Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of intersp...Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.展开更多
Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and text...Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.展开更多
Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain les...Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain less information.Many current methods,particularly those based on Feature Pyramid Network(FPN),address this challenge by leveraging multi-scale feature fusion.However,existing FPN-based methods often suffer from inadequate feature fusion due to varying resolutions across different layers,leading to suboptimal small object detection.To address this problem,we propose the Two-layerAttention Feature Pyramid Network(TA-FPN),featuring two key modules:the Two-layer Attention Module(TAM)and the Small Object Detail Enhancement Module(SODEM).TAM uses the attention module to make the network more focused on the semantic information of the object and fuse it to the lower layer,so that each layer contains similar semantic information,to alleviate the problem of small object information being submerged due to semantic gaps between different layers.At the same time,SODEM is introduced to strengthen the local features of the object,suppress background noise,enhance the information details of the small object,and fuse the enhanced features to other feature layers to ensure that each layer is rich in small object information,to improve small object detection accuracy.Our extensive experiments on challenging datasets such as Microsoft Common Objects inContext(MSCOCO)and Pattern Analysis Statistical Modelling and Computational Learning,Visual Object Classes(PASCAL VOC)demonstrate the validity of the proposedmethod.Experimental results show a significant improvement in small object detection accuracy compared to state-of-theart detectors.展开更多
Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacillicul...Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.展开更多
Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding pro...Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.展开更多
Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones...Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.展开更多
Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm f...Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm for infrared images,F-YOLOv8,is proposed.First,a spatial-to-depth network replaces the traditional backbone network's strided convolution or pooling layer.At the same time,it combines with the channel attention mechanism so that the neural network focuses on the channels with large weight values to better extract low-resolution image feature information;then an improved feature pyramid network of lightweight bidirectional feature pyramid network(L-BiFPN)is proposed,which can efficiently fuse features of different scales.In addition,a loss function of insertion of union based on the minimum point distance(MPDIoU)is introduced for bounding box regression,which obtains faster convergence speed and more accurate regression results.Experimental results on the FLIR dataset show that the improved algorithm can accurately detect infrared road targets in real time with 3%and 2.2%enhancement in mean average precision at 50%IoU(mAP50)and mean average precision at 50%—95%IoU(mAP50-95),respectively,and 38.1%,37.3%and 16.9%reduction in the number of model parameters,the model weight,and floating-point operations per second(FLOPs),respectively.To further demonstrate the detection capability of the improved algorithm,it is tested on the public dataset PASCAL VOC,and the results show that F-YOLO has excellent generalized detection performance.展开更多
In order to identify the development characteristics of fracture network in tight conglomerate reservoir of Mahu after hydraulic fracturing,a hydraulic fracturing test site was set up in the second and third members o...In order to identify the development characteristics of fracture network in tight conglomerate reservoir of Mahu after hydraulic fracturing,a hydraulic fracturing test site was set up in the second and third members of Triassic Baikouquan Formation(T1b2 and T1b3)in Ma-131 well area,which learned from the successful experience of hydraulic fracturing test sites in North America(HFTS-1).Twelve horizontal wells and a high-angle coring well MaJ02 were drilled.The orientation,connection,propagation law and major controlling factors of hydraulic fractures were analyzed by comparing results of CT scans,imaging logs,direct observation of cores from Well MaJ02,and combined with tracer monitoring data.Results indicate that:(1)Two types of fractures have developed by hydraulic fracturing,i.e.tensile fractures and shear fractures.Tensile fractures are approximately parallel to the direction of the maximum horizontal principal stress,and propagate less than 50 m from perforation clusters.Shear fractures are distributed among tensile fractures and mainly in the strike-slip mode due to the induced stress field among tensile fractures,and some of them are in conjugated pairs.Overall,tensile fractures alternate with shear fractures,with shear fractures dominated and activated after tensile ones.(2)Tracer monitoring results indicate that communication between wells was prevalent in the early stage of production,and the static pressure in the fracture gradually decreased and the connectivity between wells reduced as production progressed.(3)Density of hydraulic fractures is mainly affected by the lithology and fracturing parameters,which is smaller in the mudstone than the conglomerate.Larger fracturing scale and smaller cluster spacing lead to a higher fracture density,which are important directions to improve the well productivity.展开更多
To improve design accuracy and reliability of structures,this study solves the uncertain natural frequencies with consideration for geometric nonlinearity and structural uncertainty.Frequencies of the laminated plate ...To improve design accuracy and reliability of structures,this study solves the uncertain natural frequencies with consideration for geometric nonlinearity and structural uncertainty.Frequencies of the laminated plate with all four edges clamped(CCCC)are derived based on Navier's method and Galerkin's method.The novelty of the current work is that the number of unknowns in the displacement field model of a CCCC plate with free midsurface(CCCC-2 plate)is only three compared with four or five in cases of other exposed methods.The present analytical method is proved to be accurate and reliable by comparing linear natural frequencies and nonlinear natural frequencies with other models available in the open literature.Furthermore,a novel method for analyzing effects of mean values and tolerance zones of uncertain structural parameters on random frequencies is proposed based on a self-developed Multiscale Feature Extraction and Fusion Network(MFEFN)system.Compared with a direct Monte Carlo Simulation(MCS),the MFEFNbased procedure significantly reduces the calculation burden with a guarantee of accuracy.Our research provides a method to calculate nonlinear natural frequencies under two boundary conditions and presentes a surrogate model to predict frequencies for accuracy analysis and optimization design.展开更多
Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial co...Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial configuration of a human–object pair in order to learn the action linking the human and object in the pair.We argue that such a paradigm of pairwise feature extraction and action inference can be applied not only at the whole human and object instance level,but also at the part level at which a body part interacts with an object,and at the semantic level by considering the semantic label of an object along with human appearance and human–object spatial configuration,to infer the action.We thus propose a multi-level pairwise feature network(PFNet)for detecting human–object interactions.The network consists of three parallel streams to characterize HOI utilizing pairwise features at the above three levels;the three streams are finally fused to give the action prediction.Extensive experiments show that our proposed PFNet outperforms other state-of-the-art methods on the VCOCO dataset and achieves comparable results to the state-of-the-art on the HICO-DET dataset.展开更多
With the rapid growth of e-commerce, customers increasingly write online reviews of the product they purchase. These customer reviews are one of the most valuable sources of information affecting selection of products...With the rapid growth of e-commerce, customers increasingly write online reviews of the product they purchase. These customer reviews are one of the most valuable sources of information affecting selection of products or services. Summarizing these customer reviews is becoming an interesting area of research, inspiring researchers to develop a more condensed, concise summarization for users. However, most of the current efforts at summarization are based on general product features without feature＇s relationship. As a result, these summaries either ignore feedback from customers or do a poor job of reflecting the opinions expressed in customer reviews. To remedy this summarization shortcoming, we propose a feature network-driven quadrant mapping that captures and incorporates opinions from customer reviews. Our focus is on construction of a feature network, which is based on co-occurrence and sematic similarities, and a quadrant display showing the opinions polarity of feature groups. Moreover, the proposed approach involves clustering similar product features, and thus, it is different from standard text summarization based on abstraction and extraction. The summarized results can help customers better understand the overall opinions about a product.展开更多
With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and ...With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.展开更多
In this paper,based on a bidirectional parallel multi-branch feature pyramid network(BPMFPN),a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swa...In this paper,based on a bidirectional parallel multi-branch feature pyramid network(BPMFPN),a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles(UAVs).First,the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers.Next,the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance.In order to validate the effectiveness of the proposed algorithm,experiments are conducted on four datasets.For the PASCAL VOC dataset,the proposed algorithm achieves the mean average precision(mAP)of 85.4 on the VOC 2007 test set.With regard to the detection in optical remote sensing(DIOR)dataset,the proposed algorithm achieves 73.9 mAP.For vehicle detection in aerial imagery(VEDAI)dataset,the detection accuracy of small land vehicle(slv)targets reaches 97.4 mAP.For unmanned aerial vehicle detection and tracking(UAVDT)dataset,the proposed BPMFPN Det achieves the mAP of 48.75.Compared with the previous state-of-the-art methods,the results obtained by the proposed algorithm are more competitive.The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.展开更多
Due to the widespread use of the Internet,customer information is vulnerable to computer systems attack,which brings urgent need for the intrusion detection technology.Recently,network intrusion detection has been one...Due to the widespread use of the Internet,customer information is vulnerable to computer systems attack,which brings urgent need for the intrusion detection technology.Recently,network intrusion detection has been one of the most important technologies in network security detection.The accuracy of network intrusion detection has reached higher accuracy so far.However,these methods have very low efficiency in network intrusion detection,even the most popular SOM neural network method.In this paper,an efficient and fast network intrusion detection method was proposed.Firstly,the fundamental of the two different methods are introduced respectively.Then,the selforganizing feature map neural network based on K-means clustering(KSOM)algorithms was presented to improve the efficiency of network intrusion detection.Finally,the NSLKDD is used as network intrusion data set to demonstrate that the KSOM method can significantly reduce the number of clustering iteration than SOM method without substantially affecting the clustering results and the accuracy is much higher than Kmeans method.The Experimental results show that our method can relatively improve the accuracy of network intrusion and significantly reduce the number of clustering iteration.展开更多
In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid...In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid network(FPN)and deconvolutional single shot detector(DSSD),where the bottom layer of the feature pyramid network relies on the top layer,NFPN builds the feature pyramid network with no connections between the upper and lower layers.That is,it only fuses shallow features on similar scales.NFPN is highly portable and can be embedded in many models to further boost performance.Extensive experiments on PASCAL VOC 2007,2012,and COCO datasets demonstrate that the NFPN-based SSD without intricate tricks can exceed the DSSD model in terms of detection accuracy and inference speed,especially for small objects,e.g.,4%to 5%higher mAP(mean average precision)than SSD,and 2%to 3%higher mAP than DSSD.On VOC 2007 test set,the NFPN-based SSD with 300×300 input reaches 79.4%mAP at 34.6 frame/s,and the mAP can raise to 82.9%after using the multi-scale testing strategy.展开更多
Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area...Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area is important for breeding area planning,production value estimation,ecological survey,and storm surge prevention.However,as the aquaculture area expands,the seawater background becomes increasingly complex and spectral characteristics differ dramatically,making it difficult to determine the aquaculture area.In this study,we used a high-resolution remote-sensing satellite GF-2 image to introduce a deep-learning Richer Convolutional Features(RCF)network model to extract the aquaculture area.Then we used the density of aquaculture as an assessment index to assess the vulnerability of aquaculture areas in Sanduao.The results demonstrate that this method does not require land and water separation of the area in advance,and good extraction can be achieved in the areas with more sediment and waves,with an extraction accuracy>93%,which is suitable for large-scale aquaculture area extraction.Vulnerability assessment results indicate that the density of aquaculture in the eastern part of Sanduao is considerably high,reaching a higher vulnerability level than other parts.展开更多
Deep learning for topology optimization has been extensively studied to reduce the cost of calculation in recent years.However,the loss function of the above method is mainly based on pixel-wise errors from the image ...Deep learning for topology optimization has been extensively studied to reduce the cost of calculation in recent years.However,the loss function of the above method is mainly based on pixel-wise errors from the image perspective,which cannot embed the physical knowledge of topology optimization.Therefore,this paper presents an improved deep learning model to alleviate the above difficulty effectively.The feature pyramid network(FPN),a kind of deep learning model,is trained to learn the inherent physical law of topology optimization itself,of which the loss function is composed of pixel-wise errors and physical constraints.Since the calculation of physical constraints requires finite element analysis(FEA)with high calculating costs,the strategy of adjusting the time when physical constraints are added is proposed to achieve the balance between the training cost and the training effect.Then,two classical topology optimization problems are investigated to verify the effectiveness of the proposed method.The results show that the developed model using a small number of samples can quickly obtain the optimization structure without any iteration,which has not only high pixel-wise accuracy but also good physical performance.展开更多
There is instability in the distributed energy storage cloud group end region on the power grid side.In order to avoid large-scale fluctuating charging and discharging in the power grid environment and make the capaci...There is instability in the distributed energy storage cloud group end region on the power grid side.In order to avoid large-scale fluctuating charging and discharging in the power grid environment and make the capacitor components showa continuous and stable charging and discharging state,a hierarchical time-sharing configuration algorithm of distributed energy storage cloud group end region on the power grid side based on multi-scale and multi feature convolution neural network is proposed.Firstly,a voltage stability analysis model based onmulti-scale and multi feature convolution neural network is constructed,and the multi-scale and multi feature convolution neural network is optimized based on Self-OrganizingMaps(SOM)algorithm to analyze the voltage stability of the cloud group end region of distributed energy storage on the grid side under the framework of credibility.According to the optimal scheduling objectives and network size,the distributed robust optimal configuration control model is solved under the framework of coordinated optimal scheduling at multiple time scales;Finally,the time series characteristics of regional power grid load and distributed generation are analyzed.According to the regional hierarchical time-sharing configuration model of“cloud”,“group”and“end”layer,the grid side distributed energy storage cloud group end regional hierarchical time-sharing configuration algorithm is realized.The experimental results show that after applying this algorithm,the best grid side distributed energy storage configuration scheme can be determined,and the stability of grid side distributed energy storage cloud group end region layered timesharing configuration can be improved.展开更多
Accurate pancreas segmentation is critical for the diagnosis and management of diseases of the pancreas. It is challenging to precisely delineate pancreas due to the highly variations in volume, shape and location. In...Accurate pancreas segmentation is critical for the diagnosis and management of diseases of the pancreas. It is challenging to precisely delineate pancreas due to the highly variations in volume, shape and location. In recent years, coarse-to-fine methods have been widely used to alleviate class imbalance issue and improve pancreas segmentation accuracy. However,cascaded methods could be computationally intensive and the refined results are significantly dependent on the performance of its coarse segmentation results. To balance the segmentation accuracy and computational efficiency, we propose a Discriminative Feature Attention Network for pancreas segmentation, to effectively highlight pancreas features and improve segmentation accuracy without explicit pancreas location. The final segmentation is obtained by applying a simple yet effective post-processing step. Two experiments on both public NIH pancreas CT dataset and abdominal BTCV multi-organ dataset are individually conducted to show the effectiveness of our method for 2 D pancreas segmentation. We obtained average Dice Similarity Coefficient(DSC) of 82.82±6.09%, average Jaccard Index(JI) of 71.13± 8.30% and average Symmetric Average Surface Distance(ASD) of 1.69 ± 0.83 mm on the NIH dataset. Compared to the existing deep learning-based pancreas segmentation methods, our experimental results achieve the best average DSC and JI value.展开更多
In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training cos...In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.展开更多
基金funded by Liaoning Provincial Department of Education Project,Award number JYTMS20230418.
文摘Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.
基金Shenzhen Institute of Artificial Intelligence and Robotics for Society,Grant/Award Number:AC01202201003-02GuangDong Basic and Applied Basic Research Foundation,Grant/Award Number:2024A1515010252Longgang District Shenzhen's“Ten Action Plan”for Supporting Innovation Projects,Grant/Award Number:LGKCSDPT2024002。
文摘Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.
文摘Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain less information.Many current methods,particularly those based on Feature Pyramid Network(FPN),address this challenge by leveraging multi-scale feature fusion.However,existing FPN-based methods often suffer from inadequate feature fusion due to varying resolutions across different layers,leading to suboptimal small object detection.To address this problem,we propose the Two-layerAttention Feature Pyramid Network(TA-FPN),featuring two key modules:the Two-layer Attention Module(TAM)and the Small Object Detail Enhancement Module(SODEM).TAM uses the attention module to make the network more focused on the semantic information of the object and fuse it to the lower layer,so that each layer contains similar semantic information,to alleviate the problem of small object information being submerged due to semantic gaps between different layers.At the same time,SODEM is introduced to strengthen the local features of the object,suppress background noise,enhance the information details of the small object,and fuse the enhanced features to other feature layers to ensure that each layer is rich in small object information,to improve small object detection accuracy.Our extensive experiments on challenging datasets such as Microsoft Common Objects inContext(MSCOCO)and Pattern Analysis Statistical Modelling and Computational Learning,Visual Object Classes(PASCAL VOC)demonstrate the validity of the proposedmethod.Experimental results show a significant improvement in small object detection accuracy compared to state-of-theart detectors.
文摘Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.
基金the National Natural Science Foundation of China(No.12064027)。
文摘Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.
基金supported by the National Natural Science Foundation of China(Nos.62276204 and 62203343)the Fundamental Research Funds for the Central Universities(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470).
文摘Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.
基金supported by the National Natural Science Foundation of China(No.62103298)。
文摘Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes,an improved you only look once version 8(YOLOv8)object detection algorithm for infrared images,F-YOLOv8,is proposed.First,a spatial-to-depth network replaces the traditional backbone network's strided convolution or pooling layer.At the same time,it combines with the channel attention mechanism so that the neural network focuses on the channels with large weight values to better extract low-resolution image feature information;then an improved feature pyramid network of lightweight bidirectional feature pyramid network(L-BiFPN)is proposed,which can efficiently fuse features of different scales.In addition,a loss function of insertion of union based on the minimum point distance(MPDIoU)is introduced for bounding box regression,which obtains faster convergence speed and more accurate regression results.Experimental results on the FLIR dataset show that the improved algorithm can accurately detect infrared road targets in real time with 3%and 2.2%enhancement in mean average precision at 50%IoU(mAP50)and mean average precision at 50%—95%IoU(mAP50-95),respectively,and 38.1%,37.3%and 16.9%reduction in the number of model parameters,the model weight,and floating-point operations per second(FLOPs),respectively.To further demonstrate the detection capability of the improved algorithm,it is tested on the public dataset PASCAL VOC,and the results show that F-YOLO has excellent generalized detection performance.
基金Supported by the National Natural Science Foundation of China(52274051)CNPC-China University of Petroleum(Beijing)Strategic Cooperative Project(ZLZX2020-01).
文摘In order to identify the development characteristics of fracture network in tight conglomerate reservoir of Mahu after hydraulic fracturing,a hydraulic fracturing test site was set up in the second and third members of Triassic Baikouquan Formation(T1b2 and T1b3)in Ma-131 well area,which learned from the successful experience of hydraulic fracturing test sites in North America(HFTS-1).Twelve horizontal wells and a high-angle coring well MaJ02 were drilled.The orientation,connection,propagation law and major controlling factors of hydraulic fractures were analyzed by comparing results of CT scans,imaging logs,direct observation of cores from Well MaJ02,and combined with tracer monitoring data.Results indicate that:(1)Two types of fractures have developed by hydraulic fracturing,i.e.tensile fractures and shear fractures.Tensile fractures are approximately parallel to the direction of the maximum horizontal principal stress,and propagate less than 50 m from perforation clusters.Shear fractures are distributed among tensile fractures and mainly in the strike-slip mode due to the induced stress field among tensile fractures,and some of them are in conjugated pairs.Overall,tensile fractures alternate with shear fractures,with shear fractures dominated and activated after tensile ones.(2)Tracer monitoring results indicate that communication between wells was prevalent in the early stage of production,and the static pressure in the fracture gradually decreased and the connectivity between wells reduced as production progressed.(3)Density of hydraulic fractures is mainly affected by the lithology and fracturing parameters,which is smaller in the mudstone than the conglomerate.Larger fracturing scale and smaller cluster spacing lead to a higher fracture density,which are important directions to improve the well productivity.
基金the research project funded by the Fundamental Research Funds for the Central Universities(No.HIT.OCEP.2024038)the National Natural Science Foundation of China(No.52372351)the State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster,China(No.MS02240107)。
文摘To improve design accuracy and reliability of structures,this study solves the uncertain natural frequencies with consideration for geometric nonlinearity and structural uncertainty.Frequencies of the laminated plate with all four edges clamped(CCCC)are derived based on Navier's method and Galerkin's method.The novelty of the current work is that the number of unknowns in the displacement field model of a CCCC plate with free midsurface(CCCC-2 plate)is only three compared with four or five in cases of other exposed methods.The present analytical method is proved to be accurate and reliable by comparing linear natural frequencies and nonlinear natural frequencies with other models available in the open literature.Furthermore,a novel method for analyzing effects of mean values and tolerance zones of uncertain structural parameters on random frequencies is proposed based on a self-developed Multiscale Feature Extraction and Fusion Network(MFEFN)system.Compared with a direct Monte Carlo Simulation(MCS),the MFEFNbased procedure significantly reduces the calculation burden with a guarantee of accuracy.Our research provides a method to calculate nonlinear natural frequencies under two boundary conditions and presentes a surrogate model to predict frequencies for accuracy analysis and optimization design.
基金supported by the National Natural Science Foundation of China(Project No.61902210),a Research Grant of Beijing Higher Institution Engineering Research Center,and the Tsinghua–Tencent Joint Laboratory for Internet Innovation Technology.
文摘Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial configuration of a human–object pair in order to learn the action linking the human and object in the pair.We argue that such a paradigm of pairwise feature extraction and action inference can be applied not only at the whole human and object instance level,but also at the part level at which a body part interacts with an object,and at the semantic level by considering the semantic label of an object along with human appearance and human–object spatial configuration,to infer the action.We thus propose a multi-level pairwise feature network(PFNet)for detecting human–object interactions.The network consists of three parallel streams to characterize HOI utilizing pairwise features at the above three levels;the three streams are finally fused to give the action prediction.Extensive experiments show that our proposed PFNet outperforms other state-of-the-art methods on the VCOCO dataset and achieves comparable results to the state-of-the-art on the HICO-DET dataset.
文摘With the rapid growth of e-commerce, customers increasingly write online reviews of the product they purchase. These customer reviews are one of the most valuable sources of information affecting selection of products or services. Summarizing these customer reviews is becoming an interesting area of research, inspiring researchers to develop a more condensed, concise summarization for users. However, most of the current efforts at summarization are based on general product features without feature＇s relationship. As a result, these summaries either ignore feedback from customers or do a poor job of reflecting the opinions expressed in customer reviews. To remedy this summarization shortcoming, we propose a feature network-driven quadrant mapping that captures and incorporates opinions from customer reviews. Our focus is on construction of a feature network, which is based on co-occurrence and sematic similarities, and a quadrant display showing the opinions polarity of feature groups. Moreover, the proposed approach involves clustering similar product features, and thus, it is different from standard text summarization based on abstraction and extraction. The summarized results can help customers better understand the overall opinions about a product.
基金the National Key Research and Development Program of China(2020YFB1806800).
文摘With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.
文摘In this paper,based on a bidirectional parallel multi-branch feature pyramid network(BPMFPN),a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles(UAVs).First,the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers.Next,the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance.In order to validate the effectiveness of the proposed algorithm,experiments are conducted on four datasets.For the PASCAL VOC dataset,the proposed algorithm achieves the mean average precision(mAP)of 85.4 on the VOC 2007 test set.With regard to the detection in optical remote sensing(DIOR)dataset,the proposed algorithm achieves 73.9 mAP.For vehicle detection in aerial imagery(VEDAI)dataset,the detection accuracy of small land vehicle(slv)targets reaches 97.4 mAP.For unmanned aerial vehicle detection and tracking(UAVDT)dataset,the proposed BPMFPN Det achieves the mAP of 48.75.Compared with the previous state-of-the-art methods,the results obtained by the proposed algorithm are more competitive.The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.
文摘Due to the widespread use of the Internet,customer information is vulnerable to computer systems attack,which brings urgent need for the intrusion detection technology.Recently,network intrusion detection has been one of the most important technologies in network security detection.The accuracy of network intrusion detection has reached higher accuracy so far.However,these methods have very low efficiency in network intrusion detection,even the most popular SOM neural network method.In this paper,an efficient and fast network intrusion detection method was proposed.Firstly,the fundamental of the two different methods are introduced respectively.Then,the selforganizing feature map neural network based on K-means clustering(KSOM)algorithms was presented to improve the efficiency of network intrusion detection.Finally,the NSLKDD is used as network intrusion data set to demonstrate that the KSOM method can significantly reduce the number of clustering iteration than SOM method without substantially affecting the clustering results and the accuracy is much higher than Kmeans method.The Experimental results show that our method can relatively improve the accuracy of network intrusion and significantly reduce the number of clustering iteration.
基金The National Natural Science Foundation of China(No.61603091)。
文摘In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid network(FPN)and deconvolutional single shot detector(DSSD),where the bottom layer of the feature pyramid network relies on the top layer,NFPN builds the feature pyramid network with no connections between the upper and lower layers.That is,it only fuses shallow features on similar scales.NFPN is highly portable and can be embedded in many models to further boost performance.Extensive experiments on PASCAL VOC 2007,2012,and COCO datasets demonstrate that the NFPN-based SSD without intricate tricks can exceed the DSSD model in terms of detection accuracy and inference speed,especially for small objects,e.g.,4%to 5%higher mAP(mean average precision)than SSD,and 2%to 3%higher mAP than DSSD.On VOC 2007 test set,the NFPN-based SSD with 300×300 input reaches 79.4%mAP at 34.6 frame/s,and the mAP can raise to 82.9%after using the multi-scale testing strategy.
基金Supported by the National Key Research and Development Program of China(No.2016YFC1402003)the National Natural Science Foundation of China(No.41671436)the Innovation Project of LREIS(No.O88RAA01YA)
文摘Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area is important for breeding area planning,production value estimation,ecological survey,and storm surge prevention.However,as the aquaculture area expands,the seawater background becomes increasingly complex and spectral characteristics differ dramatically,making it difficult to determine the aquaculture area.In this study,we used a high-resolution remote-sensing satellite GF-2 image to introduce a deep-learning Richer Convolutional Features(RCF)network model to extract the aquaculture area.Then we used the density of aquaculture as an assessment index to assess the vulnerability of aquaculture areas in Sanduao.The results demonstrate that this method does not require land and water separation of the area in advance,and good extraction can be achieved in the areas with more sediment and waves,with an extraction accuracy>93%,which is suitable for large-scale aquaculture area extraction.Vulnerability assessment results indicate that the density of aquaculture in the eastern part of Sanduao is considerably high,reaching a higher vulnerability level than other parts.
基金This work was supported in part by National Natural Science Foundation of China under Grant Nos.11725211,52005505,and 62001502Post-graduate Scientific Research Innovation Project of Hunan Province under Grant No.CX20200023.
文摘Deep learning for topology optimization has been extensively studied to reduce the cost of calculation in recent years.However,the loss function of the above method is mainly based on pixel-wise errors from the image perspective,which cannot embed the physical knowledge of topology optimization.Therefore,this paper presents an improved deep learning model to alleviate the above difficulty effectively.The feature pyramid network(FPN),a kind of deep learning model,is trained to learn the inherent physical law of topology optimization itself,of which the loss function is composed of pixel-wise errors and physical constraints.Since the calculation of physical constraints requires finite element analysis(FEA)with high calculating costs,the strategy of adjusting the time when physical constraints are added is proposed to achieve the balance between the training cost and the training effect.Then,two classical topology optimization problems are investigated to verify the effectiveness of the proposed method.The results show that the developed model using a small number of samples can quickly obtain the optimization structure without any iteration,which has not only high pixel-wise accuracy but also good physical performance.
基金supported by State Grid Corporation Limited Science and Technology Project Funding(Contract No.SGCQSQ00YJJS2200380).
文摘There is instability in the distributed energy storage cloud group end region on the power grid side.In order to avoid large-scale fluctuating charging and discharging in the power grid environment and make the capacitor components showa continuous and stable charging and discharging state,a hierarchical time-sharing configuration algorithm of distributed energy storage cloud group end region on the power grid side based on multi-scale and multi feature convolution neural network is proposed.Firstly,a voltage stability analysis model based onmulti-scale and multi feature convolution neural network is constructed,and the multi-scale and multi feature convolution neural network is optimized based on Self-OrganizingMaps(SOM)algorithm to analyze the voltage stability of the cloud group end region of distributed energy storage on the grid side under the framework of credibility.According to the optimal scheduling objectives and network size,the distributed robust optimal configuration control model is solved under the framework of coordinated optimal scheduling at multiple time scales;Finally,the time series characteristics of regional power grid load and distributed generation are analyzed.According to the regional hierarchical time-sharing configuration model of“cloud”,“group”and“end”layer,the grid side distributed energy storage cloud group end regional hierarchical time-sharing configuration algorithm is realized.The experimental results show that after applying this algorithm,the best grid side distributed energy storage configuration scheme can be determined,and the stability of grid side distributed energy storage cloud group end region layered timesharing configuration can be improved.
基金Supported by the Ph.D. Research Startup Project of Minnan Normal University(KJ2021020)the National Natural Science Foundation of China(12090020 and 12090025)Zhejiang Provincial Natural Science Foundation of China(LSD19H180005)。
文摘Accurate pancreas segmentation is critical for the diagnosis and management of diseases of the pancreas. It is challenging to precisely delineate pancreas due to the highly variations in volume, shape and location. In recent years, coarse-to-fine methods have been widely used to alleviate class imbalance issue and improve pancreas segmentation accuracy. However,cascaded methods could be computationally intensive and the refined results are significantly dependent on the performance of its coarse segmentation results. To balance the segmentation accuracy and computational efficiency, we propose a Discriminative Feature Attention Network for pancreas segmentation, to effectively highlight pancreas features and improve segmentation accuracy without explicit pancreas location. The final segmentation is obtained by applying a simple yet effective post-processing step. Two experiments on both public NIH pancreas CT dataset and abdominal BTCV multi-organ dataset are individually conducted to show the effectiveness of our method for 2 D pancreas segmentation. We obtained average Dice Similarity Coefficient(DSC) of 82.82±6.09%, average Jaccard Index(JI) of 71.13± 8.30% and average Symmetric Average Surface Distance(ASD) of 1.69 ± 0.83 mm on the NIH dataset. Compared to the existing deep learning-based pancreas segmentation methods, our experimental results achieve the best average DSC and JI value.
基金funded by National Nature Science Foundation of China,grant number 61302188。
文摘In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.
