesive zone model(CZM)and the molecular dynamics(MD)method were preformed to simulate the crack propagation in NiTi shape memory alloys(SMAs).The metallographic microscope and image processing technology were employed to achieve a quantitative grain size distribution of NiTi alloys so as to provide experimental data for molecular dynamics modeling at the atomic scale.Considering the size effect of molecular dynamics model on material properties,a reasonable modeling size was provided by taking into account three characteristic dimensions from the perspective of macro,meso,and micro scales according to the Buckinghamπtheorem.Then,the corresponding MD simulation on deformation and fracture behavior was investigated to derive a parameterized traction-separation(T-S)law,and then it was embedded into cohesive elements of finite element software.Thus,the crack propagation behavior in NiTi alloys was reproduced by the finite element method(FEM).The experimental results show that the predicted initiation fracture toughness is in good agreement with experimental data.In addition,it is found that the dynamics initiation fracture toughness increases with decreasing grain size and increasing loading velocity.展开更多
Recent theoretical verification of self-similar and dissipative pure-quartic solitons(PQSs)emphasized the similarity between PQS lasers and conventional fiber lasers,but the unique equilibrium mechanism hinders the fo...Recent theoretical verification of self-similar and dissipative pure-quartic solitons(PQSs)emphasized the similarity between PQS lasers and conventional fiber lasers,but the unique equilibrium mechanism hinders the formation of PQS molecules in normal fourth-order dispersion(FOD)regimes.In this paper,we investigated the effect of filters on shaping PQSs in normal FOD based on a passively mode-locked fiber laser model.A bandpass filter eliminates the time pedestal of dissipative PQSs,thus realizing a multi-pulsing state.When the filter bandwidth is appropriate,the effective spectral filtering effect can lower the pulse splitting threshold and enable the coherent restoration from chaotic PQSs to PQS molecules.Additionally,changing the central wavelength of the filter can generate PQSs and PQS molecules with asymmetric intensity distributions.These results are important guides for the manipulation of PQSs and the construction of high repetition-frequency fiber lasers.展开更多
Understanding how and why assemblage dissimilarity changes along spatial gradient is a great challenge in ecology,because answers to these questions depend on the analytical types,dimensions,and components of beta div...Understanding how and why assemblage dissimilarity changes along spatial gradient is a great challenge in ecology,because answers to these questions depend on the analytical types,dimensions,and components of beta diversity we concerned.To obtain a comprehensive understanding of assemblage dissimilarity and its implications for biodiversity conservation in the Himalayas,we explored the elevational patterns and determinants of beta diversity and its turnover and nestedness components of pairwise and multiple types and taxonomic and phylogenetic dimensions simultaneously.Patterns of beta diversity and their components of different types and dimensions were calculated based on 96 sampling quadrats along an 1800-5400 m elevational gradient.We examined whether and how these patterns differed from random expectations using null models.Furthermore,we used random forest methods to quantify the role of environmental variables representing climate,topography,and human disturbance in determining these patterns.We found that beta diversity and its turnover component,regardless of its types and dimensions,shown a hump-shaped elevational patterns.Both pairwise and multiple phylogenetic beta diversity were remarkably lower than their taxonomic counterpart.These patterns were significantly less than random expectation and were mostly associated with climate variables.In summary,our results suggested that assemblage dissimilarity of seed plants was mostly originate from the replacement of closely related species determined by climate-driven environmental filtering.Accordingly,conservation efforts should better cover elevations with different climate types to maximalize biodiversity conservation,rather than only focus on elevations with highest species richness.Our study demonstrated that comparisons of beta diversity of different types,dimensions,and components could be conductive to consensus on the origin and mechanism of assemblage dissimilarity.展开更多
Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportatio...Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.展开更多
A new algorithm for segmentation of suspected lung ROI(regions of interest)by mean-shift clustering and multi-scale HESSIAN matrix dot filtering was proposed.Original image was firstly filtered by multi-scale HESSIAN ...A new algorithm for segmentation of suspected lung ROI(regions of interest)by mean-shift clustering and multi-scale HESSIAN matrix dot filtering was proposed.Original image was firstly filtered by multi-scale HESSIAN matrix dot filters,round suspected nodular lesions in the image were enhanced,and linear shape regions of the trachea and vascular were suppressed.Then,three types of information,such as,shape filtering value of HESSIAN matrix,gray value,and spatial location,were introduced to feature space.The kernel function of mean-shift clustering was divided into product form of three kinds of kernel functions corresponding to the three feature information.Finally,bandwidths were calculated adaptively to determine the bandwidth of each suspected area,and they were used in mean-shift clustering segmentation.Experimental results show that by the introduction of HESSIAN matrix of dot filtering information to mean-shift clustering,nodular regions can be segmented from blood vessels,trachea,or cross regions connected to the nodule,non-nodular areas can be removed from ROIs properly,and ground glass object(GGO)nodular areas can also be segmented.For the experimental data set of 127 different forms of nodules,the average accuracy of the proposed algorithm is more than 90%.展开更多
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
文摘Terrain Aided Navigation(TAN)technology has become increasingly important due to its effectiveness in environments where Global Positioning System(GPS)is unavailable.In recent years,TAN systems have been extensively researched for both aerial and underwater navigation applications.However,many TAN systems that rely on recursive Unmanned Aerial Vehicle(UAV)position estimation methods,such as Extended Kalman Filters(EKF),often face challenges with divergence and instability,particularly in highly non-linear systems.To address these issues,this paper proposes and investigates a hybrid two-stage TAN positioning system for UAVs that utilizes Particle Filter.To enhance the system’s robustness against uncertainties caused by noise and to estimate additional system states,a Fuzzy Particle Filter(FPF)is employed in the first stage.This approach introduces a novel terrain composite feature that enables a fuzzy expert system to analyze terrain non-linearities and dynamically adjust the number of particles in real-time.This design allows the UAV to be efficiently localized in GPS-denied environments while also reducing the computational complexity of the particle filter in real-time applications.In the second stage,an Error State Kalman Filter(ESKF)is implemented to estimate the UAV’s altitude.The ESKF is chosen over the conventional EKF method because it is more suitable for non-linear systems.Simulation results demonstrate that the proposed fuzzy-based terrain composite method achieves high positional accuracy while reducing computational time and memory usage.
基金The National Key Research and Development Program of China under contract No.2023YFC3107701the National Natural Science Foundation of China under contract No.42375143.
文摘To effectively extract multi-scale information from observation data and improve computational efficiency,a multi-scale second-order autoregressive recursive filter(MSRF)method is designed.The second-order autoregressive filter used in this study has been attempted to replace the traditional first-order recursive filter used in spatial multi-scale recursive filter(SMRF)method.The experimental results indicate that the MSRF scheme successfully extracts various scale information resolved by observations.Moreover,compared with the SMRF scheme,the MSRF scheme improves computational accuracy and efficiency to some extent.The MSRF scheme can not only propagate to a longer distance without the attenuation of innovation,but also reduce the mean absolute deviation between the reconstructed sea ice concentration results and observations reduced by about 3.2%compared to the SMRF scheme.On the other hand,compared with traditional first-order recursive filters using in the SMRF scheme that multiple filters are executed,the MSRF scheme only needs to perform two filter processes in one iteration,greatly improving filtering efficiency.In the two-dimensional experiment of sea ice concentration,the calculation time of the MSRF scheme is only 1/7 of that of SMRF scheme.This means that the MSRF scheme can achieve better performance with less computational cost,which is of great significance for further application in real-time ocean or sea ice data assimilation systems in the future.
文摘Filter capacitors play an important role in altern-ating current(AC)-line filtering for stabilizing voltage,sup-pressing harmonics,and improving power quality.However,traditional aluminum electrolytic capacitors(AECs)suffer from a large size,short lifespan,low power density,and poor reliability,which limits their use.In contrast,ultrafast supercapacitors(SCs)are ideal for replacing commercial AECs because of their extremely high power densities,fast charging and discharging,and excellent high-frequency re-sponse.We review the design principles and key parameters for ultrafast supercapacitors and summarize research pro-gress in recent years from the aspects of electrode materials,electrolytes,and device configurations.The preparation,structures,and frequency response performance of electrode materials mainly consisting of carbon materials such as graphene and carbon nanotubes,conductive polymers,and transition metal compounds,are focused on.Finally,future research directions for ultrafast SCs are suggested.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers 2024TIAD-CYKJCXX0121,2024NSCQ-LZX0135Chongqing 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Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.
基金supported by Communication University of China(HG23035)partly supported by the Fundamental Research Funds for the Central Universities(CUC230A013).
文摘With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.
基金funded by the Joint Fund for Regional Innovation and Development of National Natural Science Foundation of China(U21A20143)the National Science Fund for Excellent Young Scholars(52322607)the Excellent Youth Foundation of Heilongjiang Scientific Committee(YQ2022E028)。
文摘Improving the volumetric energy density of supercapacitors is essential for practical applications,which highly relies on the dense storage of ions in carbon-based electrodes.The functional units of carbon-based electrode exhibit multi-scale structural characteristics including macroscopic electrode morphologies,mesoscopic microcrystals and pores,and microscopic defects and dopants in the carbon basal plane.Therefore,the ordered combination of multi-scale structures of carbon electrode is crucial for achieving dense energy storage and high volumetric performance by leveraging the functions of various scale structu re.Considering that previous reviews have focused more on the discussion of specific scale structu re of carbon electrodes,this review takes a multi-scale perspective in which recent progresses regarding the structureperformance relationship,underlying mechanism and directional design of carbon-based multi-scale structures including carbon morphology,pore structure,carbon basal plane micro-environment and electrode technology on dense energy storage and volumetric property of supercapacitors are systematically discussed.We analyzed in detail the effects of the morphology,pore,and micro-environment of carbon electrode materials on ion dense storage,summarized the specific effects of different scale structures on volumetric property and recent research progress,and proposed the mutual influence and trade-off relationship between various scale structures.In addition,the challenges and outlooks for improving the dense storage and volumetric performance of carbon-based supercapacitors are analyzed,which can provide feasible technical reference and guidance for the design and manufacture of dense carbon-based electrode materials.
基金supported in part by the National Natural Science Foundation of China[62301374]Hubei Provincial Natural Science Foundation of China[2022CFB804]+2 种基金Hubei Provincial Education Research Project[B2022057]the Youths Science Foundation of Wuhan Institute of Technology[K202240]the 15th Graduate Education Innovation Fund of Wuhan Institute of Technology[CX2023295].
文摘This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金supported by National Natural Science Foundation of China(No.61862037)Lanzhou Jiaotong University Tianyou Innovation Team Project(No.TY202002)。
文摘To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.
基金Project(2019YFC1803601)supported by the National Key Research and Development Program of ChinaProject(52274182)supported by the National Natural Science Foundation of China+1 种基金Project(2021zzts0274)supported by the Fundamental Research Funds for the Central Universities,ChinaProject(CX20210295)supported by the Postgraduate Scientific Research Innovation Project of Hunan Province,China。
文摘Soil cement bentonite(SCB)is a common material for constructing vertical cutoff walls to prevent groundwater migration at contaminated industrial sites.However,site contaminants can degrade the durability of the cutoff wall.To enhance its performance,this study developed a silica fume-SCB(SSCB).The macroscopic and microscopic properties of SSCB were assessed by unconfined compressive strength test,variable head permeability test,X-ray diffraction(XRD),scanning electron microscopy(SEM)and nuclear magnetic resonance(NMR)spectroscopy.The correlation between its multi-scale properties was analyzed based on pore characteristics.The results indicate that increasing the silica fume substitution ratio improved SSCB strength,especially in the middle and late curing stages.Moreover,increasing the substitution ratio decreased SSCB permeability coefficient,with a more pronounced effect in earlier curing stages.Silica fume addition also refined SSCB pore structure and reduced its porosity.The fractal dimension was used to quantify SSCB pore structure complexity.Increasing silica fume content reduced small pore fractal dimension in SSCB.Concurrently,SSCB strength increased and SSCB permeability coefficient decreased.The findings of this research will demonstrate the great potential of SSCB backfill for practical applications.
基金funded by the Deanship of Research and Graduate Studies at King Khalid University through small group research under grant number RGP1/278/45.
文摘This paper introduces a novel method for medical image retrieval and classification by integrating a multi-scale encoding mechanism with Vision Transformer(ViT)architectures and a dynamic multi-loss function.The multi-scale encoding significantly enhances the model’s ability to capture both fine-grained and global features,while the dynamic loss function adapts during training to optimize classification accuracy and retrieval performance.Our approach was evaluated on the ISIC-2018 and ChestX-ray14 datasets,yielding notable improvements.Specifically,on the ISIC-2018 dataset,our method achieves an F1-Score improvement of+4.84% compared to the standard ViT,with a precision increase of+5.46% for melanoma(MEL).On the ChestX-ray14 dataset,the method delivers an F1-Score improvement of 5.3%over the conventional ViT,with precision gains of+5.0% for pneumonia(PNEU)and+5.4%for fibrosis(FIB).Experimental results demonstrate that our approach outperforms traditional CNN-based models and existing ViT variants,particularly in retrieving relevant medical cases and enhancing diagnostic accuracy.These findings highlight the potential of the proposedmethod for large-scalemedical image analysis,offering improved tools for clinical decision-making through superior classification and case comparison.
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 Key Research and Development Program of China(No.2023YFF0905400)the National Natural Science Foundation of China(No.U2341229).
文摘Relation extraction plays a crucial role in numerous downstream tasks.Dialogue relation extraction focuses on identifying relations between two arguments within a given dialogue.To tackle the problem of low information density in dialogues,methods based on trigger enhancement have been proposed,yielding positive results.However,trigger enhancement faces challenges,which cause suboptimal model performance.First,the proportion of annotated triggers is low in DialogRE.Second,feature representations of triggers and arguments often contain conflicting information.In this paper,we propose a novel Multi-Feature Filtering and Fusion trigger enhancement approach to overcome these limitations.We first obtain representations of arguments,and triggers that contain rich semantic information through attention and gate methods.Then,we design a feature filtering mechanism that eliminates conflicting features in the encoding of trigger prototype representations and their corresponding argument pairs.Additionally,we utilize large language models to create prompts based on Chain-of-Thought and In-context Learning for automated trigger extraction.Experiments show that our model increases the average F1 score by 1.3%in the dialogue relation extraction task.Ablation and case studies confirm the effectiveness of our model.Furthermore,the feature filtering method effectively integrates with other trigger enhancement models,enhancing overall performance and demonstrating its ability to resolve feature conflicts.
文摘Aluminum electrolyte capacitors(AEC)are widely used in AC filtering as traditional filter capacitors.However,their strong rigidity,high hardness,and high-risk factor have hindered the flexible development of filter capacitors.Flexible supercapacitors,due to their high energy density and outstanding cycle stability,are becoming one of the main directions for the development of filter capacitors in the future.This paper self-assembles a MnO_(2)-based flexible supercapacitor with high area capacitance and fast frequency response,and preliminarily verifies the feasibility of using the capacitor for AC filtering through simulation tests in Multisim.Finally,the AC filtering test of the flexible supercapacitor using an oscilloscope demonstrates that the ripple factor in the range of 2.7%to 8%,which confirms that the MnO_(2)-based flexible supercapacitor has a great AC filtering function and can replace traditional aluminum electrolyte capacitors in AC filtering,promoting the flexible development of electronic products.
基金Funded by the National Natural Science Foundation of China Academy of Engineering Physics and Jointly Setup"NSAF"Joint Fund(No.U1430119)。
文摘The multi-scale modeling combined with the cohesive zone model(CZM)and the molecular dynamics(MD)method were preformed to simulate the crack propagation in NiTi shape memory alloys(SMAs).The metallographic microscope and image processing technology were employed to achieve a quantitative grain size distribution of NiTi alloys so as to provide experimental data for molecular dynamics modeling at the atomic scale.Considering the size effect of molecular dynamics model on material properties,a reasonable modeling size was provided by taking into account three characteristic dimensions from the perspective of macro,meso,and micro scales according to the Buckinghamπtheorem.Then,the corresponding MD simulation on deformation and fracture behavior was investigated to derive a parameterized traction-separation(T-S)law,and then it was embedded into cohesive elements of finite element software.Thus,the crack propagation behavior in NiTi alloys was reproduced by the finite element method(FEM).The experimental results show that the predicted initiation fracture toughness is in good agreement with experimental data.In addition,it is found that the dynamics initiation fracture toughness increases with decreasing grain size and increasing loading velocity.
基金Project supported by the National Natural Science Foundation of China(Grant No.62175116)。
文摘Recent theoretical verification of self-similar and dissipative pure-quartic solitons(PQSs)emphasized the similarity between PQS lasers and conventional fiber lasers,but the unique equilibrium mechanism hinders the formation of PQS molecules in normal fourth-order dispersion(FOD)regimes.In this paper,we investigated the effect of filters on shaping PQSs in normal FOD based on a passively mode-locked fiber laser model.A bandpass filter eliminates the time pedestal of dissipative PQSs,thus realizing a multi-pulsing state.When the filter bandwidth is appropriate,the effective spectral filtering effect can lower the pulse splitting threshold and enable the coherent restoration from chaotic PQSs to PQS molecules.Additionally,changing the central wavelength of the filter can generate PQSs and PQS molecules with asymmetric intensity distributions.These results are important guides for the manipulation of PQSs and the construction of high repetition-frequency fiber lasers.
基金supported by the National Natural Science Foundation of China(grant number 31901109)Guangdong Basic and Applied Basic Research Foundation(grant number 2021A1515110744).
文摘Understanding how and why assemblage dissimilarity changes along spatial gradient is a great challenge in ecology,because answers to these questions depend on the analytical types,dimensions,and components of beta diversity we concerned.To obtain a comprehensive understanding of assemblage dissimilarity and its implications for biodiversity conservation in the Himalayas,we explored the elevational patterns and determinants of beta diversity and its turnover and nestedness components of pairwise and multiple types and taxonomic and phylogenetic dimensions simultaneously.Patterns of beta diversity and their components of different types and dimensions were calculated based on 96 sampling quadrats along an 1800-5400 m elevational gradient.We examined whether and how these patterns differed from random expectations using null models.Furthermore,we used random forest methods to quantify the role of environmental variables representing climate,topography,and human disturbance in determining these patterns.We found that beta diversity and its turnover component,regardless of its types and dimensions,shown a hump-shaped elevational patterns.Both pairwise and multiple phylogenetic beta diversity were remarkably lower than their taxonomic counterpart.These patterns were significantly less than random expectation and were mostly associated with climate variables.In summary,our results suggested that assemblage dissimilarity of seed plants was mostly originate from the replacement of closely related species determined by climate-driven environmental filtering.Accordingly,conservation efforts should better cover elevations with different climate types to maximalize biodiversity conservation,rather than only focus on elevations with highest species richness.Our study demonstrated that comparisons of beta diversity of different types,dimensions,and components could be conductive to consensus on the origin and mechanism of assemblage dissimilarity.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia through research group No.(RG-NBU-2022-1234).
文摘Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.
基金Projects(61172002,61001047,60671050)supported by the National Natural Science Foundation of ChinaProject(N100404010)supported by Fundamental Research Grant Scheme for the Central Universities,China
文摘A new algorithm for segmentation of suspected lung ROI(regions of interest)by mean-shift clustering and multi-scale HESSIAN matrix dot filtering was proposed.Original image was firstly filtered by multi-scale HESSIAN matrix dot filters,round suspected nodular lesions in the image were enhanced,and linear shape regions of the trachea and vascular were suppressed.Then,three types of information,such as,shape filtering value of HESSIAN matrix,gray value,and spatial location,were introduced to feature space.The kernel function of mean-shift clustering was divided into product form of three kinds of kernel functions corresponding to the three feature information.Finally,bandwidths were calculated adaptively to determine the bandwidth of each suspected area,and they were used in mean-shift clustering segmentation.Experimental results show that by the introduction of HESSIAN matrix of dot filtering information to mean-shift clustering,nodular regions can be segmented from blood vessels,trachea,or cross regions connected to the nodule,non-nodular areas can be removed from ROIs properly,and ground glass object(GGO)nodular areas can also be segmented.For the experimental data set of 127 different forms of nodules,the average accuracy of the proposed algorithm is more than 90%.
