We study the problem of humanactivity recognition from RGB-Depth(RGBD)sensors when the skeletons are not available.The skeleton tracking in Kinect SDK workswell when the human subject is facing thecamera and there are...We study the problem of humanactivity recognition from RGB-Depth(RGBD)sensors when the skeletons are not available.The skeleton tracking in Kinect SDK workswell when the human subject is facing thecamera and there are no occlusions.In surveillance or nursing home monitoring scenarios,however,the camera is usually mounted higher than human subjects,and there may beocclusions.The interest-point based approachis widely used in RGB based activity recognition,it can be used in both RGB and depthchannels.Whether we should extract interestpoints independently of each channel or extract interest points from only one of thechannels is discussed in this paper.The goal ofthis paper is to compare the performances ofdifferent methods of extracting interest points.In addition,we have developed a depth mapbased descriptor and built an RGBD dataset,called RGBD-SAR,for senior activity recognition.We show that the best performance isachieved when we extract interest points solely from RGB channels,and combine the RGBbased descriptors with the depth map-baseddescriptors.We also present a baseline performance of the RGBD-SAR dataset.展开更多
With the improvement of mobile equipment performance and development of Pervasive Computing,interactive computational applications such as Multi-Agent (MA) systems in Pervasive Computing Environments (PCE) become more...With the improvement of mobile equipment performance and development of Pervasive Computing,interactive computational applications such as Multi-Agent (MA) systems in Pervasive Computing Environments (PCE) become more and more prevalent. Many applications in PCE require Agent communication,manual control,and diversity of devices. Hence system in PCE must be designed flexible,and optimize the use of network,storage and computing resources. However,traditional MA software framework cannot completely adapt to these new features. A new MA software framework and its Agent Communication Modules to solve the problem brought by PCE was proposed. To describe more precisely,it presents Wright/ADL (Architecture Description Language) description of the new framework. Then,it displays an application called AI Eleven based on this new framework. AI Eleven achieves Agent-Agent communication and good collaboration for a task. Two experiments on AI Eleven will demonstrate the new framework's practicability and superiority.展开更多
A new concept of rare axis based on statistical facts is proposed, and an evaluation algorithm is designed thereafter. For the nested regular expressions containing rare axes, the proposed algorithm can reduce its eva...A new concept of rare axis based on statistical facts is proposed, and an evaluation algorithm is designed thereafter. For the nested regular expressions containing rare axes, the proposed algorithm can reduce its evaluation complexity from polynomial time to nearly linear time. The distributed technique is also employed to construct the navigation axis indexes for resource description framework(RDF) graph data. Experiment results in Drug Bank and Bio GRID show that this method can improve the query efficiency significantly while ensuring the accuracy and meet the query requirements on Web-scale RDF graph data.展开更多
Interaction is one of the crucial features of multl-agent systems, in which there are two kinds of interaction： agent-to-agent and human-to-agent. In order to unify the two kinds of interaction while designing multi-...Interaction is one of the crucial features of multl-agent systems, in which there are two kinds of interaction： agent-to-agent and human-to-agent. In order to unify the two kinds of interaction while designing multi-agent systems, this paper introduces Q language-a scenario description language for designing interaction among agents and humans. Based on Q, we propose an integrating interaction framework system for multi-agent coordination, in which Q scenarios are used to uniformly describe both kinds of interactions. Being in accordance to the characteristics of Q language, the Q-based framework makes the interaction process open and easily understood by the users. Additionally, it makes specific applications of multi-agent systems easy to be established by application designers. By applying agent negotiation in agent-mediated e-commerce and agent cooperation in interoperable information query on the Semantic Web, we illustrate how the presented framework for multi-agent coordination is implemented in concrete applications. At the same time, these two different applications also demonstrate usability of the presented framework and verify validity of Q language.展开更多
Speciation research during the last several decades has confirmed that natural selection frequently drives the genera- tion of new species. But how does this process generally unfold in nature？ We argue that answerin...Speciation research during the last several decades has confirmed that natural selection frequently drives the genera- tion of new species. But how does this process generally unfold in nature？ We argue that answering this question requires a clearer conceptual framework for understanding selection＇s role in speciation. We present a unified framework of speciation, pro- viding mechanistic descriptions of fundamentally distinct routes to speciation, and how these may interact during lineage splitting Two major categories are recognized： reproductive isolation resulting from （1） responses to selection, ＂speciation by selection,＂ or （2） non-selective processes, ＂speciation without selection.＂ Speciation by selection can occur via three mechanisms： （1） similar selection, （2） divergent selection, and （3） reinforcement selection. Understanding ecology＇s role in speciation requires uncovering how these three mechanisms contribute to reproductive isolation, and their relative importance compared to non-selective proce- sses, because all three mechanisms can occur side-by-side during speciation. To accomplish this, we highlight examination of groups of organisms inhabiting replicated environmental gradients. This scenario is common in nature, and a large literature illus- trates that both parallel and non-parallel responses to similar environments are widespread, and each can result in speciation. This recognition reveals four general pathways of speciation by similar or divergent selection--parallel and nonparallel responses to similar and divergent selection. Altogether, we present a more precise framework for speciation research, draw attention to some under-recognized features of speciation, emphasize the multidimensionality of speciation, reveal limitations of some previous tests and descriptions of speciation mechanisms, and point to a number of directions for future investigation [Current Zoology 59 （1）： 31-52, 2013].展开更多
基金supported by the National Natural Science Foundation of China under Grants No.61075045,No.61273256the Program for New Century Excellent Talents in University under Grant No.NECT-10-0292+1 种基金the National Key Basic Research Program of China(973Program)under Grant No.2011-CB707000the Fundamental Research Funds for the Central Universities
文摘We study the problem of humanactivity recognition from RGB-Depth(RGBD)sensors when the skeletons are not available.The skeleton tracking in Kinect SDK workswell when the human subject is facing thecamera and there are no occlusions.In surveillance or nursing home monitoring scenarios,however,the camera is usually mounted higher than human subjects,and there may beocclusions.The interest-point based approachis widely used in RGB based activity recognition,it can be used in both RGB and depthchannels.Whether we should extract interestpoints independently of each channel or extract interest points from only one of thechannels is discussed in this paper.The goal ofthis paper is to compare the performances ofdifferent methods of extracting interest points.In addition,we have developed a depth mapbased descriptor and built an RGBD dataset,called RGBD-SAR,for senior activity recognition.We show that the best performance isachieved when we extract interest points solely from RGB channels,and combine the RGBbased descriptors with the depth map-baseddescriptors.We also present a baseline performance of the RGBD-SAR dataset.
基金Guangdong-Hong Kong Technology Cooperation Funding Scheme, China ( No.2007A010101003)Guangdong-Ministry of Education Industry-University Cooperation Funding Scheme,China (No.2007B090200018)
文摘With the improvement of mobile equipment performance and development of Pervasive Computing,interactive computational applications such as Multi-Agent (MA) systems in Pervasive Computing Environments (PCE) become more and more prevalent. Many applications in PCE require Agent communication,manual control,and diversity of devices. Hence system in PCE must be designed flexible,and optimize the use of network,storage and computing resources. However,traditional MA software framework cannot completely adapt to these new features. A new MA software framework and its Agent Communication Modules to solve the problem brought by PCE was proposed. To describe more precisely,it presents Wright/ADL (Architecture Description Language) description of the new framework. Then,it displays an application called AI Eleven based on this new framework. AI Eleven achieves Agent-Agent communication and good collaboration for a task. Two experiments on AI Eleven will demonstrate the new framework's practicability and superiority.
基金Supported by the National Natural Science Foundation of China(No.61373035 and No.61100049)National High Technology Research and Development Program of China("863"Program,No.2013AA013204)+1 种基金Fundamental Research Funds for the Central Universities(No.3122014C018 and 3122015C022)Scientific Research Funds Supported by Civil Aviation University of China(No.09QD02X)
文摘A new concept of rare axis based on statistical facts is proposed, and an evaluation algorithm is designed thereafter. For the nested regular expressions containing rare axes, the proposed algorithm can reduce its evaluation complexity from polynomial time to nearly linear time. The distributed technique is also employed to construct the navigation axis indexes for resource description framework(RDF) graph data. Experiment results in Drug Bank and Bio GRID show that this method can improve the query efficiency significantly while ensuring the accuracy and meet the query requirements on Web-scale RDF graph data.
文摘Interaction is one of the crucial features of multl-agent systems, in which there are two kinds of interaction： agent-to-agent and human-to-agent. In order to unify the two kinds of interaction while designing multi-agent systems, this paper introduces Q language-a scenario description language for designing interaction among agents and humans. Based on Q, we propose an integrating interaction framework system for multi-agent coordination, in which Q scenarios are used to uniformly describe both kinds of interactions. Being in accordance to the characteristics of Q language, the Q-based framework makes the interaction process open and easily understood by the users. Additionally, it makes specific applications of multi-agent systems easy to be established by application designers. By applying agent negotiation in agent-mediated e-commerce and agent cooperation in interoperable information query on the Semantic Web, we illustrate how the presented framework for multi-agent coordination is implemented in concrete applications. At the same time, these two different applications also demonstrate usability of the presented framework and verify validity of Q language.
文摘Speciation research during the last several decades has confirmed that natural selection frequently drives the genera- tion of new species. But how does this process generally unfold in nature？ We argue that answering this question requires a clearer conceptual framework for understanding selection＇s role in speciation. We present a unified framework of speciation, pro- viding mechanistic descriptions of fundamentally distinct routes to speciation, and how these may interact during lineage splitting Two major categories are recognized： reproductive isolation resulting from （1） responses to selection, ＂speciation by selection,＂ or （2） non-selective processes, ＂speciation without selection.＂ Speciation by selection can occur via three mechanisms： （1） similar selection, （2） divergent selection, and （3） reinforcement selection. Understanding ecology＇s role in speciation requires uncovering how these three mechanisms contribute to reproductive isolation, and their relative importance compared to non-selective proce- sses, because all three mechanisms can occur side-by-side during speciation. To accomplish this, we highlight examination of groups of organisms inhabiting replicated environmental gradients. This scenario is common in nature, and a large literature illus- trates that both parallel and non-parallel responses to similar environments are widespread, and each can result in speciation. This recognition reveals four general pathways of speciation by similar or divergent selection--parallel and nonparallel responses to similar and divergent selection. Altogether, we present a more precise framework for speciation research, draw attention to some under-recognized features of speciation, emphasize the multidimensionality of speciation, reveal limitations of some previous tests and descriptions of speciation mechanisms, and point to a number of directions for future investigation [Current Zoology 59 （1）： 31-52, 2013].
