Why is it important to verify/validate model transformations？ The motivation is to improve the quality of the trans- formations, and therefore the quality of the generated software artifacts. Verified/validated model...Why is it important to verify/validate model transformations？ The motivation is to improve the quality of the trans- formations, and therefore the quality of the generated software artifacts. Verified/validated model transformations make it possible to ensure certain properties of the generated software artifacts. In this way, verification/validation methods can guarantee different requirements stated by the actual domain against the generated/modified/optimized software products. For example, a verified/ validated model transformation can ensure the preservation of certain properties during the model-to-model transformation. This paper emphasizes the necessity of methods that make model transformation verified/validated, discusses the different scenarios of model transformation verification and validation, and introduces the principles of a novel test-driven method for verifying/ validating model transformations. We provide a solution that makes it possible to automatically generate test input models for model transformations. Furthermore, we collect and discuss the actual open issues in the field of verification/validation of model transformations.展开更多
Model-Based Development has become an industry wide standard paradigm.As an open source alternative,Scilab/Xcos is being widely employed as a hybrid dynamic systems modeling tool.With the increasing efficiency in impl...Model-Based Development has become an industry wide standard paradigm.As an open source alternative,Scilab/Xcos is being widely employed as a hybrid dynamic systems modeling tool.With the increasing efficiency in implementation using graphical model development and code generation,the modeling and simulation community is struggling with assuring quality as well as maintainability and extendibility.Refactoring is defined as an evolutionary modernization activity where,most of the time,the structure of the artifact is changed to alter its quality characteristics,while keeping its behavior unchanged.It has been widely established as a technique for textual programming languages to improve the code structure and quality.While refactoring is also regarded as one of the key practices of model engineering,the methodologies and approaches for model refactoring are still under development.Architecture-Driven Modernization(ADM)has been introduced by the software engineering community as a model-based approach to software modernization,in which the implicit information that lies in software artifacts is extracted to models and model transformations are applied for modernization tasks.Regarding refactoring as a low level modernization task,the practices from ADM are adaptable.Accordingly,this paper proposes a model-based approach for model refactoring in order to come up with more efficient and effective model refactoring methodology that is accessible and extendable by modelers.Like other graphical modeling tools,Scilab/Xcos also possesses a formalized model specification conforming to its implicit metamodel.Rather than proposing another metamodel for knowledge extraction,this pragmatic approach proposes to conduct in place model-to-model transformations for refactoring employing the Scilab/Xcos model specification.To construct a structured model-based approach,the implicit Scilab/Xcos metamodel is explicitly presented utilizing ECORE as a meta-metamodel.Then a practical model transformation approach is established based on Scilab scripting.A Scilab toolset is provided to the modeler for in-place model-to-model transformations.Using a sample case study,it is demonstrated that proposed model transformation functions in Scilab provide a valuable refactoring tool.展开更多
Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many f...Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many fail to capture the coherent multivariate evolution within the coupled ocean-atmosphere system of the tropical Pacific.To address this three-dimensional(3D)limitation and represent ENSO-related ocean-atmosphere interactions more accurately,a novel this 3D multivariate prediction model was proposed based on a Transformer architecture,which incorporates a spatiotemporal self-attention mechanism.This model,named 3D-Geoformer,offers several advantages,enabling accurate ENSO predictions up to one and a half years in advance.Furthermore,an integrated gradient method was introduced into the model to identify the sources of predictability for sea surface temperature(SST)variability in the eastern equatorial Pacific.Results reveal that the 3D-Geoformer effectively captures ENSO-related precursors during the evolution of ENSO events,particularly the thermocline feedback processes and ocean temperature anomaly pathways on and off the equator.By extending DL-based ENSO predictions from one-dimensional Niño time series to 3D multivariate fields,the 3D-Geoformer represents a significant advancement in ENSO prediction.This study provides details in the model formulation,analysis procedures,sensitivity experiments,and illustrative examples,offering practical guidance for the application of the model in ENSO research.展开更多
In this paper,the small-signal modeling of the Indium Phosphide High Electron Mobility Transistor(InP HEMT)based on the Transformer neural network model is investigated.The AC S-parameters of the HEMT device are train...In this paper,the small-signal modeling of the Indium Phosphide High Electron Mobility Transistor(InP HEMT)based on the Transformer neural network model is investigated.The AC S-parameters of the HEMT device are trained and validated using the Transformer model.In the proposed model,the eight-layer transformer encoders are connected in series and the encoder layer of each Transformer consists of the multi-head attention layer and the feed-forward neural network layer.The experimental results show that the measured and modeled S-parameters of the HEMT device match well in the frequency range of 0.5-40 GHz,with the errors versus frequency less than 1%.Compared with other models,good accuracy can be achieved to verify the effectiveness of the proposed model.展开更多
Model-based system-of-systems(SOS)engineering(MBSoSE)is becoming a promising solution for the design of SoS with increasing complexity.However,bridging the models from the design phase to the simulation phase poses si...Model-based system-of-systems(SOS)engineering(MBSoSE)is becoming a promising solution for the design of SoS with increasing complexity.However,bridging the models from the design phase to the simulation phase poses significant challenges and requires an integrated approach.In this study,a unified requirement modeling approach is proposed based on unified architecture framework(UAF).Theoretical models are proposed which compose formalized descriptions from both topdown and bottom-up perspectives.Based on the description,the UAF profile is proposed to represent the SoS mission and constituent systems(CS)goal.Moreover,the agent-based simulation information is also described based on the overview,design concepts,and details(ODD)protocol as the complement part of the SoS profile,which can be transformed into different simulation platforms based on the eXtensible markup language(XML)technology and model-to-text method.In this way,the design of the SoS is simulated automatically in the early design stage.Finally,the method is implemented and an example is given to illustrate the whole process.展开更多
Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or...Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.展开更多
AlphaPanda(AlphaFold2[1]inspired protein-specific antibody design in a diffusional manner)is an advanced algorithm for designing complementary determining regions(CDRs)of the antibody targeted the specific epitope,com...AlphaPanda(AlphaFold2[1]inspired protein-specific antibody design in a diffusional manner)is an advanced algorithm for designing complementary determining regions(CDRs)of the antibody targeted the specific epitope,combining transformer[2]models,3DCNN[3],and diffusion[4]generative models.展开更多
Short⁃term traffic flow prediction plays a crucial role in the planning of intelligent transportation systems.Nowadays,there is a large amount of traffic flow data generated from the monitoring devices of urban road n...Short⁃term traffic flow prediction plays a crucial role in the planning of intelligent transportation systems.Nowadays,there is a large amount of traffic flow data generated from the monitoring devices of urban road networks,which contains road network traffic information with high application value.In this study,an improved spatio⁃temporal attention transformer model(ISTA⁃transformer model)is proposed to provide a more accurate method for predicting multi⁃step short⁃term traffic flow based on monitoring data.By embedding a temporal attention layer and a spatial attention layer in the model,the model learns the relationship between traffic flows at different time intervals and different geographic locations,and realizes more accurate multi⁃step short⁃time flow prediction.Finally,we validate the superiority of the model with monitoring data spanning 15 days from 620 monitoring points in Qingdao,China.In the four time steps of prediction,the MAPE(Mean Absolute Percentage Error)values of ISTA⁃transformers prediction results are 0.22,0.29,0.37,and 0.38,respectively,and its prediction accuracy is usually better than that of six baseline models(Transformer,GRU,CNN,LSTM,Seq2Seq and LightGBM),which indicates that the proposed model in this paper always has a better ability to explain the prediction results with the time steps in the multi⁃step prediction.展开更多
Hepatology encompasses various aspects,such as metabolic-associated fatty liver disease,viral hepatitis,alcoholic liver disease,liver cirrhosis,liver failure,liver tumors,and liver transplantation.The global epidemiol...Hepatology encompasses various aspects,such as metabolic-associated fatty liver disease,viral hepatitis,alcoholic liver disease,liver cirrhosis,liver failure,liver tumors,and liver transplantation.The global epidemiological situation of liver diseases is grave,posing a substantial threat to human health and quality of life.Characterized by high incidence and mortality rates,liver diseases have emerged as a prominent global public health concern.In recent years,the rapid advan-cement of artificial intelligence(AI),deep learning,and radiomics has transfor-med medical research and clinical practice,demonstrating considerable potential in hepatology.AI is capable of automatically detecting abnormal cells in liver tissue sections,enhancing the accu-racy and efficiency of pathological diagnosis.Deep learning models are able to extract features from computed tomography and magnetic resonance imaging images to facilitate liver disease classification.Machine learning models are capable of integrating clinical data to forecast disease progression and treatment responses,thus supporting clinical decision-making for personalized medicine.Through the analysis of imaging data,laboratory results,and genomic information,AI can assist in diagnosis,forecast disease progression,and optimize treatment plans,thereby improving clinical outcomes for liver disease patients.This minireview intends to comprehensively summarize the state-of-the-art theories and applications of AI in hepatology,explore the opportunities and challenges it presents in clinical practice,basic research,and translational medicine,and propose future research directions to guide the advancement of hepatology and ultimately improve patient outcomes.展开更多
Accurately predicting geomagnetic field is of great significance for space environment monitoring and space weather forecasting worldwide.This paper proposes a vision Transformer(ViT)hybrid model that leverages aurora...Accurately predicting geomagnetic field is of great significance for space environment monitoring and space weather forecasting worldwide.This paper proposes a vision Transformer(ViT)hybrid model that leverages aurora images to predict local geomagnetic station component,breaking the spatial limitations of geomagnetic stations.Our method utilizes the ViT backbone model in combination with convolutional networks to capture both the large-scale spatial correlation and distinct local feature correlation between aurora images and geomagnetic station data.Essentially,the model comprises a visual geometry group(VGG)image feature extraction network,a ViT-based encoder network,and a regression prediction network.Our experimental findings indicate that global features of aurora images play a more substantial role in predicting geomagnetic data than local features.Specifically,the hybrid model achieves a 39.1%reduction in root mean square error compared to the VGG model,a 29.5%reduction compared to the ViT model and a 35.3%reduction relative to the residual network(ResNet)model.Moreover,the fitting accuracy of the model surpasses that of the VGG,ViT,and ResNet models by 2.14%1.58%,and 4.1%,respectively.展开更多
In view of the insufficient utilization of condition-monitoring information and the improper scheduling often observed in conventional maintenance strategies for photovoltaic(PV)modules,this study proposes a predictiv...In view of the insufficient utilization of condition-monitoring information and the improper scheduling often observed in conventional maintenance strategies for photovoltaic(PV)modules,this study proposes a predictive maintenance(PdM)strategy based on Remaining Useful Life(RUL)estimation.First,a RUL prediction model is established using the Transformer architecture,which enables the effective processing of sequential degradation data.By employing the historical degradation data of PV modules,the proposed model provides accurate forecasts of the remaining useful life,thereby supplying essential inputs for maintenance decision-making.Subsequently,the RUL information obtained from the prediction process is integrated into the optimization of maintenance policies.An opposition-based learning Harris Hawks Optimization(OHHO)algorithm is introduced to jointly optimize two critical parameters:the maintenance threshold L,which specifies the degradation level at which maintenance should be performed,and the recovery factor r,which reflects the extent to which the system performance is restored after maintenance.The objective of this joint optimization is to minimize the overall operation and maintenance cost while maintaining system availability.Finally,simulation experiments are conducted to evaluate the performance of the proposed PdM strategy.The results indicate that,compared with conventional corrective maintenance(CM)and periodic maintenance(PM)strategies,the RUL-driven PdM approach achieves a reduction in the average cost rate by approximately 20.7%and 17.9%,respectively,thereby demonstrating its potential effectiveness for practical PV maintenance applications.展开更多
Rice is one of the most important staple crops globally.Rice plant diseases can severely reduce crop yields and,in extreme cases,lead to total production loss.Early diagnosis enables timely intervention,mitigates dise...Rice is one of the most important staple crops globally.Rice plant diseases can severely reduce crop yields and,in extreme cases,lead to total production loss.Early diagnosis enables timely intervention,mitigates disease severity,supports effective treatment strategies,and reduces reliance on excessive pesticide use.Traditional machine learning approaches have been applied for automated rice disease diagnosis;however,these methods depend heavily on manual image preprocessing and handcrafted feature extraction,which are labor-intensive and time-consuming and often require domain expertise.Recently,end-to-end deep learning(DL) models have been introduced for this task,but they often lack robustness and generalizability across diverse datasets.To address these limitations,we propose a novel end-toend training framework for convolutional neural network(CNN) and attention-based model ensembles(E2ETCA).This framework integrates features from two state-of-the-art(SOTA) CNN models,Inception V3 and DenseNet-201,and an attention-based vision transformer(ViT) model.The fused features are passed through an additional fully connected layer with softmax activation for final classification.The entire process is trained end-to-end,enhancing its suitability for realworld deployment.Furthermore,we extract and analyze the learned features using a support vector machine(SVM),a traditional machine learning classifier,to provide comparative insights.We evaluate the proposed E2ETCA framework on three publicly available datasets,the Mendeley Rice Leaf Disease Image Samples dataset,the Kaggle Rice Diseases Image dataset,the Bangladesh Rice Research Institute dataset,and a combined version of all three.Using standard evaluation metrics(accuracy,precision,recall,and F1-score),our framework demonstrates superior performance compared to existing SOTA methods in rice disease diagnosis,with potential applicability to other agricultural disease detection tasks.展开更多
High strength steel products with good ductility can be produced via Q&P hot stamping process,while the phase transformation of the process is more complicated than common hot stamping since two-step quenching and...High strength steel products with good ductility can be produced via Q&P hot stamping process,while the phase transformation of the process is more complicated than common hot stamping since two-step quenching and one-step carbon partitioning processes are involved.In this study,an integrated model of microstructure evolution relating to Q&P hot stamping was presented with a persuasively predicted results of mechanical properties.The transformation of diffusional phase and non-diffusional phase,including original austenite grain size individually,were considered,as well as the carbon partitioning process which affects the secondary martensite transformation temperature and the subsequent phase transformations.Afterwards,the mechanical properties including hardness,strength,and elongation were calculated through a series of theoretical and empirical models in accordance with phase contents.Especially,a modified elongation prediction model was generated ultimately with higher accuracy than the existed Mileiko’s model.In the end,the unified model was applied to simulate the Q&P hot stamping process of a U-cup part based on the finite element software LS-DYNA,where the calculated outputs were coincident with the measured consequences.展开更多
This paper focuses on synthesizing a mixed robust H_2/H_∞ linear parameter varying（LPV） controller for the longitudinal motion of an air-breathing hypersonic vehicle via a high order singular value decomposition（H...This paper focuses on synthesizing a mixed robust H_2/H_∞ linear parameter varying（LPV） controller for the longitudinal motion of an air-breathing hypersonic vehicle via a high order singular value decomposition（HOSVD） approach.The design of hypersonic flight control systems is highly challenging due to the enormous complexity of the vehicle dynamics and the presence of significant uncertainties.Motivated by recent results on both LPV control and tensor-product（TP） model transformation approach,the velocity and altitude tracking control problems for the air-breathing hypersonic vehicle is reduced to that of a state feedback stabilizing controller design for a polytopic LPV system with guaranteed performances.The controller implementation is converted into a convex optimization problem with parameterdependent linear matrix inequalities（LMIs） constraints,which is intuitively tractable using LMI control toolbox.Finally,numerical simulation results demonstrate the effectiveness of the proposed approach.展开更多
Timed abstract state machine(TASM) is a formal specification language used to specify and simulate the behavior of real-time systems. Formal verification of TASM model can be fulfilled through model checking activitie...Timed abstract state machine(TASM) is a formal specification language used to specify and simulate the behavior of real-time systems. Formal verification of TASM model can be fulfilled through model checking activities by translating into UPPAAL. Firstly, the translational semantics from TASM to UPPAAL is presented through atlas transformation language(ATL). Secondly, the implementation of the proposed model transformation tool TASM2UPPAAL is provided. Finally, a case study is given to illustrate the automatic transformation from TASM model to UPPAAL model.展开更多
Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most ...Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.展开更多
The dependence of transformer performance on the material properties was investigated using two laboratory-processed 0.23 mm thick grain-oriented electrical steels domain-refined with elec-trolytically etched grooves ...The dependence of transformer performance on the material properties was investigated using two laboratory-processed 0.23 mm thick grain-oriented electrical steels domain-refined with elec-trolytically etched grooves having different magnetic properties. The iron loss at 1.7 T, 50 Hz and the flux density at 800 A/m of material A were 0.73 W/kg and 1.89 T, respectively; and those of material B, 0.83 W/kg and 1.88 T. Model stacked and wound transformer core experiments using the tested materials exhibited performance well reflecting the material characteristics. In a three-phase stacked core with step-lap joints excited to 1.7 T, 50 Hz, the core loss, the exciting current and the noise level were 0.86 W/kg, 0.74 A and 52 dB, respectively, with material A; and 0.97 W/kg, 1.0 A and 54 dB with material B. The building factors for the core losses of the two materials were almost the same in both core configurations. The effect of higher harmonics on transformer performance was also investigated.展开更多
A detailed knowledge of the thickness of the lithosphere in the North China craton（NCC） is important for understanding the significant tectonic reactivation of the craton in Mesozoic and Ce-nozoic.We achieve this go...A detailed knowledge of the thickness of the lithosphere in the North China craton（NCC） is important for understanding the significant tectonic reactivation of the craton in Mesozoic and Ce-nozoic.We achieve this goal by applying the newly proposed continuous wavelet transform theory to the Gravity Field Model（EGM 2008） data in the region.Distinct structural variations are identified in the scalogram image of profile Alxa-Datong（大同）-Qingdao（青岛）-Yellow Sea（profile ABC）,trans-versing the main units of NCC,which we interpret as mainly representing the Moho and lithosphere-asthenosphere boundary（LAB） undulations.The imaged LAB is as shallow as 60-70 km in the south-east basin and coastal areas and deepens to no more than 140 km in the northwest mountain ranges and continental interior.A rapid change of about 30 km in the LAB depth was detected at around the boundary between the Bohai（渤海） Bay basin（BBB） and the Taihang（太行） Mountains（TM）,roughly coincident with the distinct gravity decrease of more than 100 mGal that marks the North-South Grav-ity Lineament（NSGL） in the region.At last we present the gravity modeling work based on the spectral analysis results,incorporating with the observations on high-resolution seismic images and surface to-pography.The observed structural differences between the eastern and western NCC are likely associ-ated with different lithospheric tectonics across the NSGL.Combined with seismic tomography results and geochemical and petrological data,this sug-gests that complex modification of the litho-sphere probably accompanied significant litho-spheric thinning during the tectonic reactivation of the old craton.展开更多
Solid-state phase transformation plays an important role in adjusting the microstructure and thus tuning the properties of materials. A general modular, analytical model has been widely applied to describe the kinetic...Solid-state phase transformation plays an important role in adjusting the microstructure and thus tuning the properties of materials. A general modular, analytical model has been widely applied to describe the kinetics of solid-state phase transformation involving nucleation, growth and impingement; the basic conception for iso-kinetics which constitutes a physical foundation for the kinetic models or recipes can be extended by the analytical model. Applying the model, the evolution of kinetic parameters is an effective tool for describing the crystallization of enormous amorphous alloys. In order to further improve the effectiveness of this kinetic model, recently, the recipes and the model fitting procedures were extended, with more factors （e.g., anisotropic growth, soft impingement, and thermodynamic driving force） taken into consideration in the modified models. The recent development in the field of analytical model suggests that it is a general, flexible and open kinetic model for describing the solid-state phase transformation kinetics.展开更多
Deep learning technology has been widely used in computer vision,speech recognition,natural language processing,and other related fields.The deep learning algorithm has high precision and high reliability.However,the ...Deep learning technology has been widely used in computer vision,speech recognition,natural language processing,and other related fields.The deep learning algorithm has high precision and high reliability.However,the lack of resources in the edge terminal equipment makes it difficult to run deep learning algorithms that require more memory and computing power.In this paper,we propose MoTransFrame,a general model processing framework for deep learning models.Instead of designing a model compression algorithm with a high compression ratio,MoTransFrame can transplant popular convolutional neural networks models to resources-starved edge devices promptly and accurately.By the integration method,Deep learning models can be converted into portable projects for Arduino,a typical edge device with limited resources.Our experiments show that MoTransFrame has good adaptability in edge devices with limited memories.It is more flexible than other model transplantation methods.It can keep a small loss of model accuracy when the number of parameters is compressed by tens of times.At the same time,the computational resources needed in the reasoning process are less than what the edge node could handle.展开更多
基金Project partially supported by the European Union and the European Social Fund(No.TAMOP-4.2.2.C-11/1/KONV-2012-0013)
文摘Why is it important to verify/validate model transformations？ The motivation is to improve the quality of the trans- formations, and therefore the quality of the generated software artifacts. Verified/validated model transformations make it possible to ensure certain properties of the generated software artifacts. In this way, verification/validation methods can guarantee different requirements stated by the actual domain against the generated/modified/optimized software products. For example, a verified/ validated model transformation can ensure the preservation of certain properties during the model-to-model transformation. This paper emphasizes the necessity of methods that make model transformation verified/validated, discusses the different scenarios of model transformation verification and validation, and introduces the principles of a novel test-driven method for verifying/ validating model transformations. We provide a solution that makes it possible to automatically generate test input models for model transformations. Furthermore, we collect and discuss the actual open issues in the field of verification/validation of model transformations.
文摘Model-Based Development has become an industry wide standard paradigm.As an open source alternative,Scilab/Xcos is being widely employed as a hybrid dynamic systems modeling tool.With the increasing efficiency in implementation using graphical model development and code generation,the modeling and simulation community is struggling with assuring quality as well as maintainability and extendibility.Refactoring is defined as an evolutionary modernization activity where,most of the time,the structure of the artifact is changed to alter its quality characteristics,while keeping its behavior unchanged.It has been widely established as a technique for textual programming languages to improve the code structure and quality.While refactoring is also regarded as one of the key practices of model engineering,the methodologies and approaches for model refactoring are still under development.Architecture-Driven Modernization(ADM)has been introduced by the software engineering community as a model-based approach to software modernization,in which the implicit information that lies in software artifacts is extracted to models and model transformations are applied for modernization tasks.Regarding refactoring as a low level modernization task,the practices from ADM are adaptable.Accordingly,this paper proposes a model-based approach for model refactoring in order to come up with more efficient and effective model refactoring methodology that is accessible and extendable by modelers.Like other graphical modeling tools,Scilab/Xcos also possesses a formalized model specification conforming to its implicit metamodel.Rather than proposing another metamodel for knowledge extraction,this pragmatic approach proposes to conduct in place model-to-model transformations for refactoring employing the Scilab/Xcos model specification.To construct a structured model-based approach,the implicit Scilab/Xcos metamodel is explicitly presented utilizing ECORE as a meta-metamodel.Then a practical model transformation approach is established based on Scilab scripting.A Scilab toolset is provided to the modeler for in-place model-to-model transformations.Using a sample case study,it is demonstrated that proposed model transformation functions in Scilab provide a valuable refactoring tool.
基金Supported by the Laoshan Laboratory(No.LSKJ202202402)the National Natural Science Foundation of China(No.42030410)+2 种基金the Startup Foundation for Introducing Talent of Nanjing University of Information Science&Technology,and Jiangsu Innovation Research Group(No.JSSCTD 202346)supported by the China National Postdoctoral Program for Innovative Talents(No.BX20240169)the China Postdoctoral Science Foundation(No.2141062400101)。
文摘Deep learning(DL)has become a crucial technique for predicting the El Niño-Southern Oscillation(ENSO)and evaluating its predictability.While various DL-based models have been developed for ENSO predictions,many fail to capture the coherent multivariate evolution within the coupled ocean-atmosphere system of the tropical Pacific.To address this three-dimensional(3D)limitation and represent ENSO-related ocean-atmosphere interactions more accurately,a novel this 3D multivariate prediction model was proposed based on a Transformer architecture,which incorporates a spatiotemporal self-attention mechanism.This model,named 3D-Geoformer,offers several advantages,enabling accurate ENSO predictions up to one and a half years in advance.Furthermore,an integrated gradient method was introduced into the model to identify the sources of predictability for sea surface temperature(SST)variability in the eastern equatorial Pacific.Results reveal that the 3D-Geoformer effectively captures ENSO-related precursors during the evolution of ENSO events,particularly the thermocline feedback processes and ocean temperature anomaly pathways on and off the equator.By extending DL-based ENSO predictions from one-dimensional Niño time series to 3D multivariate fields,the 3D-Geoformer represents a significant advancement in ENSO prediction.This study provides details in the model formulation,analysis procedures,sensitivity experiments,and illustrative examples,offering practical guidance for the application of the model in ENSO research.
基金Supported by the National Natural Science Foundation of China(62201293,62034003)the Open-Foundation of State Key Laboratory of Millimeter-Waves(K202313)the Jiangsu Province Youth Science and Technology Talent Support Project(JSTJ-2024-040)。
文摘In this paper,the small-signal modeling of the Indium Phosphide High Electron Mobility Transistor(InP HEMT)based on the Transformer neural network model is investigated.The AC S-parameters of the HEMT device are trained and validated using the Transformer model.In the proposed model,the eight-layer transformer encoders are connected in series and the encoder layer of each Transformer consists of the multi-head attention layer and the feed-forward neural network layer.The experimental results show that the measured and modeled S-parameters of the HEMT device match well in the frequency range of 0.5-40 GHz,with the errors versus frequency less than 1%.Compared with other models,good accuracy can be achieved to verify the effectiveness of the proposed model.
基金Fifth Electronic Research Institute of the Ministry of Industry and Information Technology(HK07202200877)Pre-research Project on Civil Aerospace Technologies of CNSA(D020101)+2 种基金Zhejiang Provincial Science and Technology Plan Project(2022C01052)Frontier Scientific Research Program of Deep Space Exploration Laboratory(2022-QYKYJHHXYF-018,2022-QYKYJH-GCXD-001)Zhiyuan Laboratory(ZYL2024001)。
文摘Model-based system-of-systems(SOS)engineering(MBSoSE)is becoming a promising solution for the design of SoS with increasing complexity.However,bridging the models from the design phase to the simulation phase poses significant challenges and requires an integrated approach.In this study,a unified requirement modeling approach is proposed based on unified architecture framework(UAF).Theoretical models are proposed which compose formalized descriptions from both topdown and bottom-up perspectives.Based on the description,the UAF profile is proposed to represent the SoS mission and constituent systems(CS)goal.Moreover,the agent-based simulation information is also described based on the overview,design concepts,and details(ODD)protocol as the complement part of the SoS profile,which can be transformed into different simulation platforms based on the eXtensible markup language(XML)technology and model-to-text method.In this way,the design of the SoS is simulated automatically in the early design stage.Finally,the method is implemented and an example is given to illustrate the whole process.
基金funded by Scientific Research Deanship at University of Hail-Saudi Arabia through Project Number RG-23092.
文摘Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.
基金supported by the Key Project of International Cooperation of Qilu University of Technology(Grant No.:QLUTGJHZ2018008)Shandong Provincial Natural Science Foundation Committee,China(Grant No.:ZR2016HB54)Shandong Provincial Key Laboratory of Microbial Engineering(SME).
文摘AlphaPanda(AlphaFold2[1]inspired protein-specific antibody design in a diffusional manner)is an advanced algorithm for designing complementary determining regions(CDRs)of the antibody targeted the specific epitope,combining transformer[2]models,3DCNN[3],and diffusion[4]generative models.
基金Sponsored by National Key Research and Development Program of China(Grant No.2020YEB1600500).
文摘Short⁃term traffic flow prediction plays a crucial role in the planning of intelligent transportation systems.Nowadays,there is a large amount of traffic flow data generated from the monitoring devices of urban road networks,which contains road network traffic information with high application value.In this study,an improved spatio⁃temporal attention transformer model(ISTA⁃transformer model)is proposed to provide a more accurate method for predicting multi⁃step short⁃term traffic flow based on monitoring data.By embedding a temporal attention layer and a spatial attention layer in the model,the model learns the relationship between traffic flows at different time intervals and different geographic locations,and realizes more accurate multi⁃step short⁃time flow prediction.Finally,we validate the superiority of the model with monitoring data spanning 15 days from 620 monitoring points in Qingdao,China.In the four time steps of prediction,the MAPE(Mean Absolute Percentage Error)values of ISTA⁃transformers prediction results are 0.22,0.29,0.37,and 0.38,respectively,and its prediction accuracy is usually better than that of six baseline models(Transformer,GRU,CNN,LSTM,Seq2Seq and LightGBM),which indicates that the proposed model in this paper always has a better ability to explain the prediction results with the time steps in the multi⁃step prediction.
文摘Hepatology encompasses various aspects,such as metabolic-associated fatty liver disease,viral hepatitis,alcoholic liver disease,liver cirrhosis,liver failure,liver tumors,and liver transplantation.The global epidemiological situation of liver diseases is grave,posing a substantial threat to human health and quality of life.Characterized by high incidence and mortality rates,liver diseases have emerged as a prominent global public health concern.In recent years,the rapid advan-cement of artificial intelligence(AI),deep learning,and radiomics has transfor-med medical research and clinical practice,demonstrating considerable potential in hepatology.AI is capable of automatically detecting abnormal cells in liver tissue sections,enhancing the accu-racy and efficiency of pathological diagnosis.Deep learning models are able to extract features from computed tomography and magnetic resonance imaging images to facilitate liver disease classification.Machine learning models are capable of integrating clinical data to forecast disease progression and treatment responses,thus supporting clinical decision-making for personalized medicine.Through the analysis of imaging data,laboratory results,and genomic information,AI can assist in diagnosis,forecast disease progression,and optimize treatment plans,thereby improving clinical outcomes for liver disease patients.This minireview intends to comprehensively summarize the state-of-the-art theories and applications of AI in hepatology,explore the opportunities and challenges it presents in clinical practice,basic research,and translational medicine,and propose future research directions to guide the advancement of hepatology and ultimately improve patient outcomes.
基金supported by the National Natural Science Foundation of China(No.41471381)the General Project of Jiangsu Natural Science Foundation(No.BK20171410)the Major Scientific and Technological Achievements Cultivation Fund of Nanjing University of Aeronautics and Astronautics(No.1011-XBD23002)。
文摘Accurately predicting geomagnetic field is of great significance for space environment monitoring and space weather forecasting worldwide.This paper proposes a vision Transformer(ViT)hybrid model that leverages aurora images to predict local geomagnetic station component,breaking the spatial limitations of geomagnetic stations.Our method utilizes the ViT backbone model in combination with convolutional networks to capture both the large-scale spatial correlation and distinct local feature correlation between aurora images and geomagnetic station data.Essentially,the model comprises a visual geometry group(VGG)image feature extraction network,a ViT-based encoder network,and a regression prediction network.Our experimental findings indicate that global features of aurora images play a more substantial role in predicting geomagnetic data than local features.Specifically,the hybrid model achieves a 39.1%reduction in root mean square error compared to the VGG model,a 29.5%reduction compared to the ViT model and a 35.3%reduction relative to the residual network(ResNet)model.Moreover,the fitting accuracy of the model surpasses that of the VGG,ViT,and ResNet models by 2.14%1.58%,and 4.1%,respectively.
基金supported by the National Natural Science Foundation of China(No.51767017)the Key Research and Development Program of Gansu Province(No.25YFGA032)the Industry Support and Guidance Project for Higher Education Institutions of Gansu Province(No.2022CYZC-22).
文摘In view of the insufficient utilization of condition-monitoring information and the improper scheduling often observed in conventional maintenance strategies for photovoltaic(PV)modules,this study proposes a predictive maintenance(PdM)strategy based on Remaining Useful Life(RUL)estimation.First,a RUL prediction model is established using the Transformer architecture,which enables the effective processing of sequential degradation data.By employing the historical degradation data of PV modules,the proposed model provides accurate forecasts of the remaining useful life,thereby supplying essential inputs for maintenance decision-making.Subsequently,the RUL information obtained from the prediction process is integrated into the optimization of maintenance policies.An opposition-based learning Harris Hawks Optimization(OHHO)algorithm is introduced to jointly optimize two critical parameters:the maintenance threshold L,which specifies the degradation level at which maintenance should be performed,and the recovery factor r,which reflects the extent to which the system performance is restored after maintenance.The objective of this joint optimization is to minimize the overall operation and maintenance cost while maintaining system availability.Finally,simulation experiments are conducted to evaluate the performance of the proposed PdM strategy.The results indicate that,compared with conventional corrective maintenance(CM)and periodic maintenance(PM)strategies,the RUL-driven PdM approach achieves a reduction in the average cost rate by approximately 20.7%and 17.9%,respectively,thereby demonstrating its potential effectiveness for practical PV maintenance applications.
基金the Begum Rokeya University,Rangpur,and the United Arab Emirates University,UAE for partially supporting this work。
文摘Rice is one of the most important staple crops globally.Rice plant diseases can severely reduce crop yields and,in extreme cases,lead to total production loss.Early diagnosis enables timely intervention,mitigates disease severity,supports effective treatment strategies,and reduces reliance on excessive pesticide use.Traditional machine learning approaches have been applied for automated rice disease diagnosis;however,these methods depend heavily on manual image preprocessing and handcrafted feature extraction,which are labor-intensive and time-consuming and often require domain expertise.Recently,end-to-end deep learning(DL) models have been introduced for this task,but they often lack robustness and generalizability across diverse datasets.To address these limitations,we propose a novel end-toend training framework for convolutional neural network(CNN) and attention-based model ensembles(E2ETCA).This framework integrates features from two state-of-the-art(SOTA) CNN models,Inception V3 and DenseNet-201,and an attention-based vision transformer(ViT) model.The fused features are passed through an additional fully connected layer with softmax activation for final classification.The entire process is trained end-to-end,enhancing its suitability for realworld deployment.Furthermore,we extract and analyze the learned features using a support vector machine(SVM),a traditional machine learning classifier,to provide comparative insights.We evaluate the proposed E2ETCA framework on three publicly available datasets,the Mendeley Rice Leaf Disease Image Samples dataset,the Kaggle Rice Diseases Image dataset,the Bangladesh Rice Research Institute dataset,and a combined version of all three.Using standard evaluation metrics(accuracy,precision,recall,and F1-score),our framework demonstrates superior performance compared to existing SOTA methods in rice disease diagnosis,with potential applicability to other agricultural disease detection tasks.
基金Supported by National Natural Science Foundation of China (Grant Nos. 51775336,U1564203)Program of Shanghai Academic Research Leadership (Grant No. 19XD1401900)
文摘High strength steel products with good ductility can be produced via Q&P hot stamping process,while the phase transformation of the process is more complicated than common hot stamping since two-step quenching and one-step carbon partitioning processes are involved.In this study,an integrated model of microstructure evolution relating to Q&P hot stamping was presented with a persuasively predicted results of mechanical properties.The transformation of diffusional phase and non-diffusional phase,including original austenite grain size individually,were considered,as well as the carbon partitioning process which affects the secondary martensite transformation temperature and the subsequent phase transformations.Afterwards,the mechanical properties including hardness,strength,and elongation were calculated through a series of theoretical and empirical models in accordance with phase contents.Especially,a modified elongation prediction model was generated ultimately with higher accuracy than the existed Mileiko’s model.In the end,the unified model was applied to simulate the Q&P hot stamping process of a U-cup part based on the finite element software LS-DYNA,where the calculated outputs were coincident with the measured consequences.
基金supported by the National Natural Science Foundation of China(6120300761304239+1 种基金61503392)the Natural Science Foundation of Shaanxi Province(2015JQ6213)
文摘This paper focuses on synthesizing a mixed robust H_2/H_∞ linear parameter varying（LPV） controller for the longitudinal motion of an air-breathing hypersonic vehicle via a high order singular value decomposition（HOSVD） approach.The design of hypersonic flight control systems is highly challenging due to the enormous complexity of the vehicle dynamics and the presence of significant uncertainties.Motivated by recent results on both LPV control and tensor-product（TP） model transformation approach,the velocity and altitude tracking control problems for the air-breathing hypersonic vehicle is reduced to that of a state feedback stabilizing controller design for a polytopic LPV system with guaranteed performances.The controller implementation is converted into a convex optimization problem with parameterdependent linear matrix inequalities（LMIs） constraints,which is intuitively tractable using LMI control toolbox.Finally,numerical simulation results demonstrate the effectiveness of the proposed approach.
基金National Natural Science Foundations of China(No. 61073013,No. 90818024)Aviation Science Foundation of China( No.2010ZAO4001)
文摘Timed abstract state machine(TASM) is a formal specification language used to specify and simulate the behavior of real-time systems. Formal verification of TASM model can be fulfilled through model checking activities by translating into UPPAAL. Firstly, the translational semantics from TASM to UPPAAL is presented through atlas transformation language(ATL). Secondly, the implementation of the proposed model transformation tool TASM2UPPAAL is provided. Finally, a case study is given to illustrate the automatic transformation from TASM model to UPPAAL model.
基金Supported by Shaanxi Province Key Research and Development Project (2021GY-280)the National Natural Science Foundation of China (No.61834005,61772417,61802304)。
文摘Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.
文摘The dependence of transformer performance on the material properties was investigated using two laboratory-processed 0.23 mm thick grain-oriented electrical steels domain-refined with elec-trolytically etched grooves having different magnetic properties. The iron loss at 1.7 T, 50 Hz and the flux density at 800 A/m of material A were 0.73 W/kg and 1.89 T, respectively; and those of material B, 0.83 W/kg and 1.88 T. Model stacked and wound transformer core experiments using the tested materials exhibited performance well reflecting the material characteristics. In a three-phase stacked core with step-lap joints excited to 1.7 T, 50 Hz, the core loss, the exciting current and the noise level were 0.86 W/kg, 0.74 A and 52 dB, respectively, with material A; and 0.97 W/kg, 1.0 A and 54 dB with material B. The building factors for the core losses of the two materials were almost the same in both core configurations. The effect of higher harmonics on transformer performance was also investigated.
基金supported by the National Natural ScienceFoundation of China (Nos. 91014002,40821061)the SpecialFund for Basic Scientific Research of Central Colleges,China University of Geosciences (Wuhan) (No. CUGL100205)+1 种基金the Ph.D. Program Foundation of Ministry of Education of Chinafor Distinguished Young Scholars (No. 200804911523)the Ministry of Education of China (No. B07039)
文摘A detailed knowledge of the thickness of the lithosphere in the North China craton（NCC） is important for understanding the significant tectonic reactivation of the craton in Mesozoic and Ce-nozoic.We achieve this goal by applying the newly proposed continuous wavelet transform theory to the Gravity Field Model（EGM 2008） data in the region.Distinct structural variations are identified in the scalogram image of profile Alxa-Datong（大同）-Qingdao（青岛）-Yellow Sea（profile ABC）,trans-versing the main units of NCC,which we interpret as mainly representing the Moho and lithosphere-asthenosphere boundary（LAB） undulations.The imaged LAB is as shallow as 60-70 km in the south-east basin and coastal areas and deepens to no more than 140 km in the northwest mountain ranges and continental interior.A rapid change of about 30 km in the LAB depth was detected at around the boundary between the Bohai（渤海） Bay basin（BBB） and the Taihang（太行） Mountains（TM）,roughly coincident with the distinct gravity decrease of more than 100 mGal that marks the North-South Grav-ity Lineament（NSGL） in the region.At last we present the gravity modeling work based on the spectral analysis results,incorporating with the observations on high-resolution seismic images and surface to-pography.The observed structural differences between the eastern and western NCC are likely associ-ated with different lithospheric tectonics across the NSGL.Combined with seismic tomography results and geochemical and petrological data,this sug-gests that complex modification of the litho-sphere probably accompanied significant litho-spheric thinning during the tectonic reactivation of the old craton.
基金financial support of the National Basic Research Program of China (No. 2011CB610403)the National Natural Science Foundation of China (Nos. 51134011 and 51431008)+1 种基金the Fundamental Research Fund of Northwestern Polytechnical University (No. JC20120223)the China National Funds for Distinguished Young Scientists (No. 51125002)
文摘Solid-state phase transformation plays an important role in adjusting the microstructure and thus tuning the properties of materials. A general modular, analytical model has been widely applied to describe the kinetics of solid-state phase transformation involving nucleation, growth and impingement; the basic conception for iso-kinetics which constitutes a physical foundation for the kinetic models or recipes can be extended by the analytical model. Applying the model, the evolution of kinetic parameters is an effective tool for describing the crystallization of enormous amorphous alloys. In order to further improve the effectiveness of this kinetic model, recently, the recipes and the model fitting procedures were extended, with more factors （e.g., anisotropic growth, soft impingement, and thermodynamic driving force） taken into consideration in the modified models. The recent development in the field of analytical model suggests that it is a general, flexible and open kinetic model for describing the solid-state phase transformation kinetics.
基金supported by The National Key Research and Development Program of China(2018YFB1800202,2016YFB1000302,SQ2019ZD090149,2018YFB0204301)the CETC Joint Advanced Research Foundation(6141B08080101)+1 种基金The Major Special Science and Technology Project of Hainan Province(ZDKJ2019008)The New Generation of Artificial Intelligence Special Action Project(AI20191125008).
文摘Deep learning technology has been widely used in computer vision,speech recognition,natural language processing,and other related fields.The deep learning algorithm has high precision and high reliability.However,the lack of resources in the edge terminal equipment makes it difficult to run deep learning algorithms that require more memory and computing power.In this paper,we propose MoTransFrame,a general model processing framework for deep learning models.Instead of designing a model compression algorithm with a high compression ratio,MoTransFrame can transplant popular convolutional neural networks models to resources-starved edge devices promptly and accurately.By the integration method,Deep learning models can be converted into portable projects for Arduino,a typical edge device with limited resources.Our experiments show that MoTransFrame has good adaptability in edge devices with limited memories.It is more flexible than other model transplantation methods.It can keep a small loss of model accuracy when the number of parameters is compressed by tens of times.At the same time,the computational resources needed in the reasoning process are less than what the edge node could handle.
