Quantized kernel least mean square(QKLMS) algorithm is an effective nonlinear adaptive online learning algorithm with good performance in constraining the growth of network size through the use of quantization for inp...Quantized kernel least mean square(QKLMS) algorithm is an effective nonlinear adaptive online learning algorithm with good performance in constraining the growth of network size through the use of quantization for input space. It can serve as a powerful tool to perform complex computing for network service and application. With the purpose of compressing the input to further improve learning performance, this article proposes a novel QKLMS with entropy-guided learning, called EQ-KLMS. Under the consecutive square entropy learning framework, the basic idea of entropy-guided learning technique is to measure the uncertainty of the input vectors used for QKLMS, and delete those data with larger uncertainty, which are insignificant or easy to cause learning errors. Then, the dataset is compressed. Consequently, by using square entropy, the learning performance of proposed EQ-KLMS is improved with high precision and low computational cost. The proposed EQ-KLMS is validated using a weather-related dataset, and the results demonstrate the desirable performance of our scheme.展开更多
In order to efficiently and realistically capture microscopic features of fluid surface,a fast and stable surface feature simulation approach for particle-based fluids is presented in this paper.This method employs a ...In order to efficiently and realistically capture microscopic features of fluid surface,a fast and stable surface feature simulation approach for particle-based fluids is presented in this paper.This method employs a steady tension and adhesion model to construct surface features with the consideration of the adsorption effect of fluid to solid.Molecular cohesion and surface area minimization are appended for surface tension,and adhesion is added to better show the microscopic characteristics of fluid surface.Besides,the model is integrated to an implicit incompressible smoothed particle hydrodynamics(SPH)method to improve the efficiency and stability of simulation.The experimental results demonstrate that the method can better simulates surface features in a variety of scenarios stably and efficiently.展开更多
It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the process.The proliferation of industrial sensors and the availability of ...It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the process.The proliferation of industrial sensors and the availability of thickening-system data make this possible.However,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive models.To address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening systems.Using a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental results.The results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system trajectories.The proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.展开更多
Physics-based fluid simulation has played an increasingly important role in the computer graphics community.Recent methods in this area have greatly improved the generation of complex visual effects and its computatio...Physics-based fluid simulation has played an increasingly important role in the computer graphics community.Recent methods in this area have greatly improved the generation of complex visual effects and its computational efficiency.Novel techniques have emerged to deal with complex boundaries,multiphase fluids,gas-liquid interfaces,and fine details.The parallel use of machine learning,image processing,and fluid control technologies has brought many interesting and novel research perspectives.In this survey,we provide an introduction to theoretical concepts underpinning physics-based fuid simulation and their practical implementation,with the aim for it to serve as a guide for both newcomers and seasoned researchers to explore the field of physics-based fuid simulation,with a focus on developments in the last decade.Driven by the distribution of recent publications in the field,we structure our survey to cover physical background;discretization approaches;computational methods that address scalability;fuid interactions with other materials and interfaces;and methods for expressive aspects of surface detail and control.From a practical perspective,we give an overview of existing implementations available for the above methods.展开更多
Recent progress in material data mining has been driven by high-capacity models trained on large datasets.However,collecting experimental data(real data)has been extremely costly owing to the amount of human effort an...Recent progress in material data mining has been driven by high-capacity models trained on large datasets.However,collecting experimental data(real data)has been extremely costly owing to the amount of human effort and expertise required.Here,we develop a novel transfer learning strategy to address problems of small or insufficient data.This strategy realizes the fusion of real and simulated data and the augmentation of training data in a data mining procedure.For a specific task of grain instance image segmentation,this strategy aims to generate synthetic data by fusing the images obtained from simulating the physical mechanism of grain formation and the“image style”information in real images.The results show that the model trained with the acquired synthetic data and only 35%of the real data can already achieve competitive segmentation performance of a model trained on all of the real data.Because the time required to perform grain simulation and to generate synthetic data are almost negligible as compared to the effort for obtaining real data,our proposed strategy is able to exploit the strong prediction power of deep learning without significantly increasing the experimental burden of training data preparation.展开更多
The original version of this article omitted the following from the Acknowledgements:“This work was supported by Beijing Top Discipline for Artificial Intelligent Science and Engineering,University of Science and Tec...The original version of this article omitted the following from the Acknowledgements:“This work was supported by Beijing Top Discipline for Artificial Intelligent Science and Engineering,University of Science and Technology Beijing”.This has now been corrected in both the PDF and HTML versions of the article.展开更多
基金supported by the National Key Technologies R&D Program of China under Grant No. 2015BAK38B01the National Natural Science Foundation of China under Grant Nos. 61174103 and 61603032+4 种基金the National Key Research and Development Program of China under Grant Nos. 2016YFB0700502, 2016YFB1001404, and 2017YFB0702300the China Postdoctoral Science Foundation under Grant No. 2016M590048the Fundamental Research Funds for the Central Universities under Grant No. 06500025the University of Science and Technology Beijing - Taipei University of Technology Joint Research Program under Grant No. TW201610the Foundation from the Taipei University of Technology of Taiwan under Grant No. NTUT-USTB-105-4
文摘Quantized kernel least mean square(QKLMS) algorithm is an effective nonlinear adaptive online learning algorithm with good performance in constraining the growth of network size through the use of quantization for input space. It can serve as a powerful tool to perform complex computing for network service and application. With the purpose of compressing the input to further improve learning performance, this article proposes a novel QKLMS with entropy-guided learning, called EQ-KLMS. Under the consecutive square entropy learning framework, the basic idea of entropy-guided learning technique is to measure the uncertainty of the input vectors used for QKLMS, and delete those data with larger uncertainty, which are insignificant or easy to cause learning errors. Then, the dataset is compressed. Consequently, by using square entropy, the learning performance of proposed EQ-KLMS is improved with high precision and low computational cost. The proposed EQ-KLMS is validated using a weather-related dataset, and the results demonstrate the desirable performance of our scheme.
基金Supported by the National Natural Science Foundation of China(61873299,61702036,61572075)Fundamental Research Funds for the Central Universities of China(FRF-TP-17-012A1)China Postdoctoral Science Foundation(2017M620619)
文摘In order to efficiently and realistically capture microscopic features of fluid surface,a fast and stable surface feature simulation approach for particle-based fluids is presented in this paper.This method employs a steady tension and adhesion model to construct surface features with the consideration of the adsorption effect of fluid to solid.Molecular cohesion and surface area minimization are appended for surface tension,and adhesion is added to better show the microscopic characteristics of fluid surface.Besides,the model is integrated to an implicit incompressible smoothed particle hydrodynamics(SPH)method to improve the efficiency and stability of simulation.The experimental results demonstrate that the method can better simulates surface features in a variety of scenarios stably and efficiently.
基金supported by National Key Research and Development Program of China(2019YFC0605300)the National Natural Science Foundation of China(61873299,61902022,61972028)+2 种基金Scientific and Technological Innovation Foundation of Shunde Graduate School,University of Science and Technology Beijing(BK21BF002)Macao Science and Technology Development Fund under Macao Funding Scheme for Key R&D Projects(0025/2019/AKP)Macao Science and Technology Development Fund(0015/2020/AMJ)。
文摘It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the process.The proliferation of industrial sensors and the availability of thickening-system data make this possible.However,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive models.To address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening systems.Using a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental results.The results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system trajectories.The proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.
基金funded by National Key R&D Program of China(No.2022ZD0118001)National Natural Science Foundation of China(Nos.62376025 and 62332017)+1 种基金Horizon 2020-Marie SklodowskaCurie Action-Individual Fellowships(No.895941)Guangdong Basic and Applied Basic Research Foundation(No.2023A1515030177)。
文摘Physics-based fluid simulation has played an increasingly important role in the computer graphics community.Recent methods in this area have greatly improved the generation of complex visual effects and its computational efficiency.Novel techniques have emerged to deal with complex boundaries,multiphase fluids,gas-liquid interfaces,and fine details.The parallel use of machine learning,image processing,and fluid control technologies has brought many interesting and novel research perspectives.In this survey,we provide an introduction to theoretical concepts underpinning physics-based fuid simulation and their practical implementation,with the aim for it to serve as a guide for both newcomers and seasoned researchers to explore the field of physics-based fuid simulation,with a focus on developments in the last decade.Driven by the distribution of recent publications in the field,we structure our survey to cover physical background;discretization approaches;computational methods that address scalability;fuid interactions with other materials and interfaces;and methods for expressive aspects of surface detail and control.From a practical perspective,we give an overview of existing implementations available for the above methods.
基金The authors acknowledge financial support from the National Key Research and Development Program of China(No.2016YFB0700500)the National Science Foundation of China(No.51574027,No.61572075,No.6170203,No.61873299)+1 种基金the Finance science and technology project of Hainan province(No.ZDYF2019009)the Fundamental Research Funds for the University of Science and Technology Beijing(No.FRF-BD-19-012A,No.FRF-TP-19-043A2).
文摘Recent progress in material data mining has been driven by high-capacity models trained on large datasets.However,collecting experimental data(real data)has been extremely costly owing to the amount of human effort and expertise required.Here,we develop a novel transfer learning strategy to address problems of small or insufficient data.This strategy realizes the fusion of real and simulated data and the augmentation of training data in a data mining procedure.For a specific task of grain instance image segmentation,this strategy aims to generate synthetic data by fusing the images obtained from simulating the physical mechanism of grain formation and the“image style”information in real images.The results show that the model trained with the acquired synthetic data and only 35%of the real data can already achieve competitive segmentation performance of a model trained on all of the real data.Because the time required to perform grain simulation and to generate synthetic data are almost negligible as compared to the effort for obtaining real data,our proposed strategy is able to exploit the strong prediction power of deep learning without significantly increasing the experimental burden of training data preparation.
文摘The original version of this article omitted the following from the Acknowledgements:“This work was supported by Beijing Top Discipline for Artificial Intelligent Science and Engineering,University of Science and Technology Beijing”.This has now been corrected in both the PDF and HTML versions of the article.
