RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still...RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.展开更多
This paper proposes a hybrid approach for recognizing human activities from trajectories. First, an improved hidden Markov model （HMM） parameter learning algorithm, HMM-PSO, is proposed, which achieves a better bala...This paper proposes a hybrid approach for recognizing human activities from trajectories. First, an improved hidden Markov model （HMM） parameter learning algorithm, HMM-PSO, is proposed, which achieves a better balance between the global and local exploitation by the nonlinear update strategy and repulsion operation. Then, the event probability sequence （EPS） which consists of a series of events is computed to describe the unique characteristic of human activities. The anatysis on EPS indicates that it is robust to the changes in viewing direction and contributes to improving the recognition rate. Finally, the effectiveness of the proposed approach is evaluated by data experiments on current popular datasets.展开更多
A new method for complex activity recognition in videos by key frames was presented. The progressive bisection strategy(PBS) was employed to divide the complex activity into a series of simple activities and the key f...A new method for complex activity recognition in videos by key frames was presented. The progressive bisection strategy(PBS) was employed to divide the complex activity into a series of simple activities and the key frames representing the simple activities were extracted by the self-splitting competitive learning(SSCL) algorithm. A new similarity criterion of complex activities was defined. Besides the regular visual factor, the order factor and the interference factor measuring the timing matching relationship of the simple activities and the discontinuous matching relationship of the simple activities respectively were considered. On these bases, the complex human activity recognition could be achieved by calculating their similarities. The recognition error was reduced compared with other methods when ignoring the recognition of simple activities. The proposed method was tested and evaluated on the self-built broadcast gymnastic database and the dancing database. The experimental results prove the superior efficiency.展开更多
Earth Science from Space is an interdisciplinary discipline that studies the interactions,mechanisms,and evolution of the Earth system through space observation.In China,the national medium-to long-term civilian space...Earth Science from Space is an interdisciplinary discipline that studies the interactions,mechanisms,and evolution of the Earth system through space observation.In China,the national medium-to long-term civilian space infrastructure development plan and the space-science pilot project from the Chinese Academy of Sciences are two programs associated with advancing the Earth science from space.This paper reports recent scientific findings,developments and the status of the six missions.It is organized as the following sections:Introduction,two satellite missions that are already in orbit—the TanSat-1 for atmospheric COand the LuTan-1 for global surface deformation,a Terrestrial Ecosystem Carbon Inventory Satellite to be launched in 2022,and three missions that passed the PhaseⅡstudy and planned for near future—the Ocean Surface Current multiscale Observation,the Terrestrial Water Resources Satellite.Climate and Atmospheric Components Exploring Satellites(CACES),followed by the conclusion.展开更多
[Objective]Surface water flooding is caused by heavy rainfall,which has been the main type of flooding in many cities across the world.Real urban environments are highly complex,and there are numerous parameters influ...[Objective]Surface water flooding is caused by heavy rainfall,which has been the main type of flooding in many cities across the world.Real urban environments are highly complex,and there are numerous parameters influencing the rainfall-runoff processes,such as road width,orientation and building coverage.The main objective is to perform a parametric study concerning the rainfall-runoff processes in complex urban environments,in order to gain a better understanding of the impact of urban characteristics on the surface runoff.[Methods]Realistic urban layouts are generated by means of procedural modelling software,which parameterises the urban configurations using 11 independent variables,including the averaged street length,street orientation,street curvature,major street width,minor street width,park coverage,etc.A shock-capturing TVD MacCormack shallow water equations solver is used to undertake a large number of computational simulations regarding the rainfall-runoff processes over realistic urban layouts.The dominating urban parameters that influence the time of concentration is unveiled,which characterises the timescale of the flood formation.[Results]In order to generalise the research outcomes,the obtained hydrographs at the outlet of the catchment are normalised so that they are independent of the catchment area,slope or rainfall intensity.The dimensionless time of concentration is thus only the functions of 12 independent parameters,including 11 parameters that governing the urban layouts and the Manning roughness coefficient of the ground.A sensitivity analysis,based on the multiple linear regression method,is performed on the 2,994 simulation cases to quantify the influence of each parameter.[Conclusion]The results show that the ground roughness and the building coverage ratio are the two most important factors that influence the urban flood formation.Their influences on the dimensionless timescale of the urban catchments’response to rainfall are quantified by empirical formulae.The research findings can provide useful guidelines for the design of future flood-resilient urban environments and the improvement of existing drainage systems in cities.展开更多
基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDC02040300)for this study.
文摘RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.
基金supported by the National Natural Science Foundation of China(60573159)the Guangdong High Technique Project(201100000514)
文摘This paper proposes a hybrid approach for recognizing human activities from trajectories. First, an improved hidden Markov model （HMM） parameter learning algorithm, HMM-PSO, is proposed, which achieves a better balance between the global and local exploitation by the nonlinear update strategy and repulsion operation. Then, the event probability sequence （EPS） which consists of a series of events is computed to describe the unique characteristic of human activities. The anatysis on EPS indicates that it is robust to the changes in viewing direction and contributes to improving the recognition rate. Finally, the effectiveness of the proposed approach is evaluated by data experiments on current popular datasets.
基金Project(50808025) supported by the National Natural Science Foundation of ChinaProject(20090162110057) supported by the Doctoral Fund of Ministry of Education,China
文摘A new method for complex activity recognition in videos by key frames was presented. The progressive bisection strategy(PBS) was employed to divide the complex activity into a series of simple activities and the key frames representing the simple activities were extracted by the self-splitting competitive learning(SSCL) algorithm. A new similarity criterion of complex activities was defined. Besides the regular visual factor, the order factor and the interference factor measuring the timing matching relationship of the simple activities and the discontinuous matching relationship of the simple activities respectively were considered. On these bases, the complex human activity recognition could be achieved by calculating their similarities. The recognition error was reduced compared with other methods when ignoring the recognition of simple activities. The proposed method was tested and evaluated on the self-built broadcast gymnastic database and the dancing database. The experimental results prove the superior efficiency.
文摘Earth Science from Space is an interdisciplinary discipline that studies the interactions,mechanisms,and evolution of the Earth system through space observation.In China,the national medium-to long-term civilian space infrastructure development plan and the space-science pilot project from the Chinese Academy of Sciences are two programs associated with advancing the Earth science from space.This paper reports recent scientific findings,developments and the status of the six missions.It is organized as the following sections:Introduction,two satellite missions that are already in orbit—the TanSat-1 for atmospheric COand the LuTan-1 for global surface deformation,a Terrestrial Ecosystem Carbon Inventory Satellite to be launched in 2022,and three missions that passed the PhaseⅡstudy and planned for near future—the Ocean Surface Current multiscale Observation,the Terrestrial Water Resources Satellite.Climate and Atmospheric Components Exploring Satellites(CACES),followed by the conclusion.
文摘[Objective]Surface water flooding is caused by heavy rainfall,which has been the main type of flooding in many cities across the world.Real urban environments are highly complex,and there are numerous parameters influencing the rainfall-runoff processes,such as road width,orientation and building coverage.The main objective is to perform a parametric study concerning the rainfall-runoff processes in complex urban environments,in order to gain a better understanding of the impact of urban characteristics on the surface runoff.[Methods]Realistic urban layouts are generated by means of procedural modelling software,which parameterises the urban configurations using 11 independent variables,including the averaged street length,street orientation,street curvature,major street width,minor street width,park coverage,etc.A shock-capturing TVD MacCormack shallow water equations solver is used to undertake a large number of computational simulations regarding the rainfall-runoff processes over realistic urban layouts.The dominating urban parameters that influence the time of concentration is unveiled,which characterises the timescale of the flood formation.[Results]In order to generalise the research outcomes,the obtained hydrographs at the outlet of the catchment are normalised so that they are independent of the catchment area,slope or rainfall intensity.The dimensionless time of concentration is thus only the functions of 12 independent parameters,including 11 parameters that governing the urban layouts and the Manning roughness coefficient of the ground.A sensitivity analysis,based on the multiple linear regression method,is performed on the 2,994 simulation cases to quantify the influence of each parameter.[Conclusion]The results show that the ground roughness and the building coverage ratio are the two most important factors that influence the urban flood formation.Their influences on the dimensionless timescale of the urban catchments’response to rainfall are quantified by empirical formulae.The research findings can provide useful guidelines for the design of future flood-resilient urban environments and the improvement of existing drainage systems in cities.
