The problem of fusing multiagent preference orderings, with information on agent's importance being incomplete certain with respect to a set of possible courses of action, is described. The approach is developed for ...The problem of fusing multiagent preference orderings, with information on agent's importance being incomplete certain with respect to a set of possible courses of action, is described. The approach is developed for dealing with the fusion problem described in the following sections and requires that each agent provides a preference ordering over the different alternatives completely independent of the other agents, and the information on agent's importance is incomplete certain. In this approach, the ternary comparison matrix of the alternatives is constructed, the eigenvector associated with the maximum eigenvalue of the ternary comparison matrix is attained so as to normalize priority vector of the alternatives. The interval number of the alternatives is then obtained by solving two sorts of linear programming problems. By comparing the interval numbers of the alternatives, the ranking of alternatives can be generated. Finally, some examples are given to show the feasibility and effectiveness of the method.展开更多
The multi-sensors fusion refers to the synergistic combination of sensory data from multiple sensors to provide more accurate and reliable information. The potential benefits of the Fusion are multi-sensors’ redundan...The multi-sensors fusion refers to the synergistic combination of sensory data from multiple sensors to provide more accurate and reliable information. The potential benefits of the Fusion are multi-sensors’ redundancy and extra information acquired. The fusion of redundant information can reduce the overall uncertainty and thus helps to provide information specified more precisely. Several sensors providing redundant information can also be used to increase reliability in the case of error, omission or failure of sensors. The combination operators are exponential and are more complex in terms of calculation;the Dempster-Shafer operator is exponential for more than three (3) information sources?[1] [2]. Our work focuses on the definition of another formulation of this operation, and puts it in a matrix form to illuminate the computational complexity, more precision guaranty and a minimal execution time. We propose to use each information source in a form of a matrix, which contains 0 value in lines that do not contain the masses (m(Ai) = 0) or once m(Ai) is not null (m(Ai) ≠ 0). The use of this expressed matrix attempts to ameliorate Dempster-Shafer operator via initialing either a criterion or criteria sources’ solution, increasing the efficiency of the Dempster-Shafer operator and facilitates the combination among the sources. We evaluate our approach by conducting a case study for showing the effectiveness of this matrix.展开更多
现有的网联自动驾驶车辆(Connected and Automated Vehicles,CAV)换道决策模型鲁棒性较差,存在安全隐患,且单纯依赖自车信息、较小范围内的感知信息,难以在CAV与人工驾驶车辆(Human-Driven Vehicles,HDV)混行的环境中推断出最优动作.综...现有的网联自动驾驶车辆(Connected and Automated Vehicles,CAV)换道决策模型鲁棒性较差,存在安全隐患,且单纯依赖自车信息、较小范围内的感知信息,难以在CAV与人工驾驶车辆(Human-Driven Vehicles,HDV)混行的环境中推断出最优动作.综合考虑感知信息、自车以及车-车通信(Vehicle-to-Vehicle,V2V)范围内上、下游CAV信息,提出一种混合交通流环境下集成多源信息融合的深度强化学习(Multi-Source Information Fusion Deep Reinforcement Learning,MSIF-DRL)端到端网联自动驾驶换道决策模型.首先,构建含有多源信息的状态空间,并为不同信息分配权重;其次,通过编码网络将各种动态信息编码到高维特征空间,进行信息融合得到特征图;然后,将其扁平化送入拥有优先经验回放机制的竞争双深度Q网络中,进行动作的选择和评估;最后,分别设计适用于主线、匝道CAV的奖励函数引导所提MSIF-DRL模型解决高速公路合流区驾驶场景中CAV的自由以及强制换道问题.基于SUMO软件在各种仿真条件下进行实验,将所提出的MSIF-DRL换道决策模型与现有换道模型进行比较,验证其有效性和优越性.研究结果表明:相较于现有模型,所提MSIF-DRL模型在各种仿真条件下均拥有最高的奖励值、换道成功率、合流成功率、平均行车速度、舒适性以及最低的碰撞风险,其中换道成功率、合流成功率、平均行车速度最大分别提升了29.17%、27.71%、17.43%;随着渗透率的提高,该模型在处理混合交通流环境下CAV的换道决策问题时拥有更强的性能和鲁棒性.展开更多
针对语义分布不平衡环境下的语义偏好和决策信息的复杂性问题,为提高决策的准确性,提出了一个新型不平衡语言尺度函数.它可通过改变语义偏好参数来调节相邻语义之间的偏差,适用于不同的决策环境,并对相关性质进行了证明.在犹豫不确定语...针对语义分布不平衡环境下的语义偏好和决策信息的复杂性问题,为提高决策的准确性,提出了一个新型不平衡语言尺度函数.它可通过改变语义偏好参数来调节相邻语义之间的偏差,适用于不同的决策环境,并对相关性质进行了证明.在犹豫不确定语言型Z-numbers(hesitant uncertain linguistic Z-numbers,简称HULZNs)的环境下,定义了两个HULZNs之间的距离以及部分运算,建立了优先加权平均运算算子和一种新型多准则群决策模型.最后,对提出的新模型利用实例进行了分析,验证了方法的有效性和可行性.展开更多
To solve the problem of information fusion from multiple sources in innovation alliances, an information fusion model based on the Bayesian network is presented. The multi-source information fusion process of innovati...To solve the problem of information fusion from multiple sources in innovation alliances, an information fusion model based on the Bayesian network is presented. The multi-source information fusion process of innovation alliances was classified into three layers, namely, the information perception layer, the feature clustering layer,and the decision fusion layer. The agencies in the alliance were defined as sensors through which information is perceived and obtained, and the features were clustered. Finally, various types of information were fused by the innovation alliance based on the fusion algorithm to achieve complete and comprehensive information. The model was applied to a study on economic information prediction, where the accuracy of the fusion results was higher than that from a single source and the errors obtained were also smaller with the MPE less than 3%, which demonstrates the proposed fusion method is more effective and reasonable. This study provides a reasonable basis for decision-making of innovation alliances.展开更多
The interval numbers are used to types and observation of sensors, a new fusion represent the characteristic values of object method for multi-sensor object recognition is proposed from the viewpoint of decision makin...The interval numbers are used to types and observation of sensors, a new fusion represent the characteristic values of object method for multi-sensor object recognition is proposed from the viewpoint of decision making theory. The method defines the distance matrix and grey association matrix between all object types and unknown object. After solving the optimization problem of maximizing the standard deviations for all attributes, the weights of the attributes are obtained. Thus, the result of recognition for the unknown object is given by the grey association degree. This method avoids the subjectivity of selecting attributes weights. It is straightforward and can be performed on computer easily. The simulated example demonstrates the feasibility and effectiveness of the proposed method.展开更多
基金This project was supported by the National Natural Science Foundation of China(70631004).
文摘The problem of fusing multiagent preference orderings, with information on agent's importance being incomplete certain with respect to a set of possible courses of action, is described. The approach is developed for dealing with the fusion problem described in the following sections and requires that each agent provides a preference ordering over the different alternatives completely independent of the other agents, and the information on agent's importance is incomplete certain. In this approach, the ternary comparison matrix of the alternatives is constructed, the eigenvector associated with the maximum eigenvalue of the ternary comparison matrix is attained so as to normalize priority vector of the alternatives. The interval number of the alternatives is then obtained by solving two sorts of linear programming problems. By comparing the interval numbers of the alternatives, the ranking of alternatives can be generated. Finally, some examples are given to show the feasibility and effectiveness of the method.
文摘The multi-sensors fusion refers to the synergistic combination of sensory data from multiple sensors to provide more accurate and reliable information. The potential benefits of the Fusion are multi-sensors’ redundancy and extra information acquired. The fusion of redundant information can reduce the overall uncertainty and thus helps to provide information specified more precisely. Several sensors providing redundant information can also be used to increase reliability in the case of error, omission or failure of sensors. The combination operators are exponential and are more complex in terms of calculation;the Dempster-Shafer operator is exponential for more than three (3) information sources?[1] [2]. Our work focuses on the definition of another formulation of this operation, and puts it in a matrix form to illuminate the computational complexity, more precision guaranty and a minimal execution time. We propose to use each information source in a form of a matrix, which contains 0 value in lines that do not contain the masses (m(Ai) = 0) or once m(Ai) is not null (m(Ai) ≠ 0). The use of this expressed matrix attempts to ameliorate Dempster-Shafer operator via initialing either a criterion or criteria sources’ solution, increasing the efficiency of the Dempster-Shafer operator and facilitates the combination among the sources. We evaluate our approach by conducting a case study for showing the effectiveness of this matrix.
文摘现有的网联自动驾驶车辆(Connected and Automated Vehicles,CAV)换道决策模型鲁棒性较差,存在安全隐患,且单纯依赖自车信息、较小范围内的感知信息,难以在CAV与人工驾驶车辆(Human-Driven Vehicles,HDV)混行的环境中推断出最优动作.综合考虑感知信息、自车以及车-车通信(Vehicle-to-Vehicle,V2V)范围内上、下游CAV信息,提出一种混合交通流环境下集成多源信息融合的深度强化学习(Multi-Source Information Fusion Deep Reinforcement Learning,MSIF-DRL)端到端网联自动驾驶换道决策模型.首先,构建含有多源信息的状态空间,并为不同信息分配权重;其次,通过编码网络将各种动态信息编码到高维特征空间,进行信息融合得到特征图;然后,将其扁平化送入拥有优先经验回放机制的竞争双深度Q网络中,进行动作的选择和评估;最后,分别设计适用于主线、匝道CAV的奖励函数引导所提MSIF-DRL模型解决高速公路合流区驾驶场景中CAV的自由以及强制换道问题.基于SUMO软件在各种仿真条件下进行实验,将所提出的MSIF-DRL换道决策模型与现有换道模型进行比较,验证其有效性和优越性.研究结果表明:相较于现有模型,所提MSIF-DRL模型在各种仿真条件下均拥有最高的奖励值、换道成功率、合流成功率、平均行车速度、舒适性以及最低的碰撞风险,其中换道成功率、合流成功率、平均行车速度最大分别提升了29.17%、27.71%、17.43%;随着渗透率的提高,该模型在处理混合交通流环境下CAV的换道决策问题时拥有更强的性能和鲁棒性.
文摘针对语义分布不平衡环境下的语义偏好和决策信息的复杂性问题,为提高决策的准确性,提出了一个新型不平衡语言尺度函数.它可通过改变语义偏好参数来调节相邻语义之间的偏差,适用于不同的决策环境,并对相关性质进行了证明.在犹豫不确定语言型Z-numbers(hesitant uncertain linguistic Z-numbers,简称HULZNs)的环境下,定义了两个HULZNs之间的距离以及部分运算,建立了优先加权平均运算算子和一种新型多准则群决策模型.最后,对提出的新模型利用实例进行了分析,验证了方法的有效性和可行性.
基金supported by the National Natural Science Foundation of China(Nos.71472053,71429001,and91646105)
文摘To solve the problem of information fusion from multiple sources in innovation alliances, an information fusion model based on the Bayesian network is presented. The multi-source information fusion process of innovation alliances was classified into three layers, namely, the information perception layer, the feature clustering layer,and the decision fusion layer. The agencies in the alliance were defined as sensors through which information is perceived and obtained, and the features were clustered. Finally, various types of information were fused by the innovation alliance based on the fusion algorithm to achieve complete and comprehensive information. The model was applied to a study on economic information prediction, where the accuracy of the fusion results was higher than that from a single source and the errors obtained were also smaller with the MPE less than 3%, which demonstrates the proposed fusion method is more effective and reasonable. This study provides a reasonable basis for decision-making of innovation alliances.
基金This project is supported by National Natural Science Foundation of China (10626029) Jiangxi Province Natural Science Foundation of China (0611082) Science and Technology Project of Jiangxi province educational department in China (GJJ08350)
文摘The interval numbers are used to types and observation of sensors, a new fusion represent the characteristic values of object method for multi-sensor object recognition is proposed from the viewpoint of decision making theory. The method defines the distance matrix and grey association matrix between all object types and unknown object. After solving the optimization problem of maximizing the standard deviations for all attributes, the weights of the attributes are obtained. Thus, the result of recognition for the unknown object is given by the grey association degree. This method avoids the subjectivity of selecting attributes weights. It is straightforward and can be performed on computer easily. The simulated example demonstrates the feasibility and effectiveness of the proposed method.