Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale regi...Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale region of interest(ROI).However,some noise signals that are not easily separated in a single-scale space can be easily separated in a multi-scale space.Also,existing spatiotemporal networks mainly focus on local spatiotemporal information and do not emphasize temporal information,which is crucial in pulse extraction problems,resulting in insufficient spatiotemporal feature modelling.Methods Here,we propose a multi-scale facial video pulse extraction network based on separable spatiotemporal convolution(SSTC)and dimension separable attention(DSAT).First,to solve the problem of a single-scale ROI,we constructed a multi-scale feature space for initial signal separation.Second,SSTC and DSAT were designed for efficient spatiotemporal correlation modeling,which increased the information interaction between the long-span time and space dimensions;this placed more emphasis on temporal features.Results The signal-to-noise ratio(SNR)of the proposed network reached 9.58dB on the PURE dataset and 6.77dB on the UBFC-rPPG dataset,outperforming state-of-the-art algorithms.Conclusions The results showed that fusing multi-scale signals yielded better results than methods based on only single-scale signals.The proposed SSTC and dimension-separable attention mechanism will contribute to more accurate pulse signal extraction.展开更多
An information-theoretic measure is introduced for evaluating the dynamical coupling of spatiotemporally chaotic signals produced by extended systems. The measure of the one-way coupled map lattices and the one-dimens...An information-theoretic measure is introduced for evaluating the dynamical coupling of spatiotemporally chaotic signals produced by extended systems. The measure of the one-way coupled map lattices and the one-dimensional, homogeneous, diffusively coupled map lattices is computed with the symbolic analysis method. The numerical results show that the information measure is applicable to determining the dynamical coupling between two directly coupled or indirectly coupled chaotic signals.展开更多
Backgrounds This work emphasizes the current research status of the urban Digital Twins to establish an intelligent spatiotemporal framework.A Geospatial Artificial Intelligent(GeoAI)system is developed based on the G...Backgrounds This work emphasizes the current research status of the urban Digital Twins to establish an intelligent spatiotemporal framework.A Geospatial Artificial Intelligent(GeoAI)system is developed based on the Geographic Information System and Artificial Intelligence.It integrates multi-video technology and Virtual City in urban Digital Twins.Methods Besides,an improved small object detection model is proposed:YOLOv5-Pyramid,and Siamese network video tracking models,namely MPSiam and FSSiamese,are established.Finally,an experimental platform is built to verify the georeferencing correction scheme of video images.Result The MultiplyAccumulate value of MPSiam is 0.5B,and that of ResNet50-Siam is 4.5B.Besides,the model is compressed by 4.8times.The inference speed has increased by 3.3 times,reaching 83 Frames Per Second.3%of the Average Expectation Overlap is lost.Therefore,the urban Digital Twins-oriented GeoAI framework established here has excellent performance for video georeferencing and target detection problems.展开更多
Segmentation of semantic Video Object Planes (VOP's) from video sequence is a key to the standard MPEG-4 with content-based video coding. In this paper, the approach of automatic Segmentation of VOP's Based on...Segmentation of semantic Video Object Planes (VOP's) from video sequence is a key to the standard MPEG-4 with content-based video coding. In this paper, the approach of automatic Segmentation of VOP's Based on Spatio-Temporal Information (SBSTI) is proposed.The proceeding results demonstrate the good performance of the algorithm.展开更多
Cyanobacterial harmful algal blooms(CyanoHABs)in inland waters are now among the most pressing environmental issues worldwide,especially in China.Satellite remote sensing has limitations in monitoring CyanoHABs in sma...Cyanobacterial harmful algal blooms(CyanoHABs)in inland waters are now among the most pressing environmental issues worldwide,especially in China.Satellite remote sensing has limitations in monitoring CyanoHABs in small water bodies due to spatial and temporal resolution limitations.While literature and news media have the potential to supplement satellite remote sensing in monitoring CyanoHABs,they have currently not received sufficient attention.In this study,we combined information on the distributions of CyanoHABs from literature and media for the first time to comprehensively assess the spatiotemporal variation in CyanoHABs in China.We collected,cleaned,validated,and organized data from literature and media on CyanoHABs in China,resulting in the establishment of a comprehensive database on CyanoHABs in China's inland waters(ChinaCyanoDB)covering 198 water bodies,525 records for 1950-2021.The majority of water bodies with CyanoHABs(CyanoWaters)are located in the eastern China,mainly concentrated in the middle and lower Yangtze region,with a clear upward trend in their number over the last four decades.The ChinaCyanoDB and analytical results can provide valuable data support for monitoring and managing CyanoHABs in China while the database construction method may also be applied to other countries and regions.展开更多
Trajectory data mining is widely used in military and civil applications,such as early warning and surveillance system,intelligent traffic system and so on.Through trajectory similarity measurement and clustering,targ...Trajectory data mining is widely used in military and civil applications,such as early warning and surveillance system,intelligent traffic system and so on.Through trajectory similarity measurement and clustering,target behavior patterns can be found from massive spatiotemporal trajectory data.In order to mine frequent behaviors of targets from complex historical trajectory data,a behavior pattern mining algorithm based on spatiotemporal trajectory multidimensional information fusion is proposed in this paper.Firstly,spatial–temporal Hausdorff distance is pro-posed to measure multidimensional information differences of spatiotemporal trajectories,which can distinguish the behaviors with similar location but different course and velocity.On this basis,by combining the idea of k-nearest neighbor and density peak clustering,a new trajectory clustering algorithm is proposed to mine behavior patterns from trajectory data with uneven density distribu-tion.Finally,we implement the proposed algorithm in simulated and radar measured trajectory data respectively.The experimental results show that the proposed algorithm can mine target behavior patterns from different complex application scenarios more quickly and accurately com-pared to the existing methods,which has a good application prospect in intelligent monitoring tasks.展开更多
A significant step toward constructing high‐efficiency neuromorphic systems is the electronic emulation of advanced synaptic functions of the human brain.While previous studies have focused on mimicking the basic fun...A significant step toward constructing high‐efficiency neuromorphic systems is the electronic emulation of advanced synaptic functions of the human brain.While previous studies have focused on mimicking the basic functions of synapses using single‐gate transistors,multigate transistors offer an opportunity to simulate more complex and advanced memory‐forming behaviors in biological synapses.In this study,a simple and general method is used to assemble rubber semiconductors into suspended two‐phase composite films that are transferred to the surface of the ion‐conducting membrane to fabricate flexible multiterminal photoelectronic neurotransistors.The suspended ion conductive film is used as the gate dielectrics and supporting substrate.The prepared devices exhibit excellent electrical stability and mechanical flexibility after being bent.Basic photoelectronic synaptic behavior and pulse‐dependent plasticity are emulated.Furthermore,the device realizes the spatiotemporally integrated electrical and optical stimuli to mimic spatiotemporal information processing.This study provides a promising direction for constructing more complex spiking neural networks and more powerful neuromorphic systems with brain‐like dynamic spatiotemporal processing functions.展开更多
基金Supported by the National Natural Science Foundation of China(61903336,61976190)the Natural Science Foundation of Zhejiang Province(LY21F030015)。
文摘Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale region of interest(ROI).However,some noise signals that are not easily separated in a single-scale space can be easily separated in a multi-scale space.Also,existing spatiotemporal networks mainly focus on local spatiotemporal information and do not emphasize temporal information,which is crucial in pulse extraction problems,resulting in insufficient spatiotemporal feature modelling.Methods Here,we propose a multi-scale facial video pulse extraction network based on separable spatiotemporal convolution(SSTC)and dimension separable attention(DSAT).First,to solve the problem of a single-scale ROI,we constructed a multi-scale feature space for initial signal separation.Second,SSTC and DSAT were designed for efficient spatiotemporal correlation modeling,which increased the information interaction between the long-span time and space dimensions;this placed more emphasis on temporal features.Results The signal-to-noise ratio(SNR)of the proposed network reached 9.58dB on the PURE dataset and 6.77dB on the UBFC-rPPG dataset,outperforming state-of-the-art algorithms.Conclusions The results showed that fusing multi-scale signals yielded better results than methods based on only single-scale signals.The proposed SSTC and dimension-separable attention mechanism will contribute to more accurate pulse signal extraction.
基金Project supported by China Postdoctoral Science Foundation and the Postdoctoral Science Foundation of Central South University, China.
文摘An information-theoretic measure is introduced for evaluating the dynamical coupling of spatiotemporally chaotic signals produced by extended systems. The measure of the one-way coupled map lattices and the one-dimensional, homogeneous, diffusively coupled map lattices is computed with the symbolic analysis method. The numerical results show that the information measure is applicable to determining the dynamical coupling between two directly coupled or indirectly coupled chaotic signals.
基金Supported by Key R&D Program of the Ministry of Science and Technology (2019YFC0810704)Key R&D Program of Guangdong Province (2019B111102002)Shenzhen Science and Technology Program (KCXFZ202002011007040)。
文摘Backgrounds This work emphasizes the current research status of the urban Digital Twins to establish an intelligent spatiotemporal framework.A Geospatial Artificial Intelligent(GeoAI)system is developed based on the Geographic Information System and Artificial Intelligence.It integrates multi-video technology and Virtual City in urban Digital Twins.Methods Besides,an improved small object detection model is proposed:YOLOv5-Pyramid,and Siamese network video tracking models,namely MPSiam and FSSiamese,are established.Finally,an experimental platform is built to verify the georeferencing correction scheme of video images.Result The MultiplyAccumulate value of MPSiam is 0.5B,and that of ResNet50-Siam is 4.5B.Besides,the model is compressed by 4.8times.The inference speed has increased by 3.3 times,reaching 83 Frames Per Second.3%of the Average Expectation Overlap is lost.Therefore,the urban Digital Twins-oriented GeoAI framework established here has excellent performance for video georeferencing and target detection problems.
文摘Segmentation of semantic Video Object Planes (VOP's) from video sequence is a key to the standard MPEG-4 with content-based video coding. In this paper, the approach of automatic Segmentation of VOP's Based on Spatio-Temporal Information (SBSTI) is proposed.The proceeding results demonstrate the good performance of the algorithm.
基金supported by the International Research Centre of Big Data for Sustainable Development Goals(CBAS)[grant no CBASYX0906]the National Natural Science Foundation of China[grant no 42271363,41971318]the Dragon 5 Cooperation[grant no 59193]..
文摘Cyanobacterial harmful algal blooms(CyanoHABs)in inland waters are now among the most pressing environmental issues worldwide,especially in China.Satellite remote sensing has limitations in monitoring CyanoHABs in small water bodies due to spatial and temporal resolution limitations.While literature and news media have the potential to supplement satellite remote sensing in monitoring CyanoHABs,they have currently not received sufficient attention.In this study,we combined information on the distributions of CyanoHABs from literature and media for the first time to comprehensively assess the spatiotemporal variation in CyanoHABs in China.We collected,cleaned,validated,and organized data from literature and media on CyanoHABs in China,resulting in the establishment of a comprehensive database on CyanoHABs in China's inland waters(ChinaCyanoDB)covering 198 water bodies,525 records for 1950-2021.The majority of water bodies with CyanoHABs(CyanoWaters)are located in the eastern China,mainly concentrated in the middle and lower Yangtze region,with a clear upward trend in their number over the last four decades.The ChinaCyanoDB and analytical results can provide valuable data support for monitoring and managing CyanoHABs in China while the database construction method may also be applied to other countries and regions.
基金co-supported by the National Key R&D Program of China(No.2021YFA0715202)the National Natural Science Foundation of China(Nos.62022092,61790550,62171453)the Outstanding Youth Innovation Team Program of University in Shandong Province,China(No.2021KJ005).
文摘Trajectory data mining is widely used in military and civil applications,such as early warning and surveillance system,intelligent traffic system and so on.Through trajectory similarity measurement and clustering,target behavior patterns can be found from massive spatiotemporal trajectory data.In order to mine frequent behaviors of targets from complex historical trajectory data,a behavior pattern mining algorithm based on spatiotemporal trajectory multidimensional information fusion is proposed in this paper.Firstly,spatial–temporal Hausdorff distance is pro-posed to measure multidimensional information differences of spatiotemporal trajectories,which can distinguish the behaviors with similar location but different course and velocity.On this basis,by combining the idea of k-nearest neighbor and density peak clustering,a new trajectory clustering algorithm is proposed to mine behavior patterns from trajectory data with uneven density distribu-tion.Finally,we implement the proposed algorithm in simulated and radar measured trajectory data respectively.The experimental results show that the proposed algorithm can mine target behavior patterns from different complex application scenarios more quickly and accurately com-pared to the existing methods,which has a good application prospect in intelligent monitoring tasks.
基金supported by the National Natural Science Foundation of China(Nos.61975241 and 52173192)the Huxiang Youth Talent Program of Hunan Province(No.2020RC3010)+3 种基金the Science and Technology Innovation Program of Hunan Province(No.2020RC4004)the Special Funding for the Construction of Innovative Provinces in Hunan Province(No.2020GK2024)the National Key Research and Development Program of China(No.2017YFA0206600)Fundamental Research Funds for the Central Universities of Central South University(No.1053320213517).
文摘A significant step toward constructing high‐efficiency neuromorphic systems is the electronic emulation of advanced synaptic functions of the human brain.While previous studies have focused on mimicking the basic functions of synapses using single‐gate transistors,multigate transistors offer an opportunity to simulate more complex and advanced memory‐forming behaviors in biological synapses.In this study,a simple and general method is used to assemble rubber semiconductors into suspended two‐phase composite films that are transferred to the surface of the ion‐conducting membrane to fabricate flexible multiterminal photoelectronic neurotransistors.The suspended ion conductive film is used as the gate dielectrics and supporting substrate.The prepared devices exhibit excellent electrical stability and mechanical flexibility after being bent.Basic photoelectronic synaptic behavior and pulse‐dependent plasticity are emulated.Furthermore,the device realizes the spatiotemporally integrated electrical and optical stimuli to mimic spatiotemporal information processing.This study provides a promising direction for constructing more complex spiking neural networks and more powerful neuromorphic systems with brain‐like dynamic spatiotemporal processing functions.
基金The National Natural Science Foundation of China Youth Program(No.52108139)Hunan Provincial Natural Science Foundation Youth Program(No.2023JJ40290).