This paper introduces the structure of a multiagent design system with machine learning mechanism and its application in mechanical design. Firs of are it introduces a hierarchical structure of the multiagent design ...This paper introduces the structure of a multiagent design system with machine learning mechanism and its application in mechanical design. Firs of are it introduces a hierarchical structure of the multiagent design system and takes a mechanical design system as an example. This structure provides a computational platform for cooperative design and sharing learning of multiple design agents. The paper analyses the principle of design activity and puts forward the architecture and learning mechanism of a design agent in datail. The architecture of a design agent is for providing support to learning activity and is based on the analysis of the design activity This is followed by a description of the design knowledge base framework and sharing learning process of multiagent. The main advantages of the system is that complex design task can be done by multiagent in a distributed environment and leaming results can be shared by a group of design agents. This system has partly been implemented in Visual C++ based on Mechanical Desktop 2.0 environment.展开更多
This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature repr...This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.展开更多
文摘This paper introduces the structure of a multiagent design system with machine learning mechanism and its application in mechanical design. Firs of are it introduces a hierarchical structure of the multiagent design system and takes a mechanical design system as an example. This structure provides a computational platform for cooperative design and sharing learning of multiple design agents. The paper analyses the principle of design activity and puts forward the architecture and learning mechanism of a design agent in datail. The architecture of a design agent is for providing support to learning activity and is based on the analysis of the design activity This is followed by a description of the design knowledge base framework and sharing learning process of multiagent. The main advantages of the system is that complex design task can be done by multiagent in a distributed environment and leaming results can be shared by a group of design agents. This system has partly been implemented in Visual C++ based on Mechanical Desktop 2.0 environment.
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by Hunan Provincial Science and Technology Department,China
文摘This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.
