Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the f...Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.展开更多
Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso...Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.展开更多
With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)da...With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.展开更多
The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prosta...The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.展开更多
Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often...Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often handpicked and need more delicate operations in intelligent picking machines.Compared with traditional image processing techniques,deep learning models have stronger feature extraction capabilities,and better generalization and are more suitable for practical tea shoot harvesting.However,current research mostly focuses on shoot detection and cannot directly accomplish end-to-end shoot segmentation tasks.We propose a tea shoot instance segmentation model based on multi-scale mixed attention(Mask2FusionNet)using a dataset from the tea garden in Hangzhou.We further analyzed the characteristics of the tea shoot dataset,where the proportion of small to medium-sized targets is 89.9%.Our algorithm is compared with several mainstream object segmentation algorithms,and the results demonstrate that our model achieves an accuracy of 82%in recognizing the tea shoots,showing a better performance compared to other models.Through ablation experiments,we found that ResNet50,PointRend strategy,and the Feature Pyramid Network(FPN)architecture can improve performance by 1.6%,1.4%,and 2.4%,respectively.These experiments demonstrated that our proposed multi-scale and point selection strategy optimizes the feature extraction capability for overlapping small targets.The results indicate that the proposed Mask2FusionNet model can perform the shoot segmentation in unstructured environments,realizing the individual distinction of tea shoots,and complete extraction of the shoot edge contours with a segmentation accuracy of 82.0%.The research results can provide algorithmic support for the segmentation and intelligent harvesting of premium tea shoots at different scales.展开更多
With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The networ...With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The network security environment in the era of big data presents the characteristics of large amounts of data,high diversity,and high real-time requirements.Traditional security defense methods and tools have been unable to cope with the complex and changing network security threats.This paper proposes a machine-learning security defense algorithm based on metadata association features.Emphasize control over unauthorized users through privacy,integrity,and availability.The user model is established and the mapping between the user model and the metadata of the data source is generated.By analyzing the user model and its corresponding mapping relationship,the query of the user model can be decomposed into the query of various heterogeneous data sources,and the integration of heterogeneous data sources based on the metadata association characteristics can be realized.Define and classify customer information,automatically identify and perceive sensitive data,build a behavior audit and analysis platform,analyze user behavior trajectories,and complete the construction of a machine learning customer information security defense system.The experimental results show that when the data volume is 5×103 bit,the data storage integrity of the proposed method is 92%.The data accuracy is 98%,and the success rate of data intrusion is only 2.6%.It can be concluded that the data storage method in this paper is safe,the data accuracy is always at a high level,and the data disaster recovery performance is good.This method can effectively resist data intrusion and has high air traffic control security.It can not only detect all viruses in user data storage,but also realize integrated virus processing,and further optimize the security defense effect of user big data.展开更多
In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) ba...In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.展开更多
Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (...Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.展开更多
Machining process data is the core of computer aided process planning application systems.It is also provides essen- tial content for product life cycle engineering.The character of CAPP that supports product LCE and ...Machining process data is the core of computer aided process planning application systems.It is also provides essen- tial content for product life cycle engineering.The character of CAPP that supports product LCE and virtual manufacturing is an- alyzed.The structure and content of machining process data concerning green manufacturing is also examined.A logic model of Machining Process Data has been built based on an object oriented approach,using UML technology and a physical model of machin- ing process data that utilizes XML technology.To realize the integration of design and process,an approach based on graph-based volume decomposition was apposed.Instead,to solve the problem of generation in the machining process,case-based reasoning and rule-based reasoning have been applied synthetically.Finally,the integration framework and interface that deal with the CAPP integration with CAD,CAM,PDM,and ERP are discussed.展开更多
In light of degradation of particle filtering and robust weakness in the utilization of single feature tracking,this paper presents a kernel particle filtering tracking method based on multi-feature integration.In thi...In light of degradation of particle filtering and robust weakness in the utilization of single feature tracking,this paper presents a kernel particle filtering tracking method based on multi-feature integration.In this paper,a new weight upgrading method is given out during kernel particle filtering at first,and then robust tracking is realized by integrating color and texture features under the framework of kernel particle filtering.Space histogram and integral histogram is adopted to calculate color and texture features respectively.These two calculation methods effectively overcome their own defectiveness,and meanwhile,improve the real timing for particle filtering.This algorithm has also improved sampling effectiveness,resolved redundant calculation for particle filtering and degradation of particles.Finally,the experiment for target tracking is realized by using the method under complicated background and shelter.Experiment results show that the method can reliably and accurately track target and deal with target sheltering situation properly.展开更多
Face detection is applied to many tasks such as auto focus control, surveillance, user interface, and face recognition. Processing speed and detection accuracy of the face detection have been improved continuously. Th...Face detection is applied to many tasks such as auto focus control, surveillance, user interface, and face recognition. Processing speed and detection accuracy of the face detection have been improved continuously. This paper describes a novel method of fast face detection with multi-scale window search free from image resizing. We adopt statistics of gradient images (SGI) as image features and append an overlapping cell array to improve detection accuracy. The SGI feature is scale invariant and insensitive to small difference of pixel value. These characteristics enable the multi-scale window search without image resizing. Experimental results show that processing speed of our method is 3.66 times faster than a conventional method, adopting HOG features combined to an SVM classifier, without accuracy degradation.展开更多
In allusion to the difficulty of integrating data with different models in integrating spatial information, the characteristics of raster structure, vector structure and mixed model were analyzed, and a hierarchical v...In allusion to the difficulty of integrating data with different models in integrating spatial information, the characteristics of raster structure, vector structure and mixed model were analyzed, and a hierarchical vector-raster integrative full feature model was put forward by integrating the advantage of vector and raster model and using the object-oriented method. The data structures of the four basic features, i.e. point, line, surface and solid, were described. An application was analyzed and described, and the characteristics of this model were described. In this model, all objects in the real world are divided into and described as features with hierarchy, and all the data are organized in vector. This model can describe data based on feature, field, network and other models, and avoid the disadvantage of inability to integrate data based on different models and perform spatial analysis on them in spatial information integration.展开更多
Three materials(agar,konjac glucomannan(KGM)andκ-carrageenan)were used to prepare ternary systems,i.e.,sol-gels and their dried composites conditioned at varied relative humidity(RH)(33%,54%and 75%).Combined methods,...Three materials(agar,konjac glucomannan(KGM)andκ-carrageenan)were used to prepare ternary systems,i.e.,sol-gels and their dried composites conditioned at varied relative humidity(RH)(33%,54%and 75%).Combined methods,e.g.,scanning electron microscopy,small-angle X-ray scattering,infrared spectroscopy(IR)and X-ray diffraction(XRD),were used to disclose howκ-carrageenan addition tailors the features of agar/KGM/κ-carrageenan ternary system.As affirmed by IR and XRD,the ternary systems withκ-carrageenan below 25%(agar/KGM/carrageenan,50:25:25,m/m)displayed proper component interactions,which increased the sol-gel transition temperature and the hardness of obtained gels.For instance,the ternary composites could show hardness about 3 to 4 times higher than that for binary counterpart.These gels were dehydrated to acquire ternary composites.Compared to agar/KGM composite,the ternary composites showed fewer crystallites and nanoscale orders,and newly-formed nanoscale structures from chain assembly.Such multi-scale structures,for composites withκ-carrageenan below 25%,showed weaker changes with RH,as revealed by especially morphologic and crystalline features.Consequently,the ternary composites with lessκ-carrageenan(below 25%)exhibited stabilized elongation at break and hydrophilicity at different RHs.This hints to us that agar/KGM/κ-carrageenan composite systems can display series applications with improved features,e.g.,increased sol-gel transition point.展开更多
A system for classifying four basic table tennis strokes using wearable devices and deep learning networks is proposed in this study.The wearable device consisted of a six-axis sensor,Raspberry Pi 3,and a power bank.M...A system for classifying four basic table tennis strokes using wearable devices and deep learning networks is proposed in this study.The wearable device consisted of a six-axis sensor,Raspberry Pi 3,and a power bank.Multiple kernel sizes were used in convolutional neural network(CNN)to evaluate their performance for extracting features.Moreover,a multiscale CNN with two kernel sizes was used to perform feature fusion at different scales in a concatenated manner.The CNN achieved recognition of the four table tennis strokes.Experimental data were obtained from20 research participants who wore sensors on the back of their hands while performing the four table tennis strokes in a laboratory environment.The data were collected to verify the performance of the proposed models for wearable devices.Finally,the sensor and multi-scale CNN designed in this study achieved accuracy and F1 scores of 99.58%and 99.16%,respectively,for the four strokes.The accuracy for five-fold cross validation was 99.87%.This result also shows that the multi-scale convolutional neural network has better robustness after fivefold cross validation.展开更多
Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead t...Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.展开更多
Feature recognition aims at extracting manufacturing features with geometrical information from solid model and is considered to be an efficient way of changing the interactive NC machining programming mode.Existing r...Feature recognition aims at extracting manufacturing features with geometrical information from solid model and is considered to be an efficient way of changing the interactive NC machining programming mode.Existing recognition methods have some disadvantages in practical applications.They can essentially handle prismatic components with regular shapes and are difficult to recognize the intersecting features and curved surfaces.Besides,the robustness of them is not strong enough.A new feature recognition approach is proposed based on the analysis of aircraft integral panels' geometry and machining characteristics.In this approach,the aircraft integral panel is divided into a number of local machining domains.The machining domains are extracted and recognized first by finding the principal face of machining domain and extracting the sides around the principal face.Then the machining domains are divided into various features in terms of the face type.The main sections of the proposed method are presented including the definition,classification and structure of machining domain,the relationship between machining domain and principal face loop,the rules of machining domains recognition,and the algorithm of machining feature recognition.In addition,a robotic feature recognition module is developed for aircraft integral panels and tested with several panels.Test results show that the strategy presented is robust and valid.Features extracted can be post processed and linked to various downstream applications.The approach is able to solve the difficulties in recognizing the aircraft integral panel's features and automatic obtaining the machining zone in NC programming,and can be used to further develop the automatic programming of NC machining.展开更多
In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact t...In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact that only a relatively low number of distinct values of a particular visual feature is present in most images. To extract color feature and build indices into our image database we take into consideration factors such as human color perception and perceptual range, and the image is partitioned into a set of regions by using a simple classifying scheme. The compact color feature vector and the spatial color histogram, which are extracted from the seqmented image region, are used for representing the color and spatial information in the image. We have also developed the region-based distance measures to compare the similarity of two images. Extensive tests on a large image collection were conducted to demonstrate the effectiveness of the proposed approach.展开更多
A blank panel design algorithm based on feature mapping methods for integral wing skin panels with supercritical airfoil surface is presented.The model of a wing panel is decomposed into features,and features of the p...A blank panel design algorithm based on feature mapping methods for integral wing skin panels with supercritical airfoil surface is presented.The model of a wing panel is decomposed into features,and features of the panel are decomposed into information of location,direction,dimension and Boolean types.Features are mapped into the plane through optimal surface development algorithm.The plane panel is modeled by rebuilding the mapped features.Blanks of shot-peen forming panels are designed to identify the effectiveness of the methods.展开更多
In industrial process control systems,there is overwhelming evidence corroborating the notion that economic or technical limitations result in some key variables that are very difficult to measure online.The data-driv...In industrial process control systems,there is overwhelming evidence corroborating the notion that economic or technical limitations result in some key variables that are very difficult to measure online.The data-driven soft sensor is an effective solution because it provides a reliable and stable online estimation of such variables.This paper employs a deep neural network with multiscale feature extraction layers to build soft sensors,which are applied to the benchmarked Tennessee-Eastman process(TEP)and a real wind farm case.The comparison of modelling results demonstrates that the multiscale feature extraction layers have the following advantages over other methods.First,the multiscale feature extraction layers significantly reduce the number of parameters compared to the other deep neural networks.Second,the multiscale feature extraction layers can powerfully extract dataset characteristics.Finally,the multiscale feature extraction layers with fully considered historical measurements can contain richer useful information and improved representation compared to traditional data-driven models.展开更多
Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usuall...Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are neglected.It is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains unsolved.Meanwhile,the channel information in high-level feature is also not well mined.Inevitably,the performance of grasp detection is degraded.To solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle residual.Both low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature fusion.Such a hierarchical fusion guarantees the quality of grasp prediction.Furthermore,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective branches.By such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the network.Besides,an information enhancement module is added before the encoder to reinforce input information.The proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.展开更多
基金supported in part by the National Natural Science Foundation of China(Grant No.62062003)Natural Science Foundation of Ningxia(Grant No.2023AAC03293).
文摘Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.
文摘Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.
基金supported by the National Key Research and Development Project(No.2020YFC1512000)the General Projects of Key R&D Programs in Shaanxi Province(No.2020GY-060)Xi’an Science&Technology Project(No.2020KJRC 0126)。
文摘With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.
基金This work was supported in part by the National Natural Science Foundation of China(Grant#:82260362)in part by the National Key R&D Program of China(Grant#:2021ZD0111000)+1 种基金in part by the Key R&D Project of Hainan Province(Grant#:ZDYF2021SHFZ243)in part by the Major Science and Technology Project of Haikou(Grant#:2020-009).
文摘The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.
基金This research was supported by the National Natural Science Foundation of China No.62276086the National Key R&D Program of China No.2022YFD2000100Zhejiang Provincial Natural Science Foundation of China under Grant No.LTGN23D010002.
文摘Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often handpicked and need more delicate operations in intelligent picking machines.Compared with traditional image processing techniques,deep learning models have stronger feature extraction capabilities,and better generalization and are more suitable for practical tea shoot harvesting.However,current research mostly focuses on shoot detection and cannot directly accomplish end-to-end shoot segmentation tasks.We propose a tea shoot instance segmentation model based on multi-scale mixed attention(Mask2FusionNet)using a dataset from the tea garden in Hangzhou.We further analyzed the characteristics of the tea shoot dataset,where the proportion of small to medium-sized targets is 89.9%.Our algorithm is compared with several mainstream object segmentation algorithms,and the results demonstrate that our model achieves an accuracy of 82%in recognizing the tea shoots,showing a better performance compared to other models.Through ablation experiments,we found that ResNet50,PointRend strategy,and the Feature Pyramid Network(FPN)architecture can improve performance by 1.6%,1.4%,and 2.4%,respectively.These experiments demonstrated that our proposed multi-scale and point selection strategy optimizes the feature extraction capability for overlapping small targets.The results indicate that the proposed Mask2FusionNet model can perform the shoot segmentation in unstructured environments,realizing the individual distinction of tea shoots,and complete extraction of the shoot edge contours with a segmentation accuracy of 82.0%.The research results can provide algorithmic support for the segmentation and intelligent harvesting of premium tea shoots at different scales.
基金This work was supported by the National Natural Science Foundation of China(U2133208,U20A20161).
文摘With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The network security environment in the era of big data presents the characteristics of large amounts of data,high diversity,and high real-time requirements.Traditional security defense methods and tools have been unable to cope with the complex and changing network security threats.This paper proposes a machine-learning security defense algorithm based on metadata association features.Emphasize control over unauthorized users through privacy,integrity,and availability.The user model is established and the mapping between the user model and the metadata of the data source is generated.By analyzing the user model and its corresponding mapping relationship,the query of the user model can be decomposed into the query of various heterogeneous data sources,and the integration of heterogeneous data sources based on the metadata association characteristics can be realized.Define and classify customer information,automatically identify and perceive sensitive data,build a behavior audit and analysis platform,analyze user behavior trajectories,and complete the construction of a machine learning customer information security defense system.The experimental results show that when the data volume is 5×103 bit,the data storage integrity of the proposed method is 92%.The data accuracy is 98%,and the success rate of data intrusion is only 2.6%.It can be concluded that the data storage method in this paper is safe,the data accuracy is always at a high level,and the data disaster recovery performance is good.This method can effectively resist data intrusion and has high air traffic control security.It can not only detect all viruses in user data storage,but also realize integrated virus processing,and further optimize the security defense effect of user big data.
基金supported by the National Natural Science Foundation of China (62271255,61871218)the Fundamental Research Funds for the Central University (3082019NC2019002)+1 种基金the Aeronautical Science Foundation (ASFC-201920007002)the Program of Remote Sensing Intelligent Monitoring and Emergency Services for Regional Security Elements。
文摘In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.
文摘Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.
文摘Machining process data is the core of computer aided process planning application systems.It is also provides essen- tial content for product life cycle engineering.The character of CAPP that supports product LCE and virtual manufacturing is an- alyzed.The structure and content of machining process data concerning green manufacturing is also examined.A logic model of Machining Process Data has been built based on an object oriented approach,using UML technology and a physical model of machin- ing process data that utilizes XML technology.To realize the integration of design and process,an approach based on graph-based volume decomposition was apposed.Instead,to solve the problem of generation in the machining process,case-based reasoning and rule-based reasoning have been applied synthetically.Finally,the integration framework and interface that deal with the CAPP integration with CAD,CAM,PDM,and ERP are discussed.
基金Sponsored by Natural Science Foundation of Heilongjiang Province of China(Grant No.QC2001C060)the Science and Technology Research Projectsin Office of Education of Heilongjiang province(Grant No.11531307)
文摘In light of degradation of particle filtering and robust weakness in the utilization of single feature tracking,this paper presents a kernel particle filtering tracking method based on multi-feature integration.In this paper,a new weight upgrading method is given out during kernel particle filtering at first,and then robust tracking is realized by integrating color and texture features under the framework of kernel particle filtering.Space histogram and integral histogram is adopted to calculate color and texture features respectively.These two calculation methods effectively overcome their own defectiveness,and meanwhile,improve the real timing for particle filtering.This algorithm has also improved sampling effectiveness,resolved redundant calculation for particle filtering and degradation of particles.Finally,the experiment for target tracking is realized by using the method under complicated background and shelter.Experiment results show that the method can reliably and accurately track target and deal with target sheltering situation properly.
文摘Face detection is applied to many tasks such as auto focus control, surveillance, user interface, and face recognition. Processing speed and detection accuracy of the face detection have been improved continuously. This paper describes a novel method of fast face detection with multi-scale window search free from image resizing. We adopt statistics of gradient images (SGI) as image features and append an overlapping cell array to improve detection accuracy. The SGI feature is scale invariant and insensitive to small difference of pixel value. These characteristics enable the multi-scale window search without image resizing. Experimental results show that processing speed of our method is 3.66 times faster than a conventional method, adopting HOG features combined to an SVM classifier, without accuracy degradation.
基金Project (40473029) supported bythe National Natural Science Foundation of China project (04JJ3046) supported bytheNatural Science Foundation of Hunan Province , China
文摘In allusion to the difficulty of integrating data with different models in integrating spatial information, the characteristics of raster structure, vector structure and mixed model were analyzed, and a hierarchical vector-raster integrative full feature model was put forward by integrating the advantage of vector and raster model and using the object-oriented method. The data structures of the four basic features, i.e. point, line, surface and solid, were described. An application was analyzed and described, and the characteristics of this model were described. In this model, all objects in the real world are divided into and described as features with hierarchy, and all the data are organized in vector. This model can describe data based on feature, field, network and other models, and avoid the disadvantage of inability to integrate data based on different models and perform spatial analysis on them in spatial information integration.
基金the National Natural Science Foundation of China(32172240)BL19U2 beamline of National Facility for Protein Science in Shanghai(NFPS)at Shanghai Synchrotron Radiation Facility,for their assistance during data collection。
文摘Three materials(agar,konjac glucomannan(KGM)andκ-carrageenan)were used to prepare ternary systems,i.e.,sol-gels and their dried composites conditioned at varied relative humidity(RH)(33%,54%and 75%).Combined methods,e.g.,scanning electron microscopy,small-angle X-ray scattering,infrared spectroscopy(IR)and X-ray diffraction(XRD),were used to disclose howκ-carrageenan addition tailors the features of agar/KGM/κ-carrageenan ternary system.As affirmed by IR and XRD,the ternary systems withκ-carrageenan below 25%(agar/KGM/carrageenan,50:25:25,m/m)displayed proper component interactions,which increased the sol-gel transition temperature and the hardness of obtained gels.For instance,the ternary composites could show hardness about 3 to 4 times higher than that for binary counterpart.These gels were dehydrated to acquire ternary composites.Compared to agar/KGM composite,the ternary composites showed fewer crystallites and nanoscale orders,and newly-formed nanoscale structures from chain assembly.Such multi-scale structures,for composites withκ-carrageenan below 25%,showed weaker changes with RH,as revealed by especially morphologic and crystalline features.Consequently,the ternary composites with lessκ-carrageenan(below 25%)exhibited stabilized elongation at break and hydrophilicity at different RHs.This hints to us that agar/KGM/κ-carrageenan composite systems can display series applications with improved features,e.g.,increased sol-gel transition point.
基金supporting of the Ministry of Science and Technology MOST(Grant No.MOST 108–2221-E-150–022-MY3,MOST 110–2634-F-019–002)the National Taiwan Ocean University,China.
文摘A system for classifying four basic table tennis strokes using wearable devices and deep learning networks is proposed in this study.The wearable device consisted of a six-axis sensor,Raspberry Pi 3,and a power bank.Multiple kernel sizes were used in convolutional neural network(CNN)to evaluate their performance for extracting features.Moreover,a multiscale CNN with two kernel sizes was used to perform feature fusion at different scales in a concatenated manner.The CNN achieved recognition of the four table tennis strokes.Experimental data were obtained from20 research participants who wore sensors on the back of their hands while performing the four table tennis strokes in a laboratory environment.The data were collected to verify the performance of the proposed models for wearable devices.Finally,the sensor and multi-scale CNN designed in this study achieved accuracy and F1 scores of 99.58%and 99.16%,respectively,for the four strokes.The accuracy for five-fold cross validation was 99.87%.This result also shows that the multi-scale convolutional neural network has better robustness after fivefold cross validation.
基金Supported by Open Project of the Ministry of Industry and Information Technology Key Laboratory of Performance and Reliability Testing and Evaluation for Basic Software and Hardware。
文摘Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.
文摘Feature recognition aims at extracting manufacturing features with geometrical information from solid model and is considered to be an efficient way of changing the interactive NC machining programming mode.Existing recognition methods have some disadvantages in practical applications.They can essentially handle prismatic components with regular shapes and are difficult to recognize the intersecting features and curved surfaces.Besides,the robustness of them is not strong enough.A new feature recognition approach is proposed based on the analysis of aircraft integral panels' geometry and machining characteristics.In this approach,the aircraft integral panel is divided into a number of local machining domains.The machining domains are extracted and recognized first by finding the principal face of machining domain and extracting the sides around the principal face.Then the machining domains are divided into various features in terms of the face type.The main sections of the proposed method are presented including the definition,classification and structure of machining domain,the relationship between machining domain and principal face loop,the rules of machining domains recognition,and the algorithm of machining feature recognition.In addition,a robotic feature recognition module is developed for aircraft integral panels and tested with several panels.Test results show that the strategy presented is robust and valid.Features extracted can be post processed and linked to various downstream applications.The approach is able to solve the difficulties in recognizing the aircraft integral panel's features and automatic obtaining the machining zone in NC programming,and can be used to further develop the automatic programming of NC machining.
文摘In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact that only a relatively low number of distinct values of a particular visual feature is present in most images. To extract color feature and build indices into our image database we take into consideration factors such as human color perception and perceptual range, and the image is partitioned into a set of regions by using a simple classifying scheme. The compact color feature vector and the spatial color histogram, which are extracted from the seqmented image region, are used for representing the color and spatial information in the image. We have also developed the region-based distance measures to compare the similarity of two images. Extensive tests on a large image collection were conducted to demonstrate the effectiveness of the proposed approach.
文摘A blank panel design algorithm based on feature mapping methods for integral wing skin panels with supercritical airfoil surface is presented.The model of a wing panel is decomposed into features,and features of the panel are decomposed into information of location,direction,dimension and Boolean types.Features are mapped into the plane through optimal surface development algorithm.The plane panel is modeled by rebuilding the mapped features.Blanks of shot-peen forming panels are designed to identify the effectiveness of the methods.
基金supported by National Natural Science Foundation of China(No.61873142)the Science and Technology Research Program of the Chongqing Municipal Education Commission,China(Nos.KJZD-K202201901,KJQN202201109,KJQN202101904,KJQN202001903 and CXQT21035)+2 种基金the Scientific Research Foundation of Chongqing University of Technology,China(No.2019ZD76)the Scientific Research Foundation of Chongqing Institute of Engineering,China(No.2020xzky05)the Chongqing Municipal Natural Science Foundation,China(No.cstc2020jcyj-msxmX0666).
文摘In industrial process control systems,there is overwhelming evidence corroborating the notion that economic or technical limitations result in some key variables that are very difficult to measure online.The data-driven soft sensor is an effective solution because it provides a reliable and stable online estimation of such variables.This paper employs a deep neural network with multiscale feature extraction layers to build soft sensors,which are applied to the benchmarked Tennessee-Eastman process(TEP)and a real wind farm case.The comparison of modelling results demonstrates that the multiscale feature extraction layers have the following advantages over other methods.First,the multiscale feature extraction layers significantly reduce the number of parameters compared to the other deep neural networks.Second,the multiscale feature extraction layers can powerfully extract dataset characteristics.Finally,the multiscale feature extraction layers with fully considered historical measurements can contain richer useful information and improved representation compared to traditional data-driven models.
基金This work was supported by the National Natural Science Foundation of China(Nos.62073322 and 61633020)the CIE-Tencent Robotics X Rhino-Bird Focused Research Program(No.2022-07)the Beijing Natural Science Foundation(No.2022MQ05).
文摘Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are neglected.It is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains unsolved.Meanwhile,the channel information in high-level feature is also not well mined.Inevitably,the performance of grasp detection is degraded.To solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle residual.Both low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature fusion.Such a hierarchical fusion guarantees the quality of grasp prediction.Furthermore,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective branches.By such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the network.Besides,an information enhancement module is added before the encoder to reinforce input information.The proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.