Search scope:
排序: Display mode:
Prospects for multi-agent collaboration and gaming: challenge, technology, and application Perspective
Yu LIU, Zhi LI, Zhizhuo JIANG, You HE
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 7, Pages 1002-1009 doi: 10.1631/FITEE.2200055
Keywords: 多智能体;博弈论;集体智能;强化学习;智能控制
Multi-band Synchronization Model for Speech Recognition Under Noisy Condition
Sun Wei,Wu Zhenyang
Strategic Study of CAE 2006, Volume 8, Issue 3, Pages 31-34
Based on perception characteristic of human ear, this paper proposes synchronization multi-band maximum likelihood linear regression algorithm for robust speech recognition under noisy condition. The algorithm utilizes maximum likelihood as estimation criteria to compensate the effects of noisy condition with multi-band synchronization model and noise corruption assumption. The tests show that the proposed algorithm improves the performance of recognition system effectively.
Keywords: hidden Markov model maximum likelihood multi-band synchronization model speech recognition
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Engineering 2021, Volume 7, Issue 12, Pages 1751-1765 doi: 10.1016/j.eng.2020.10.023
Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.
Keywords: Dissolved oxygen concentrations forecasting Time-series multi-step forecasting Multi-factor analysis Empirical wavelet transform decomposition Multi-model optimization ensemble
Study on Grey Incidence Decision Model of the Dynamic Multiple-attribute
Dang Yaoguo,Liu Sifeng,Liu Bin,Tao Yong
Strategic Study of CAE 2005, Volume 7, Issue 2, Pages 69-72
Based on the decision character of the dynamic multiple-attribute system, in initializing the attribute data, a new linear changing operator in [-1,1], which is easy to compute and be applied, is proposed. By this method to find the positive and negative ideal precept of each period, a new grey incidence decision model of the dynamic multi-attribute is establishod. In this model, the developing character of each attribute in the system is fully consider, and applied to grey incidence analysis. All of the above provide a scientific and applied decision method for the dynamic multiple - attribute decision problems. Lastly, this method is demonstrated to be scientific and effective with a practical example.
Keywords: grey incidence analysis multi-attribute decision model
Supervised topic models with weighted words: multi-label document classification None
Yue-peng ZOU, Ji-hong OUYANG, Xi-ming LI
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 4, Pages 513-523 doi: 10.1631/FITEE.1601668
Keywords: Supervised topic model Multi-label classification Class frequency Labeled latent Dirichlet allocation (L-LDA) Dependency-LDA
Derivation of the multi-model generalized labeled multi-Bernoulli filter: a solution to multi-target hybrid systems Research Articles
Weihua Wu, Yichao Cai, Hongbin Jin, Mao Zheng, Xun Feng, Zewen Guan,weihuawu1987@163.com
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 1, Pages 1-140 doi: 10.1631/FITEE.2000105
Keywords: Multi-maneuvering-target tracking Multi-model Generalized labeled multi-Bernoulli filter Multi-target hybrid systems
The model and process simulation of multi-effect two stage evaporation system with solid separation
Li Ling, Ruan Qi
Strategic Study of CAE 2008, Volume 10, Issue 10, Pages 54-60
A mathematical model of conventional design for the multi-effect two stage evaporation system with condensed water flash and solid separation was established. The equilibrium was correlated to equation and the model could be solved with computer easily. Then the complex manual calculating was avoided. Mass balance and energy balance equations of the system were expressed in matrix equation that has the advantage of clear structure and high modularization. By holding or omitting correlative block-smatrix in matrix equation, matrix equation could be used to describe the multi-effect two stage evaporation system without condensed water flash or solid separation. The model was solved by combining matrix method with iteration method. The practical example indicated that condensed water flash is an effective method to save energy. And the algorithm increases the convergence speed and stability.
Keywords: solid separation mathematical model of multi-effect two stage evaporation condensed water flash
Embracing non-orthogonalmultiple access in future wireless networks None
Zhi-guo DING, Mai XU, Yan CHEN, Mu-gen PENG, H. Vincent POOR
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 3, Pages 322-339 doi: 10.1631/FITEE.1800051
Keywords: Non-orthogonal multiple access (NOMA) Wireless caching Multiple-input multiple-output (MIMO) NOMA Cooperative NOMA Millimeter-wave networks Visible light communications (VLC)
混合-增强智能:协作与认知 Review
南宁 郑,子熠 刘,鹏举 任,永强 马,仕韬 陈,思雨 余,建儒 薛,霸东 陈,飞跃 王
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 153-179 doi: 10.1631/FITEE.1700053
Human–Robot Collaboration Framework Based on Impedance Control in Robotic Assembly Article
Xingwei Zhao,Yiming Chen,Lu Qian,Bo Tao,Han Ding
Engineering 2023, Volume 30, Issue 11, Pages 83-92 doi: 10.1016/j.eng.2022.08.022
Human–robot (HR) collaboration (HRC) is an emerging research field because of the complementary advantages of humans and robots. An HRC framework for robotic assembly based on impedance control is proposed in this paper. In the HRC framework, the human is the decision maker, the robot acts as the executor, while the assembly environment provides constraints. The robot is the main executor to perform the assembly action, which has the position control, drag and drop, positive impedance control, and negative impedance control modes. To reveal the characteristics of the HRC framework, the switch condition map of different control modes and the stability analysis of the HR coupled system are discussed. In the end, HRC assembly experiments are conducted, where the HRC assembly task can be accomplished when the assembling tolerance is 0.08 mm or with the interference fit. Experiments show that the HRC assembly has the complementary advantages of humans and robots and is efficient in finishing complex assembly tasks.
Keywords: Human–robot collaboration Impedance control Robotic assembly
Fang Weifeng,Yang Lizhong,Huang Rui
Strategic Study of CAE 2003, Volume 5, Issue 3, Pages 67-71
In recent years, Cellular Automata (CA) micro-simulation has emerged as an effective technique for modeling traffic flow and achieved a lot of success. But the human movement and occupant evacuation are much more complex than traffic flow. It is necessary for us to consider more human behavior characteristics if try to apply the model in practice. For the advantages of agent in simulating human intelligence, a multi-agent model based on CA is presented which focuses on simulating the human behavior and the effect on human by building structure. In the model, people are represented by agents and they move over the network which is represented by a lattice of cells. Agents can perceive the local environment and chcx)se their moving direction autonomously. In order to simulate human movement in very complex structure building the acquainting and evacuating states based on the ideas of artificial life are introduced and that is proved successful in simulation. Using this model the effect of the building structure on human behavior can be studied and the performance of building design can be assessed.
Keywords: Cellular automata model multi-agent human behavior performance-based design
The Mathematics Model and Matrix Method of Complex Cocurrent Multi-Effect Evaporation
Ruan Qi,Chen Wenbo,Huang Shihuang,Ye Changshen
Strategic Study of CAE 2001, Volume 3, Issue 4, Pages 36-41
The model of complex cocurrent multi-effect evaporation with condensed water flash and extra vapor elicitation is established. The conventional model of cocurrent multi-effect evaporation is a simplified example of the model. A new algorithm (iteration method combining with matrix method) is presented. The results show that the new algorithm is which increases the convergent speed and stability, more efficient than the Newton method and Broyden method. With condensed water flash and preheating cane sugar solution from 26.7 to 90℃ by elicitation extra vapor,the fresh vapor expenditure of cocurrent three-effect evaporation is decreased by about 16%.
Keywords: condensed water flash extra vapor elicitation cocurrent multi-effect evaporation mathematics model matrix method
Synthetic optimization modeling on mining and utilization of multi-deposits in Gushan mine area
Cai Sijing,Wang Wenxiao,Zheng Minggui
Strategic Study of CAE 2011, Volume 13, Issue 3, Pages 56-62
Based on the concept of full-scale mining,that is,the concept of research on the mining and utilizing of mineral resources of multi-deposits in a mine area by systematic and dynamic considering of mine full-life process, a synthetic optimizing model of artificial neutral network (ANN) export system is set up.By using the model ,a synthetic optimization for the mining and utilization deposits at Gushan mine area is carried out, and the suggested ore production scale for the Gushan mine area is 5.4~6.8 million t/a. The optimized results are helpful to the strengthening construction, the improvement of economical and social benefit and the sustainable development of Gushan mine area.
Keywords: Gushan mine area multi-deposits mining full-scale mining concept ANNexport system model
Vehicle-road collaboration based on BRT-lane TDM support by vehicle-infrastructure integration
Dong Hongzhao,Ling Yue,Liu Dongxu,Guo Mingfei
Strategic Study of CAE 2012, Volume 14, Issue 7, Pages 68-73
In order to increase the availability of the part-time idle BRT-lane, this paper proposes a method of time division multiplexing (TDM) to share BRT-lane with other kind of vehicles based on vehicle road collaboration. The TDM control strategy is established based on Vehicle-Infrastructure Integration and vehicles collaboration. The algorithm is researched to forecast the segmented BRT travel time. According to the real time traffic information, a comprehensive model is given to estimate the vehicles' lane-changing time from/to the BRT-lane to/from its neighbor lane and determine the timing sequence for vehicles collaboration. Finally the experiment demonstrates that the predicted value of the travel time and lane changing time is closed to the true value. The control strategy of the vehicles collaboration could promise other kind of vehicles to share BRT-lane without disturbing BRT's priority.
Keywords: Vehicle-Infrastructure Integration vehicles collaboration BRT-lane time division multiplexing (TDM) lane-changing time model
Digital Earth Model of Multiple Scales and Its Application in Virtulizing Earth
Li Boheng
Strategic Study of CAE 2000, Volume 2, Issue 4, Pages 12-15
The digital earth model is composed of three parts: digital frame model, digital elevation model, and digital earth-unit model. The question of building virtual earth in science mainly includes two sections: building the digital earth model and applying and developing modeling information effectively. The five characteristics of virtual earth and the key technologies for building digital earth model are introduced. This paper also discusses the seven engineering fields in which the digital terrain model is widely used. In the process of constructing ,researching, and developing the digital earth model, attention should be paid to environment pollution, plough land decrease, waterlogging and east-west regional variances, which have influence on China´s na-tional economic construction.
Keywords: digial earth virtual earth information
Title Author Date Type Operation
Prospects for multi-agent collaboration and gaming: challenge, technology, and application
Yu LIU, Zhi LI, Zhizhuo JIANG, You HE
Journal Article
Multi-band Synchronization Model for Speech Recognition Under Noisy Condition
Sun Wei,Wu Zhenyang
Journal Article
A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble
Hui Liu, Rui Yang, Zhu Duan, Haiping Wu
Journal Article
Study on Grey Incidence Decision Model of the Dynamic Multiple-attribute
Dang Yaoguo,Liu Sifeng,Liu Bin,Tao Yong
Journal Article
Supervised topic models with weighted words: multi-label document classification
Yue-peng ZOU, Ji-hong OUYANG, Xi-ming LI
Journal Article
Derivation of the multi-model generalized labeled multi-Bernoulli filter: a solution to multi-target hybrid systems
Weihua Wu, Yichao Cai, Hongbin Jin, Mao Zheng, Xun Feng, Zewen Guan,weihuawu1987@163.com
Journal Article
The model and process simulation of multi-effect two stage evaporation system with solid separation
Li Ling, Ruan Qi
Journal Article
Embracing non-orthogonalmultiple access in future wireless networks
Zhi-guo DING, Mai XU, Yan CHEN, Mu-gen PENG, H. Vincent POOR
Journal Article
Human–Robot Collaboration Framework Based on Impedance Control in Robotic Assembly
Xingwei Zhao,Yiming Chen,Lu Qian,Bo Tao,Han Ding
Journal Article
A Multi-agent Model Based on Cellular Automata for Simulating Human Behavior to Assess Building Design
Fang Weifeng,Yang Lizhong,Huang Rui
Journal Article
The Mathematics Model and Matrix Method of Complex Cocurrent Multi-Effect Evaporation
Ruan Qi,Chen Wenbo,Huang Shihuang,Ye Changshen
Journal Article
Synthetic optimization modeling on mining and utilization of multi-deposits in Gushan mine area
Cai Sijing,Wang Wenxiao,Zheng Minggui
Journal Article
Vehicle-road collaboration based on BRT-lane TDM support by vehicle-infrastructure integration
Dong Hongzhao,Ling Yue,Liu Dongxu,Guo Mingfei
Journal Article