The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face sign...The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face significant computational costs due to the time-consuming process of training neural networks and evaluating their performance.Traditional NAS approaches,which rely on exhaustive evaluations and large training datasets,are inefficient for solving complex image classification tasks within limited time frames.To address these challenges,this paper proposes a novel NAS algorithm that integrates a hierarchical evaluation strategy based on Surrogate models,specifically using supernet to pre-trainweights and randomforests as performance predictors.This hierarchical framework combines rapid Surrogate model evaluations with traditional,precise evaluations to balance the trade-off between performance accuracy and computational efficiency.The algorithm significantly reduces the time required for model evaluation by predicting the fitness of candidate architectures using a random forest Surrogate model,thus alleviating the need for full training cycles for each architecture.The proposed method also incorporates evolutionary operations such as mutation and crossover to refine the search process and improve the accuracy of the resulting architectures.Experimental evaluations on the CIFAR-10 and CIFAR-100 datasets demonstrate that the proposed hierarchical evaluation strategy reduces the search time and costs compared to traditional methods,while achieving comparable or even superior model performance.The results suggest that this approach can efficiently handle resourceconstrained tasks,providing a promising solution for accelerating the NAS process without compromising the quality of the generated architectures.展开更多
To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved p...To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved product development group. This paper reviews the state-of-the-art of HLA evolved modular FOM. In particular, related concepts, the overall impact on HLA standards, extension principles, and merging processes are discussed. Also permitted and restricted combinations, and merging rules are provided, and the influence on HLA interface specification is given. The comparison between modular FOM and base object model （BOM） is performed to illustrate the importance of their combination. The applications of modular FOM are summarized. Finally, the significance to facilitate compoable simulation both in academia and practice is presented and future directions are pointed out.展开更多
In order to solve the problem that the ripple-effect analy- sis for the operational architecture of air defense systems （OAADS） is hardly described in quantity with previous modeling approaches, a supernetwork model...In order to solve the problem that the ripple-effect analy- sis for the operational architecture of air defense systems （OAADS） is hardly described in quantity with previous modeling approaches, a supernetwork modeling approach for the OAADS is put for- ward by extending granular computing. Based on that operational units and links are equal to different information granularities, the supernetwork framework of the OAADS is constructed as a “four- network within two-layer” structure by forming dynamic operating coalitions, and measuring indexes of the ripple-effect analysis for the OAADS are given combining with Laplace spectral radius. In this framework, via analyzing multidimensional attributes which inherit relations between operational units in different granular scales, an extended granular computing is put forward integrating with a topological structure. Then the operation process within the supernetwork framework, including transformation relations be- tween two layers in the vertical view and mapping relations among functional networks in the horizontal view, is studied in quantity. As the application case shows, comparing with previous modeling approaches, the supernetwork model can validate and analyze the operation mechanism in the air defense architecture, and the ripple-effect analysis can be used to confirm the key operational unit with micro and macro viewpoints.展开更多
To analyze the behavioral model of the command,control,communication,computer,intelligence,surveillance,reconnaissance(C4ISR)architecture,we propose an executable modeling and analyzing approach to it.First,the meta c...To analyze the behavioral model of the command,control,communication,computer,intelligence,surveillance,reconnaissance(C4ISR)architecture,we propose an executable modeling and analyzing approach to it.First,the meta concept model of the C4ISR architecture is introduced.According to the meta concept model,we construct the executable meta models of the C4ISR architecture by extending the meta models of fUML.Then,we define the concrete syntax and executable activity algebra(EAA)semantics for executable models.The semantics functions are introduced to translating the syntax description of executable models into the item of EAA.To support the execution of models,we propose the executable rules which are the structural operational semantics of EAA.Finally,an area air defense of the C4ISR system is used to illustrate the feasibility of the approach.展开更多
In this paper,a novel method of ultra-lightweight convolution neural network(CNN)design based on neural architecture search(NAS)and knowledge distillation(KD)is proposed.It can realize the automatic construction of th...In this paper,a novel method of ultra-lightweight convolution neural network(CNN)design based on neural architecture search(NAS)and knowledge distillation(KD)is proposed.It can realize the automatic construction of the space target inverse synthetic aperture radar(ISAR)image recognition model with ultra-lightweight and high accuracy.This method introduces the NAS method into the radar image recognition for the first time,which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model(STIIARM).On this basis,the NAS model’s knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure(FSP)distillation method.Thus,the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided,and the ultralightweight STIIARM can be obtained.In the method,the Inverted Linear Bottleneck(ILB)and Inverted Residual Block(IRB)are firstly taken as each block’s basic structure in CNN.And the expansion ratio,output filter size,number of IRBs,and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space.Then,the recognition accuracy and computational complexity are taken as the objective function and constraint conditions,respectively,and the global optimization model of the CNN architecture search is established.Next,the simulated annealing(SA)algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly.After that,based on the three principles of similar block structure,the same corresponding channel number,and the minimum computational complexity,the more lightweight student model is designed,and the FSP matrix pairing between the NAS model and student model is completed.Finally,by minimizing the loss between the FSP matrix pairs of the NAS model and student model,the student model’s weight adjustment is completed.Thus the ultra-lightweight and high accuracy STIIARM is obtained.The proposed method’s effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.展开更多
Combat system effectiveness simulation (CSES) is a special type of complex system simulation. Three non-functional requirements (NFRs), i.e. model composability, domain specific modeling, and model evolvability, are g...Combat system effectiveness simulation (CSES) is a special type of complex system simulation. Three non-functional requirements (NFRs), i.e. model composability, domain specific modeling, and model evolvability, are gaining higher priority from CSES users when evaluating different modeling methodologies for CSES. Traditional CSES modeling methodologies are either domain-neutral (lack of domain characteristics consideration and limited support for model composability) or domain-oriented (lack of openness and evolvability) and fall short of the three NFRs. Inspired by the concept of architecture in systems engineering and software engineering fields, we extend it into a concept of model architecture for complex simulation systems, and propose a model architecture-oriented modeling methodology in which the model architecture plays a central role in achieving the three NFRs. Various model-driven engineering (MDE) approaches and technologies, including simulation modeling platform (SMP), unified modeling language (UML), domain specific modeling (DSM), eclipse modeling framework (EMF), graphical modeling framework (GMF), and so forth, are applied where possible in representing the CSES model architecture and its components' behaviors from physical and cognitive domain aspects. A prototype CSES system, called weapon effectiveness simulation system (WESS), and a non-trivial air-combat simulation example are presented to demonstrate the methodology.展开更多
According to the different geometries and reflected characteristics in the seismic sections, the carbonate platform margin of the northern slope can be summarized as three basic depositional architectures in the Late ...According to the different geometries and reflected characteristics in the seismic sections, the carbonate platform margin of the northern slope can be summarized as three basic depositional architectures in the Late Ordovician Lianglitage （良里塔格） Formation of the Tazhong （塔中） uplift. The type one mainly located in the west of the carbonate platform margin, and it showed obvious imbricate progradation from the interior to the margin of the platform. The type two was in the middle of the carbonate platform margin, which showed retrogradational stacking pattern in the same transgres- sive systems tract period, and the slope strata of the platform margin showed progradational sequence in the highstand systems tract period. The type three located in the east of the carbonate platform margin, and it showed the parallel aggradational architecture. The crossing well section along the northern slope of the Tazhong carbonate platform showed that the depositional thickness became thinner from the east to the west. The thickest belt located in the east of the platform margin, and became thinner rapidly towards the basin and the platform interior. These indicated that the paleogeomorphology ofthe Tazhong uplift was probably high in the west and low in the east during the period of the Late Ordovician Lianglitage Formation. According to the interpretation of seismic profiles and the computer modelling result, the depositional architectures of sequence O31-2 showed aggradation, retrogradation and progradation from the east to the west of the carbonate platform margin during the transgression period. This meant that the accommodation became smaller gradually from the east to the west along the northern carbonate platform margin of the Tazhong uplift.The difference of the accommodation was probably caused by the difference of tectonic subsidence. Also, computer-aided modelling can be used to deeply understand the importance of various control parameters on the carbonate platform depositional architectures and processes.展开更多
This paper addresses the issue of designing the detailed architectures of Field-Programmable Gate Arrays(FPGAs), which has a great impact on the overall performances of an FPGA in practice. Firstly, a novel FPGA archi...This paper addresses the issue of designing the detailed architectures of Field-Programmable Gate Arrays(FPGAs), which has a great impact on the overall performances of an FPGA in practice. Firstly, a novel FPGA architecture description model is proposed based on an easy-to-use file format known as YAML. This format permits the description of any detailed architecture of hard blocks and channels. Then a general algorithm of building FPGA resource graph is presented. The proposed model is scalable and capable of dealing with detailed architecture design and can be used in FPGA architecture evaluation system which is developed to enable detailed architecture design. Experimental results show that a maximum of 16.36% reduction in total wirelength and a maximum of 9.34% reduction in router effort can be obtained by making very little changes to detailed architectures, which verifies the necessity and effectiveness of the proposed model.展开更多
To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new lig...To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.展开更多
On the basis of a special project for teaching reform, in order to change the boring and dull situation of History of Chinese Architecture in students, ancient architecture model was introduced in the teaching process...On the basis of a special project for teaching reform, in order to change the boring and dull situation of History of Chinese Architecture in students, ancient architecture model was introduced in the teaching process of the pure history course. Through the interpretation, construction, and exhibition stages,the ability of students in grasping the knowledge of architecture history can be strengthened. Then, from the historical background, physical composition, artistic conception of space, structural system, detailed structure, and architectural evolution, the positive significance of ancient architecture model to the teaching of the History of Chinese Architecture was discussed, in the hope of providing certain theoretical basis for the teaching of the History of Chinese Architecture.展开更多
Chain architecture effect on static and dynamic properties of unentangled polymers is explored by molecular dynamics simulation and Rouse mode analysis based on graph theory.For open chains,although they generally obe...Chain architecture effect on static and dynamic properties of unentangled polymers is explored by molecular dynamics simulation and Rouse mode analysis based on graph theory.For open chains,although they generally obey ideal scaling in chain dimensions,local structure exhibits nonideal behavior due to the incomplete excluded volume(EV)screening,the reduced mean square internal distance(MSID)can be well described by Wittmer'theory for linear chains and the resulting chain swelling is architecture dependent,i.e.,the more branches a bit stronger swelling.For rings,unlike open chains they are compact in term of global sizes.Due to EV effect and nonconcatenated constraints their local structure exhibits a quite different non-Gaussian behavior from open chains,i.e.,reduced MSID curves do not collapse to a single master curve and fail to converge to a chain-length-independent constant,which makes the direct application of Wittmer's theory to rings quite questionable.Deviation from ideality is further evidenced by limited applicability of Rouse prediction to mode amplitude and relaxation time at high modes as well as the non-constant and mode-dependent scaled Rouse mode amplitudes,while the latter is architecture-dependent and even molecular weight dependent for rings.The chain relaxation time is architecture-dependent,but the same scaling dependence on chain dimensions does hold for all studied architectures.Despite mode orthogonality at static state,the role of cross-correlation in orientation relaxation increases with time and the time-dependent coupling parameter rises faster for rings than open chains even at short time scales it is lower for rings.展开更多
Section model making is an important part of teaching of architecture major in colleges and universities,which can train students’ comprehensive ability and professional quality,and make students meet the needs of th...Section model making is an important part of teaching of architecture major in colleges and universities,which can train students’ comprehensive ability and professional quality,and make students meet the needs of the construction industry.In order to ensure the quality of section model making,it is necessary to collect and analyze the data in the early stage to ensure the smooth process of manual production.As far as the production process is concerned,it is necessary to do a good job in the early planning and control of the manual modeling,and pay attention to the coordination and cooperation of the group and the later inspection.展开更多
Control signaling is mandatory for the operation and management of all types of communication networks,including the Third Generation Partnership Project(3GPP)mobile broadband networks.However,they consume important a...Control signaling is mandatory for the operation and management of all types of communication networks,including the Third Generation Partnership Project(3GPP)mobile broadband networks.However,they consume important and scarce network resources such as bandwidth and processing power.There have been several reports of these control signaling turning into signaling storms halting network operations and causing the respective Telecom companies big financial losses.This paper draws its motivation from such real network disaster incidents attributed to signaling storms.In this paper,we present a thorough survey of the causes,of the signaling storm problems in 3GPP-based mobile broadband networks and discuss in detail their possible solutions and countermeasures.We provide relevant analytical models to help quantify the effect of the potential causes and benefits of their corresponding solutions.Another important contribution of this paper is the comparison of the possible causes and solutions/countermeasures,concerning their effect on several important network aspects such as architecture,additional signaling,fidelity,etc.,in the form of a table.This paper presents an update and an extension of our earlier conference publication.To our knowledge,no similar survey study exists on the subject.展开更多
To address the challenges posed by resource shortage or surplus to enterprises productivity,Internet platforms have been widely used,which can balance shortage and surplus in broader environments. However,the existing...To address the challenges posed by resource shortage or surplus to enterprises productivity,Internet platforms have been widely used,which can balance shortage and surplus in broader environments. However,the existing resource management models lack openness,sharing ability and scalability,which make it difficult for many heterogeneous resources to co-exist in the same system. It is also difficult to resolve the conflicts between distributed self-management and centralized scheduling in the system. This paper analyzes the characteristics of resources in the distributed environment and proposes a new resource management architecture by considering the resource aggregation capacity of cloud computing. The architecture includes a universal resource scheduling optimization model which has been applied successfully in double-district multi-ship-scheduling multi-container-yard empty containers transporting of international shipping logistics. Applications in all these domains prove that this new resource management architecture is feasible and can achieve the expected effect.展开更多
Beyond 3G (B3G) system, the future mobile communication system, is envisioned as a user-centric, open, and convergent information infrastructure capable of providing personalized services. It is extremely important to...Beyond 3G (B3G) system, the future mobile communication system, is envisioned as a user-centric, open, and convergent information infrastructure capable of providing personalized services. It is extremely important to develop service models and architectures for B3G system. A three-dimension service model is proposed. The dimensions are identified as service support scope, service capability definition, and adaptive feature elements. Then, the hierarchical service architecture for B3G is introduced. The enabling technologies for B3G service architecture are discussed in this paper, such as Virtual Home Environment (VHE), service support environment, service openness, distributed computing, intelligent technology, and profile.展开更多
Under the current background of an information society,the digital transformation of enterprises has become a necessary means to enhance the competitiveness of enterprises.This article is based on the industrial Inter...Under the current background of an information society,the digital transformation of enterprises has become a necessary means to enhance the competitiveness of enterprises.This article is based on the industrial Internet platform,the digital planning and architecture of enterprises research.First,we analyze the current challenges of digital transformation and the development opportunities brought by the industrial Internet.Then,we propose a digital planning method based on the industrial Internet platform,which takes the full connectivity of people,machine and things and intelligent decision making as the core,takes data collection,processing,analysis and application as the main line,and finally forms the top-level design of the digital transformation of enterprises.At the same time,we also built an industrial Internet platform architecture model,including the previous end perception layer,network transmission layer,platform service layer,and application innovation layer for four levels,to support enterprises in innovative applications and decision support under the industrial Internet environment.Research shows that this kind of enterprise digital planning and architecture based on an industrial Internet platform can effectively promote enterprises to achieve business model innovation,system innovation,and strengthen the flexibility and agility of enterprises to respond to market changes.The results of this research not only have important theoretical and practical significance for guiding enterprises to carry out digital planning and build an industrial Internet platform,but also provide useful reference for relevant policy formulation.展开更多
End-to-end object detection Transformer(DETR)successfully established the paradigm of the Transformer architecture in the field of object detection.Its end-to-end detection process and the idea of set prediction have ...End-to-end object detection Transformer(DETR)successfully established the paradigm of the Transformer architecture in the field of object detection.Its end-to-end detection process and the idea of set prediction have become one of the hottest network architectures in recent years.There has been an abundance of work improving upon DETR.However,DETR and its variants require a substantial amount of memory resources and computational costs,and the vast number of parameters in these networks is unfavorable for model deployment.To address this issue,a greedy pruning(GP)algorithm is proposed,applied to a variant denoising-DETR(DN-DETR),which can eliminate redundant parameters in the Transformer architecture of DN-DETR.Considering the different roles of the multi-head attention(MHA)module and the feed-forward network(FFN)module in the Transformer architecture,a modular greedy pruning(MGP)algorithm is proposed.This algorithm separates the two modules and applies their respective optimal strategies and parameters.The effectiveness of the proposed algorithm is validated on the COCO 2017 dataset.The model obtained through the MGP algorithm reduces the parameters by 49%and the number of floating point operations(FLOPs)by 44%compared to the Transformer architecture of DN-DETR.At the same time,the mean average precision(mAP)of the model increases from 44.1%to 45.3%.展开更多
During the critical transformation period of landscape architecture major after the adjustment of disciplinary structure and the changes in market demand,private colleges and universities,as important places for culti...During the critical transformation period of landscape architecture major after the adjustment of disciplinary structure and the changes in market demand,private colleges and universities,as important places for cultivating local talents,have pain points such as uneven quality of teachers and students and weak innovation and practice.The practice system with“multi-dimensional Integration”integrates four dimensions:interdisciplinary integration,spatial and temporal intersection,historical inheritance,and behavioral activity,deepens the disciplinary connotation,and integrates the three elements of nature,humanity,and technology,aiming to provide a new path for private colleges and universities to cultivate application-oriented and compound talents with innovative capabilities.In terms of optimizing talent cultivation and adapting to industry changes,this system provides thinking and reference for landscape architecture major,helping the major reshape its core competitiveness and promoting educational innovation and industry development.展开更多
Characterizing the architecture of tree root systems is essential to advance the development of root-inspired anchorage in engineered systems.This study explores the structural root architectures of orchard trees to u...Characterizing the architecture of tree root systems is essential to advance the development of root-inspired anchorage in engineered systems.This study explores the structural root architectures of orchard trees to understand the interplays between the mechanical behavior of roots and the root architecture.Full three-dimensional(3D)models of natural tree root systems,Lovell,Marianna,and Myrobalan,that were extracted from the ground by vertical pullout are reconstructed through photogrammetry and later skeletonized as nodes and root branch segments.Combined analyses of the full 3D models and skeletonized models enable a detailed examination of basic bulk properties and quantification of architectural parameters.While the root segments are divided into three categories,trunk root,main lateral root,and remaining roots,the patterns in branching and diameter distributions show significant differences between the trunk and main laterals versus the remaining lateral roots.In general,the branching angle decreases over the sequence of bifurcations.The main lateral roots near the trunk show significant spreading while the lateral roots near the ends grow roughly parallel to the parent root.For branch length,the roots bifurcate more frequently near the trunk and later they grow longer.Local thickness analysis confirms that the root diameter decays at a higher rate near the trunk than in the remaining lateral roots,while the total cross-sectional area across a bifurcation node remains mostly conserved.The histograms of branching angle,and branch length and thickness gradient can be described using lognormal and exponential distributions,respectively.This unique study presents data to characterize mechanically important structural roots,which may help link root architecture to the mechanical behaviors of root structures.展开更多
Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition ...Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.展开更多
文摘The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face significant computational costs due to the time-consuming process of training neural networks and evaluating their performance.Traditional NAS approaches,which rely on exhaustive evaluations and large training datasets,are inefficient for solving complex image classification tasks within limited time frames.To address these challenges,this paper proposes a novel NAS algorithm that integrates a hierarchical evaluation strategy based on Surrogate models,specifically using supernet to pre-trainweights and randomforests as performance predictors.This hierarchical framework combines rapid Surrogate model evaluations with traditional,precise evaluations to balance the trade-off between performance accuracy and computational efficiency.The algorithm significantly reduces the time required for model evaluation by predicting the fitness of candidate architectures using a random forest Surrogate model,thus alleviating the need for full training cycles for each architecture.The proposed method also incorporates evolutionary operations such as mutation and crossover to refine the search process and improve the accuracy of the resulting architectures.Experimental evaluations on the CIFAR-10 and CIFAR-100 datasets demonstrate that the proposed hierarchical evaluation strategy reduces the search time and costs compared to traditional methods,while achieving comparable or even superior model performance.The results suggest that this approach can efficiently handle resourceconstrained tasks,providing a promising solution for accelerating the NAS process without compromising the quality of the generated architectures.
基金supported by the National Natural Science Foundation of China(6067406960574056).
文摘To improve the agility, dynamics, composability, reusability, and development efficiency restricted by monolithic federation object model （FOM）, a modular FOM is proposed by high level architecture （HLA） evolved product development group. This paper reviews the state-of-the-art of HLA evolved modular FOM. In particular, related concepts, the overall impact on HLA standards, extension principles, and merging processes are discussed. Also permitted and restricted combinations, and merging rules are provided, and the influence on HLA interface specification is given. The comparison between modular FOM and base object model （BOM） is performed to illustrate the importance of their combination. The applications of modular FOM are summarized. Finally, the significance to facilitate compoable simulation both in academia and practice is presented and future directions are pointed out.
基金supported by the National Natural Science Foundation of China(61272011)
文摘In order to solve the problem that the ripple-effect analy- sis for the operational architecture of air defense systems （OAADS） is hardly described in quantity with previous modeling approaches, a supernetwork modeling approach for the OAADS is put for- ward by extending granular computing. Based on that operational units and links are equal to different information granularities, the supernetwork framework of the OAADS is constructed as a “four- network within two-layer” structure by forming dynamic operating coalitions, and measuring indexes of the ripple-effect analysis for the OAADS are given combining with Laplace spectral radius. In this framework, via analyzing multidimensional attributes which inherit relations between operational units in different granular scales, an extended granular computing is put forward integrating with a topological structure. Then the operation process within the supernetwork framework, including transformation relations be- tween two layers in the vertical view and mapping relations among functional networks in the horizontal view, is studied in quantity. As the application case shows, comparing with previous modeling approaches, the supernetwork model can validate and analyze the operation mechanism in the air defense architecture, and the ripple-effect analysis can be used to confirm the key operational unit with micro and macro viewpoints.
文摘To analyze the behavioral model of the command,control,communication,computer,intelligence,surveillance,reconnaissance(C4ISR)architecture,we propose an executable modeling and analyzing approach to it.First,the meta concept model of the C4ISR architecture is introduced.According to the meta concept model,we construct the executable meta models of the C4ISR architecture by extending the meta models of fUML.Then,we define the concrete syntax and executable activity algebra(EAA)semantics for executable models.The semantics functions are introduced to translating the syntax description of executable models into the item of EAA.To support the execution of models,we propose the executable rules which are the structural operational semantics of EAA.Finally,an area air defense of the C4ISR system is used to illustrate the feasibility of the approach.
文摘In this paper,a novel method of ultra-lightweight convolution neural network(CNN)design based on neural architecture search(NAS)and knowledge distillation(KD)is proposed.It can realize the automatic construction of the space target inverse synthetic aperture radar(ISAR)image recognition model with ultra-lightweight and high accuracy.This method introduces the NAS method into the radar image recognition for the first time,which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model(STIIARM).On this basis,the NAS model’s knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure(FSP)distillation method.Thus,the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided,and the ultralightweight STIIARM can be obtained.In the method,the Inverted Linear Bottleneck(ILB)and Inverted Residual Block(IRB)are firstly taken as each block’s basic structure in CNN.And the expansion ratio,output filter size,number of IRBs,and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space.Then,the recognition accuracy and computational complexity are taken as the objective function and constraint conditions,respectively,and the global optimization model of the CNN architecture search is established.Next,the simulated annealing(SA)algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly.After that,based on the three principles of similar block structure,the same corresponding channel number,and the minimum computational complexity,the more lightweight student model is designed,and the FSP matrix pairing between the NAS model and student model is completed.Finally,by minimizing the loss between the FSP matrix pairs of the NAS model and student model,the student model’s weight adjustment is completed.Thus the ultra-lightweight and high accuracy STIIARM is obtained.The proposed method’s effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.
基金supported by the National Natural Science Foundation of China(61273198)
文摘Combat system effectiveness simulation (CSES) is a special type of complex system simulation. Three non-functional requirements (NFRs), i.e. model composability, domain specific modeling, and model evolvability, are gaining higher priority from CSES users when evaluating different modeling methodologies for CSES. Traditional CSES modeling methodologies are either domain-neutral (lack of domain characteristics consideration and limited support for model composability) or domain-oriented (lack of openness and evolvability) and fall short of the three NFRs. Inspired by the concept of architecture in systems engineering and software engineering fields, we extend it into a concept of model architecture for complex simulation systems, and propose a model architecture-oriented modeling methodology in which the model architecture plays a central role in achieving the three NFRs. Various model-driven engineering (MDE) approaches and technologies, including simulation modeling platform (SMP), unified modeling language (UML), domain specific modeling (DSM), eclipse modeling framework (EMF), graphical modeling framework (GMF), and so forth, are applied where possible in representing the CSES model architecture and its components' behaviors from physical and cognitive domain aspects. A prototype CSES system, called weapon effectiveness simulation system (WESS), and a non-trivial air-combat simulation example are presented to demonstrate the methodology.
基金supported by the Frontier Research Project of Marine Facies of the Oil Industry in China and the National Basic Research Program of China(Nos.2011CB201100-03 and 2006CB202302)the National Natural Science Foundation of China(Nos.41130422 and 40372056)
文摘According to the different geometries and reflected characteristics in the seismic sections, the carbonate platform margin of the northern slope can be summarized as three basic depositional architectures in the Late Ordovician Lianglitage （良里塔格） Formation of the Tazhong （塔中） uplift. The type one mainly located in the west of the carbonate platform margin, and it showed obvious imbricate progradation from the interior to the margin of the platform. The type two was in the middle of the carbonate platform margin, which showed retrogradational stacking pattern in the same transgres- sive systems tract period, and the slope strata of the platform margin showed progradational sequence in the highstand systems tract period. The type three located in the east of the carbonate platform margin, and it showed the parallel aggradational architecture. The crossing well section along the northern slope of the Tazhong carbonate platform showed that the depositional thickness became thinner from the east to the west. The thickest belt located in the east of the platform margin, and became thinner rapidly towards the basin and the platform interior. These indicated that the paleogeomorphology ofthe Tazhong uplift was probably high in the west and low in the east during the period of the Late Ordovician Lianglitage Formation. According to the interpretation of seismic profiles and the computer modelling result, the depositional architectures of sequence O31-2 showed aggradation, retrogradation and progradation from the east to the west of the carbonate platform margin during the transgression period. This meant that the accommodation became smaller gradually from the east to the west along the northern carbonate platform margin of the Tazhong uplift.The difference of the accommodation was probably caused by the difference of tectonic subsidence. Also, computer-aided modelling can be used to deeply understand the importance of various control parameters on the carbonate platform depositional architectures and processes.
基金Supported by National High Technology Research and Develop Program of China(No.2012AA012301)National Science and Technology Major Project of China(No.2013ZX03006004)
文摘This paper addresses the issue of designing the detailed architectures of Field-Programmable Gate Arrays(FPGAs), which has a great impact on the overall performances of an FPGA in practice. Firstly, a novel FPGA architecture description model is proposed based on an easy-to-use file format known as YAML. This format permits the description of any detailed architecture of hard blocks and channels. Then a general algorithm of building FPGA resource graph is presented. The proposed model is scalable and capable of dealing with detailed architecture design and can be used in FPGA architecture evaluation system which is developed to enable detailed architecture design. Experimental results show that a maximum of 16.36% reduction in total wirelength and a maximum of 9.34% reduction in router effort can be obtained by making very little changes to detailed architectures, which verifies the necessity and effectiveness of the proposed model.
基金support provided by the National Natural Science Foundation of China(22122802,22278044,and 21878028)the Chongqing Science Fund for Distinguished Young Scholars(CSTB2022NSCQ-JQX0021)the Fundamental Research Funds for the Central Universities(2022CDJXY-003).
文摘To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.
基金Sponsored by The Special Project for Teaching Reform of Young Teachers of University of Science and Technology Liaoning in 2015 "Reform of Teaching System of the History of Chinese Architecture Based on Practical Personnel Training Mode" (qnjj-2015-09)The Project of the 13~(th) Five-Year Plan for Education and Science of Liaoning Province in 2016 "Research on Innovative and Practical Talents Training Model of Architecture Discipline Based on CDIO Concept"(JG16DB222)
文摘On the basis of a special project for teaching reform, in order to change the boring and dull situation of History of Chinese Architecture in students, ancient architecture model was introduced in the teaching process of the pure history course. Through the interpretation, construction, and exhibition stages,the ability of students in grasping the knowledge of architecture history can be strengthened. Then, from the historical background, physical composition, artistic conception of space, structural system, detailed structure, and architectural evolution, the positive significance of ancient architecture model to the teaching of the History of Chinese Architecture was discussed, in the hope of providing certain theoretical basis for the teaching of the History of Chinese Architecture.
基金supported by the National Natural Science Foundation of China(Nos.21790343,21574142,21174154)the National Key Research and Development Program of China(No.2016YFB1100800).
文摘Chain architecture effect on static and dynamic properties of unentangled polymers is explored by molecular dynamics simulation and Rouse mode analysis based on graph theory.For open chains,although they generally obey ideal scaling in chain dimensions,local structure exhibits nonideal behavior due to the incomplete excluded volume(EV)screening,the reduced mean square internal distance(MSID)can be well described by Wittmer'theory for linear chains and the resulting chain swelling is architecture dependent,i.e.,the more branches a bit stronger swelling.For rings,unlike open chains they are compact in term of global sizes.Due to EV effect and nonconcatenated constraints their local structure exhibits a quite different non-Gaussian behavior from open chains,i.e.,reduced MSID curves do not collapse to a single master curve and fail to converge to a chain-length-independent constant,which makes the direct application of Wittmer's theory to rings quite questionable.Deviation from ideality is further evidenced by limited applicability of Rouse prediction to mode amplitude and relaxation time at high modes as well as the non-constant and mode-dependent scaled Rouse mode amplitudes,while the latter is architecture-dependent and even molecular weight dependent for rings.The chain relaxation time is architecture-dependent,but the same scaling dependence on chain dimensions does hold for all studied architectures.Despite mode orthogonality at static state,the role of cross-correlation in orientation relaxation increases with time and the time-dependent coupling parameter rises faster for rings than open chains even at short time scales it is lower for rings.
基金Sponsored by Special Funds for Innovation and Entrepreneurship Training Program for College Students of University of Science and Technology Liaoning(101462019423).
文摘Section model making is an important part of teaching of architecture major in colleges and universities,which can train students’ comprehensive ability and professional quality,and make students meet the needs of the construction industry.In order to ensure the quality of section model making,it is necessary to collect and analyze the data in the early stage to ensure the smooth process of manual production.As far as the production process is concerned,it is necessary to do a good job in the early planning and control of the manual modeling,and pay attention to the coordination and cooperation of the group and the later inspection.
基金the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2024-9/1).
文摘Control signaling is mandatory for the operation and management of all types of communication networks,including the Third Generation Partnership Project(3GPP)mobile broadband networks.However,they consume important and scarce network resources such as bandwidth and processing power.There have been several reports of these control signaling turning into signaling storms halting network operations and causing the respective Telecom companies big financial losses.This paper draws its motivation from such real network disaster incidents attributed to signaling storms.In this paper,we present a thorough survey of the causes,of the signaling storm problems in 3GPP-based mobile broadband networks and discuss in detail their possible solutions and countermeasures.We provide relevant analytical models to help quantify the effect of the potential causes and benefits of their corresponding solutions.Another important contribution of this paper is the comparison of the possible causes and solutions/countermeasures,concerning their effect on several important network aspects such as architecture,additional signaling,fidelity,etc.,in the form of a table.This paper presents an update and an extension of our earlier conference publication.To our knowledge,no similar survey study exists on the subject.
基金Support by the National Key Technology Research and Development Program of China(No.2012BAA13B01,2014BAF07B02)the National Natural Science Foundation of China(No.61273038)+1 种基金Natural Science Foundation of Shandong Province(No.ZR2015FM006)Science and Technology Major Project of the Ministry of Science and Technology of Shandong Province(No.2015ZDXX0201B02)
文摘To address the challenges posed by resource shortage or surplus to enterprises productivity,Internet platforms have been widely used,which can balance shortage and surplus in broader environments. However,the existing resource management models lack openness,sharing ability and scalability,which make it difficult for many heterogeneous resources to co-exist in the same system. It is also difficult to resolve the conflicts between distributed self-management and centralized scheduling in the system. This paper analyzes the characteristics of resources in the distributed environment and proposes a new resource management architecture by considering the resource aggregation capacity of cloud computing. The architecture includes a universal resource scheduling optimization model which has been applied successfully in double-district multi-ship-scheduling multi-container-yard empty containers transporting of international shipping logistics. Applications in all these domains prove that this new resource management architecture is feasible and can achieve the expected effect.
基金Project ofNational "863" Plan of China (No.2004AA119030)
文摘Beyond 3G (B3G) system, the future mobile communication system, is envisioned as a user-centric, open, and convergent information infrastructure capable of providing personalized services. It is extremely important to develop service models and architectures for B3G system. A three-dimension service model is proposed. The dimensions are identified as service support scope, service capability definition, and adaptive feature elements. Then, the hierarchical service architecture for B3G is introduced. The enabling technologies for B3G service architecture are discussed in this paper, such as Virtual Home Environment (VHE), service support environment, service openness, distributed computing, intelligent technology, and profile.
文摘Under the current background of an information society,the digital transformation of enterprises has become a necessary means to enhance the competitiveness of enterprises.This article is based on the industrial Internet platform,the digital planning and architecture of enterprises research.First,we analyze the current challenges of digital transformation and the development opportunities brought by the industrial Internet.Then,we propose a digital planning method based on the industrial Internet platform,which takes the full connectivity of people,machine and things and intelligent decision making as the core,takes data collection,processing,analysis and application as the main line,and finally forms the top-level design of the digital transformation of enterprises.At the same time,we also built an industrial Internet platform architecture model,including the previous end perception layer,network transmission layer,platform service layer,and application innovation layer for four levels,to support enterprises in innovative applications and decision support under the industrial Internet environment.Research shows that this kind of enterprise digital planning and architecture based on an industrial Internet platform can effectively promote enterprises to achieve business model innovation,system innovation,and strengthen the flexibility and agility of enterprises to respond to market changes.The results of this research not only have important theoretical and practical significance for guiding enterprises to carry out digital planning and build an industrial Internet platform,but also provide useful reference for relevant policy formulation.
基金Shanghai Municipal Commission of Economy and Information Technology,China(No.202301054)。
文摘End-to-end object detection Transformer(DETR)successfully established the paradigm of the Transformer architecture in the field of object detection.Its end-to-end detection process and the idea of set prediction have become one of the hottest network architectures in recent years.There has been an abundance of work improving upon DETR.However,DETR and its variants require a substantial amount of memory resources and computational costs,and the vast number of parameters in these networks is unfavorable for model deployment.To address this issue,a greedy pruning(GP)algorithm is proposed,applied to a variant denoising-DETR(DN-DETR),which can eliminate redundant parameters in the Transformer architecture of DN-DETR.Considering the different roles of the multi-head attention(MHA)module and the feed-forward network(FFN)module in the Transformer architecture,a modular greedy pruning(MGP)algorithm is proposed.This algorithm separates the two modules and applies their respective optimal strategies and parameters.The effectiveness of the proposed algorithm is validated on the COCO 2017 dataset.The model obtained through the MGP algorithm reduces the parameters by 49%and the number of floating point operations(FLOPs)by 44%compared to the Transformer architecture of DN-DETR.At the same time,the mean average precision(mAP)of the model increases from 44.1%to 45.3%.
基金Sponsored by the Quality Engineering Project of Education Department of Anhui Province(2022jyxm671)Research Team Project of Anhui Xinhua University(kytd202202)+1 种基金Key Project of Scientific Research(Natural Science)of Higher Education Institutions in Anhui Province(2022AH051861)Teaching Reform Research and Practice Quality Engineering Project of Anhui Xinhua University(2024jy035).
文摘During the critical transformation period of landscape architecture major after the adjustment of disciplinary structure and the changes in market demand,private colleges and universities,as important places for cultivating local talents,have pain points such as uneven quality of teachers and students and weak innovation and practice.The practice system with“multi-dimensional Integration”integrates four dimensions:interdisciplinary integration,spatial and temporal intersection,historical inheritance,and behavioral activity,deepens the disciplinary connotation,and integrates the three elements of nature,humanity,and technology,aiming to provide a new path for private colleges and universities to cultivate application-oriented and compound talents with innovative capabilities.In terms of optimizing talent cultivation and adapting to industry changes,this system provides thinking and reference for landscape architecture major,helping the major reshape its core competitiveness and promoting educational innovation and industry development.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(RS-2024-00340851)the Engineering Research Center Program of the National Science Foundation(NSF)under NSF Cooperative Agreement EEC-1449501.
文摘Characterizing the architecture of tree root systems is essential to advance the development of root-inspired anchorage in engineered systems.This study explores the structural root architectures of orchard trees to understand the interplays between the mechanical behavior of roots and the root architecture.Full three-dimensional(3D)models of natural tree root systems,Lovell,Marianna,and Myrobalan,that were extracted from the ground by vertical pullout are reconstructed through photogrammetry and later skeletonized as nodes and root branch segments.Combined analyses of the full 3D models and skeletonized models enable a detailed examination of basic bulk properties and quantification of architectural parameters.While the root segments are divided into three categories,trunk root,main lateral root,and remaining roots,the patterns in branching and diameter distributions show significant differences between the trunk and main laterals versus the remaining lateral roots.In general,the branching angle decreases over the sequence of bifurcations.The main lateral roots near the trunk show significant spreading while the lateral roots near the ends grow roughly parallel to the parent root.For branch length,the roots bifurcate more frequently near the trunk and later they grow longer.Local thickness analysis confirms that the root diameter decays at a higher rate near the trunk than in the remaining lateral roots,while the total cross-sectional area across a bifurcation node remains mostly conserved.The histograms of branching angle,and branch length and thickness gradient can be described using lognormal and exponential distributions,respectively.This unique study presents data to characterize mechanically important structural roots,which may help link root architecture to the mechanical behaviors of root structures.
基金supported by the National Natural Science Foundation of China(No.62066041).
文摘Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.
