检索结果-南通市图书馆

User preference-based intelligent road route recommendation using SARSA and dynamic programming

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Control and Decision 2023年第3期10卷 443-453页

作者： Roopa Ravish Shanta Rangaswamy Arpitha V Vasuprada U PES University BengaluruIndia Rashtreeya Vidyalaya College of Engineering BengaluruIndia

Traffic congestion is one of the main challenges in transportation engineering. It directly impactsthe economy by increasing travel time and affecting the environment by excessive fuel consumptionand emission. Road route recommendation to overcome the congestion by alternativeroute suggestions has gained high importance. The existing route recommendation systems areproposed using the reinforcement learning algorithm (Q-learning). The techniques suggestedin this paper are state-action-reward-state-action (SARSA) algorithm and dynamic programming(DP) to guide the commuters to reach the destination with an optimal solution. The algorithmconsiders travel time, cost, flexibility, and traffic intensity as the user preference attributes torecommend an optimal route. The recommended system is implemented by building a roadnetwork graph. We assign values to each user preference attribute along the edges, which cantake high(1) or low(0) values. By considering these values, the system recommends the *** proposed system performance is evaluated based on computation time, cumulative reward,and accuracy. The results show that DP outperforms the SARSA algorithm.

关键词： Intelligent transport system machine learning techniques in ITS SARSA algorithm dynamic programming route guidance system travel time prediction traveller information system

Smoothing ramp events in wind farm based on dynamic programming in energy internet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers in Energy 2018年第4期12卷 550-559页

作者： Jiang LI Guodong LIU Shuo ZHANG School of Electrical Engineering Northeast Electric Power UniversityJilin 132012China

The concept of energy internet has been gradually accepted, which can optimize the consumption of fossil energy and renewable energy resources. When wind power is integrated into the main grid, ramp events caused by stochastic wind power fluctuation may threaten the security of power systems. This paper proposes a dynamic programming method in smoothing ramp events. First, the energy internet model of wind power, pumped storage power station, and gas power station is established. Then, the optimization problem in the energy internet is transformed into a multi-stage dynamic programming problem, and the dynamic programming method proposed is applied to solve the optimization problem. Finally, the evaluation functions are introduced to evaluate pollutant emissions. The results show that the dynamic programming method proposed is effective for smoothing wind power and reducing ramp events in energy internet.

关键词： energy intemet wind power ramp events dynamic programming

CONTROLLING ROBOT MANIPULATORS BY dynamic programming

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mechanica Sinica 1995年第1期11卷 20-33页

作者： MarcJ.Richard Department

A certain number of considerations should be taken into account in the dynamic control of robot manipulators as highly complex non-linear *** this article,we provide a detailed presentation of the mechanical and electrical impli- cations of robots equipped with DC motor *** model takes into account all non-linear aspects of the ***,we develop computational algorithms for optimal control based on dynamic *** robot's trajectory must be predefined,but performance criteria and constraints applying to the system are not limited and we may adapt them freely to the robot and the task being *** an example,a manipulator arm with 3 degrees of freedom is analyzed.

关键词： dynamic programming robot manipulators optimal control dynamic modelling method

dynamic programming methodology for multi-criteria group decision-making under ordinal preferences

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2010年第6期21卷 975-980页

作者： Wu Li Guanqi Guo Chaoyuan Yue Yong Zhao School of Information and Communication Engineering Hunan Institute of Science and Technology Yueyang 414006 E R. China Institute of Systems Engineering Huazhong University of Science and Technology Wuhan 430074 P. R. China

A method of minimizing rankings inconsistency is proposed for a decision-making problem with rankings of alternatives given by multiple decision makers according to multiple criteria. For each criteria, at first, the total inconsistency between the rankings of all alternatives for the group and the ones for every decision maker is defined after the decision maker weights in respect to the criteria are considered. Similarly, the total inconsistency between their final rankings for the group and the ones under every criteria is determined after the criteria weights are taken into account. Then two nonlinear integer programming models minimizing respectively the two total inconsistencies above are developed and then transformed to two dynamic programming models to obtain separately the rankings of all alternatives for the group with respect to each criteria and their final rankings. A supplier selection case illustrated the proposed method, and some discussions on the results verified its effectiveness. This work develops a new measurement of ordinal preferences’ inconsistency in multi-criteria group decision-making （MCGDM） and extends the cook-seiford social selection function to MCGDM considering weights of criteria and decision makers and can obtain unique ranking result.

关键词： multi-criteria group decision-making (MCGDM) ordinal preference minimum deviation method dynamic programming Cook-Seiford social selection function.

Multi-view video color correction using dynamic programming

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2008年第6期19卷 1115-1120页

作者： Shao Feng Jiang Gangyi Yu Mei Faculty of Information Science and Engineering Ningbo Univ. Ningbo 315211 P. R. China National Key Lab of Software New Technology Nanjing Univ. Nanjing 210093 P. R. China

Color inconsistency between views is an important problem to be solved in multi-view video systems. A multi-view video color correction method using dynamic programming is proposed. Three-dimensional histograms are constructed with sequential conditional probability in HSI color space. Then, dynamic programming is used to seek the best color mapping relation with the minimum cost path between target image histogram and source image histogram. Finally, video tracking technique is performed to correct multi-view video. Experimental results show that the proposed method can obtain better subjective and objective performance in color correction.

关键词： multi-view video color correction dynamic programming video tracking

A dynamic programming Track-Before-Detect Algorithm Based on Local Linearization for Non-Gaussian Clutter Background

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第3期25卷 583-590页

作者： ZHENG Daikun WANG Shouyong QIN Xing Air Force Early Warning Academy

The dynamic programming track before detect(DP-TBD) algorithm has been widely used for detection and tracking of weak targets. The selection of the merit function has an immediate influence on the performance of the DP-TBD. The amplitude merit function is easy to calculate, but the performance of which will decrease in the presence of non-Gaussian clutter. The likelihood ratio merit function in closed analytical form is difficult to derive under non-Gaussian background without target signal parameters. To solve this problem, a novel DPTBD algorithm based on local linearization is *** maximum of the state conditional probability ratio of the target as the optimal criteria, a recursive integration equation is derived. The equation is locally linearized by Taylor series expansion and a suboptimal multi-frame test statistic is developed. The calculation of new merit function in the statistic needs only clutter distribution model,and heavy clutter peak can be restrained by making use of clutter distribution characters. So the proposed algorithm can efficiently extract weak target in strong non-Gaussian clutter. Numerical simulations are provided to assess and compare the performance of the proposed algorithm. It turns out that the proposed algorithm has better detection and tracking performance than the widely used DPTBD algorithm at present and is resilient to various clutter distribution models.

关键词： Target detection Track-before-detect dynamic programming Local linearization Non-Gaussian clutter

Further Improvement on dynamic programming for Optimal Bit ALlocation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2003年第1期18卷 109-113页

作者：陈毅松汪国平董士海 HCI and Multimedia Laboratory Peking University Beijing 100871 P.R. China

dynamic programming algorithms based on Lagrange multiplier method is often used for obtaining an optimal bit allocation strategy to minimize the total distortion given a constrained rate budget in both source and channel coding applications. Due to possible large quantizer set and improper initialization, the algorithm often suffers from heavy computational complexity. There have been many solutions in recent years to the above question. In this paper,a simple but efficient algorithm is presented to further speed up the convergence of the *** algorithm can be easily realized and get the final solution much faster. The experimental result shows that our new algorithm can figure out the optimal solution with a speed 5-7 times faster than the original algorithm.

关键词： bit allocation Lagrange multiplier method dynamic programming

Deployment of Sensors in WSN: An Efficient Approach Based on dynamic programming

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第1期24卷 33-37页

作者： LI Yongyan GAO Wen WU Chunming WANG Yansong University of Shaoxing at Shang Yu Institute of Computer System Architecture Zhejiang University ZTE Corporation

Efficient sensor node deployment is extremely important in wireless sensor networks. It earns great practical meanings through using fewer sensor nodes as far as possible to satisfy different requirements such as the requirement on coverage and overcoming the potential sensor node failures and the adverse influence from the environment. We propose an efficient approach for the deployment of sensor nodes in wireless networks, termed as EDSNDA, which is excellent in taking both the requirements of sensor coverage and network connectivity into consideration when minimizing the number of necessary sensor nodes to the best of its ability. We proposed a new coverage model of sensor node. Based on the sensor coverage model, we establish four dynamic programming models in four different practical situations, respectively. The algorithms are then proposed which are used for solving the corresponding dynamic programming models. The validity of the method is justified by simulation studies in which the method is compared with the current representative methods. The simulation results show that our method performs better than the other ones with fewer sensor nodes, better coverage and network connectivity result in the same circumstance.

关键词： Wireless sensor network Sensor node deployment dynamic programming Sensor coverage model

PDP: Parallel dynamic programming

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2017年第1期4卷 1-5页

作者： Fei-Yue Wang Jie Zhang Qinglai Wei Xinhu Zheng Li Li IEEE State Key Laboratory of Management and Control for Complex Systems(SKL-MCCS) Institute of AutomationChinese Academy of Sciences(CASIA) School of Computer and Control Engineering University of Chinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences(SKL-MCCSCASIA) Qingdao Academy of Intelligent Industries Department of Computer Science and Engineering University of Minnesota Department of Automation Tsinghua University

Deep reinforcement learning is a focus research area in artificial intelligence. The principle of optimality in dynamic programming is a key to the success of reinforcement learning methods. The principle of adaptive dynamic programming(ADP)is first presented instead of direct dynamic programming(DP),and the inherent relationship between ADP and deep reinforcement learning is developed. Next, analytics intelligence, as the necessary requirement, for the real reinforcement learning, is discussed. Finally, the principle of the parallel dynamic programming, which integrates dynamic programming and analytics intelligence, is presented as the future computational intelligence.

关键词： Parallel dynamic programming dynamic programming Adaptive dynamic programming Reinforcement learning Deep learning Neural networks Artificial intelligence