Based on the framework of method of successive averages(MSA), a modified stochastic user-equilibrium assignment algorithm was proposed, which can be used to calculate the passenger flow distribution of urban rail tran...Based on the framework of method of successive averages(MSA), a modified stochastic user-equilibrium assignment algorithm was proposed, which can be used to calculate the passenger flow distribution of urban rail transit(URT) under network operation. In order to describe the congestion's impact to passengers' route choices, a generalized cost function with in-vehicle congestion was set up. Building on the k-th shortest path algorithm, a method for generating choice set with time constraint was embedded, considering the characteristics of network operation. A simple but efficient route choice model, which was derived from travel surveys for URT passengers in China, was introduced to perform the stochastic network loading at each iteration in the algorithm. Initial tests on the URT network in Shanghai City show that the methodology, with rational calculation time, promises to compute more precisely the passenger flow distribution of URT under network operation, compared with those practical algorithms used in today's China.展开更多
A fuzzy modeling method for complex systems is studied. The notation of general stochastic neural network (GSNN) is presented and a new modeling method is given based on the combination of the modified Takagi and Suge...A fuzzy modeling method for complex systems is studied. The notation of general stochastic neural network (GSNN) is presented and a new modeling method is given based on the combination of the modified Takagi and Sugeno's (MTS) fuzzy model and one-order GSNN. Using expectation-maximization(EM) algorithm, parameter estimation and model selection procedures are given. It avoids the shortcomings brought by other methods such as BP algorithm, when the number of parameters is large, BP algorithm is still difficult to apply directly without fine tuning and subjective tinkering. Finally, the simulated example demonstrates the effectiveness.展开更多
The traffic equilibrium assignment problem under tradable credit scheme(TCS) in a bi-modal stochastic transportation network is investigated in this paper. To describe traveler’s risk-taking behaviors under uncertain...The traffic equilibrium assignment problem under tradable credit scheme(TCS) in a bi-modal stochastic transportation network is investigated in this paper. To describe traveler’s risk-taking behaviors under uncertainty, the cumulative prospect theory(CPT) is adopted. Travelers are assumed to choose the paths with the minimum perceived generalized path costs, consisting of time prospect value(PV) and monetary cost. At equilibrium with a given TCS, the endogenous reference points and credit price remain constant, and are consistent with the equilibrium flow pattern and the corresponding travel time distributions of road sub-network. To describe such an equilibrium state, the CPT-based stochastic user equilibrium(SUE) conditions can be formulated under TCS. An equivalent variational inequality(VI) model embedding a parameterized fixed point(FP) model is then established, with its properties analyzed theoretically. A heuristic solution algorithm is developed to solve the model, which contains two-layer iterations. The outer iteration is a bisection-based contraction method to find the equilibrium credit price, and the inner iteration is essentially the method of successive averages(MSA) to determine the corresponding CPT-based SUE network flow pattern. Numerical experiments are provided to validate the model and algorithm.展开更多
The goal of this research is to develop an emergency disaster relief mobilization tool that determines the mobilization levels of commodities, medical service and helicopters （which will be utilized as the primary me...The goal of this research is to develop an emergency disaster relief mobilization tool that determines the mobilization levels of commodities, medical service and helicopters （which will be utilized as the primary means of transport in a mountain region struck by a devastating earthquake） at pointed temporary facilities, including helicopter-based delivery plans for commodities and evacuation plans for critical population, in which relief demands are considered as uncertain. The proposed mobilization model is a two-stage stochastic mixed integer program with two objectives： maximizing the expected fill rate and minimizing the total expenditure of the mobilization campaign. Scenario decomposition based heuristic algorithms are also developed according to the structure of the proposed model. The computational results of a numerical example, which is constructed from the scenarios of the Great Wenchuan Earthquake, indicate that the model can provide valuable decision support for the mobilization of post-earthquake relief, and the proposed algorithms also have high efficiency in computation.展开更多
The process of making decisions is something humans do inherently and routinely,to the extent that it appears commonplace. However,in order to achieve good overall performance,decisions must take into account both the...The process of making decisions is something humans do inherently and routinely,to the extent that it appears commonplace. However,in order to achieve good overall performance,decisions must take into account both the outcomes of past decisions and opportunities of future ones. Reinforcement learning,which is fundamental to sequential decision-making,consists of the following components: 1 A set of decisions epochs; 2 A set of environment states; 3 A set of available actions to transition states; 4 State-action dependent immediate rewards for each action.At each decision,the environment state provides the decision maker with a set of available actions from which to choose. As a result of selecting a particular action in the state,the environment generates an immediate reward for the decision maker and shifts to a different state and decision. The ultimate goal for the decision maker is to maximize the total reward after a sequence of time steps.This paper will focus on an archetypal example of reinforcement learning,the stochastic multi-armed bandit problem. After introducing the dilemma,I will briefly cover the most common methods used to solve it,namely the UCB and εn- greedy algorithms. I will also introduce my own greedy implementation,the strict-greedy algorithm,which more tightly follows the greedy pattern in algorithm design,and show that it runs comparably to the two accepted algorithms.展开更多
基金Project(2007AA11Z236) supported by the National High Technology Research and Development Program of ChinaProject(2012M5209O1) supported by China Postdoctoral Science Foundation
文摘Based on the framework of method of successive averages(MSA), a modified stochastic user-equilibrium assignment algorithm was proposed, which can be used to calculate the passenger flow distribution of urban rail transit(URT) under network operation. In order to describe the congestion's impact to passengers' route choices, a generalized cost function with in-vehicle congestion was set up. Building on the k-th shortest path algorithm, a method for generating choice set with time constraint was embedded, considering the characteristics of network operation. A simple but efficient route choice model, which was derived from travel surveys for URT passengers in China, was introduced to perform the stochastic network loading at each iteration in the algorithm. Initial tests on the URT network in Shanghai City show that the methodology, with rational calculation time, promises to compute more precisely the passenger flow distribution of URT under network operation, compared with those practical algorithms used in today's China.
文摘A fuzzy modeling method for complex systems is studied. The notation of general stochastic neural network (GSNN) is presented and a new modeling method is given based on the combination of the modified Takagi and Sugeno's (MTS) fuzzy model and one-order GSNN. Using expectation-maximization(EM) algorithm, parameter estimation and model selection procedures are given. It avoids the shortcomings brought by other methods such as BP algorithm, when the number of parameters is large, BP algorithm is still difficult to apply directly without fine tuning and subjective tinkering. Finally, the simulated example demonstrates the effectiveness.
基金Project(BX20180268)supported by National Postdoctoral Program for Innovative Talent,ChinaProject(300102228101)supported by Fundamental Research Funds for the Central Universities of China+1 种基金Project(51578150)supported by the National Natural Science Foundation of ChinaProject(18YJCZH130)supported by the Humanities and Social Science Project of Chinese Ministry of Education
文摘The traffic equilibrium assignment problem under tradable credit scheme(TCS) in a bi-modal stochastic transportation network is investigated in this paper. To describe traveler’s risk-taking behaviors under uncertainty, the cumulative prospect theory(CPT) is adopted. Travelers are assumed to choose the paths with the minimum perceived generalized path costs, consisting of time prospect value(PV) and monetary cost. At equilibrium with a given TCS, the endogenous reference points and credit price remain constant, and are consistent with the equilibrium flow pattern and the corresponding travel time distributions of road sub-network. To describe such an equilibrium state, the CPT-based stochastic user equilibrium(SUE) conditions can be formulated under TCS. An equivalent variational inequality(VI) model embedding a parameterized fixed point(FP) model is then established, with its properties analyzed theoretically. A heuristic solution algorithm is developed to solve the model, which contains two-layer iterations. The outer iteration is a bisection-based contraction method to find the equilibrium credit price, and the inner iteration is essentially the method of successive averages(MSA) to determine the corresponding CPT-based SUE network flow pattern. Numerical experiments are provided to validate the model and algorithm.
基金supported by the National Natural Science Foundation of China 71371181 91024006China Postdoctoral Science Foundation (2012M521918)
文摘The goal of this research is to develop an emergency disaster relief mobilization tool that determines the mobilization levels of commodities, medical service and helicopters （which will be utilized as the primary means of transport in a mountain region struck by a devastating earthquake） at pointed temporary facilities, including helicopter-based delivery plans for commodities and evacuation plans for critical population, in which relief demands are considered as uncertain. The proposed mobilization model is a two-stage stochastic mixed integer program with two objectives： maximizing the expected fill rate and minimizing the total expenditure of the mobilization campaign. Scenario decomposition based heuristic algorithms are also developed according to the structure of the proposed model. The computational results of a numerical example, which is constructed from the scenarios of the Great Wenchuan Earthquake, indicate that the model can provide valuable decision support for the mobilization of post-earthquake relief, and the proposed algorithms also have high efficiency in computation.
文摘The process of making decisions is something humans do inherently and routinely,to the extent that it appears commonplace. However,in order to achieve good overall performance,decisions must take into account both the outcomes of past decisions and opportunities of future ones. Reinforcement learning,which is fundamental to sequential decision-making,consists of the following components: 1 A set of decisions epochs; 2 A set of environment states; 3 A set of available actions to transition states; 4 State-action dependent immediate rewards for each action.At each decision,the environment state provides the decision maker with a set of available actions from which to choose. As a result of selecting a particular action in the state,the environment generates an immediate reward for the decision maker and shifts to a different state and decision. The ultimate goal for the decision maker is to maximize the total reward after a sequence of time steps.This paper will focus on an archetypal example of reinforcement learning,the stochastic multi-armed bandit problem. After introducing the dilemma,I will briefly cover the most common methods used to solve it,namely the UCB and εn- greedy algorithms. I will also introduce my own greedy implementation,the strict-greedy algorithm,which more tightly follows the greedy pattern in algorithm design,and show that it runs comparably to the two accepted algorithms.
