With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State I...With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.展开更多
Neutron time-of-flight(ToF)measurement is a highly accurate method for obtaining the kinetic energy of a neutron by measuring its velocity,but requires precise acquisition of the neutron signal arrival time.However,th...Neutron time-of-flight(ToF)measurement is a highly accurate method for obtaining the kinetic energy of a neutron by measuring its velocity,but requires precise acquisition of the neutron signal arrival time.However,the high hardware costs and data burden associated with the acquisition of neutron ToF signals pose significant challenges.Higher sampling rates increase the data volume,data processing,and storage hardware costs.Compressed sampling can address these challenges,but it faces issues regarding optimal sampling efficiency and high-quality reconstructed signals.This paper proposes a revolutionary deep learning-based compressed sampling(DL-CS)algorithm for reconstructing neutron ToF signals that outperform traditional compressed sampling methods.This approach comprises four modules:random projection,rising dimensions,initial reconstruction,and final reconstruction.Initially,the technique adaptively compresses neutron ToF signals sequentially using three convolutional layers,replacing random measurement matrices in traditional compressed sampling theory.Subsequently,the signals are reconstructed using a modified inception module,long short-term memory,and self-attention.The performance of this deep compressed sampling method was quantified using the percentage root-mean-square difference,correlation coefficient,and reconstruction time.Experimental results showed that our proposed DL-CS approach can significantly enhance signal quality compared with other compressed sampling methods.This is evidenced by a percentage root-mean-square difference,correlation coefficient,and reconstruction time results of 5%,0.9988,and 0.0108 s,respectively,obtained for sampling rates below 10%for the neutron ToF signal generated using an electron-beam-driven photoneutron source.The results showed that the proposed DL-CS approach significantly improves the signal quality compared with other compressed sampling methods,exhibiting excellent reconstruction accuracy and speed.展开更多
Remote sensing image segmentation has a wide range of applications in land cover classification,urban building recognition,crop monitoring,and other fields.In recent years,with the booming development of deep learning...Remote sensing image segmentation has a wide range of applications in land cover classification,urban building recognition,crop monitoring,and other fields.In recent years,with the booming development of deep learning,remote sensing image segmentation models based on deep learning have gradually emerged and produced a large number of scientific research achievements.This article is based on deep learning and reviews the latest achievements in remote sensing image segmentation,exploring future development directions.Firstly,the basic concepts,characteristics,classification,tasks,and commonly used datasets of remote sensingimages are presented.Secondly,the segmentation models based on deep learning were classified and summarized,and the principles,characteristics,and applications of various models were presented.Then,the key technologies involved in deep learning remote sensing image segmentation were introduced.Finally,the future development direction and applicationprospects of remote sensing image segmentation were discussed.This article reviews the latest research achievements in remote sensing image segmentationfrom the perspective of deep learning,which can provide reference and inspiration for the research of remote sensing image segmentation.展开更多
This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined...This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined with multi-source remote sensing data achieved high-precision recognition of urban three-dimensional greening with 92.8% overall accuracy.Analysis of spatiotemporal evolution patterns in Shanghai,Hangzhou,and Nanjing revealed that threedimensional greening shows a development trend from demonstration to popularization,with 16.5% annual growth rate.The study quantitatively assessed ecological benefits of various three-dimensional greening types.Results indicate that modular vertical greening and intensive roof gardens yield highest ecological benefits,while climbing-type vertical greening and extensive roof gardens offer optimal benefit-cost ratios.Integration of multiple forms generates 15-22% synergistic enhancement.Compared with traditional planning,the multi-objective optimization-based layout achieved 27.5% increase in carbon sequestration,32.6% improvement in temperature regulation,35.8% enhancement in stormwater management,and 42.3% rise in biodiversity index.Three pilot projects validated that actual ecological benefits reached 90.3-102.3% of predicted values.Multi-scenario simulations indicate optimized layouts can reduce urban heat island intensity by 15.2-18.7%,increase carbon neutrality contribution to 8.6-10.2%,and decrease stormwater runoff peaks by 25.3-32.6%.The findings provide technical methods for urban three-dimensional greening optimization and smart eco-city construction,promoting sustainable urban development.展开更多
Spectrum sensing is a key technology for cognitive radios.We present spectrum sensing as a classification problem and propose a sensing method based on deep learning classification.We normalize the received signal pow...Spectrum sensing is a key technology for cognitive radios.We present spectrum sensing as a classification problem and propose a sensing method based on deep learning classification.We normalize the received signal power to overcome the effects of noise power uncertainty.We train the model with as many types of signals as possible as well as noise data to enable the trained network model to adapt to untrained new signals.We also use transfer learning strategies to improve the performance for real-world signals.Extensive experiments are conducted to evaluate the performance of this method.The simulation results show that the proposed method performs better than two traditional spectrum sensing methods,i.e.,maximum-minimum eigenvalue ratio-based method and frequency domain entropy-based method.In addition,the experimental results of the new untrained signal types show that our method can adapt to the detection of these new signals.Furthermore,the real-world signal detection experiment results show that the detection performance can be further improved by transfer learning.Finally,experiments under colored noise show that our proposed method has superior detection performance under colored noise,while the traditional methods have a significant performance degradation,which further validate the superiority of our method.展开更多
A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their ...A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their superiority over conventional change detection methods.However,the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved.As of today,few in-depth reviews have investigated the mechanisms of DLCD.Without such a review,five critical questions remain unclear.Does DLCD provide improved information representation for change detection?If so,how?How to select an appropriate DLCD method and why?How much does each type of change benefits from DLCD in terms of its performance?What are the major limitations of existing DLCD methods and what are the prospects for DLCD?To address these five questions,we reviewed according to the following strategies.We grouped the DLCD information assemblages into the four unique dimensions of remote sensing:spectral,spatial,temporal,and multi-sensor.For the extraction of information in each dimension,the difference between DLCD and conventional change detection methods was compared.We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools:separate and coupled models.Their advantages,limitations,applicability,and performance were thoroughly investigated and explicitly presented.We examined the variations in performance between DLCD and conventional change detection.We depicted two limitations of DLCD,i.e.training sample and hardware and software dilemmas.Based on these analyses,we identified directions for future developments.As a result of our review,we found that DLCD’s advantages over conventional change detection can be attributed to three factors:improved information representation;improved change detection methods;and performance enhancements.DLCD has to surpass the limitations with regard to training samples and computing infrastructure.We envision this review can boost developments of deep learning in change detection applications.展开更多
Drones,also known as mini-unmanned aerial vehicles(UAVs),are enjoying great popularity in recent years due to their advantages of low cost,easy to pilot and small size,which also makes them hard to detect.They can pro...Drones,also known as mini-unmanned aerial vehicles(UAVs),are enjoying great popularity in recent years due to their advantages of low cost,easy to pilot and small size,which also makes them hard to detect.They can provide real time situational awareness information by live videos or high definition pictures and pose serious threats to public security.In this article,we combine collaborative spectrum sensing with deep learning to effectively detect potential illegal drones with states of high uncertainty.First,we formulate the detection of potential illegal drones under illegitimate access and rogue power emission as a quaternary hypothesis test problem.Then,we propose an algorithm of image classification based on convolutional neural network which converts the cooperative spectrum sensing data at a sensing slot into one image.Furthermore,to exploit more information and improve the detection performance,we develop a trajectory classification algorithm which converts theflight process of the drones in consecutive multiple sensing slots into trajectory images.In addition,simulations are provided to verify the proposed methods’performance under various parameter configurations.展开更多
The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the rob...The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing model.PUAA adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing model.We design three PUAA methods in black box scenario.In or-der to defend against PUAA,we propose a defense method based on autoencoder named DeepFilter.We apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective defense.Extensive experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of DeepFilter.Results show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing model.In addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.展开更多
Computational ghost imaging(CGI)provides an elegant framework for indirect imaging,but its application has been restricted by low imaging performance.Herein,we propose a novel approach that significantly improves the ...Computational ghost imaging(CGI)provides an elegant framework for indirect imaging,but its application has been restricted by low imaging performance.Herein,we propose a novel approach that significantly improves the imaging performance of CGI.In this scheme,we optimize the conventional CGI data processing algorithm by using a novel compressed sensing(CS)algorithm based on a deep convolution generative adversarial network(DCGAN).CS is used to process the data output by a conventional CGI device.The processed data are trained by a DCGAN to reconstruct the image.Qualitative and quantitative results show that this method significantly improves the quality of reconstructed images by jointly training a generator and the optimization process for reconstruction via meta-learning.Moreover,the background noise can be eliminated well by this method.展开更多
Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches ...Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches develop,techniques for RSI classifiers with DL have attained important breakthroughs,providing a new opportunity for the research and development of RSI classifiers.This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification(ISMOGCN-HRSC)model.The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs.In the presented ISMOGCN-HRSC model,the synergic deep learning(SDL)model is exploited to produce feature vectors.The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs.The ISMO algorithm is used to enhance the classification efficiency of the GCN method,which is derived by integrating chaotic concepts into the SMO algorithm.The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset.展开更多
We explore an end-to-end wavefront sensing approach based on deep learning,which aims to deal with the high-order turbulence and the discontinuous aberration caused by optical system obstructions commonly encountered ...We explore an end-to-end wavefront sensing approach based on deep learning,which aims to deal with the high-order turbulence and the discontinuous aberration caused by optical system obstructions commonly encountered in real-world ground-based telescope observations.We have considered factors such as the entrance pupil wavefront containing high-order turbulence and discontinuous aberrations due to obstruction by the secondary mirror and spider,realistically simulating the observation conditions of ground-based telescopes.By comparing with the Marechal criterion(0.075λ),we validate the effectiveness of the proposed approach.Experimental results show that the deep learning wavefront sensing approach can correct the distorted wavefront affect by high-order turbulence to close to the diffraction limit.We also analyze the limitations of this approach,using the direct zonal phase output method,where the residual wavefront stems from the fitting error.Furthermore,we have explored the wavefront reconstruction accuracy of different noise intensities and the central obstruction ratios.Within a noise intensity range of 1%–1.9%,the root mean square error(RMSE)of the residual wavefront is less than Marechal criterion.In the range of central obstruction ratios from 0.0 to 0.3 commonly used in ground-based telescopes,the RMSE of the residual wavefront is greater than 0.039λand less than 0.041λ.This research provides an efficient and valid wavefront sensing approach for high-resolution observation with ground-based telescopes.展开更多
The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicti...The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.展开更多
The deep integration of digital-AI technologies is reshaping the forms and logic of higher education teaching.However,university faculty professional development faces the limitations of the“technical enablement”par...The deep integration of digital-AI technologies is reshaping the forms and logic of higher education teaching.However,university faculty professional development faces the limitations of the“technical enablement”paradigm,leading to a cycle of“technological anxiety-performative innovation-meaning depletion.”Based on sociocultural theory,expansive learning theory,and teacher identity theory,this paper constructs a“technology-cognition-identity”co-evolution theoretical framework.It proposes a new paradigm centered on“teacher deep learning,”operationalized into three dimensions:critical technological cognition,reflective practice iteration,and identity reconstruction.Accordingly,the article puts forward strategic recommendations targeting multiple stakeholders,including the state,universities,faculty development centers,and enterprises,aiming to propel teachers from“being empowered”to“self-empowerment,”and to achieve the synergistic development of educational wisdom and professional autonomy in the digital-AI era.展开更多
The thawing of ice-rich permafrost leads to the formation of thermokarst landforms.Precise mapping of retrogressive thaw slumps(RTSs)is imperative for assessing the degradation and carbon exchange of permafrost at bot...The thawing of ice-rich permafrost leads to the formation of thermokarst landforms.Precise mapping of retrogressive thaw slumps(RTSs)is imperative for assessing the degradation and carbon exchange of permafrost at both local and regional scales on the Tibetan Plateau(TP).However,previous methods for RTSs mapping rely on a large number of samples and complex classifiers with low automation level or unnecessary complexity.We propose an automatic mapping network(AmRTSNet)for producing decimeter-level RTSs maps from GaoFen-7 images based on deep learning.Both the quantitative metrics and qualitative evaluations show that AmRTSNet trained in the Beiluhe offers significant advantages over previous methods.Without further fine-tuning,we conducted RTSs automatic mapping based on AmRTSNet in the Wulanwula,Chumarhe,and Gaolinggo.Over 141,312 ha on the TP have been automatically mapped,comprising 926 RTS regions with a total RTS area of 2318.72 ha.The average statistics of the mapped RTSs show low roundness(0.38),moderate rectangularity(0.61),and high convexity(0.79).About 90%of the RTSs are smaller than 6 ha.The average aspect ratio is 2.18.RTSs are unevenly distributed in belt-like aggregations with dominant density peaks.RTSs often concentrate in hillslopes and along lateral streams,with more dense areas more likely to have larger RTSs.展开更多
Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check da...Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check dams is critical for quantitatively evaluating hydrological and ecological effects and planning the construction of new dams.Thus,this study developed a check dam detection framework for broad areas from high-resolution remote sensing images using an ensemble approach of deep learning and geospatial analysis.First,we made a sample dataset of check dams using GaoFen-2(GF-2)and Google Earth images.Next,we evaluated five popular deep-learning-based object detectors,including Faster R-CNN,You Only Look Once(version 3)(YOLOv3),Cascade R-CNN,YOLOX,and VarifocalNet(VFNet),to identify the best one for check dam detection.Finally,we analyzed the location characteristics of the check dams and used geographical constraints to optimize the detection results.Precision,recall,average precision at intersection over union(IoU)threshold of 0.50(AP_(50)),IoU threshold of 0.75(AP_(75)),and average value for 10 IoU thresholds ranging from 0.50-0.95 with a 0.05 step(AP_(50-95)),and inference time were used to evaluate model performance.All the five deep learning networks could identify check dams quickly and accurately,with AP_(50-95),AP_(50),and AP_(75)values higher than 60.0%,90.0%,and 70.0%,respectively,except for YOLOv3.The VFNet had the best performance,followed by YOLOX.The proposed framework was tested in the Yanhe River Basin and yielded promising results,with a recall rate of 87.0%for 521 check dams.Furthermore,the geographic analysis deleted about 50%of the false detection boxes,increasing the identification accuracy of check dams from 78.6%to 87.6%.Simultaneously,this framework recognized 568 recently constructed check dams and small check dams not recorded in the known check dam survey datasets.The extraction results will support efficient watershed management and guide future studies on soil erosion in the Loess Plateau.展开更多
To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats ...To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats such as jamming, spoofing and faked sensing attacks during both sensing and information exchange processes in large-scale dynamic and heterogeneous networks. In this article, we investigate secure mobile crowdsensing and present ways to use deep learning(DL) methods, such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning, to improve approaches to MCS security, including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DLbased approaches compared to traditional security schemes and identify the challenges that must be addressed to implement these approaches in practical MCS systems.展开更多
When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in inco...When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.展开更多
Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent ...Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.展开更多
Remote sensing(RS)presents laser scanning measurements,aerial photos,and high-resolution satellite images,which are utilized for extracting a range of traffic-related and road-related features.RS has a weakness,such a...Remote sensing(RS)presents laser scanning measurements,aerial photos,and high-resolution satellite images,which are utilized for extracting a range of traffic-related and road-related features.RS has a weakness,such as traffic fluctuations on small time scales that could distort the accuracy of predicted road and traffic features.This article introduces an Optimal Deep Learning for Traffic Critical Prediction Model on High-Resolution Remote Sensing Images(ODLTCP-HRRSI)to resolve these issues.The presented ODLTCP-HRRSI technique majorly aims to forecast the critical traffic in smart cities.To attain this,the presented ODLTCP-HRRSI model performs two major processes.At the initial stage,the ODLTCP-HRRSI technique employs a convolutional neural network with an auto-encoder(CNN-AE)model for productive and accurate traffic flow.Next,the hyperparameter adjustment of the CNN-AE model is performed via the Bayesian adaptive direct search optimization(BADSO)algorithm.The experimental outcomes demonstrate the enhanced performance of the ODLTCP-HRRSI technique over recent approaches with maximum accuracy of 98.23%.展开更多
The frequent occurrence of extreme weather events has rendered numerous landslides to a global natural disaster issue.It is crucial to rapidly and accurately determine the boundaries of landslides for geohazards evalu...The frequent occurrence of extreme weather events has rendered numerous landslides to a global natural disaster issue.It is crucial to rapidly and accurately determine the boundaries of landslides for geohazards evaluation and emergency response.Therefore,the Skip Connection DeepLab neural network(SCDnn),a deep learning model based on 770 optical remote sensing images of landslide,is proposed to improve the accuracy of landslide boundary detection.The SCDnn model is optimized for the over-segmentation issue which occurs in conventional deep learning models when there is a significant degree of similarity between topographical geomorphic features.SCDnn exhibits notable improvements in landslide feature extraction and semantic segmentation by combining an enhanced Atrous Spatial Pyramid Convolutional Block(ASPC)with a coding structure that reduces model complexity.The experimental results demonstrate that SCDnn can identify landslide boundaries in 119 images with MIoU values between 0.8and 0.9;while 52 images with MIoU values exceeding 0.9,which exceeds the identification accuracy of existing techniques.This work can offer a novel technique for the automatic extensive identification of landslide boundaries in remote sensing images in addition to establishing the groundwork for future inve stigations and applications in related domains.展开更多
基金supported by National Natural Science Foundation of China(NSFC)under grant U23A20310.
文摘With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.
基金supported by the National Defense Technology Foundation Program of China(No.JSJT2022209A001-3)Sichuan Science and Technology Program(No.2021JDRC0011)+1 种基金Nuclear Energy Development Research Program of China(Research on High Energy X-ray Imaging of Nuclear Fuel)Scientific Research and Innovation Team Program of Sichuan University of Science and Engineering(No.SUSE652A001).
文摘Neutron time-of-flight(ToF)measurement is a highly accurate method for obtaining the kinetic energy of a neutron by measuring its velocity,but requires precise acquisition of the neutron signal arrival time.However,the high hardware costs and data burden associated with the acquisition of neutron ToF signals pose significant challenges.Higher sampling rates increase the data volume,data processing,and storage hardware costs.Compressed sampling can address these challenges,but it faces issues regarding optimal sampling efficiency and high-quality reconstructed signals.This paper proposes a revolutionary deep learning-based compressed sampling(DL-CS)algorithm for reconstructing neutron ToF signals that outperform traditional compressed sampling methods.This approach comprises four modules:random projection,rising dimensions,initial reconstruction,and final reconstruction.Initially,the technique adaptively compresses neutron ToF signals sequentially using three convolutional layers,replacing random measurement matrices in traditional compressed sampling theory.Subsequently,the signals are reconstructed using a modified inception module,long short-term memory,and self-attention.The performance of this deep compressed sampling method was quantified using the percentage root-mean-square difference,correlation coefficient,and reconstruction time.Experimental results showed that our proposed DL-CS approach can significantly enhance signal quality compared with other compressed sampling methods.This is evidenced by a percentage root-mean-square difference,correlation coefficient,and reconstruction time results of 5%,0.9988,and 0.0108 s,respectively,obtained for sampling rates below 10%for the neutron ToF signal generated using an electron-beam-driven photoneutron source.The results showed that the proposed DL-CS approach significantly improves the signal quality compared with other compressed sampling methods,exhibiting excellent reconstruction accuracy and speed.
文摘Remote sensing image segmentation has a wide range of applications in land cover classification,urban building recognition,crop monitoring,and other fields.In recent years,with the booming development of deep learning,remote sensing image segmentation models based on deep learning have gradually emerged and produced a large number of scientific research achievements.This article is based on deep learning and reviews the latest achievements in remote sensing image segmentation,exploring future development directions.Firstly,the basic concepts,characteristics,classification,tasks,and commonly used datasets of remote sensingimages are presented.Secondly,the segmentation models based on deep learning were classified and summarized,and the principles,characteristics,and applications of various models were presented.Then,the key technologies involved in deep learning remote sensing image segmentation were introduced.Finally,the future development direction and applicationprospects of remote sensing image segmentation were discussed.This article reviews the latest research achievements in remote sensing image segmentationfrom the perspective of deep learning,which can provide reference and inspiration for the research of remote sensing image segmentation.
文摘This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined with multi-source remote sensing data achieved high-precision recognition of urban three-dimensional greening with 92.8% overall accuracy.Analysis of spatiotemporal evolution patterns in Shanghai,Hangzhou,and Nanjing revealed that threedimensional greening shows a development trend from demonstration to popularization,with 16.5% annual growth rate.The study quantitatively assessed ecological benefits of various three-dimensional greening types.Results indicate that modular vertical greening and intensive roof gardens yield highest ecological benefits,while climbing-type vertical greening and extensive roof gardens offer optimal benefit-cost ratios.Integration of multiple forms generates 15-22% synergistic enhancement.Compared with traditional planning,the multi-objective optimization-based layout achieved 27.5% increase in carbon sequestration,32.6% improvement in temperature regulation,35.8% enhancement in stormwater management,and 42.3% rise in biodiversity index.Three pilot projects validated that actual ecological benefits reached 90.3-102.3% of predicted values.Multi-scenario simulations indicate optimized layouts can reduce urban heat island intensity by 15.2-18.7%,increase carbon neutrality contribution to 8.6-10.2%,and decrease stormwater runoff peaks by 25.3-32.6%.The findings provide technical methods for urban three-dimensional greening optimization and smart eco-city construction,promoting sustainable urban development.
基金supported in part by National Natural Science Foundation of China under Grant No. 61871398in part by China Postdoctoral Science Foundation under Grant No. 2018M631122
文摘Spectrum sensing is a key technology for cognitive radios.We present spectrum sensing as a classification problem and propose a sensing method based on deep learning classification.We normalize the received signal power to overcome the effects of noise power uncertainty.We train the model with as many types of signals as possible as well as noise data to enable the trained network model to adapt to untrained new signals.We also use transfer learning strategies to improve the performance for real-world signals.Extensive experiments are conducted to evaluate the performance of this method.The simulation results show that the proposed method performs better than two traditional spectrum sensing methods,i.e.,maximum-minimum eigenvalue ratio-based method and frequency domain entropy-based method.In addition,the experimental results of the new untrained signal types show that our method can adapt to the detection of these new signals.Furthermore,the real-world signal detection experiment results show that the detection performance can be further improved by transfer learning.Finally,experiments under colored noise show that our proposed method has superior detection performance under colored noise,while the traditional methods have a significant performance degradation,which further validate the superiority of our method.
文摘A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their superiority over conventional change detection methods.However,the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved.As of today,few in-depth reviews have investigated the mechanisms of DLCD.Without such a review,five critical questions remain unclear.Does DLCD provide improved information representation for change detection?If so,how?How to select an appropriate DLCD method and why?How much does each type of change benefits from DLCD in terms of its performance?What are the major limitations of existing DLCD methods and what are the prospects for DLCD?To address these five questions,we reviewed according to the following strategies.We grouped the DLCD information assemblages into the four unique dimensions of remote sensing:spectral,spatial,temporal,and multi-sensor.For the extraction of information in each dimension,the difference between DLCD and conventional change detection methods was compared.We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools:separate and coupled models.Their advantages,limitations,applicability,and performance were thoroughly investigated and explicitly presented.We examined the variations in performance between DLCD and conventional change detection.We depicted two limitations of DLCD,i.e.training sample and hardware and software dilemmas.Based on these analyses,we identified directions for future developments.As a result of our review,we found that DLCD’s advantages over conventional change detection can be attributed to three factors:improved information representation;improved change detection methods;and performance enhancements.DLCD has to surpass the limitations with regard to training samples and computing infrastructure.We envision this review can boost developments of deep learning in change detection applications.
基金supported by the Foundation of Graduate Innovation Center in NUAA under Grant No. kfjj20190414the open research fund of Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space (Nanjing Univ. Aeronaut. Astronaut.), Ministry of Industry and Information Technology, Nanjing, 211106, China (No. KF20181913)+2 种基金National Natural Science Foundation of China (No. 61631020, No. 61871398, No. 61931011 and No. 61801216)the Natural Science Foundation for Distinguished Young Scholars of Jiangsu Province (No. BK20190030)the Natural Science Foundation of Jiangsu Province (No. BK20180420)
文摘Drones,also known as mini-unmanned aerial vehicles(UAVs),are enjoying great popularity in recent years due to their advantages of low cost,easy to pilot and small size,which also makes them hard to detect.They can provide real time situational awareness information by live videos or high definition pictures and pose serious threats to public security.In this article,we combine collaborative spectrum sensing with deep learning to effectively detect potential illegal drones with states of high uncertainty.First,we formulate the detection of potential illegal drones under illegitimate access and rogue power emission as a quaternary hypothesis test problem.Then,we propose an algorithm of image classification based on convolutional neural network which converts the cooperative spectrum sensing data at a sensing slot into one image.Furthermore,to exploit more information and improve the detection performance,we develop a trajectory classification algorithm which converts theflight process of the drones in consecutive multiple sensing slots into trajectory images.In addition,simulations are provided to verify the proposed methods’performance under various parameter configurations.
基金the National Nat-ural Science Foundation of China under Grant No.62072406,No.U19B2016,No.U20B2038 and No.61871398the Natural Science Foundation of Zhejiang Province under Grant No.LY19F020025the Major Special Funding for“Science and Tech-nology Innovation 2025”in Ningbo under Grant No.2018B10063.
文摘The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing model.PUAA adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing model.We design three PUAA methods in black box scenario.In or-der to defend against PUAA,we propose a defense method based on autoencoder named DeepFilter.We apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective defense.Extensive experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of DeepFilter.Results show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing model.In addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11704221,11574178,and 61675115)the Taishan Scholar Project of Shandong Province,China(Grant No.tsqn201812059)。
文摘Computational ghost imaging(CGI)provides an elegant framework for indirect imaging,but its application has been restricted by low imaging performance.Herein,we propose a novel approach that significantly improves the imaging performance of CGI.In this scheme,we optimize the conventional CGI data processing algorithm by using a novel compressed sensing(CS)algorithm based on a deep convolution generative adversarial network(DCGAN).CS is used to process the data output by a conventional CGI device.The processed data are trained by a DCGAN to reconstruct the image.Qualitative and quantitative results show that this method significantly improves the quality of reconstructed images by jointly training a generator and the optimization process for reconstruction via meta-learning.Moreover,the background noise can be eliminated well by this method.
文摘Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches develop,techniques for RSI classifiers with DL have attained important breakthroughs,providing a new opportunity for the research and development of RSI classifiers.This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification(ISMOGCN-HRSC)model.The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs.In the presented ISMOGCN-HRSC model,the synergic deep learning(SDL)model is exploited to produce feature vectors.The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs.The ISMO algorithm is used to enhance the classification efficiency of the GCN method,which is derived by integrating chaotic concepts into the SMO algorithm.The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset.
基金supported by the National Natural Science Foundation of China(NSFC)(U2031140).
文摘We explore an end-to-end wavefront sensing approach based on deep learning,which aims to deal with the high-order turbulence and the discontinuous aberration caused by optical system obstructions commonly encountered in real-world ground-based telescope observations.We have considered factors such as the entrance pupil wavefront containing high-order turbulence and discontinuous aberrations due to obstruction by the secondary mirror and spider,realistically simulating the observation conditions of ground-based telescopes.By comparing with the Marechal criterion(0.075λ),we validate the effectiveness of the proposed approach.Experimental results show that the deep learning wavefront sensing approach can correct the distorted wavefront affect by high-order turbulence to close to the diffraction limit.We also analyze the limitations of this approach,using the direct zonal phase output method,where the residual wavefront stems from the fitting error.Furthermore,we have explored the wavefront reconstruction accuracy of different noise intensities and the central obstruction ratios.Within a noise intensity range of 1%–1.9%,the root mean square error(RMSE)of the residual wavefront is less than Marechal criterion.In the range of central obstruction ratios from 0.0 to 0.3 commonly used in ground-based telescopes,the RMSE of the residual wavefront is greater than 0.039λand less than 0.041λ.This research provides an efficient and valid wavefront sensing approach for high-resolution observation with ground-based telescopes.
基金supported in part by the Science and Technology Department of Sichuan Province(No.2025ZNSFSC0427,No.2024ZDZX0035)the Open Project Fund of Vehicle Measurement,Control and Safety Key Laboratory of Sichuan Province(No.QCCK2024-004)the Industrial and Educational Integration Project of Yibin(No.YB-XHU-20240001)。
文摘The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.
基金The 2025 Shanghai Educational Science Research Project“Research on Value-Added Evaluation of University Teachers’Deep Learning Empowered by Digital Intelligence:From the Perspective of University Teachers’New Quality Literacy”(C2025028)。
文摘The deep integration of digital-AI technologies is reshaping the forms and logic of higher education teaching.However,university faculty professional development faces the limitations of the“technical enablement”paradigm,leading to a cycle of“technological anxiety-performative innovation-meaning depletion.”Based on sociocultural theory,expansive learning theory,and teacher identity theory,this paper constructs a“technology-cognition-identity”co-evolution theoretical framework.It proposes a new paradigm centered on“teacher deep learning,”operationalized into three dimensions:critical technological cognition,reflective practice iteration,and identity reconstruction.Accordingly,the article puts forward strategic recommendations targeting multiple stakeholders,including the state,universities,faculty development centers,and enterprises,aiming to propel teachers from“being empowered”to“self-empowerment,”and to achieve the synergistic development of educational wisdom and professional autonomy in the digital-AI era.
基金The Second Tibetan Plateau Scientific Expedition and Research,No.2022QZKK0101National Natural Science Foundation of China,No.42271427。
文摘The thawing of ice-rich permafrost leads to the formation of thermokarst landforms.Precise mapping of retrogressive thaw slumps(RTSs)is imperative for assessing the degradation and carbon exchange of permafrost at both local and regional scales on the Tibetan Plateau(TP).However,previous methods for RTSs mapping rely on a large number of samples and complex classifiers with low automation level or unnecessary complexity.We propose an automatic mapping network(AmRTSNet)for producing decimeter-level RTSs maps from GaoFen-7 images based on deep learning.Both the quantitative metrics and qualitative evaluations show that AmRTSNet trained in the Beiluhe offers significant advantages over previous methods.Without further fine-tuning,we conducted RTSs automatic mapping based on AmRTSNet in the Wulanwula,Chumarhe,and Gaolinggo.Over 141,312 ha on the TP have been automatically mapped,comprising 926 RTS regions with a total RTS area of 2318.72 ha.The average statistics of the mapped RTSs show low roundness(0.38),moderate rectangularity(0.61),and high convexity(0.79).About 90%of the RTSs are smaller than 6 ha.The average aspect ratio is 2.18.RTSs are unevenly distributed in belt-like aggregations with dominant density peaks.RTSs often concentrate in hillslopes and along lateral streams,with more dense areas more likely to have larger RTSs.
基金This research was supported by the National Natural Science Foundation of China(41977064)the National Key R&D Program of China(2021YFD1900700).
文摘Check dams are widely used on the Loess Plateau in China to control soil and water losses,develop agricultural land,and improve watershed ecology.Detailed information on the number and spatial distribution of check dams is critical for quantitatively evaluating hydrological and ecological effects and planning the construction of new dams.Thus,this study developed a check dam detection framework for broad areas from high-resolution remote sensing images using an ensemble approach of deep learning and geospatial analysis.First,we made a sample dataset of check dams using GaoFen-2(GF-2)and Google Earth images.Next,we evaluated five popular deep-learning-based object detectors,including Faster R-CNN,You Only Look Once(version 3)(YOLOv3),Cascade R-CNN,YOLOX,and VarifocalNet(VFNet),to identify the best one for check dam detection.Finally,we analyzed the location characteristics of the check dams and used geographical constraints to optimize the detection results.Precision,recall,average precision at intersection over union(IoU)threshold of 0.50(AP_(50)),IoU threshold of 0.75(AP_(75)),and average value for 10 IoU thresholds ranging from 0.50-0.95 with a 0.05 step(AP_(50-95)),and inference time were used to evaluate model performance.All the five deep learning networks could identify check dams quickly and accurately,with AP_(50-95),AP_(50),and AP_(75)values higher than 60.0%,90.0%,and 70.0%,respectively,except for YOLOv3.The VFNet had the best performance,followed by YOLOX.The proposed framework was tested in the Yanhe River Basin and yielded promising results,with a recall rate of 87.0%for 521 check dams.Furthermore,the geographic analysis deleted about 50%of the false detection boxes,increasing the identification accuracy of check dams from 78.6%to 87.6%.Simultaneously,this framework recognized 568 recently constructed check dams and small check dams not recorded in the known check dam survey datasets.The extraction results will support efficient watershed management and guide future studies on soil erosion in the Loess Plateau.
基金supported in part by the National Natural Science Foundation of China under Grant 61671396 and 91638204in part by the open research fund of National Mobile Communications Research Laboratory,Southeast University(No.2018D08)in part by Science and Technology Innovation Project of Foshan City,China(Grant No.2015IT100095)
文摘To improve the quality of multimedia services and stimulate secure sensing in Internet of Things applications, such as healthcare and traffic monitoring, mobile crowdsensing(MCS) systems must address security threats such as jamming, spoofing and faked sensing attacks during both sensing and information exchange processes in large-scale dynamic and heterogeneous networks. In this article, we investigate secure mobile crowdsensing and present ways to use deep learning(DL) methods, such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning, to improve approaches to MCS security, including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DLbased approaches compared to traditional security schemes and identify the challenges that must be addressed to implement these approaches in practical MCS systems.
基金This work was supported in part by the Key Project of Natural Science Research of Anhui Provincial Department of Education under Grant KJ2017A416in part by the Fund of National Sensor Network Engineering Technology Research Center(No.NSNC202103).
文摘When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.
基金the Deanship of Scientific Research at King Khalid University for funding this work through Large Groups Project under Grant Number(25/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R303)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR28.
文摘Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.
文摘Remote sensing(RS)presents laser scanning measurements,aerial photos,and high-resolution satellite images,which are utilized for extracting a range of traffic-related and road-related features.RS has a weakness,such as traffic fluctuations on small time scales that could distort the accuracy of predicted road and traffic features.This article introduces an Optimal Deep Learning for Traffic Critical Prediction Model on High-Resolution Remote Sensing Images(ODLTCP-HRRSI)to resolve these issues.The presented ODLTCP-HRRSI technique majorly aims to forecast the critical traffic in smart cities.To attain this,the presented ODLTCP-HRRSI model performs two major processes.At the initial stage,the ODLTCP-HRRSI technique employs a convolutional neural network with an auto-encoder(CNN-AE)model for productive and accurate traffic flow.Next,the hyperparameter adjustment of the CNN-AE model is performed via the Bayesian adaptive direct search optimization(BADSO)algorithm.The experimental outcomes demonstrate the enhanced performance of the ODLTCP-HRRSI technique over recent approaches with maximum accuracy of 98.23%.
基金supported by the National Natural Science Foundation of China(Grant Nos.42090054,41931295)the Natural Science Foundation of Hubei Province of China(2022CFA002)。
文摘The frequent occurrence of extreme weather events has rendered numerous landslides to a global natural disaster issue.It is crucial to rapidly and accurately determine the boundaries of landslides for geohazards evaluation and emergency response.Therefore,the Skip Connection DeepLab neural network(SCDnn),a deep learning model based on 770 optical remote sensing images of landslide,is proposed to improve the accuracy of landslide boundary detection.The SCDnn model is optimized for the over-segmentation issue which occurs in conventional deep learning models when there is a significant degree of similarity between topographical geomorphic features.SCDnn exhibits notable improvements in landslide feature extraction and semantic segmentation by combining an enhanced Atrous Spatial Pyramid Convolutional Block(ASPC)with a coding structure that reduces model complexity.The experimental results demonstrate that SCDnn can identify landslide boundaries in 119 images with MIoU values between 0.8and 0.9;while 52 images with MIoU values exceeding 0.9,which exceeds the identification accuracy of existing techniques.This work can offer a novel technique for the automatic extensive identification of landslide boundaries in remote sensing images in addition to establishing the groundwork for future inve stigations and applications in related domains.
