High spatiotemporal resolution brain electrical signals are critical for basic neuroscience research and high-precision focus diagnostic localization,as the spatial scale of some pathologic signals is at the submillim...High spatiotemporal resolution brain electrical signals are critical for basic neuroscience research and high-precision focus diagnostic localization,as the spatial scale of some pathologic signals is at the submillimeter or micrometer level.This entails connecting hundreds or thousands of electrode wires on a limited surface.This study reported a class of flexible,ultrathin,highdensity electrocorticogram(ECoG)electrode arrays.The challenge of a large number of wiring arrangements was overcome by a laminated structure design and processing technology improvement.The flexible,ultrathin,high-density ECoG electrode array was conformably attached to the cortex for reliable,high spatial resolution electrophysiologic recordings.The minimum spacing between electrodes was 15μm,comparable to the diameter of a single neuron.Eight hundred electrodes were prepared with an electrode density of 4444 mm^(-2).In focal epilepsy surgery,the flexible,high-density,laminated ECoG electrode array with 36 electrodes was applied to collect epileptic spike waves inrabbits,improving the positioning accuracy of epilepsy lesions from the centimeter to the submillimeter level.The flexible,high-density,laminated ECoG electrode array has potential clinical applications in intractable epilepsy and other neurologic diseases requiring high-precision electroencephalogram acquisition.展开更多
We proposed and compared three methods(filter burnup,single energy burnup,and burnup extremum analysis)to build a high-resolution neutronics model for 238Pu production in high-flux reactors.The filter burnup and singl...We proposed and compared three methods(filter burnup,single energy burnup,and burnup extremum analysis)to build a high-resolution neutronics model for 238Pu production in high-flux reactors.The filter burnup and single energy burnup methods have no theoretical approximation and can achieve a spectrum resolution of up to~1 eV,thereby constructing the importance curve and yield curve of the full energy range.The burnup extreme analysis method combines the importance and yield curves to consider the influence of irradiation time on production efficiency,thereby constructing extreme curves.The three curves,which quantify the transmutation rate of the nuclei in each energy region,are of physical significance because they have similar distributions.A high-resolution neutronics model for ^(238)Pu production was established based on these three curves,and its universality and feasibility were proven.The neutronics model can guide the neutron spectrum optimization and improve the yield of ^(238)Pu by up to 18.81%.The neutronics model revealed the law of nuclei transmutation in all energy regions with high spectrum resolution,thus providing theoretical support for high-flux reactor design and irradiation production of ^(238)Pu.展开更多
Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely exp...Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.展开更多
In recent years,the Industrial Internet and Industry 4.0 came into being.With the development of modern industrial intelligent manufacturing technology,digital twins,Web3 and many other digital entity applications are...In recent years,the Industrial Internet and Industry 4.0 came into being.With the development of modern industrial intelligent manufacturing technology,digital twins,Web3 and many other digital entity applications are also proposed.These applications apply architectures such as distributed learning,resource sharing,and arithmetic trading,which make high demands on identity authentication,asset authentication,resource addressing,and service location.Therefore,an efficient,secure,and trustworthy Industrial Internet identity resolution system is needed.However,most of the traditional identity resolution systems follow DNS architecture or tree structure,which has the risk of a single point of failure and DDoS attack.And they cannot guarantee the security and privacy of digital identity,personal assets,and device information.So we consider a decentralized approach for identity management,identity authentication,and asset verification.In this paper,we propose a distributed trusted active identity resolution system based on the inter-planetary file system(IPFS)and non-fungible token(NFT),which can provide distributed identity resolution services.And we have designed the system architecture,identity service process,load balancing strategy and smart contract service.In addition,we use Jmeter to verify the performance of the system,and the results show that the system has good high concurrent performance and robustness.展开更多
Flurbiprofen(FB),a nonsteroidal anti-inflammatory drug,is widely employed in treating ocular inflammation owing to its remarkable anti-inflammatory effects.However,the racemic nature of its commercially available form...Flurbiprofen(FB),a nonsteroidal anti-inflammatory drug,is widely employed in treating ocular inflammation owing to its remarkable anti-inflammatory effects.However,the racemic nature of its commercially available formulation(Ocufen^(R))limits the full potential of its therapeutic activity,as the(S)-enantiomer is responsible for the desired antiinflammatory effects.Additionally,the limited corneal permeability of FB significantly restricts its bioavailability.In this study,we successfully separated the chiral isomers of FB to obtain the highly active(S)-FB.Subsequently,utilizing ion-pairing technology,we coupled(S)-FB with various counter-ions,such as sodium,diethylamine,trimethamine(TMA),and l-arginine,to enhance its ocular bioavailability.A comprehensive evaluation encompassed balanced solubility,octanol-water partition coefficient,corneal permeability,ocular pharmacokinetics,tissue distribution,and in vivo ocular anti-inflammatory activity of each chiral isomer salt.Among the various formulations,S-FBTMA exhibited superior water solubility(about 1–12 mg/ml),lipid solubility(1<lgP_(ow)<3)and corneal permeability.In comparison to Ocufen^(R),S-FBTMA demonstrated significantly higher in vivo antiinflammatory activity and lower ocular irritability(such as conjunctival congestion and tingling).The findings from this research highlight the potential of chiral separation and ion-pair enhanced permeation techniques in providing pharmaceutical enterprises focused on drug development with a valuable avenue for improving therapeutic outcomes.展开更多
Various electromagnetic signals are excited by the beam in the acceleration and beam-diagnostic elements of a particle accelerator.It is important to obtain time-domain waveforms of these signals with high temporal re...Various electromagnetic signals are excited by the beam in the acceleration and beam-diagnostic elements of a particle accelerator.It is important to obtain time-domain waveforms of these signals with high temporal resolution for research,such as the study of beam–cavity interactions and bunch-by-bunch parameter measurements.Therefore,a signal reconstruction algorithm with ultrahigh spatiotemporal resolution and bunch phase compensation based on equivalent sampling is proposed in this paper.Compared with traditional equivalent sampling,the use of phase compensation and setting the bunch signal zero-crossing point as the time reference can construct a more accurate reconstructed signal.The basic principles of the method,simulation,and experimental comparison are also introduced.Based on the beam test platform of the Shanghai Synchrotron Radiation Facility(SSRF)and the method of experimental verification,the factors that affect the reconstructed signal quality are analyzed and discussed,including the depth of the sampled data,quantization noise of analog-to-digital converter,beam transverse oscillation,and longitudinal oscillation.The results of the beam experiments show that under the user operation conditions of the SSRF,a beam excitation signal with an amplitude uncertainty of 2%can be reconstructed.展开更多
We propose a fast,adaptive multiscale resolution spectral measurement method based on compressed sensing.The method can apply variable measurement resolution over the entire spectral range to reduce the measurement ti...We propose a fast,adaptive multiscale resolution spectral measurement method based on compressed sensing.The method can apply variable measurement resolution over the entire spectral range to reduce the measurement time by over 75%compared to a global high-resolution measurement.Mimicking the characteristics of the human retina system,the resolution distribution follows the principle of gradually decreasing.The system allows the spectral peaks of interest to be captured dynamically or to be specified a priori by a user.The system was tested by measuring single and dual spectral peaks,and the results of spectral peaks are consistent with those of global high-resolution measurements.展开更多
Conventional microscopes designed for submicron resolution in biological research are hindered by a limited field of view,typically around 1 mm.This restriction poses a challenge when attempting to simultaneously anal...Conventional microscopes designed for submicron resolution in biological research are hindered by a limited field of view,typically around 1 mm.This restriction poses a challenge when attempting to simultaneously analyze various parts of a sample,such as different brain areas.In addition,conventional objective lenses struggle to perform consistently across the required range of wavelengths for brain imaging in vivo.Here we present a novel mesoscopic objective lens with an impressive field of view of 8 mm,a numerical aperture of 0.5,and a working wavelength range from 400 to 1000 nm.We achieved a resolution of 0.74μm in fluorescent beads imaging.The versatility of this lens was further demonstrated through high-quality images of mouse brain and kidney sections in a wide-field imaging system,a confocal laser scanning system,and a two-photon imaging system.This mesoscopic objective lens holds immense promise for advancing multi-wavelength imaging of large fields of view at high resolution.展开更多
Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,huma...Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,humanpose estimation has achieved great success in multiple fields such as animation and sports.However,to obtainaccurate positioning results,existing methods may suffer from large model sizes,a high number of parameters,and increased complexity,leading to high computing costs.In this paper,we propose a new lightweight featureencoder to construct a high-resolution network that reduces the number of parameters and lowers the computingcost.We also introduced a semantic enhancement module that improves global feature extraction and networkperformance by combining channel and spatial dimensions.Furthermore,we propose a dense connected spatialpyramid pooling module to compensate for the decrease in image resolution and information loss in the network.Finally,ourmethod effectively reduces the number of parameters and complexitywhile ensuring high performance.Extensive experiments show that our method achieves a competitive performance while dramatically reducing thenumber of parameters,and operational complexity.Specifically,our method can obtain 89.9%AP score on MPIIVAL,while the number of parameters and the complexity of operations were reduced by 41%and 36%,respectively.展开更多
Terahertz heterodyne receivers with high sensitivity and spectral resolution are crucial for various applications.Here,we present a room-temperature atomic terahertz heterodyne receiver that achieves ultrahigh sensiti...Terahertz heterodyne receivers with high sensitivity and spectral resolution are crucial for various applications.Here,we present a room-temperature atomic terahertz heterodyne receiver that achieves ultrahigh sensitivity and frequency resolution.At a signal frequency of 338.7 GHz,we obtain a sensitivity of 2.88±0.09V·cm^(−1)·Hz^(−1/2) for electric field measurements.The calibrated linear dynamical range spans approximately 89 dB,ranging from−110 dBV/cm to−21 dBV/cm.We demodulate a 400 symbol stream encoded in 4-state phase-shift keying,demonstrating excellent phase detection capability.By scanning the frequency of the local oscillator,we realize a terahertz spectrometer with Hz level frequency resolution.This resolution is more than two orders of magnitude higher than that of existing terahertz spectrometers.The demonstrated terahertz heterodyne receiver holds promising potential for working across the entire terahertz spectrum,significantly advancing its practical applications.展开更多
Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS...Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.展开更多
Mussel aquaculture and large yellow croaker aquaculture areas and their environmental characteristics in Zhoushan were analyzed using satellite data and in-situ surveys.A new two-step remote sensing method was propose...Mussel aquaculture and large yellow croaker aquaculture areas and their environmental characteristics in Zhoushan were analyzed using satellite data and in-situ surveys.A new two-step remote sensing method was proposed and applied to determine the basic environmental characteristics of the best mussel and large yellow croaker aquaculture areas.This methodology includes the first step of extraction of the location distribution and the second step of the extraction of internal environmental factors.The fishery ranching index(FRI1,FRI2)was established to extract the mussel and the large yellow croaker aquaculture area in Zhoushan,using Gaofen-1(GF-1)and Gaofen-6(GF-6)satellite data with a special resolution of 2 m.In the second step,the environmental factors such as sea surface temperature(SST),chlorophyll a(Chl-a)concentration,current and tide,suspended sediment concentration(SSC)in mussel aquaculture area and large yellow croaker aquaculture area were extracted and analyzed in detail.The results show the following three points.(1)For the extraction of the mussel aquaculture area,FRI1 and FRI2 are complementary,and the combination of FRI1 and FRI2 is suitable to extract the mussel aquaculture area.As for the large yellow croaker aquaculture area extraction,FRI2 is suitable.(2)Mussel aquaculture and the large yellow croaker aquaculture area in Zhoushan are mainly located on the side near the islands that are away from the eastern open waters.The water environment factor template suitable for mussel and large yellow croaker aquaculture was determined.(3)This two-step remote sensing method can be used for the preliminary screening of potential site selection for the mussels and large yellow croaker aquaculture area in the future.the fishery ranching index(FRI1,FRI2)in this paper can be applied to extract the mussel and large yellow croaker aquaculture areas in coastal waters around the world.展开更多
High-energy gamma-ray radiography has exceptional penetration ability and has become an indispensable nondestructive testing(NDT)tool in various fields.For high-energy photons,point projection radiography is almost th...High-energy gamma-ray radiography has exceptional penetration ability and has become an indispensable nondestructive testing(NDT)tool in various fields.For high-energy photons,point projection radiography is almost the only feasible imaging method,and its spatial resolution is primarily constrained by the size of the gamma-ray source.In conventional industrial applications,gamma-ray sources are commonly based on electron beams driven by accelerators,utilizing the process of bremsstrahlung radiation.The size of the gamma-ray source is dependent on the dimensional characteristics of the electron beam.Extensive research has been conducted on various advanced accelerator technologies that have the potential to greatly improve spatial resolution in NDT.In our investigation of laser-driven gamma-ray sources,a spatial resolution of about 90μm is achieved when the areal density of the penetrated object is 120 g/cm^(2).A virtual source approach is proposed to optimize the size of the gamma-ray source used for imaging,with the aim of maximizing spatial resolution.In this virtual source approach,the gamma ray can be considered as being emitted from a virtual source within the convertor,where the equivalent gamma-ray source size in imaging is much smaller than the actual emission area.On the basis of Monte Carlo simulations,we derive a set of evaluation formulas for virtual source scale and gamma-ray emission angle.Under optimal conditions,the virtual source size can be as small as 15μm,which can significantly improve the spatial resolution of high-penetration imaging to less than 50μm.展开更多
The spaceborne platform has unprecedently provided the global eddy-permitting(typically about 0.25°)products of sea surface salinity(SSS),however the existing SSS products can hardly resolve mesoscale motions due...The spaceborne platform has unprecedently provided the global eddy-permitting(typically about 0.25°)products of sea surface salinity(SSS),however the existing SSS products can hardly resolve mesoscale motions due to the heavy noises therein and the over-smoothing in denoising processes.By means of the multi-fractal fusion(MFF),the high-resolution SSS product is synthesized with the template of sea surface temperature(SST).Two low-resolution SSS products and four SST products are considered as the source data and the templates respectively to determine the best combination.The fused products are validated by the in situ observations and intercompared via SSS maps,Singularity Exponent maps and wavenumber spectra.The results demonstrate that the MFF can perform a good work in mitigating the noises and improving the resolution.The combination of the climate change initiative SSS and the remote sensing system SST can produce the 0.1°denoised product whose global mean standard derivation of salinity against Argo is 0.21 and the feature resolution can reach 30−40 km.展开更多
Slope limiters play an essential role in maintaining the non-oscillatory behavior of high-resolution methods for nonlinear conservation laws.The family of minmod limiters serves as the prototype example.Here,we revisi...Slope limiters play an essential role in maintaining the non-oscillatory behavior of high-resolution methods for nonlinear conservation laws.The family of minmod limiters serves as the prototype example.Here,we revisit the question of non-oscillatory behavior of high-resolution central schemes in terms of the slope limiter proposed by van Albada et al.(Astron Astrophys 108:76–84,1982).The van Albada(vA)limiter is smoother near extrema,and consequently,in many cases,it outperforms the results obtained using the standard minmod limiter.In particular,we prove that the vA limiter ensures the one-dimensional Total-Variation Diminishing(TVD)stability and demonstrate that it yields noticeable improvement in computation of one-and two-dimensional systems.展开更多
High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-...High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution enhancement.Our method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data transmission.To validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical applications.The proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement tasks.This unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom dataset.The implications of this research extend to optimizing low-bitrate video streaming scenarios.By selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth conditions.Empirical results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual quality.This work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited environments.The innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.展开更多
The research examined the role of media in promoting peace and conflict resolution in North Kivu,Democratic Republic of Congo.The security situation in the Democratic Republic of the Congo(DRC),particularly in the eas...The research examined the role of media in promoting peace and conflict resolution in North Kivu,Democratic Republic of Congo.The security situation in the Democratic Republic of the Congo(DRC),particularly in the eastern region of North Kivu,has been deteriorating.The study was anchored in social identity theory.The research methodology employed for this study was qualitative,focusing on the analysis of Mr.Edgar Mateso’s contributions to Radio Okapi’s“Dialogue entre Congolais”program during the period from 2019 to 2023.The research was conducted within the broader context of the persistent war and conflict in the Democratic Republic of Congo,providing valuable insights into the dynamics and challenges of addressing the ongoing insecurity and violence in the region.The study found that media,exemplified by Radio Okapi,plays a multifaceted and significant role in promoting peace and conflict resolution in North Kivu,Democratic Republic of Congo(DRC).It serves as a critical source of accurate information,enabling informed decision-making regarding ceasefire agreements,peace talks,and humanitarian aid.Media fosters dialogue and understanding among different stakeholders,contributing to reconciliation efforts.Additionally,it raises awareness about the human cost of the conflict,challenges misinformation,monitors peace agreements,amplifies the concerns of the affected population,and promotes human rights and justice.Media also engages youth,serves as an early warning system,and attracts global attention to the conflict.It is recommended that media organizations in North Kivu continue their efforts to facilitate dialogue and understanding among different stakeholder groups.Additionally,media should maintain its focus on raising awareness about the human cost of the conflict,ensuring that the suffering of civilians remains in the spotlight and generates international empathy and support.Media outlets should also continue their role as watchdogs by closely monitoring the implementation of ceasefire agreements and reporting any violations transparently.To strengthen media’s role in promoting peace,there should be continued advocacy for peace through dedicated radio programs,news reports,and editorial content.Internationally,media should continue to provide comprehensive coverage of the conflict in North Kivu,attracting global attention and shaping the perception of the conflict on the global stage.Lastly,media organizations should preserve a lasting legacy of peace by archiving peace-related content,documentaries,and narratives of reconciliation.展开更多
With the rapid development of the Internet,the network ideology of colleges and universities is facing severe challenges.This paper deeply analyzes the root of the risk of network ideology and makes a specific investi...With the rapid development of the Internet,the network ideology of colleges and universities is facing severe challenges.This paper deeply analyzes the root of the risk of network ideology and makes a specific investigation of the status quo of network public opinion in colleges and universities.On this basis,the study explores and puts forward a series of targeted risk prevention and resolution strategies,aiming at providing a systematic solution for the network ideology security of colleges and universities.In this paper,with the combination of theory and practice as the path,we verify the effectiveness and applicability of the proposed strategy through the analysis of the implementation effect of the strategy.This study also provides theoretical support and practical guidance for the prevention and control of ideological risks and public opinion guidance in universities under the network environment,which has important practical significance.With the continuous progress of network technology,the threats to the network ideology of colleges and universities are increasing.For example,the spread of false information has become a serious problem affecting the security of college network ideology.展开更多
We report a comprehensive numerical study of super resolution (SR) structured illumination microscopy (SIM) utilizing the classic Heintzmann-Cremer SIM process and algorithm. In particular, we investigated the impact ...We report a comprehensive numerical study of super resolution (SR) structured illumination microscopy (SIM) utilizing the classic Heintzmann-Cremer SIM process and algorithm. In particular, we investigated the impact of the diffraction limit of the underlying imaging system on the optimal SIM grating frequency that can be used to obtain the highest SR enhancement with non-continuous spatial frequency support. Besides confirming the previous theoretical and experimental work that SR-SIM can achieve an enhancement close to 3 times the diffraction limit with grating pattern illuminations, we also observe and report a series of more subtle effects of SR-SIM with non-continuous spatial frequency support. Our simulations show that when the SIM grating frequency exceeds twice that of the diffraction limit, the higher SIM grating frequency can help achieve a higher SR enhancement for the underlying imaging systems whose diffraction limit is low, though this enhancement is obtained at the cost of losing resolution at some lower resolution targets. Our simulations also show that, for underlying imaging systems with high diffraction limits, however, SR-SIM grating frequencies above twice the diffraction limits tend to bring no significant extra enhancement. Furthermore, we observed that there exists a limit grating frequency above which the SR enhancement effect is lost, and the reconstructed images essentially have the same resolution as the one obtained directly from the underlying imaging system without using the SIM process.展开更多
Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrat...Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrates high spatial resolution remote sensing imagery with deep learning techniques,proposing a novel method for identifying rooftops of traditional Chinese village buildings using high-definition remote sensing images.Using 0.54 m spatial resolution imagery of traditional village areas as the data source,this method analyzes the geometric and spectral image characteristics of village building rooftops.It constructs a deep learning feature sample library tailored to the target types.Employing a semantically enhanced version of the improved Mask R-CNN(Mask Region-based Convolutional Neural Network)for building recognition,the study conducts experiments on localized imagery from different regions.The results demonstrated that the modified Mask R-CNN effectively identifies traditional village building rooftops,achieving an of 0.7520 and an of 0.7400.It improves the current problem of misidentification and missed detection caused by feature heterogeneity.This method offers a viable and effective approach for industrialized data monitoring of traditional villages,contributing to their sustainable development.展开更多
基金support of the National Natural Science Foundation of China(Nos.U20A6001,12002190,11972207,and 11921002)the Fundamental Research Funds for the Central Universities,China(No.SWUKQ22029)the Chongqing Natural Science Foundation of China(No.CSTB2022NSCQ-MSX1635).
文摘High spatiotemporal resolution brain electrical signals are critical for basic neuroscience research and high-precision focus diagnostic localization,as the spatial scale of some pathologic signals is at the submillimeter or micrometer level.This entails connecting hundreds or thousands of electrode wires on a limited surface.This study reported a class of flexible,ultrathin,highdensity electrocorticogram(ECoG)electrode arrays.The challenge of a large number of wiring arrangements was overcome by a laminated structure design and processing technology improvement.The flexible,ultrathin,high-density ECoG electrode array was conformably attached to the cortex for reliable,high spatial resolution electrophysiologic recordings.The minimum spacing between electrodes was 15μm,comparable to the diameter of a single neuron.Eight hundred electrodes were prepared with an electrode density of 4444 mm^(-2).In focal epilepsy surgery,the flexible,high-density,laminated ECoG electrode array with 36 electrodes was applied to collect epileptic spike waves inrabbits,improving the positioning accuracy of epilepsy lesions from the centimeter to the submillimeter level.The flexible,high-density,laminated ECoG electrode array has potential clinical applications in intractable epilepsy and other neurologic diseases requiring high-precision electroencephalogram acquisition.
基金supported by Natural Science Foundation of China (No. 12305190)Lingchuang Research Project of China National Nuclear Corporation (CNNC)the Science and Technology on Reactor System Design Technology Laboratory
文摘We proposed and compared three methods(filter burnup,single energy burnup,and burnup extremum analysis)to build a high-resolution neutronics model for 238Pu production in high-flux reactors.The filter burnup and single energy burnup methods have no theoretical approximation and can achieve a spectrum resolution of up to~1 eV,thereby constructing the importance curve and yield curve of the full energy range.The burnup extreme analysis method combines the importance and yield curves to consider the influence of irradiation time on production efficiency,thereby constructing extreme curves.The three curves,which quantify the transmutation rate of the nuclei in each energy region,are of physical significance because they have similar distributions.A high-resolution neutronics model for ^(238)Pu production was established based on these three curves,and its universality and feasibility were proven.The neutronics model can guide the neutron spectrum optimization and improve the yield of ^(238)Pu by up to 18.81%.The neutronics model revealed the law of nuclei transmutation in all energy regions with high spectrum resolution,thus providing theoretical support for high-flux reactor design and irradiation production of ^(238)Pu.
基金the TCL Science and Technology Innovation Fundthe Youth Science and Technology Talent Promotion Project of Jiangsu Association for Science and Technology,Grant/Award Number:JSTJ‐2023‐017+4 种基金Shenzhen Municipal Science and Technology Innovation Council,Grant/Award Number:JSGG20220831105002004National Natural Science Foundation of China,Grant/Award Number:62201468Postdoctoral Research Foundation of China,Grant/Award Number:2022M722599the Fundamental Research Funds for the Central Universities,Grant/Award Number:D5000210966the Guangdong Basic and Applied Basic Research Foundation,Grant/Award Number:2021A1515110079。
文摘Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.
基金supported by the National Natural Science Foundation of China(No.92267301).
文摘In recent years,the Industrial Internet and Industry 4.0 came into being.With the development of modern industrial intelligent manufacturing technology,digital twins,Web3 and many other digital entity applications are also proposed.These applications apply architectures such as distributed learning,resource sharing,and arithmetic trading,which make high demands on identity authentication,asset authentication,resource addressing,and service location.Therefore,an efficient,secure,and trustworthy Industrial Internet identity resolution system is needed.However,most of the traditional identity resolution systems follow DNS architecture or tree structure,which has the risk of a single point of failure and DDoS attack.And they cannot guarantee the security and privacy of digital identity,personal assets,and device information.So we consider a decentralized approach for identity management,identity authentication,and asset verification.In this paper,we propose a distributed trusted active identity resolution system based on the inter-planetary file system(IPFS)and non-fungible token(NFT),which can provide distributed identity resolution services.And we have designed the system architecture,identity service process,load balancing strategy and smart contract service.In addition,we use Jmeter to verify the performance of the system,and the results show that the system has good high concurrent performance and robustness.
基金financially supported by the National Postdoctoral Foundation of China(No.2023M730375)Liaoning Province Department of Education Project(No.LJKMZ20221365)the State Key Laboratory of Natural and Biomimetic Drugs(No.K202215)。
文摘Flurbiprofen(FB),a nonsteroidal anti-inflammatory drug,is widely employed in treating ocular inflammation owing to its remarkable anti-inflammatory effects.However,the racemic nature of its commercially available formulation(Ocufen^(R))limits the full potential of its therapeutic activity,as the(S)-enantiomer is responsible for the desired antiinflammatory effects.Additionally,the limited corneal permeability of FB significantly restricts its bioavailability.In this study,we successfully separated the chiral isomers of FB to obtain the highly active(S)-FB.Subsequently,utilizing ion-pairing technology,we coupled(S)-FB with various counter-ions,such as sodium,diethylamine,trimethamine(TMA),and l-arginine,to enhance its ocular bioavailability.A comprehensive evaluation encompassed balanced solubility,octanol-water partition coefficient,corneal permeability,ocular pharmacokinetics,tissue distribution,and in vivo ocular anti-inflammatory activity of each chiral isomer salt.Among the various formulations,S-FBTMA exhibited superior water solubility(about 1–12 mg/ml),lipid solubility(1<lgP_(ow)<3)and corneal permeability.In comparison to Ocufen^(R),S-FBTMA demonstrated significantly higher in vivo antiinflammatory activity and lower ocular irritability(such as conjunctival congestion and tingling).The findings from this research highlight the potential of chiral separation and ion-pair enhanced permeation techniques in providing pharmaceutical enterprises focused on drug development with a valuable avenue for improving therapeutic outcomes.
基金supported by the National Key R&D Program of China(No.2022YFA1602201)the international partnership program of the Chinese Academy of Sciences(No.211134KYSB20200057).
文摘Various electromagnetic signals are excited by the beam in the acceleration and beam-diagnostic elements of a particle accelerator.It is important to obtain time-domain waveforms of these signals with high temporal resolution for research,such as the study of beam–cavity interactions and bunch-by-bunch parameter measurements.Therefore,a signal reconstruction algorithm with ultrahigh spatiotemporal resolution and bunch phase compensation based on equivalent sampling is proposed in this paper.Compared with traditional equivalent sampling,the use of phase compensation and setting the bunch signal zero-crossing point as the time reference can construct a more accurate reconstructed signal.The basic principles of the method,simulation,and experimental comparison are also introduced.Based on the beam test platform of the Shanghai Synchrotron Radiation Facility(SSRF)and the method of experimental verification,the factors that affect the reconstructed signal quality are analyzed and discussed,including the depth of the sampled data,quantization noise of analog-to-digital converter,beam transverse oscillation,and longitudinal oscillation.The results of the beam experiments show that under the user operation conditions of the SSRF,a beam excitation signal with an amplitude uncertainty of 2%can be reconstructed.
基金Project supported by the Natural Science Foundation of Shandong Province,China(Grant Nos.ZR2020MF119 and ZR2020MA082)the National Natural Science Foundation of China(Grant No.62002208)the National Key Research and Development Program of China(Grant No.2018YFB0504302).
文摘We propose a fast,adaptive multiscale resolution spectral measurement method based on compressed sensing.The method can apply variable measurement resolution over the entire spectral range to reduce the measurement time by over 75%compared to a global high-resolution measurement.Mimicking the characteristics of the human retina system,the resolution distribution follows the principle of gradually decreasing.The system allows the spectral peaks of interest to be captured dynamically or to be specified a priori by a user.The system was tested by measuring single and dual spectral peaks,and the results of spectral peaks are consistent with those of global high-resolution measurements.
基金supported by National Key R&D Program of China(grant no.2022YFC2404201)the Chinese Academy of Sciences Project for Young Scientists in Basic Research(grant no.YSBR067).
文摘Conventional microscopes designed for submicron resolution in biological research are hindered by a limited field of view,typically around 1 mm.This restriction poses a challenge when attempting to simultaneously analyze various parts of a sample,such as different brain areas.In addition,conventional objective lenses struggle to perform consistently across the required range of wavelengths for brain imaging in vivo.Here we present a novel mesoscopic objective lens with an impressive field of view of 8 mm,a numerical aperture of 0.5,and a working wavelength range from 400 to 1000 nm.We achieved a resolution of 0.74μm in fluorescent beads imaging.The versatility of this lens was further demonstrated through high-quality images of mouse brain and kidney sections in a wide-field imaging system,a confocal laser scanning system,and a two-photon imaging system.This mesoscopic objective lens holds immense promise for advancing multi-wavelength imaging of large fields of view at high resolution.
基金the National Natural Science Foundation of China(Grant Number 62076246).
文摘Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,humanpose estimation has achieved great success in multiple fields such as animation and sports.However,to obtainaccurate positioning results,existing methods may suffer from large model sizes,a high number of parameters,and increased complexity,leading to high computing costs.In this paper,we propose a new lightweight featureencoder to construct a high-resolution network that reduces the number of parameters and lowers the computingcost.We also introduced a semantic enhancement module that improves global feature extraction and networkperformance by combining channel and spatial dimensions.Furthermore,we propose a dense connected spatialpyramid pooling module to compensate for the decrease in image resolution and information loss in the network.Finally,ourmethod effectively reduces the number of parameters and complexitywhile ensuring high performance.Extensive experiments show that our method achieves a competitive performance while dramatically reducing thenumber of parameters,and operational complexity.Specifically,our method can obtain 89.9%AP score on MPIIVAL,while the number of parameters and the complexity of operations were reduced by 41%and 36%,respectively.
基金supported by the National Key Research and Development Program of China(Grant No.2021YFA1402004)the Key-Area Research and Development Program of Guangdong Province,China(Grant Nos.2019B030330001 and 2020B0301030008)+2 种基金the National Natural Science Foundation of China(Grant Nos.12225405,12204182,and U20A2074)the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0301705)the Natural Science Foundation of Guangdong Province,China(Grant No.2022A1515012026).
文摘Terahertz heterodyne receivers with high sensitivity and spectral resolution are crucial for various applications.Here,we present a room-temperature atomic terahertz heterodyne receiver that achieves ultrahigh sensitivity and frequency resolution.At a signal frequency of 338.7 GHz,we obtain a sensitivity of 2.88±0.09V·cm^(−1)·Hz^(−1/2) for electric field measurements.The calibrated linear dynamical range spans approximately 89 dB,ranging from−110 dBV/cm to−21 dBV/cm.We demodulate a 400 symbol stream encoded in 4-state phase-shift keying,demonstrating excellent phase detection capability.By scanning the frequency of the local oscillator,we realize a terahertz spectrometer with Hz level frequency resolution.This resolution is more than two orders of magnitude higher than that of existing terahertz spectrometers.The demonstrated terahertz heterodyne receiver holds promising potential for working across the entire terahertz spectrum,significantly advancing its practical applications.
基金National Key R&D Program of China,Grant/Award Number:2022YFC3300704National Natural Science Foundation of China,Grant/Award Numbers:62171038,62088101,62006023。
文摘Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.
基金The National Key Research and Development Program of China under contract Nos 2023YFD2401900 and 2020YFD09008004the National Natural Science Foundation of China Key International(Regional)Cooperative Research Project under contract No.42020104009the Basic Public Welfare Research Program of Zhejiang Province under contract No.LGF21D010004.
文摘Mussel aquaculture and large yellow croaker aquaculture areas and their environmental characteristics in Zhoushan were analyzed using satellite data and in-situ surveys.A new two-step remote sensing method was proposed and applied to determine the basic environmental characteristics of the best mussel and large yellow croaker aquaculture areas.This methodology includes the first step of extraction of the location distribution and the second step of the extraction of internal environmental factors.The fishery ranching index(FRI1,FRI2)was established to extract the mussel and the large yellow croaker aquaculture area in Zhoushan,using Gaofen-1(GF-1)and Gaofen-6(GF-6)satellite data with a special resolution of 2 m.In the second step,the environmental factors such as sea surface temperature(SST),chlorophyll a(Chl-a)concentration,current and tide,suspended sediment concentration(SSC)in mussel aquaculture area and large yellow croaker aquaculture area were extracted and analyzed in detail.The results show the following three points.(1)For the extraction of the mussel aquaculture area,FRI1 and FRI2 are complementary,and the combination of FRI1 and FRI2 is suitable to extract the mussel aquaculture area.As for the large yellow croaker aquaculture area extraction,FRI2 is suitable.(2)Mussel aquaculture and the large yellow croaker aquaculture area in Zhoushan are mainly located on the side near the islands that are away from the eastern open waters.The water environment factor template suitable for mussel and large yellow croaker aquaculture was determined.(3)This two-step remote sensing method can be used for the preliminary screening of potential site selection for the mussels and large yellow croaker aquaculture area in the future.the fishery ranching index(FRI1,FRI2)in this paper can be applied to extract the mussel and large yellow croaker aquaculture areas in coastal waters around the world.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.12175212,11991071,12004353,11975214,and 11905202)the National Key R&D Program of China(Grant No.2022YFA1603300)+1 种基金the Science Challenge Project(Project No.TZ2018005)the Sciences and Technology on Plasma Physics Laboratory at CAEP(Grant No.6142A04200103).
文摘High-energy gamma-ray radiography has exceptional penetration ability and has become an indispensable nondestructive testing(NDT)tool in various fields.For high-energy photons,point projection radiography is almost the only feasible imaging method,and its spatial resolution is primarily constrained by the size of the gamma-ray source.In conventional industrial applications,gamma-ray sources are commonly based on electron beams driven by accelerators,utilizing the process of bremsstrahlung radiation.The size of the gamma-ray source is dependent on the dimensional characteristics of the electron beam.Extensive research has been conducted on various advanced accelerator technologies that have the potential to greatly improve spatial resolution in NDT.In our investigation of laser-driven gamma-ray sources,a spatial resolution of about 90μm is achieved when the areal density of the penetrated object is 120 g/cm^(2).A virtual source approach is proposed to optimize the size of the gamma-ray source used for imaging,with the aim of maximizing spatial resolution.In this virtual source approach,the gamma ray can be considered as being emitted from a virtual source within the convertor,where the equivalent gamma-ray source size in imaging is much smaller than the actual emission area.On the basis of Monte Carlo simulations,we derive a set of evaluation formulas for virtual source scale and gamma-ray emission angle.Under optimal conditions,the virtual source size can be as small as 15μm,which can significantly improve the spatial resolution of high-penetration imaging to less than 50μm.
基金The National Natural Science Foundation of China under contract Nos 42206205,41976188 and 42276205.
文摘The spaceborne platform has unprecedently provided the global eddy-permitting(typically about 0.25°)products of sea surface salinity(SSS),however the existing SSS products can hardly resolve mesoscale motions due to the heavy noises therein and the over-smoothing in denoising processes.By means of the multi-fractal fusion(MFF),the high-resolution SSS product is synthesized with the template of sea surface temperature(SST).Two low-resolution SSS products and four SST products are considered as the source data and the templates respectively to determine the best combination.The fused products are validated by the in situ observations and intercompared via SSS maps,Singularity Exponent maps and wavenumber spectra.The results demonstrate that the MFF can perform a good work in mitigating the noises and improving the resolution.The combination of the climate change initiative SSS and the remote sensing system SST can produce the 0.1°denoised product whose global mean standard derivation of salinity against Argo is 0.21 and the feature resolution can reach 30−40 km.
基金Research was supported in part by the ONR Grant N00014-2112773.
文摘Slope limiters play an essential role in maintaining the non-oscillatory behavior of high-resolution methods for nonlinear conservation laws.The family of minmod limiters serves as the prototype example.Here,we revisit the question of non-oscillatory behavior of high-resolution central schemes in terms of the slope limiter proposed by van Albada et al.(Astron Astrophys 108:76–84,1982).The van Albada(vA)limiter is smoother near extrema,and consequently,in many cases,it outperforms the results obtained using the standard minmod limiter.In particular,we prove that the vA limiter ensures the one-dimensional Total-Variation Diminishing(TVD)stability and demonstrate that it yields noticeable improvement in computation of one-and two-dimensional systems.
基金funded by National Key Research and Development Program of China(No.2022YFC3302103).
文摘High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution enhancement.Our method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data transmission.To validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical applications.The proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement tasks.This unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom dataset.The implications of this research extend to optimizing low-bitrate video streaming scenarios.By selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth conditions.Empirical results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual quality.This work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited environments.The innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.
文摘The research examined the role of media in promoting peace and conflict resolution in North Kivu,Democratic Republic of Congo.The security situation in the Democratic Republic of the Congo(DRC),particularly in the eastern region of North Kivu,has been deteriorating.The study was anchored in social identity theory.The research methodology employed for this study was qualitative,focusing on the analysis of Mr.Edgar Mateso’s contributions to Radio Okapi’s“Dialogue entre Congolais”program during the period from 2019 to 2023.The research was conducted within the broader context of the persistent war and conflict in the Democratic Republic of Congo,providing valuable insights into the dynamics and challenges of addressing the ongoing insecurity and violence in the region.The study found that media,exemplified by Radio Okapi,plays a multifaceted and significant role in promoting peace and conflict resolution in North Kivu,Democratic Republic of Congo(DRC).It serves as a critical source of accurate information,enabling informed decision-making regarding ceasefire agreements,peace talks,and humanitarian aid.Media fosters dialogue and understanding among different stakeholders,contributing to reconciliation efforts.Additionally,it raises awareness about the human cost of the conflict,challenges misinformation,monitors peace agreements,amplifies the concerns of the affected population,and promotes human rights and justice.Media also engages youth,serves as an early warning system,and attracts global attention to the conflict.It is recommended that media organizations in North Kivu continue their efforts to facilitate dialogue and understanding among different stakeholder groups.Additionally,media should maintain its focus on raising awareness about the human cost of the conflict,ensuring that the suffering of civilians remains in the spotlight and generates international empathy and support.Media outlets should also continue their role as watchdogs by closely monitoring the implementation of ceasefire agreements and reporting any violations transparently.To strengthen media’s role in promoting peace,there should be continued advocacy for peace through dedicated radio programs,news reports,and editorial content.Internationally,media should continue to provide comprehensive coverage of the conflict in North Kivu,attracting global attention and shaping the perception of the conflict on the global stage.Lastly,media organizations should preserve a lasting legacy of peace by archiving peace-related content,documentaries,and narratives of reconciliation.
文摘With the rapid development of the Internet,the network ideology of colleges and universities is facing severe challenges.This paper deeply analyzes the root of the risk of network ideology and makes a specific investigation of the status quo of network public opinion in colleges and universities.On this basis,the study explores and puts forward a series of targeted risk prevention and resolution strategies,aiming at providing a systematic solution for the network ideology security of colleges and universities.In this paper,with the combination of theory and practice as the path,we verify the effectiveness and applicability of the proposed strategy through the analysis of the implementation effect of the strategy.This study also provides theoretical support and practical guidance for the prevention and control of ideological risks and public opinion guidance in universities under the network environment,which has important practical significance.With the continuous progress of network technology,the threats to the network ideology of colleges and universities are increasing.For example,the spread of false information has become a serious problem affecting the security of college network ideology.
文摘We report a comprehensive numerical study of super resolution (SR) structured illumination microscopy (SIM) utilizing the classic Heintzmann-Cremer SIM process and algorithm. In particular, we investigated the impact of the diffraction limit of the underlying imaging system on the optimal SIM grating frequency that can be used to obtain the highest SR enhancement with non-continuous spatial frequency support. Besides confirming the previous theoretical and experimental work that SR-SIM can achieve an enhancement close to 3 times the diffraction limit with grating pattern illuminations, we also observe and report a series of more subtle effects of SR-SIM with non-continuous spatial frequency support. Our simulations show that when the SIM grating frequency exceeds twice that of the diffraction limit, the higher SIM grating frequency can help achieve a higher SR enhancement for the underlying imaging systems whose diffraction limit is low, though this enhancement is obtained at the cost of losing resolution at some lower resolution targets. Our simulations also show that, for underlying imaging systems with high diffraction limits, however, SR-SIM grating frequencies above twice the diffraction limits tend to bring no significant extra enhancement. Furthermore, we observed that there exists a limit grating frequency above which the SR enhancement effect is lost, and the reconstructed images essentially have the same resolution as the one obtained directly from the underlying imaging system without using the SIM process.
文摘Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrates high spatial resolution remote sensing imagery with deep learning techniques,proposing a novel method for identifying rooftops of traditional Chinese village buildings using high-definition remote sensing images.Using 0.54 m spatial resolution imagery of traditional village areas as the data source,this method analyzes the geometric and spectral image characteristics of village building rooftops.It constructs a deep learning feature sample library tailored to the target types.Employing a semantically enhanced version of the improved Mask R-CNN(Mask Region-based Convolutional Neural Network)for building recognition,the study conducts experiments on localized imagery from different regions.The results demonstrated that the modified Mask R-CNN effectively identifies traditional village building rooftops,achieving an of 0.7520 and an of 0.7400.It improves the current problem of misidentification and missed detection caused by feature heterogeneity.This method offers a viable and effective approach for industrialized data monitoring of traditional villages,contributing to their sustainable development.
