Search scope:
排序: Display mode:
Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking Research Article
Qiang GUO, Long TENG, Tianxiang YIN, Yunfei GUO, Xinliang WU, Wenming SONG
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1647-1656 doi: 10.1631/FITEE.2300348
Keywords: Target tracking Gaussian process Data-driven Online learning Model-driven Probabilistic data association
Han YAN, Chongquan ZHONG, Yuhu WU, Liyong ZHANG, Wei LU
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1557-1573 doi: 10.1631/FITEE.2200515
Keywords: Convolutional neural network Gaussian process Hybrid model Hyperparameter optimization Mixed-variable Particle swarm optimization
Novel 3D point set registration method based on regionalized Gaussian process map reconstruction Research
Bo Li, Yu Zhang, Wen-jie Zhao, Ping Li,jameslb20@hotmail.com,zhangyu80@zju.edu.cn,zhaowenjie8@zju.edu.cn,pli@iipc.zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 5, Pages 649-808 doi: 10.1631/FITEE.1900457
Keywords: 点集配准;高斯过程;智能无人系统
Identification of important factors influencing nonlinear counting systems Research Article
Xinmin ZHANG, Jingbo WANG, Chihang WEI, Zhihuan SONG,xinminzhang@zju.edu.cn,wangjingbobo@zju.edu.cn,chhwei@zju.edu.cn,songzhihuan@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 1, Pages 123-133 doi: 10.1631/FITEE.2000324
Keywords: Important factors Nonlinear counting system Generalized Gaussian process regression Sensitivity analysis Steel casting-rolling process
A saliency and Gaussian net model for retinal vessel segmentation Research Articles
Lan-yan XUE, Jia-wen LIN, Xin-rong CAO, Shao-hua ZHENG, Lun YU
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 8, Pages 1075-1086 doi: 10.1631/FITEE.1700404
Keywords: Retinal vessel segmentation Saliency model Gaussian net (GNET) Feature learning
Tian-cheng LI, Jin-ya SU, Wei LIU, Juan M. CORCHADO
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 12, Pages 1913-1939 doi: 10.1631/FITEE.1700379
Keywords: Kalman filter Gaussian filter Time series estimation Bayesian filtering Nonlinear filtering Constrained filtering Gaussian mixture Maneuver Unknown inputs
A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving Article
Jinxin Liu, Yugong Luo, Zhihua Zhong, Keqiang Li, Heye Huang, Hui Xiong
Engineering 2022, Volume 19, Issue 12, Pages 228-239 doi: 10.1016/j.eng.2021.12.020
In mixed and dynamic traffic environments, accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles (AVs) to accomplish reasonable behavioral decisions and guarantee driving safety. In this paper, we propose an integrated probabilistic architecture for long-term vehicle trajectory prediction, which consists of a driving inference model (DIM) and a trajectory prediction model (TPM). The DIM is designed and employed to accurately infer the potential driving intention based on a dynamic Bayesian network. The proposed DIM incorporates the basic traffic rules and multivariate vehicle motion information. To further improve the prediction accuracy and realize uncertainty estimation, we develop a Gaussian process (GP)-based TPM, considering both the short-term prediction results of the vehicle model and the driving motion characteristics. Afterward, the effectiveness of our novel approach is demonstrated by conducting experiments on a public naturalistic driving dataset under lane-changing scenarios. The superior performance on the task of long-term trajectory prediction is presented and verified by comparing with other advanced methods.
Keywords: Autonomous driving Dynamic Bayesian network Driving intention recognition Gaussian process Vehicle trajectory prediction
Fu Jun,Xu Weipu
Strategic Study of CAE 2004, Volume 6, Issue 12, Pages 56-61
Based on the unified estimation-theoretic framework, an effective method of using the gradual Gaussian multidimensional pre-filter to improve the optical flow estimation is presented. The pre-filtering and smoothing effect, which attenuate the temporal aliasing and the interesting signal structure of the optical flow field, are altered with adjusting the spatiotemporal standard deviation parameters. The first 50 frames of the standard Flower Garden and Football video sequence are tested as the reference image sequences, and the LK algorithm as the reference optical flow computing method. Experimental results in objective evaluation show that the optimum temporal standard deviation parameter is 0.4, the optimum spatial standard deviation parameter is in a range of 1.6~2.0 under the condition that the pre-filtering window size is 5 × 5 pixels. After pre-filtering the image sequence by the Gaussian multidimensional filter, the average PSNR of the reconstructed frames enhance 2.572 dB, higher than that using the standard optical flow computing method by nearly 13.6 % .
Keywords: optical flow computing Gaussian multidimensional filter PSNR motion estimation
High-precision Numerical Computation of High-degree Gauss quadrature Nodes
Zhang Qingli,Wang Xiaomei,Yin Shaotang,Jiang Haihe
Strategic Study of CAE 2008, Volume 10, Issue 2, Pages 35-40
Gauss quadrature is used widely in many fields such as the engineering numerical computation, X-ray diffraction profile analysis, spectroscopy,and so on. The nodes and weight factors of Gauss-quadrature are essential data to the numerical integration. A method to compute the zeroes of the high-degree Legendre, Laguerre and Hermite polynomials, which are the nodes of Gauss-Legendre, Gauss-Laguerre and Gauss-Hermite Quadrature, respectively, is studied, and a very efficient algorithm scan-iteration method(SIM) is given. According to the properties of Legendre, Laguerre and Hermite polynomials, their definitions are modified a little, and the stable recursive relations to compute their value are obtained. To extract these polynomials, their root intervals are searched with a certain step within a certain range. After the intervals of all roots are obtained, the roots with the desired precision can be gotten by the general iteration methods such as secant or bisection method. Numerical experiments indicate that the method is very efficient and the high-precise roots of Legendre, Laguerre and Hermite polynomials can be extracted.
Keywords: Gauss quadrature Legendre polynomial Laguerre polynomial Hermite polynomial extract roots
Membrane Crystallization for Process Intensification and Control: A Review Review
Xiaobin Jiang, Yushan Shao, Lei Sheng, Peiyu Li, Gaohong He
Engineering 2021, Volume 7, Issue 1, Pages 50-62 doi: 10.1016/j.eng.2020.06.024
Crystallization is a fundamental separation technology used for the production of particulate solids. Accurate nucleation and growth process control are vitally important but difficult. A novel controlling technology that can simultaneously intensify the overall crystallization process remains a significant challenge. Membrane crystallization (MCr), which has progressed significantly in recent years, is a hybrid technology platform with great potential to address this goal. This review illustrates the basic concepts of MCr and its promising applications for crystallization control and process intensification, including a state-of-the-art review of key MCr-utilized membrane materials, process control mechanisms, and optimization strategies based on diverse hybrid membranes and crystallization processes. Finally, efforts to promote MCr technology to industrial use, unexplored issues, and open questions to be addressed are outlined.
Keywords: Membrane crystallization Nucleation Process control Process intensification
A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring Article
Chunhua Yang, Huiping Liang, Keke Huang, Yonggang Li, Weihua Gui
Engineering 2021, Volume 7, Issue 9, Pages 1262-1273 doi: 10.1016/j.eng.2020.08.028
Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the
collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.
Keywords: Process monitoring Multimode process Dictionary learning Transfer learning
Research of Collaborative Design Process Management Based on Activity Method
Hao Yongping,Zhang Jianfu,Shi Chunjing,Shao Weiping
Strategic Study of CAE 2005, Volume 7, Issue 12, Pages 69-73
By analyzing the components of an activity and the relationship of the process modeling, a topological structure of the collaborative design process management system was presented. According to the situation and characteristic of the product development process, a number of the important issues about process modeling, AU design environment, process monitoring and the data exchange between systems were discussed. At last, a user interface of the collaborative design environment and the display of process monitoring are also given.
Keywords: activity theory activity unit process modeling design process management
The demonstration,decision process and practice of Three Gorges Project
Pan Jiazheng
Strategic Study of CAE 2011, Volume 13, Issue 7, Pages 4-8
The world-famous Three Gorges Project (TGP) is the largest hydropower station in the world and also the largest water resources and hydropower project constructed in China. The impoundment of Three Gorges Reservoir reached the design water level of 175 m for the first time on October 26, 2010, which marked that the various functions such as flood control, power generation and navigation of TGP can meet the design requirements. It took nearly 100 years from conception, demonstration, design, construction and operation to final completion of TGP. How was the conception of TGP proposed? What a role it should be? What are different opinions existed? How was the project demonstrated? What was the conclusion of demonstration? Those are the issues that many people care about but do not quite understand. A compendious introduction is made in memory of the achievement of the century dream.
Keywords: Three Gorges Project demonstration and decision process
Integrated Membrane Separation Processes
Gao Congjie,Yu Sanchuan,Jin keyong
Strategic Study of CAE 2000, Volume 2, Issue 7, Pages 43-46
The application of integrated membrane separation processes in water purification, wastewater treatment, cleaning manufacture, etc. , was reviewed in this paper. Processes such as preparation of ultrapure water, drinking water purification, sewage treatment and reuse, organic wastewater treatment, multipurpose use of whey, sea water desalination were discussed in detail. The advantages and prospect of integrated membrane separation process were also analyzed in the review.
Keywords: membrane separation integrated membrane separation process water purification desalination cleaning manufacture
Research on the Nearshore Process of the Typical Coast of the Bohai Bay
Yun Caixing
Strategic Study of CAE 2001, Volume 3, Issue 3, Pages 42-51
Since the coast of the Bohai Bay is a typical plain silty one, the problems about engineering sediments, such as fine sediment transportation and how to reduce silting amount for the port and waterway, have come across one after another in the construction of the Tianjin Port and the Huanghua Port of Hebei Province, the two largest artificial ports in China. On the basis of the data observed in situ in the coastal area of the Dakou River in the southwestern Bohai Bay, this paper analyzes comprehensively hydrodynamics, sediment trans-portation, sedimentation of the coastal beach and alluvial and silting evolution, which provide a theoretical basis for the strategic decision of “the shallow water used as the deep water” in the plain silty coast.
Keywords: the Bohai Bay nearshore process sediment transportation
Title Author Date Type Operation
Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking
Qiang GUO, Long TENG, Tianxiang YIN, Yunfei GUO, Xinliang WU, Wenming SONG
Journal Article
A hybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search
Han YAN, Chongquan ZHONG, Yuhu WU, Liyong ZHANG, Wei LU
Journal Article
Novel 3D point set registration method based on regionalized Gaussian process map reconstruction
Bo Li, Yu Zhang, Wen-jie Zhao, Ping Li,jameslb20@hotmail.com,zhangyu80@zju.edu.cn,zhaowenjie8@zju.edu.cn,pli@iipc.zju.edu.cn
Journal Article
Identification of important factors influencing nonlinear counting systems
Xinmin ZHANG, Jingbo WANG, Chihang WEI, Zhihuan SONG,xinminzhang@zju.edu.cn,wangjingbobo@zju.edu.cn,chhwei@zju.edu.cn,songzhihuan@zju.edu.cn
Journal Article
A saliency and Gaussian net model for retinal vessel segmentation
Lan-yan XUE, Jia-wen LIN, Xin-rong CAO, Shao-hua ZHENG, Lun YU
Journal Article
ApproximateGaussian conjugacy: parametric recursive filtering under nonlinearity,multimodality, uncertainty, and constraint, and beyond
Tian-cheng LI, Jin-ya SU, Wei LIU, Juan M. CORCHADO
Journal Article
A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving
Jinxin Liu, Yugong Luo, Zhihua Zhong, Keqiang Li, Heye Huang, Hui Xiong
Journal Article
The Improving Characteristics of the Gradual Gaussian Multidimensional Pre-filter for Optical Flow Estimation
Fu Jun,Xu Weipu
Journal Article
High-precision Numerical Computation of High-degree Gauss quadrature Nodes
Zhang Qingli,Wang Xiaomei,Yin Shaotang,Jiang Haihe
Journal Article
Membrane Crystallization for Process Intensification and Control: A Review
Xiaobin Jiang, Yushan Shao, Lei Sheng, Peiyu Li, Gaohong He
Journal Article
A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring
Chunhua Yang, Huiping Liang, Keke Huang, Yonggang Li, Weihua Gui
Journal Article
Research of Collaborative Design Process Management Based on Activity Method
Hao Yongping,Zhang Jianfu,Shi Chunjing,Shao Weiping
Journal Article
The demonstration,decision process and practice of Three Gorges Project
Pan Jiazheng
Journal Article