Owing to the dramatic mobile IP growth,the emerging Internet of Things,and cloud-based applications,wireless networking is witnessing a paradigm shift.By fully exploiting spatial degrees of freedom,massive multiple-in...Owing to the dramatic mobile IP growth,the emerging Internet of Things,and cloud-based applications,wireless networking is witnessing a paradigm shift.By fully exploiting spatial degrees of freedom,massive multiple-input-multiple-output(MIMO) systems promise significant gains in data rates and link reliability.Although the research community has recognized the theoretical benefits of these systems,building the hardware of such complex systems is a challenge in practice.This paper presents a time division duplex(TDD)-based 128-antenna massive MIMO prototype system from theory to reality.First,an analytical signal model is provided to facilitate the setup of a feasible massive MIMO prototype system.Second,a link-level simulation consistent with practical TDDbased massive MIMO systems is conducted to guide and validate the massive MIMO system design.We design and implement the TDDbased 128-antenna massive MIMO prototype system with the guidelines obtained from the link-level simulation.Uplink real-time video transmission and downlink data transmission under the configuration of multiple single-antenna users are achieved.Comparisons withstate-of-the-art prototypes demonstrate the advantages of the proposed system in terms of antenna number,bandwidth,latency,and throughput.The proposed system is also equipped with scalability,which makes the system applicable to a wide range of massive scenarios.展开更多
The prototype system Object-Oriented Computer Aided Process Planning(OOCAP),which aims at simulating machine process planning for designed componentsby constructing a knowledge based system in an Object-Oriented envir...The prototype system Object-Oriented Computer Aided Process Planning(OOCAP),which aims at simulating machine process planning for designed componentsby constructing a knowledge based system in an Object-Oriented environment Smalltalkand is implemented in PS/2 80,is presented in this paper.The integration of rules,factsand operations in objects is the key concept in the system.Additionally,the system simu-lares machining processes and shows the whole procedure from selecting materials to get-ring products with animations.展开更多
In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaini...In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaining energy levels and battery replacement is both inadequate and costly.This paper introduces an energy management system for indoor IoT,which includes a mobile energy station(ES)for enabling on-demand wireless energy transfer(WET)in radio frequency(RF),some energy receivers(ERs),and a cloud server.By implementing a two-stage positioning system and embedding energy receivers into traditional IoT devices,we robustly manage their energy storage.The experimental results demonstrate that the energy receiver can harvest a minimum power of 58 mW.展开更多
无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到...无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。展开更多
To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,wh...To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,which can acquire reference signals through flexible wired/wireless switching access.Based on this method,the Minimum Mean Square Error algorithm with known channel state information is derived in detail,determining the upper limit of the cancellation performance,and the Adaptive Dithered Linear Search algorithm for real-time engineering cancellation is given.The correctness of theoretical analysis is verified by the practical self-interference channel measured by a vector network analyzer.Furthermore,we have designed and implemented the corresponding multiinterference cancellation prototype with the digitallyassisted structure,capable of handling multiple interferences(up to three)and supporting a large receive bandwidth of 100 MHz as well as a wide frequency coverage from 30 MHz to 3000 MHz.Prototype test results demonstrate that in the presence of three interferences,when the single interference bandwidth is 0.2/2/20 MHz(corresponding to the receive bandwidth of 2/20/100 MHz),the cancellation performance can reach 46/32/22 dB or more.展开更多
Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each l...Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.展开更多
Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are st...Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
Digital Ocean is a new research domain of Digital Earth.Because of the spatiotemporal,three-dimensional(3D)and intrinsically dynamic nature of ocean data,it is more difficult to make a breakthrough in this domain.The ...Digital Ocean is a new research domain of Digital Earth.Because of the spatiotemporal,three-dimensional(3D)and intrinsically dynamic nature of ocean data,it is more difficult to make a breakthrough in this domain.The construction of the China Digital Ocean Prototype System(CDOPS)pushes Digital Ocean a step forward from its operation as a mere concept to its achievement as a realistic system.In this paper,the technical framework of the CDOPS is discussed,including its data,function,and application layers.Then,two key technologies are studied in detail that will enable the construction of the 3D ocean environment and the visualization of the ocean model output data.Practical demonstrations show that the CDOPS provides a technical reference for the development of Digital Ocean.This paper is based on an ongoing research project of the development of CDOPS that aims at the facilitation,integration,sharing,accessing,visualization,and use of the ocean data and model computing data from the Digital Earth perspective.展开更多
Digital Earth is an information expression of the real Earth,and is a new way of understanding the Earth in the twenty-first century.This paper introduces a Digital Earth Prototype System(DEPS)developed at the Chinese...Digital Earth is an information expression of the real Earth,and is a new way of understanding the Earth in the twenty-first century.This paper introduces a Digital Earth Prototype System(DEPS)developed at the Chinese Academy of Sciences(CAS)and supported by the Knowledge Innovation Program of the Chinese Academy of Sciences.Discussions are made to the theoretical model and technical framework of the Digital Earth,and its related key technologies on spatial information processing,spatial data warehouse technology,virtual reality technology,high-performance and parallel computing.The DEPS consists of seven sub-systems including the spatial data,metadata,model database,Grid geoscience computing,spatial information database,maps service and virtual reality.Meanwhile,we developed a series of application systems such as the environment monitoring for the Olympic Games 2008 in Beijing,natural disasters evaluation,digital city,digital archeology,Asia regional aerosol and climate change.The DEPS/CAS displayed the application ability and potential of the Digital Earth in three levels:the global,national and regional.展开更多
Digital lightning is an important thematic branch of the digital earth.Lightning data are complex,momentary,discrete,dynamic and spatio-temporal in nature.Hence,making great progress in their management,analysis and s...Digital lightning is an important thematic branch of the digital earth.Lightning data are complex,momentary,discrete,dynamic and spatio-temporal in nature.Hence,making great progress in their management,analysis and service is challenging.Many studies have been directed towards this field all over the world.Some different relevant systems are currently available.However,most of them focus on a single or a few aspects of lightning applications,rather than taking an overall account of lightning detection,management,analysis and service from the strategic perspective of the digital earth.Lightning disaster also demands a better developed spatial information technology in this field than at present.The idea of the digital earth offers a reasonable scheme to address these issues.Based on reviews of the concept,development and progress of the digital earth,an integrated technical framework of a digital lightning prototype system(DLPS)is proposed,including its data,functions and implementation of subsystems,which aims at the facilitation,management,accessing,visualisation,application,release and sharing of lightning data.Some key technologies are also carefully discussed to facilitate the construction of the DLPS.This framework could provide a helpful guide to future lightning research and hazard mitigation,as well as enrich connotation on the digital earth.So far,there are still many difficulties in multilevel grid construction that need to be solved.展开更多
Transmission of 40Gbit/s NRZ signal was successfully demonstrated over 219km of installed SMF in KT's Daejeon area network. After transmission, the measured power penalty was 0.5dB for all the tributary channels.
Facing the challenges of the next generation exascale computing,National University of Defense Technology has developed a prototype system to explore opportunities,solutions,and limits toward the next generation Tianh...Facing the challenges of the next generation exascale computing,National University of Defense Technology has developed a prototype system to explore opportunities,solutions,and limits toward the next generation Tianhe system.This paper briefly introduces the prototype system,which is deployed at the National Supercomputer Center in Tianjin and has a theoretical peak performance of 3.15 Pflops.A total of 512 compute nodes are found where each node has three proprietary CPUs called Matrix-2000+.The system memory is 98.3 TB,and the storage is 1.4 PB in total.展开更多
Drive system is the key device of armored chassis. Its working state and reliability influence the maneuver performance of armored chassis directly. In order to simulate the failure process and evaluate the service re...Drive system is the key device of armored chassis. Its working state and reliability influence the maneuver performance of armored chassis directly. In order to simulate the failure process and evaluate the service reliability of drive system in training or battle missions,a new kind of dynamic simulation model and driving simulation platform of the complete drive system were established based on virtual prototype and finite element technology in this paper. Using the platform, the kinematics and dynamic characteristics of drive system were studied and analyzed in detail,the dynamic load spectrum of key components was obtained,the service life was predicted, and the service reliability evaluation results were provided. A simulation example of transmission gear was shown to illustrate the simulation and evaluation process. The result proves that the simulation method not only can be used to compute and evaluate the service reliability of complex mechanical mechanism, but also has high precision and reasonable computational cost. Therefore,simulation and reliability analysis based on virtual prototype of the armored chassis drive system will provide scientific reference for the formulation of armored chassis reasonable repair cycle.展开更多
Terminal devices deployed in outdoor environments are facing a thorny problem of power supply.Data and energy integrated network(DEIN)is a promising technology to solve the problem,which simultaneously transfers data ...Terminal devices deployed in outdoor environments are facing a thorny problem of power supply.Data and energy integrated network(DEIN)is a promising technology to solve the problem,which simultaneously transfers data and energy through radio frequency signals.State-of-the-art researches mostly focus on theoretical aspects.By contrast,we provide a complete design and implementation of a fully functioning DEIN system with the support of an unmanned aerial vehicle(UAV).The UAV can be dispatched to areas of interest to remotely recharge batteryless terminals,while collecting essential information from them.Then,the UAV uploads the information to remote base stations.Our system verifies the feasibility of the DEIN in practical applications.展开更多
A multi-purpose prototype test system is developed to study the mechanical behavior of tunnel sup-porting structure,including a modular counterforce device,a powerful loading equipment,an advanced intelligent manageme...A multi-purpose prototype test system is developed to study the mechanical behavior of tunnel sup-porting structure,including a modular counterforce device,a powerful loading equipment,an advanced intelligent management system and an efficient noncontact deformation measurement system.The functions of the prototype test system are adjustable size and shape of the modular counterforce structure,sufficient load reserve and accurate loading,multi-connection linkage intelligent management,and high-precision and continuously positioned noncontact deformation measurement.The modular counterforce structure is currently the largest in the world,with an outer diameter of 20.5 m,an inner diameter of 16.5 m and a height of 6 m.The case application proves that the prototype test system can reproduce the mechanical behavior of the tunnel lining during load-bearing,deformation and failure processes in detail.展开更多
Virtual prototype of pipe wagon articulating (PWA) system has been developed and simulated based on the kinematics and dynamics of machinery and Automatic Dynamic Analysis of Mechanical Systems (ADAMS) software. It ha...Virtual prototype of pipe wagon articulating (PWA) system has been developed and simulated based on the kinematics and dynamics of machinery and Automatic Dynamic Analysis of Mechanical Systems (ADAMS) software. It has been integrated with real-time three dimensional (3-D) system simulations for detailed and responsive interaction with dynamic virtual environments. By using this virtual model, the conceptual design examination and performance analysis of the PWA system have been realized dynamically in virtual laboratory. System dynamic force, displacement and tension of pipe have been measured through verifying this 3- D virtual prototype. By comparing the static tension and dynamic tension of pipe, the difference between the two kind tensions has been found. The simulated dynamic tension is much greater than the static tension obtained from the static theory. The results attained in this work suggest that the conceptual designed PWA system can meet the requirements of the operation.展开更多
A design scheme of a single Inverted Pendulum Virtual Prototype based on the combination of software and hardware is introduced.It uses hardware platform of C8051F020 single chip and the software of Matlab,Visual Basi...A design scheme of a single Inverted Pendulum Virtual Prototype based on the combination of software and hardware is introduced.It uses hardware platform of C8051F020 single chip and the software of Matlab,Visual Basic and Kingview.It can simulate the force and movement of Inverted Pendulum expediently and intuitively.The combination of software and hardware makes the system closer to the reality.The concrete scheme is introduced in the paper and the result of PID control which verifies the correctness of the scheme.展开更多
Microbial growth in the water injection system is a well-known problem with severe operational and financial consequences for the petroleum industry, including microbiologically influenced corrosion (MIC), reduced inj...Microbial growth in the water injection system is a well-known problem with severe operational and financial consequences for the petroleum industry, including microbiologically influenced corrosion (MIC), reduced injectivity, reservoir plugging, production downtime, and extensive repair costs. Monitoring of system microbiology is required in any mitigation strategy, enabling operators to apply and adjust countermeasures properly and in due time. In previous studies [1] [2], DNA staining technology with SYBR Green dye was evaluated to have a sufficient detection limit and automation potential for real-time detection of microbial activity in the Saudi Aramco injection seawater. In this study, technical requirements and design solutions were defined, and an autonomous microbe sensor (AMS) prototype was constructed, tested and optimized in the laboratory, and validated in the field for automated detection of microorganisms in the harsh Saudi Arabia desert environment and injection seawater. The AMS prototype was able to monitor and follow the general microbial status in the system, including detection of periods with increased microbial growth or decreased microbial numbers following biocide injection. The infield AMS detection limit was 10<sup>5</sup> cells/mL. The long-term field testing also identified the areas for technical improvement and optimization for further development of a more robust and better performing commercial microbial sensing device.展开更多
Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for...Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.展开更多
基金supported in part by the National Science Foundation(NSFC) for Distinguished Young Scholars of China with Grant 61625106the National Natural Science Foundation of China under Grant 61531011the Hong Kong,Macao and Taiwan Science and Technology Cooperation Program of China(2016YFE0123100)
文摘Owing to the dramatic mobile IP growth,the emerging Internet of Things,and cloud-based applications,wireless networking is witnessing a paradigm shift.By fully exploiting spatial degrees of freedom,massive multiple-input-multiple-output(MIMO) systems promise significant gains in data rates and link reliability.Although the research community has recognized the theoretical benefits of these systems,building the hardware of such complex systems is a challenge in practice.This paper presents a time division duplex(TDD)-based 128-antenna massive MIMO prototype system from theory to reality.First,an analytical signal model is provided to facilitate the setup of a feasible massive MIMO prototype system.Second,a link-level simulation consistent with practical TDDbased massive MIMO systems is conducted to guide and validate the massive MIMO system design.We design and implement the TDDbased 128-antenna massive MIMO prototype system with the guidelines obtained from the link-level simulation.Uplink real-time video transmission and downlink data transmission under the configuration of multiple single-antenna users are achieved.Comparisons withstate-of-the-art prototypes demonstrate the advantages of the proposed system in terms of antenna number,bandwidth,latency,and throughput.The proposed system is also equipped with scalability,which makes the system applicable to a wide range of massive scenarios.
文摘The prototype system Object-Oriented Computer Aided Process Planning(OOCAP),which aims at simulating machine process planning for designed componentsby constructing a knowledge based system in an Object-Oriented environment Smalltalkand is implemented in PS/2 80,is presented in this paper.The integration of rules,factsand operations in objects is the key concept in the system.Additionally,the system simu-lares machining processes and shows the whole procedure from selecting materials to get-ring products with animations.
基金supported in part by the Natural Science Foundation of China(NSFC)under Grant 61971102in part by the Key Research and Development Program of Zhejiang Province under Grant 2022C01093.
文摘In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaining energy levels and battery replacement is both inadequate and costly.This paper introduces an energy management system for indoor IoT,which includes a mobile energy station(ES)for enabling on-demand wireless energy transfer(WET)in radio frequency(RF),some energy receivers(ERs),and a cloud server.By implementing a two-stage positioning system and embedding energy receivers into traditional IoT devices,we robustly manage their energy storage.The experimental results demonstrate that the energy receiver can harvest a minimum power of 58 mW.
文摘无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。
基金supported in part by the National Natural Science Foundation of China under Grant 62071094in part by the National Key Laboratory of Wireless Communications Foundation under Grant IFN202402in part by the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation under Grant GZC20240217.
文摘To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,which can acquire reference signals through flexible wired/wireless switching access.Based on this method,the Minimum Mean Square Error algorithm with known channel state information is derived in detail,determining the upper limit of the cancellation performance,and the Adaptive Dithered Linear Search algorithm for real-time engineering cancellation is given.The correctness of theoretical analysis is verified by the practical self-interference channel measured by a vector network analyzer.Furthermore,we have designed and implemented the corresponding multiinterference cancellation prototype with the digitallyassisted structure,capable of handling multiple interferences(up to three)and supporting a large receive bandwidth of 100 MHz as well as a wide frequency coverage from 30 MHz to 3000 MHz.Prototype test results demonstrate that in the presence of three interferences,when the single interference bandwidth is 0.2/2/20 MHz(corresponding to the receive bandwidth of 2/20/100 MHz),the cancellation performance can reach 46/32/22 dB or more.
基金supported in part by the Gansu Haizhi Characteristic Demonstration Project(No.GSHZTS2022-2).
文摘Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.
基金supported by the National Natural Science Foundation of China under Grant No.62162009the Key Technologies R&D Program of He’nan Province under Grant No.242102211065+1 种基金the Scientific Research Innovation Team of Xuchang University under GrantNo.2022CXTD003Postgraduate Education Reform and Quality Improvement Project of Henan Province under Grant No.YJS2024JD38.
文摘Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
基金The study is funded by the National High Technology Research and Development Program of China(863 Program)(No.2009AA12Z208,No.2009AA12Z225)the 908 Project of the State Oceanic Administration,China(No.908-03-03-02)。
文摘Digital Ocean is a new research domain of Digital Earth.Because of the spatiotemporal,three-dimensional(3D)and intrinsically dynamic nature of ocean data,it is more difficult to make a breakthrough in this domain.The construction of the China Digital Ocean Prototype System(CDOPS)pushes Digital Ocean a step forward from its operation as a mere concept to its achievement as a realistic system.In this paper,the technical framework of the CDOPS is discussed,including its data,function,and application layers.Then,two key technologies are studied in detail that will enable the construction of the 3D ocean environment and the visualization of the ocean model output data.Practical demonstrations show that the CDOPS provides a technical reference for the development of Digital Ocean.This paper is based on an ongoing research project of the development of CDOPS that aims at the facilitation,integration,sharing,accessing,visualization,and use of the ocean data and model computing data from the Digital Earth perspective.
基金supported by National Basic Research Program of China(973 Program,NO.2009CB723906)the Knowledge Innovation Program of Chinese Academy of Sciences(NO.KKCX1-YW-01).
文摘Digital Earth is an information expression of the real Earth,and is a new way of understanding the Earth in the twenty-first century.This paper introduces a Digital Earth Prototype System(DEPS)developed at the Chinese Academy of Sciences(CAS)and supported by the Knowledge Innovation Program of the Chinese Academy of Sciences.Discussions are made to the theoretical model and technical framework of the Digital Earth,and its related key technologies on spatial information processing,spatial data warehouse technology,virtual reality technology,high-performance and parallel computing.The DEPS consists of seven sub-systems including the spatial data,metadata,model database,Grid geoscience computing,spatial information database,maps service and virtual reality.Meanwhile,we developed a series of application systems such as the environment monitoring for the Olympic Games 2008 in Beijing,natural disasters evaluation,digital city,digital archeology,Asia regional aerosol and climate change.The DEPS/CAS displayed the application ability and potential of the Digital Earth in three levels:the global,national and regional.
基金The authors would like to appreciate the financial support for this study from the National Key Technology R&D Program of China(Grant#2008BAC36B01)the Program for New Century Excellent Talent of Ministry of Education of China(Grant#NCET-07-0340)+1 种基金the Natural Science Foundation for Outstanding Scholarship of Hubei Province in China(Grant#2008CDB364)the National Natural Science Foundation of China(Grant#41072199 and 40672179).
文摘Digital lightning is an important thematic branch of the digital earth.Lightning data are complex,momentary,discrete,dynamic and spatio-temporal in nature.Hence,making great progress in their management,analysis and service is challenging.Many studies have been directed towards this field all over the world.Some different relevant systems are currently available.However,most of them focus on a single or a few aspects of lightning applications,rather than taking an overall account of lightning detection,management,analysis and service from the strategic perspective of the digital earth.Lightning disaster also demands a better developed spatial information technology in this field than at present.The idea of the digital earth offers a reasonable scheme to address these issues.Based on reviews of the concept,development and progress of the digital earth,an integrated technical framework of a digital lightning prototype system(DLPS)is proposed,including its data,functions and implementation of subsystems,which aims at the facilitation,management,accessing,visualisation,application,release and sharing of lightning data.Some key technologies are also carefully discussed to facilitate the construction of the DLPS.This framework could provide a helpful guide to future lightning research and hazard mitigation,as well as enrich connotation on the digital earth.So far,there are still many difficulties in multilevel grid construction that need to be solved.
文摘Transmission of 40Gbit/s NRZ signal was successfully demonstrated over 219km of installed SMF in KT's Daejeon area network. After transmission, the measured power penalty was 0.5dB for all the tributary channels.
基金supported by the National Key Research and Development Program of China(No.2016YFB0200401)。
文摘Facing the challenges of the next generation exascale computing,National University of Defense Technology has developed a prototype system to explore opportunities,solutions,and limits toward the next generation Tianhe system.This paper briefly introduces the prototype system,which is deployed at the National Supercomputer Center in Tianjin and has a theoretical peak performance of 3.15 Pflops.A total of 512 compute nodes are found where each node has three proprietary CPUs called Matrix-2000+.The system memory is 98.3 TB,and the storage is 1.4 PB in total.
文摘Drive system is the key device of armored chassis. Its working state and reliability influence the maneuver performance of armored chassis directly. In order to simulate the failure process and evaluate the service reliability of drive system in training or battle missions,a new kind of dynamic simulation model and driving simulation platform of the complete drive system were established based on virtual prototype and finite element technology in this paper. Using the platform, the kinematics and dynamic characteristics of drive system were studied and analyzed in detail,the dynamic load spectrum of key components was obtained,the service life was predicted, and the service reliability evaluation results were provided. A simulation example of transmission gear was shown to illustrate the simulation and evaluation process. The result proves that the simulation method not only can be used to compute and evaluate the service reliability of complex mechanical mechanism, but also has high precision and reasonable computational cost. Therefore,simulation and reliability analysis based on virtual prototype of the armored chassis drive system will provide scientific reference for the formulation of armored chassis reasonable repair cycle.
基金partly funded by Natural Science Foundation of China(No.61971102 and 62132004)Sichuan Science and Technology Program(No.22QYCX0168)the Municipal Government of Quzhou(Grant No.2021D003)。
文摘Terminal devices deployed in outdoor environments are facing a thorny problem of power supply.Data and energy integrated network(DEIN)is a promising technology to solve the problem,which simultaneously transfers data and energy through radio frequency signals.State-of-the-art researches mostly focus on theoretical aspects.By contrast,we provide a complete design and implementation of a fully functioning DEIN system with the support of an unmanned aerial vehicle(UAV).The UAV can be dispatched to areas of interest to remotely recharge batteryless terminals,while collecting essential information from them.Then,the UAV uploads the information to remote base stations.Our system verifies the feasibility of the DEIN in practical applications.
文摘A multi-purpose prototype test system is developed to study the mechanical behavior of tunnel sup-porting structure,including a modular counterforce device,a powerful loading equipment,an advanced intelligent management system and an efficient noncontact deformation measurement system.The functions of the prototype test system are adjustable size and shape of the modular counterforce structure,sufficient load reserve and accurate loading,multi-connection linkage intelligent management,and high-precision and continuously positioned noncontact deformation measurement.The modular counterforce structure is currently the largest in the world,with an outer diameter of 20.5 m,an inner diameter of 16.5 m and a height of 6 m.The case application proves that the prototype test system can reproduce the mechanical behavior of the tunnel lining during load-bearing,deformation and failure processes in detail.
文摘Virtual prototype of pipe wagon articulating (PWA) system has been developed and simulated based on the kinematics and dynamics of machinery and Automatic Dynamic Analysis of Mechanical Systems (ADAMS) software. It has been integrated with real-time three dimensional (3-D) system simulations for detailed and responsive interaction with dynamic virtual environments. By using this virtual model, the conceptual design examination and performance analysis of the PWA system have been realized dynamically in virtual laboratory. System dynamic force, displacement and tension of pipe have been measured through verifying this 3- D virtual prototype. By comparing the static tension and dynamic tension of pipe, the difference between the two kind tensions has been found. The simulated dynamic tension is much greater than the static tension obtained from the static theory. The results attained in this work suggest that the conceptual designed PWA system can meet the requirements of the operation.
文摘A design scheme of a single Inverted Pendulum Virtual Prototype based on the combination of software and hardware is introduced.It uses hardware platform of C8051F020 single chip and the software of Matlab,Visual Basic and Kingview.It can simulate the force and movement of Inverted Pendulum expediently and intuitively.The combination of software and hardware makes the system closer to the reality.The concrete scheme is introduced in the paper and the result of PID control which verifies the correctness of the scheme.
文摘Microbial growth in the water injection system is a well-known problem with severe operational and financial consequences for the petroleum industry, including microbiologically influenced corrosion (MIC), reduced injectivity, reservoir plugging, production downtime, and extensive repair costs. Monitoring of system microbiology is required in any mitigation strategy, enabling operators to apply and adjust countermeasures properly and in due time. In previous studies [1] [2], DNA staining technology with SYBR Green dye was evaluated to have a sufficient detection limit and automation potential for real-time detection of microbial activity in the Saudi Aramco injection seawater. In this study, technical requirements and design solutions were defined, and an autonomous microbe sensor (AMS) prototype was constructed, tested and optimized in the laboratory, and validated in the field for automated detection of microorganisms in the harsh Saudi Arabia desert environment and injection seawater. The AMS prototype was able to monitor and follow the general microbial status in the system, including detection of periods with increased microbial growth or decreased microbial numbers following biocide injection. The infield AMS detection limit was 10<sup>5</sup> cells/mL. The long-term field testing also identified the areas for technical improvement and optimization for further development of a more robust and better performing commercial microbial sensing device.
基金supported in part by the National Natural Science Foundation of China(No.12302252)。
文摘Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.
