The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communica...The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.展开更多
Deep learning offers a novel opportunity to achieve both high-quality and high-speed computer-generated holography(CGH).Current data-driven deep learning algorithms face the challenge that the labeled training dataset...Deep learning offers a novel opportunity to achieve both high-quality and high-speed computer-generated holography(CGH).Current data-driven deep learning algorithms face the challenge that the labeled training datasets limit the training performance and generalization.The model-driven deep learning introduces the diffraction model into the neural network.It eliminates the need for the labeled training dataset and has been extensively applied to hologram generation.However,the existing model-driven deep learning algorithms face the problem of insufficient constraints.In this study,we propose a model-driven neural network capable of high-fidelity 4K computer-generated hologram generation,called 4K Diffraction Model-driven Network(4K-DMDNet).The constraint of the reconstructed images in the frequency domain is strengthened.And a network structure that combines the residual method and sub-pixel convolution method is built,which effectively enhances the fitting ability of the network for inverse problems.The generalization of the 4K-DMDNet is demonstrated with binary,grayscale and 3D images.High-quality full-color optical reconstructions of the 4K holograms have been achieved at the wavelengths of 450 nm,520 nm,and 638 nm.展开更多
Model-Driven Engineering (MDE) by reframing software development as the transformation of high-level models, promises lots of gains to Software Engineering in terms of productivity, quality and reusability. Although a...Model-Driven Engineering (MDE) by reframing software development as the transformation of high-level models, promises lots of gains to Software Engineering in terms of productivity, quality and reusability. Although a number of empirical studies have established the reality of these gains, there are still lots of reluctances toward the adoption of MDE in practice. This resistance can be explained by several technological and social factors among which a natural scepticism toward novel approaches. In this paper we attempt to provide arguments to help alleviate this scepticism by conducting an assessment of a MDE approach. Our goal is to show that although this MDE is novel, it retains similarities with the conventional Software Engineering approach while automating aspects of it.展开更多
Although the Model-Driven paradigm is being accepted in the research environment as a very useful and powerful option for effective software development, its real application in the enterprise context is still a chall...Although the Model-Driven paradigm is being accepted in the research environment as a very useful and powerful option for effective software development, its real application in the enterprise context is still a challenge for software engineering. Several causes can be stacked out, but one of them can be the lack of tool support for the efficient application of this paradigm. This paper presents a set of tools, grouped in a suite named NDT-Suite, which under the Model-Driven paradigm offer a suitable solution for software development. These tools explore different options that this paradigm can improve such as, development, quality assurance or requirement treatment. Besides, this paper analyses how they are being successfully applied in the industry.展开更多
The IEC 61131-3 standard defines a model and a set of programming languages for the development of industrial automation software. It is widely accepted by industry and most of the commercial tool vendors advertise co...The IEC 61131-3 standard defines a model and a set of programming languages for the development of industrial automation software. It is widely accepted by industry and most of the commercial tool vendors advertise compliance with it. On the other side, Model Driven Development (MDD) has been proved as a quite successful paradigm in general-purpose computing. This was the motivation for exploiting the benefits of MDD in the industrial automation domain. With the emerging IEC 61131 specification that defines an object-oriented (OO) extension to the function block model, there will be a push to the industry to better exploit the benefits of MDD in automation systems development. This work discusses possible alternatives to integrate the current but also the emerging specification of IEC 61131 in the model driven development process of automation systems. IEC 61499, UML and SysML are considered as possible alternatives to allow the developer to work in higher layers of abstraction than the one supported by IEC 61131 and to more effectively move from requirement specifications into the implementation model of the system.展开更多
Web Service Composition provides an opportunity for enterprises to increase the ability to adapt themselves to frequent changes in users' requirements by integrating existing services. Our research has focused on ...Web Service Composition provides an opportunity for enterprises to increase the ability to adapt themselves to frequent changes in users' requirements by integrating existing services. Our research has focused on proposing a framework to support dynamic composition and to use both SOAP-based and RESTful Web services simultaneously in composite services. In this paper a framework called "Model-driven Dynamic Composition of Heterogeneous Service" (MDCHeS) is introduced. It is elaborated in three different ways;each represents a particular view of the framework: data view, which consists of a Meta model and composition elements as well their relationships;process view, which introduces composition phases and used models in each phase;and component view, which shows an abstract view of the components and their interactions. In order to increase the dynamicity of MDCHeS framework, Model Driven Architecture and proxy based ideas are used.展开更多
This study explored the transformative potential of artificial intelligence(AI)in addressing the challenges posed by terahertz ultra-massive multiple-input multiple-output(UM-MIMO)systems.It begins by outlining the ch...This study explored the transformative potential of artificial intelligence(AI)in addressing the challenges posed by terahertz ultra-massive multiple-input multiple-output(UM-MIMO)systems.It begins by outlining the characteristics of terahertz UM-MIMO systems and identifies three primary challenges for transceiver design:computational complexity,modeling difficulty,and measurement limitations.The study posits that AI provides a promising solution to these challenges.Three systematic research roadmaps are proposed for developing AI algorithms tailored to terahertz UM-MIMO systems.The first roadmap,model-driven deep learning(DL),emphasizes the importance of leveraging available domain knowledge and advocates the adoption of AI only to enhance bottleneck modules within an established signal processing or optimization framework.Four essential steps are discussed:algorithmic frameworks,basis algorithms,loss function design,and neural architecture design.The second roadmap presents channel state information(CSI)foundation models,aimed at unifying the design of different transceiver modules by focusing on their shared foundation,that is,the wireless channel.The training of a single compact foundation model is proposed to estimate the score function of wireless channels,which serve as a versatile prior for designing a wide variety of transceiver modules.Four essential steps are outlined:general frameworks,conditioning,site-specific adaptation,and the joint design of CSI foundation models and model-driven DL.The third roadmap aims to explore potential directions for applying pretrained large language models(LLMs)to terahertz UM-MIMO systems.Several application scenarios are envisioned,including LLM-based estimation,optimization,search,network management,and protocol understanding.Finally,the study highlights open problems and future research directions.展开更多
Salient object detection(SOD)models struggle to simultaneously preserve global structure,maintain sharp object boundaries,and sustain computational efficiency in complex scenes.In this study,we propose SPSALNet,a task...Salient object detection(SOD)models struggle to simultaneously preserve global structure,maintain sharp object boundaries,and sustain computational efficiency in complex scenes.In this study,we propose SPSALNet,a task-driven two-stage(macro–micro)architecture that restructures the SOD process around superpixel representations.In the proposed approach,a“split-and-enhance”principle,introduced to our knowledge for the first time in the SOD literature,hierarchically classifies superpixels and then applies targeted refinement only to ambiguous or error-prone regions.At the macro stage,the image is partitioned into content-adaptive superpixel regions,and each superpixel is represented by a high-dimensional region-level feature vector.These representations define a regional decomposition problem in which superpixels are assigned to three classes:background,object interior,and transition regions.Superpixel tokens interact with a global feature vector from a deep network backbone through a cross-attention module and are projected into an enriched embedding space that jointly encodes local topology and global context.At the micro stage,the model employs a U-Net-based refinement process that allocates computational resources only to ambiguous transition regions.The image and distance–similarity maps derived from superpixels are processed through a dual-encoder pathway.Subsequently,channel-aware fusion blocks adaptively combine information from these two sources,producing sharper and more stable object boundaries.Experimental results show that SPSALNet achieves high accuracy with lower computational cost compared to recent competing methods.On the PASCAL-S and DUT-OMRON datasets,SPSALNet exhibits a clear performance advantage across all key metrics,and it ranks first on accuracy-oriented measures on HKU-IS.On the challenging DUT-OMRON benchmark,SPSALNet reaches a MAE of 0.034.Across all datasets,it preserves object boundaries and regional structure in a stable and competitive manner.展开更多
Inspections of power transmission lines(PTLs)conducted using unmanned aerial vehicles(UAVs)are complicated by the fine structure of the lines and complex backgrounds,making accurate and efficient segmentation challeng...Inspections of power transmission lines(PTLs)conducted using unmanned aerial vehicles(UAVs)are complicated by the fine structure of the lines and complex backgrounds,making accurate and efficient segmentation challenging.This study presents the Wavelet-Guided Transformer U-Net(WGT-UNet)model,a new hybrid net-work that combines Convolutional Neural Networks(CNNs),Discrete Wavelet Transform(DWT),and Transformer architectures.The model’s primary contribution is based on spatial and channel attention mechanisms derived from wavelet subbands to guide the Transformer’s self-attention structure.Thus,low and high frequency components are separated at each stage using DWT,suppressing structural noise and making linear objects more prominent.The developed design is supported by multi-component hybrid cost functions that simultaneously solve class imbalance,edge sharpness,structural integrity,and spatial regularity issues.Furthermore,high segmentation success has been achieved in producing sharp boundaries and continuous line structures with the DWT-guided attention mechanism.Experiments conducted on the TTPLA dataset reveal that the version using the ConvNeXt backbone outperforms the current state-of-the-art approaches with an F1-Score of 79.33%and an Intersection over Union(IoU)value of 68.38%.The models and visual outputs of the developed method and all compared models can be accessed at https://github.com/burhanbarakli/WGT-UNET.展开更多
Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of elec...Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of electric vehicles,and the continuous power supply of electronic devices.This paper systematically describes the RUL prediction methods of lithium-ion batteries and comprehensively summarizes the development status and future trends in this field.First,the battery degradation mechanisms and lightweight data acquisition are analyzed.Secondly,a systematic classification model is constructed for the more widely used lithium battery RUL prediction methods,and the application characteristics and implementation limitations of different methods are analyzed in detail.An innovative classification framework for hybrid methods is proposed based on the depth of physical-data interaction.Then,collaborative modelling of calendar ageing and cyclic ageing is discussed,revealing their coupled effects and corresponding RUL prediction methods.Finally,the technical bottlenecks faced by the current RUL prediction of lithium batteries are identified,potential solutions are proposed,and the future development trends are outlined.展开更多
基金funded in part by the National Natural Science Foundation of China under Grant 62401167 and 62192712in part by the Key Laboratory of Marine Environmental Survey Technology and Application,Ministry of Natural Resources,P.R.China under Grant MESTA-2023-B001in part by the Stable Supporting Fund of National Key Laboratory of Underwater Acoustic Technology under Grant JCKYS2022604SSJS007.
文摘The Underwater Acoustic(UWA)channel is bandwidth-constrained and experiences doubly selective fading.It is challenging to acquire perfect channel knowledge for Orthogonal Frequency Division Multiplexing(OFDM)communications using a finite number of pilots.On the other hand,Deep Learning(DL)approaches have been very successful in wireless OFDM communications.However,whether they will work underwater is still a mystery.For the first time,this paper compares two categories of DL-based UWA OFDM receivers:the DataDriven(DD)method,which performs as an end-to-end black box,and the Model-Driven(MD)method,also known as the model-based data-driven method,which combines DL and expert OFDM receiver knowledge.The encoder-decoder framework and Convolutional Neural Network(CNN)structure are employed to establish the DD receiver.On the other hand,an unfolding-based Minimum Mean Square Error(MMSE)structure is adopted for the MD receiver.We analyze the characteristics of different receivers by Monte Carlo simulations under diverse communications conditions and propose a strategy for selecting a proper receiver under different communication scenarios.Field trials in the pool and sea are also conducted to verify the feasibility and advantages of the DL receivers.It is observed that DL receivers perform better than conventional receivers in terms of bit error rate.
基金We are grateful for financial supports from National Natural Science Foundation of China(62035003,61775117)China Postdoctoral Science Foundation(BX2021140)Tsinghua University Initiative Scientific Research Program(20193080075).
文摘Deep learning offers a novel opportunity to achieve both high-quality and high-speed computer-generated holography(CGH).Current data-driven deep learning algorithms face the challenge that the labeled training datasets limit the training performance and generalization.The model-driven deep learning introduces the diffraction model into the neural network.It eliminates the need for the labeled training dataset and has been extensively applied to hologram generation.However,the existing model-driven deep learning algorithms face the problem of insufficient constraints.In this study,we propose a model-driven neural network capable of high-fidelity 4K computer-generated hologram generation,called 4K Diffraction Model-driven Network(4K-DMDNet).The constraint of the reconstructed images in the frequency domain is strengthened.And a network structure that combines the residual method and sub-pixel convolution method is built,which effectively enhances the fitting ability of the network for inverse problems.The generalization of the 4K-DMDNet is demonstrated with binary,grayscale and 3D images.High-quality full-color optical reconstructions of the 4K holograms have been achieved at the wavelengths of 450 nm,520 nm,and 638 nm.
文摘Model-Driven Engineering (MDE) by reframing software development as the transformation of high-level models, promises lots of gains to Software Engineering in terms of productivity, quality and reusability. Although a number of empirical studies have established the reality of these gains, there are still lots of reluctances toward the adoption of MDE in practice. This resistance can be explained by several technological and social factors among which a natural scepticism toward novel approaches. In this paper we attempt to provide arguments to help alleviate this scepticism by conducting an assessment of a MDE approach. Our goal is to show that although this MDE is novel, it retains similarities with the conventional Software Engineering approach while automating aspects of it.
文摘Although the Model-Driven paradigm is being accepted in the research environment as a very useful and powerful option for effective software development, its real application in the enterprise context is still a challenge for software engineering. Several causes can be stacked out, but one of them can be the lack of tool support for the efficient application of this paradigm. This paper presents a set of tools, grouped in a suite named NDT-Suite, which under the Model-Driven paradigm offer a suitable solution for software development. These tools explore different options that this paradigm can improve such as, development, quality assurance or requirement treatment. Besides, this paper analyses how they are being successfully applied in the industry.
文摘The IEC 61131-3 standard defines a model and a set of programming languages for the development of industrial automation software. It is widely accepted by industry and most of the commercial tool vendors advertise compliance with it. On the other side, Model Driven Development (MDD) has been proved as a quite successful paradigm in general-purpose computing. This was the motivation for exploiting the benefits of MDD in the industrial automation domain. With the emerging IEC 61131 specification that defines an object-oriented (OO) extension to the function block model, there will be a push to the industry to better exploit the benefits of MDD in automation systems development. This work discusses possible alternatives to integrate the current but also the emerging specification of IEC 61131 in the model driven development process of automation systems. IEC 61499, UML and SysML are considered as possible alternatives to allow the developer to work in higher layers of abstraction than the one supported by IEC 61131 and to more effectively move from requirement specifications into the implementation model of the system.
文摘Web Service Composition provides an opportunity for enterprises to increase the ability to adapt themselves to frequent changes in users' requirements by integrating existing services. Our research has focused on proposing a framework to support dynamic composition and to use both SOAP-based and RESTful Web services simultaneously in composite services. In this paper a framework called "Model-driven Dynamic Composition of Heterogeneous Service" (MDCHeS) is introduced. It is elaborated in three different ways;each represents a particular view of the framework: data view, which consists of a Meta model and composition elements as well their relationships;process view, which introduces composition phases and used models in each phase;and component view, which shows an abstract view of the components and their interactions. In order to increase the dynamicity of MDCHeS framework, Model Driven Architecture and proxy based ideas are used.
基金supported in part by the Hong Kong Research Grant Council(16209023)。
文摘This study explored the transformative potential of artificial intelligence(AI)in addressing the challenges posed by terahertz ultra-massive multiple-input multiple-output(UM-MIMO)systems.It begins by outlining the characteristics of terahertz UM-MIMO systems and identifies three primary challenges for transceiver design:computational complexity,modeling difficulty,and measurement limitations.The study posits that AI provides a promising solution to these challenges.Three systematic research roadmaps are proposed for developing AI algorithms tailored to terahertz UM-MIMO systems.The first roadmap,model-driven deep learning(DL),emphasizes the importance of leveraging available domain knowledge and advocates the adoption of AI only to enhance bottleneck modules within an established signal processing or optimization framework.Four essential steps are discussed:algorithmic frameworks,basis algorithms,loss function design,and neural architecture design.The second roadmap presents channel state information(CSI)foundation models,aimed at unifying the design of different transceiver modules by focusing on their shared foundation,that is,the wireless channel.The training of a single compact foundation model is proposed to estimate the score function of wireless channels,which serve as a versatile prior for designing a wide variety of transceiver modules.Four essential steps are outlined:general frameworks,conditioning,site-specific adaptation,and the joint design of CSI foundation models and model-driven DL.The third roadmap aims to explore potential directions for applying pretrained large language models(LLMs)to terahertz UM-MIMO systems.Several application scenarios are envisioned,including LLM-based estimation,optimization,search,network management,and protocol understanding.Finally,the study highlights open problems and future research directions.
文摘Salient object detection(SOD)models struggle to simultaneously preserve global structure,maintain sharp object boundaries,and sustain computational efficiency in complex scenes.In this study,we propose SPSALNet,a task-driven two-stage(macro–micro)architecture that restructures the SOD process around superpixel representations.In the proposed approach,a“split-and-enhance”principle,introduced to our knowledge for the first time in the SOD literature,hierarchically classifies superpixels and then applies targeted refinement only to ambiguous or error-prone regions.At the macro stage,the image is partitioned into content-adaptive superpixel regions,and each superpixel is represented by a high-dimensional region-level feature vector.These representations define a regional decomposition problem in which superpixels are assigned to three classes:background,object interior,and transition regions.Superpixel tokens interact with a global feature vector from a deep network backbone through a cross-attention module and are projected into an enriched embedding space that jointly encodes local topology and global context.At the micro stage,the model employs a U-Net-based refinement process that allocates computational resources only to ambiguous transition regions.The image and distance–similarity maps derived from superpixels are processed through a dual-encoder pathway.Subsequently,channel-aware fusion blocks adaptively combine information from these two sources,producing sharper and more stable object boundaries.Experimental results show that SPSALNet achieves high accuracy with lower computational cost compared to recent competing methods.On the PASCAL-S and DUT-OMRON datasets,SPSALNet exhibits a clear performance advantage across all key metrics,and it ranks first on accuracy-oriented measures on HKU-IS.On the challenging DUT-OMRON benchmark,SPSALNet reaches a MAE of 0.034.Across all datasets,it preserves object boundaries and regional structure in a stable and competitive manner.
文摘Inspections of power transmission lines(PTLs)conducted using unmanned aerial vehicles(UAVs)are complicated by the fine structure of the lines and complex backgrounds,making accurate and efficient segmentation challenging.This study presents the Wavelet-Guided Transformer U-Net(WGT-UNet)model,a new hybrid net-work that combines Convolutional Neural Networks(CNNs),Discrete Wavelet Transform(DWT),and Transformer architectures.The model’s primary contribution is based on spatial and channel attention mechanisms derived from wavelet subbands to guide the Transformer’s self-attention structure.Thus,low and high frequency components are separated at each stage using DWT,suppressing structural noise and making linear objects more prominent.The developed design is supported by multi-component hybrid cost functions that simultaneously solve class imbalance,edge sharpness,structural integrity,and spatial regularity issues.Furthermore,high segmentation success has been achieved in producing sharp boundaries and continuous line structures with the DWT-guided attention mechanism.Experiments conducted on the TTPLA dataset reveal that the version using the ConvNeXt backbone outperforms the current state-of-the-art approaches with an F1-Score of 79.33%and an Intersection over Union(IoU)value of 68.38%.The models and visual outputs of the developed method and all compared models can be accessed at https://github.com/burhanbarakli/WGT-UNET.
基金supported by the National Natural Science Foundation of China(No.U23A20651)the Central Government Guides Local Science and Technology Development Foundation(No.2023ZYDF022)+1 种基金the Sichuan Science and Technology Program(2024ZDZX0031)the Open Fund Project of State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines(No.SKLMRDPC23KF19).
文摘Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of electric vehicles,and the continuous power supply of electronic devices.This paper systematically describes the RUL prediction methods of lithium-ion batteries and comprehensively summarizes the development status and future trends in this field.First,the battery degradation mechanisms and lightweight data acquisition are analyzed.Secondly,a systematic classification model is constructed for the more widely used lithium battery RUL prediction methods,and the application characteristics and implementation limitations of different methods are analyzed in detail.An innovative classification framework for hybrid methods is proposed based on the depth of physical-data interaction.Then,collaborative modelling of calendar ageing and cyclic ageing is discussed,revealing their coupled effects and corresponding RUL prediction methods.Finally,the technical bottlenecks faced by the current RUL prediction of lithium batteries are identified,potential solutions are proposed,and the future development trends are outlined.
