Sleep monitoring is an important part of health management because sleep quality is crucial for restoration of human health.However,current commercial products of polysomnography are cumbersome with connecting wires a...Sleep monitoring is an important part of health management because sleep quality is crucial for restoration of human health.However,current commercial products of polysomnography are cumbersome with connecting wires and state-of-the-art flexible sensors are still interferential for being attached to the body.Herein,we develop a flexible-integrated multimodal sensing patch based on hydrogel and its application in unconstraint sleep monitoring.The patch comprises a bottom hydrogel-based dualmode pressure–temperature sensing layer and a top electrospun nanofiber-based non-contact detection layer as one integrated device.The hydrogel as core substrate exhibits strong toughness and water retention,and the multimodal sensing of temperature,pressure,and non-contact proximity is realized based on different sensing mechanisms with no crosstalk interference.The multimodal sensing function is verified in a simulated real-world scenario by a robotic hand grasping objects to validate its practicability.Multiple multimodal sensing patches integrated on different locations of a pillow are assembled for intelligent sleep monitoring.Versatile human–pillow interaction information as well as their evolution over time are acquired and analyzed by a one-dimensional convolutional neural network.Track of head movement and recognition of bad patterns that may lead to poor sleep are achieved,which provides a promising approach for sleep monitoring.展开更多
Benefiting from the widespread potential applications in the era of the Internet of Thing and metaverse,triboelectric and piezoelectric nanogenerators(TENG&PENG)have attracted considerably increasing attention.The...Benefiting from the widespread potential applications in the era of the Internet of Thing and metaverse,triboelectric and piezoelectric nanogenerators(TENG&PENG)have attracted considerably increasing attention.Their outstanding characteristics,such as self-powered ability,high output performance,integration compatibility,cost-effectiveness,simple configurations,and versatile operation modes,could effectively expand the lifetime of vastly distributed wearable,implantable,and environmental devices,eventually achieving self-sustainable,maintenance-free,and reliable systems.However,current triboelectric/piezoelectric based active(i.e.self-powered)sensors still encounter serious bottlenecks in continuous monitoring and multimodal applications due to their intrinsic limitations of monomodal kinetic response and discontinuous transient output.This work systematically summarizes and evaluates the recent research endeavors to address the above challenges,with detailed discussions on the challenge origins,designing strategies,device performance,and corresponding diverse applications.Finally,conclusions and outlook regarding the research gap in self-powered continuous multimodal monitoring systems are provided,proposing the necessity of future research development in this field.展开更多
Human skin perceives external environmental stimulus by the synergies between the subcutaneous tactile corpuscles.Soft electronics with multiple sensing capabilities by mimicking the function of human skin are of sign...Human skin perceives external environmental stimulus by the synergies between the subcutaneous tactile corpuscles.Soft electronics with multiple sensing capabilities by mimicking the function of human skin are of significance in health monitoring and artificial sensation.The last decade has witnessed unprecedented development and convergence between multimodal tactile sensing devices and soft bioelectronics.Despite these advances,traditional flexible electronics achieve multimodal tactile sensing for pressure,strain,temperature,and humidity by integrating monomodal sensing devices together.This strategy results in high energy consumption,limited integration,and complex manufacturing process.Various multimodal sensors and crosstalk-free sensing mechanisms have been proposed to bridge the gap between natural sensory system and artificial perceptual system.In this review,we provide a comprehensive summary of tactile sensing mechanism,integration design principles,signal-decoupling strategies,and current applications for multimodal tactile perception.Finally,we highlight the current challenges and present the future perspectives to promote the development of multimodal tactile perception.展开更多
Muscles,the fundamental components supporting all human movement,exhibit various signals upon contraction,including mechanical signals indicat-ing tremors or mechanical deformation and electrical signals responsive to...Muscles,the fundamental components supporting all human movement,exhibit various signals upon contraction,including mechanical signals indicat-ing tremors or mechanical deformation and electrical signals responsive to muscle fiber activation.For noninvasive wearable devices,these signals can be measured using surface electromyography(sEMG)and force myography(FMG)techniques,respectively.However,relying on a single source of infor-mation is insufficient for a comprehensive evaluation of muscle condition.In order to accurately and effectively evaluate the various states of muscles,it is necessary to integrate sEMG and FMG in a spatiotemporally synchronized manner.This study presents a flexible sensor for multimodal muscle state monitoring,integrating serpentine-structured sEMG electrodes with fingerprint-like FMG sensors into a patch approximately 250μm thick.This design achieves a multimodal assessment of muscle conditions while maintaining a compact form factor.A thermo-responsive adhesive hydrogel is incorporated to enhance skin adhesion,improving the signal-to-noise ratio of the sEMG signals(33.07 dB)and ensuring the stability of the FMG sensor dur-ing mechanical deformation and tremors.The patterned coupled sensing patch demonstrates its utility in tracking muscular strength,assessing fatigue levels,and discerning features of muscle dysfunction by analyzing the time-domain and frequency-domain characteristics of the mechanical–electrical coupled signals,highlighting its potential application in sports training and rehabilita-tion monitoring.展开更多
Flexible sensors have been widely investigated due to their broad application prospects in various flexible electronics.However,most of the presently studied flexible sensors are only suitable for working at room temp...Flexible sensors have been widely investigated due to their broad application prospects in various flexible electronics.However,most of the presently studied flexible sensors are only suitable for working at room temperature,and their applications at high or low temperatures are still a big challenge.In this work,we present a multimodal flexible sensor based on functional oxide La0.7Sr0.3MnO3(LSMO)thin film deposited on mica substrate.As a strain sensor,it shows excellent sensitivity to mechanical bending and high bending durability(up to 3600 cycles).Moreover,the LSMO/Mica sensor also shows a sensitive response to the magnetic field,implying its multimodal sensing ability.Most importantly,it can work in a wide temperature range from extreme low temperature down to 20K to high temperature up to 773 K.The flexible sensor based on the flexible LSMO/mica hetero-structure shows great potential applications for flexible electronics using at extreme temperature environment in the future.展开更多
Research on the flexible hybrid epidermal electronic system(FHEES)has attracted considerable attention due to its potential applications in human-machine interaction and healthcare.Through material and structural inno...Research on the flexible hybrid epidermal electronic system(FHEES)has attracted considerable attention due to its potential applications in human-machine interaction and healthcare.Through material and structural innovations,FHEES combines the advantages of traditional stiff electronic devices and flexible electronic technology,enabling it to be worn conformally on the skin while retaining complex system functionality.FHEESs use multimodal sensing to enhance the identification accuracy of the wearer's motion modes,intentions,or health status,thus realizing more comprehensive physiological signal acquisition.However,the heterogeneous integration of soft and stiff components makes balancing comfort and performance in designing and implementing multimodal FHEESs challenging.Herein,multimodal FHEESs are first introduced in 2 types based on their different system structure:all-in-one and assembled,reflecting totally different heterogeneous integration strategies.Characteristics and the key design issues(such as interconnect design,interface strategy,substrate selection,etc.)of the 2 multimodal FHEESs are emphasized.Besides,the applications and advantages of the 2 multimodal FHEESs in recent research have been presented,with a focus on the control and medical fields.Finally,the prospects and challenges of the multimodal FHEES are discussed.展开更多
The detection of multiple trace analytes using single sensors is often impeded by the limited sensitivity of material and the interference form overlapping signals in complex mixtures.Here,we introduce an efficient an...The detection of multiple trace analytes using single sensors is often impeded by the limited sensitivity of material and the interference form overlapping signals in complex mixtures.Here,we introduce an efficient and durable heterostructured high-entropy alloy(HEA)material,where non-noble HEA nanoparticles are used to disperse and stabilize Pt clusters(denoted as HEA@Pt).The HEA@Pt exhibits high sensitivity to three trace analytes(dopamine,uric acid,and paracetamol)during the electrochemical detection process,leveraging its multifunctional catalytic sensing capabilities for diverse mixtures.Additionally,to address the challenge of signal overlap,we integrate a recurrent neural network into multimodal sensing,combined with machine learning(ML)algorithms to accurately identify multiple analytes in mixtures.After five-fold cross-validation,the prediction accuracy deviations for dopamine,uric acid,and paracetamol were 3.20,9.18 and 3.84,respectively,with goodness-of-fit values of 0.984,0.992 and 0.990.The model achieved a prediction accuracy of 96.67%for unknown mixture samples,demonstrating robust generalization performance.This approach of multifunctional HEA combined with ML algorithms effectively overcomes detection errors caused by the complex detection of multiple chemical substances and the overlap of multiple response signals,thereby enabling accurate and reliable identification of multi-target analytes.展开更多
Seismic hazards pose a major threat to life safety,social development,and the economy.Traditional seismic vulnerability and risk assessments,such as field survey methods,may not be suitable for densely built-up urban ...Seismic hazards pose a major threat to life safety,social development,and the economy.Traditional seismic vulnerability and risk assessments,such as field survey methods,may not be suitable for densely built-up urban areas due to the limited availability of comprehensive data and potential subjectivity in judgment.To overcome these limitations,an integrated method for seismic vulnerability and risk assessment based on multimodal remote sensing data,support vector machine(SVM)and GIScience methods was proposed and applied to the central urban area of Jinan City,Shandong Province,China.First,an area with representative buildings was selected for field survey research,and an attribute information base established.Then,the SVM method was used to establish the susceptibility proxies,which were applied to the whole study area after accuracy evaluation.Finally,the spatial distribution of seismic vulnerability and risk under different seismic intensity scenarios(from VI to X)was analyzed in GIScience.The results show that the average building vulnerability index in the central urban area of Jinan City is 0.53,indicating that the overall seismic performance of buildings is at a moderate level.Under the seismic intensity scenario of VIII,the buildings in the Starting area and New urban district of Jinan would mostly suffer‘Moderate’damage,while Old urban areas,with more seismic-resistant buildings,would experience only‘Slight’damage.This study aims to offer an efficient and accurate method for assessing seismic vulnerability in mid to large-sized cities characterized by concentrated population densities and rapid urbanization,as well as provide a valuable reference for efforts in urban renewal,seismic mitigation,and land planning,particularly in cities and regions of developing countries.Additionally,it contributes to the realization of Sustainable Development Goal 11,which seeks to make cities and human settlements inclusive,safe,resilient,and sustainable.展开更多
Optical microcavities have the ability to confne photons in small mode volumes for long periods of time,greatly enhancing light-matter interactions,and have become one of the research hotspots in international academi...Optical microcavities have the ability to confne photons in small mode volumes for long periods of time,greatly enhancing light-matter interactions,and have become one of the research hotspots in international academia.In recent years,sensing applications in complex environments have inspired the development of multimode optical microcavity sensors.These multimode sensors can be used not only for multi-parameter detection but also to improve measurement precision.In this review,we introduce multimode sensing methods based on optical microcavities and present an overview of the multimode single/multi-parameter optical microcavities sensors.Expected further research activities are also put forward.展开更多
The fine classification of large-scale scenes is becoming more and more important in optical remote sensing applications.As two kinds of typical optical remote sensing data,multispectral images(MSIs)and hyperspectral ...The fine classification of large-scale scenes is becoming more and more important in optical remote sensing applications.As two kinds of typical optical remote sensing data,multispectral images(MSIs)and hyperspectral images(HSIs)have complementary characteristics.The MSI has a large swath and short revisit period,but the number of bands is limited with low spectral resolution,leading to weak separability of between class spectra.Compared with MSI,HSI has hundreds of bands and each of them is narrow in bandwidth,which enable it to have the ability of fine classification,but too long in aspects of revisit period.To make efficient use of their combined advantages,multispectral-hyperspectral remote sensing image collaborative classification has become one of hot topics in remote sensing.To deal with the collaborative classification,most of current methods are unsupervised and only consider the HSI reconstruction as the objective.In this paper,a class-guided coupled dictionary learning method is proposed,which is obviously distinguished from the current methods.Specifically,the proposed method utilizes the labels of training samples to construct discriminative sparse representation coefficient error and classification error as regularization terms,so as to enforce the learned coupled dictionaries to be both representational and discriminative.The learned coupled dictionaries facilitate pixels from the same category have similar sparse represent coefficients,while pixels from different categories have different sparse represent coefficients.The experiments on three pairs of HSI and MSI have shown better classification performance.展开更多
基金supported by the National Key Research and Development Program of China under Grant(2024YFE0100400)Taishan Scholars Project Special Funds(tsqn202312035)+2 种基金the open research foundation of State Key Laboratory of Integrated Chips and Systems,the Tianjin Science and Technology Plan Project(No.22JCZDJC00630)the Higher Education Institution Science and Technology Research Project of Hebei Province(No.JZX2024024)Jinan City-University Integrated Development Strategy Project under Grant(JNSX2023017).
文摘Sleep monitoring is an important part of health management because sleep quality is crucial for restoration of human health.However,current commercial products of polysomnography are cumbersome with connecting wires and state-of-the-art flexible sensors are still interferential for being attached to the body.Herein,we develop a flexible-integrated multimodal sensing patch based on hydrogel and its application in unconstraint sleep monitoring.The patch comprises a bottom hydrogel-based dualmode pressure–temperature sensing layer and a top electrospun nanofiber-based non-contact detection layer as one integrated device.The hydrogel as core substrate exhibits strong toughness and water retention,and the multimodal sensing of temperature,pressure,and non-contact proximity is realized based on different sensing mechanisms with no crosstalk interference.The multimodal sensing function is verified in a simulated real-world scenario by a robotic hand grasping objects to validate its practicability.Multiple multimodal sensing patches integrated on different locations of a pillow are assembled for intelligent sleep monitoring.Versatile human–pillow interaction information as well as their evolution over time are acquired and analyzed by a one-dimensional convolutional neural network.Track of head movement and recognition of bad patterns that may lead to poor sleep are achieved,which provides a promising approach for sleep monitoring.
基金supported by the National Key R&D Program of China(Grant Nos.2022YFB3603403,2021YFB3600502)the National Natural Science Foundation of China(Grant Nos.62075040,62301150)+3 种基金the Southeast University Interdisciplinary Research Program for Young Scholars(2024FGC1007)the Start-up Research Fund of Southeast University(RF1028623164)the Nanjing Science and Technology Innovation Project for Returned Overseas Talent(4206002302)the Fundamental Research Funds for the Central Universities(2242024K40015).
文摘Benefiting from the widespread potential applications in the era of the Internet of Thing and metaverse,triboelectric and piezoelectric nanogenerators(TENG&PENG)have attracted considerably increasing attention.Their outstanding characteristics,such as self-powered ability,high output performance,integration compatibility,cost-effectiveness,simple configurations,and versatile operation modes,could effectively expand the lifetime of vastly distributed wearable,implantable,and environmental devices,eventually achieving self-sustainable,maintenance-free,and reliable systems.However,current triboelectric/piezoelectric based active(i.e.self-powered)sensors still encounter serious bottlenecks in continuous monitoring and multimodal applications due to their intrinsic limitations of monomodal kinetic response and discontinuous transient output.This work systematically summarizes and evaluates the recent research endeavors to address the above challenges,with detailed discussions on the challenge origins,designing strategies,device performance,and corresponding diverse applications.Finally,conclusions and outlook regarding the research gap in self-powered continuous multimodal monitoring systems are provided,proposing the necessity of future research development in this field.
基金the Taishan Young Scholar Program of Shandong Province(No.tsqnz20231235)National Natural Science Foundation of China(Grant Nos.22104021,52303075,22227804)+1 种基金Natural Science Foundation of Shandong Province(ZR2023QB227)Department of Science and Technology of Guangdong Province(2022A1515110014).
文摘Human skin perceives external environmental stimulus by the synergies between the subcutaneous tactile corpuscles.Soft electronics with multiple sensing capabilities by mimicking the function of human skin are of significance in health monitoring and artificial sensation.The last decade has witnessed unprecedented development and convergence between multimodal tactile sensing devices and soft bioelectronics.Despite these advances,traditional flexible electronics achieve multimodal tactile sensing for pressure,strain,temperature,and humidity by integrating monomodal sensing devices together.This strategy results in high energy consumption,limited integration,and complex manufacturing process.Various multimodal sensors and crosstalk-free sensing mechanisms have been proposed to bridge the gap between natural sensory system and artificial perceptual system.In this review,we provide a comprehensive summary of tactile sensing mechanism,integration design principles,signal-decoupling strategies,and current applications for multimodal tactile perception.Finally,we highlight the current challenges and present the future perspectives to promote the development of multimodal tactile perception.
基金National Key Research and Development Program of China,Grant/Award Number:2022YFE0111700National Natural Science Foundation of China,Grant/Award Numbers:T2125003,82202075+3 种基金Beijing Natural Science Foundation,Grant/Award Number:L212010National Postdoctoral Program for Innovative Talents,Grant/Award Number:BX20220380China Postdoctoral Science Foundation,Grant/Award Number:2022M710389Fundamental Research Funds for the Central Universities。
文摘Muscles,the fundamental components supporting all human movement,exhibit various signals upon contraction,including mechanical signals indicat-ing tremors or mechanical deformation and electrical signals responsive to muscle fiber activation.For noninvasive wearable devices,these signals can be measured using surface electromyography(sEMG)and force myography(FMG)techniques,respectively.However,relying on a single source of infor-mation is insufficient for a comprehensive evaluation of muscle condition.In order to accurately and effectively evaluate the various states of muscles,it is necessary to integrate sEMG and FMG in a spatiotemporally synchronized manner.This study presents a flexible sensor for multimodal muscle state monitoring,integrating serpentine-structured sEMG electrodes with fingerprint-like FMG sensors into a patch approximately 250μm thick.This design achieves a multimodal assessment of muscle conditions while maintaining a compact form factor.A thermo-responsive adhesive hydrogel is incorporated to enhance skin adhesion,improving the signal-to-noise ratio of the sEMG signals(33.07 dB)and ensuring the stability of the FMG sensor dur-ing mechanical deformation and tremors.The patterned coupled sensing patch demonstrates its utility in tracking muscular strength,assessing fatigue levels,and discerning features of muscle dysfunction by analyzing the time-domain and frequency-domain characteristics of the mechanical–electrical coupled signals,highlighting its potential application in sports training and rehabilita-tion monitoring.
基金This work was supported financially by the National Natural Science Foundation of China(No.51872099)the Project for Guangdong Province Universities and Colleges Pearl River Scholar Funded Scheme(2016),the Guangdong Innovative Research Team Program(No.2013C102)+1 种基金the Guangdong Provincial Key Laboratory of Optical Information Materials and Technology(No.2017B030301007)Science and Technology Program of Guangzhou(No.2019050001).
文摘Flexible sensors have been widely investigated due to their broad application prospects in various flexible electronics.However,most of the presently studied flexible sensors are only suitable for working at room temperature,and their applications at high or low temperatures are still a big challenge.In this work,we present a multimodal flexible sensor based on functional oxide La0.7Sr0.3MnO3(LSMO)thin film deposited on mica substrate.As a strain sensor,it shows excellent sensitivity to mechanical bending and high bending durability(up to 3600 cycles).Moreover,the LSMO/Mica sensor also shows a sensitive response to the magnetic field,implying its multimodal sensing ability.Most importantly,it can work in a wide temperature range from extreme low temperature down to 20K to high temperature up to 773 K.The flexible sensor based on the flexible LSMO/mica hetero-structure shows great potential applications for flexible electronics using at extreme temperature environment in the future.
基金supported by the National Key Research and Development Program of China(grant numbers 2022YFB3204100 and 2021YFC3002200)the National Natural Science Foundation of China(grant numbers U20A20168,51861145202,and 62274101).
文摘Research on the flexible hybrid epidermal electronic system(FHEES)has attracted considerable attention due to its potential applications in human-machine interaction and healthcare.Through material and structural innovations,FHEES combines the advantages of traditional stiff electronic devices and flexible electronic technology,enabling it to be worn conformally on the skin while retaining complex system functionality.FHEESs use multimodal sensing to enhance the identification accuracy of the wearer's motion modes,intentions,or health status,thus realizing more comprehensive physiological signal acquisition.However,the heterogeneous integration of soft and stiff components makes balancing comfort and performance in designing and implementing multimodal FHEESs challenging.Herein,multimodal FHEESs are first introduced in 2 types based on their different system structure:all-in-one and assembled,reflecting totally different heterogeneous integration strategies.Characteristics and the key design issues(such as interconnect design,interface strategy,substrate selection,etc.)of the 2 multimodal FHEESs are emphasized.Besides,the applications and advantages of the 2 multimodal FHEESs in recent research have been presented,with a focus on the control and medical fields.Finally,the prospects and challenges of the multimodal FHEES are discussed.
基金supported by the National Natural Science Foundation of China(Nos.52422505,12274124,and 52401280)the National Key R&D Program of China(No.2021YFA1202300)+1 种基金the Shanghai Pilot Program for Basic Research(No.22TQ1400100-6)the Fundamental Research Funds for the Central Universities,and the Innovative Research Group Project of the National Natural Science Foundation of China(No.52321002).
文摘The detection of multiple trace analytes using single sensors is often impeded by the limited sensitivity of material and the interference form overlapping signals in complex mixtures.Here,we introduce an efficient and durable heterostructured high-entropy alloy(HEA)material,where non-noble HEA nanoparticles are used to disperse and stabilize Pt clusters(denoted as HEA@Pt).The HEA@Pt exhibits high sensitivity to three trace analytes(dopamine,uric acid,and paracetamol)during the electrochemical detection process,leveraging its multifunctional catalytic sensing capabilities for diverse mixtures.Additionally,to address the challenge of signal overlap,we integrate a recurrent neural network into multimodal sensing,combined with machine learning(ML)algorithms to accurately identify multiple analytes in mixtures.After five-fold cross-validation,the prediction accuracy deviations for dopamine,uric acid,and paracetamol were 3.20,9.18 and 3.84,respectively,with goodness-of-fit values of 0.984,0.992 and 0.990.The model achieved a prediction accuracy of 96.67%for unknown mixture samples,demonstrating robust generalization performance.This approach of multifunctional HEA combined with ML algorithms effectively overcomes detection errors caused by the complex detection of multiple chemical substances and the overlap of multiple response signals,thereby enabling accurate and reliable identification of multi-target analytes.
基金supported in part by the National Natural Science Foundation of China(Grant No.42201077)the Natural Science Foundation of Shandong Province(No.ZR2021QD074)+2 种基金the China Postdoctoral Science Foundation(No.2023M732105)the Lhasa National Geophysical Observation and Research Station(No.NORSLS22-05)the Youth Innovation Team Project of Higher School in Shandong Province,China(No.2024KJH087).
文摘Seismic hazards pose a major threat to life safety,social development,and the economy.Traditional seismic vulnerability and risk assessments,such as field survey methods,may not be suitable for densely built-up urban areas due to the limited availability of comprehensive data and potential subjectivity in judgment.To overcome these limitations,an integrated method for seismic vulnerability and risk assessment based on multimodal remote sensing data,support vector machine(SVM)and GIScience methods was proposed and applied to the central urban area of Jinan City,Shandong Province,China.First,an area with representative buildings was selected for field survey research,and an attribute information base established.Then,the SVM method was used to establish the susceptibility proxies,which were applied to the whole study area after accuracy evaluation.Finally,the spatial distribution of seismic vulnerability and risk under different seismic intensity scenarios(from VI to X)was analyzed in GIScience.The results show that the average building vulnerability index in the central urban area of Jinan City is 0.53,indicating that the overall seismic performance of buildings is at a moderate level.Under the seismic intensity scenario of VIII,the buildings in the Starting area and New urban district of Jinan would mostly suffer‘Moderate’damage,while Old urban areas,with more seismic-resistant buildings,would experience only‘Slight’damage.This study aims to offer an efficient and accurate method for assessing seismic vulnerability in mid to large-sized cities characterized by concentrated population densities and rapid urbanization,as well as provide a valuable reference for efforts in urban renewal,seismic mitigation,and land planning,particularly in cities and regions of developing countries.Additionally,it contributes to the realization of Sustainable Development Goal 11,which seeks to make cities and human settlements inclusive,safe,resilient,and sustainable.
基金the National Natural Science Foundation of China(Grant Nos.11974058,61307050,and 61701271)the Beijing Nova Program(No.Z201100006820125)+2 种基金Beijing Municipal Science and Technology Commission,in part by the Beijing Natural Science Foundation(No.Z210004)the Shandong Natural Science Foundation(No.ZR2016AM27)the State Key Laboratory of Information Photonics and Optical Communications(No.IPOC2021ZT01),BUPT,China.
文摘Optical microcavities have the ability to confne photons in small mode volumes for long periods of time,greatly enhancing light-matter interactions,and have become one of the research hotspots in international academia.In recent years,sensing applications in complex environments have inspired the development of multimode optical microcavity sensors.These multimode sensors can be used not only for multi-parameter detection but also to improve measurement precision.In this review,we introduce multimode sensing methods based on optical microcavities and present an overview of the multimode single/multi-parameter optical microcavities sensors.Expected further research activities are also put forward.
基金supported by the National Natural Youth Science Foundation Project (Grant No. 62001142)the Key International Cooperation Project (Grant No. 61720106002)+1 种基金the Distinguished Young Scholars of National Natural Science Foundation of China (Grant No. 62025107)Heilongjiang Postdoctoral Fund (Grant No. LBH-Z20068)
文摘The fine classification of large-scale scenes is becoming more and more important in optical remote sensing applications.As two kinds of typical optical remote sensing data,multispectral images(MSIs)and hyperspectral images(HSIs)have complementary characteristics.The MSI has a large swath and short revisit period,but the number of bands is limited with low spectral resolution,leading to weak separability of between class spectra.Compared with MSI,HSI has hundreds of bands and each of them is narrow in bandwidth,which enable it to have the ability of fine classification,but too long in aspects of revisit period.To make efficient use of their combined advantages,multispectral-hyperspectral remote sensing image collaborative classification has become one of hot topics in remote sensing.To deal with the collaborative classification,most of current methods are unsupervised and only consider the HSI reconstruction as the objective.In this paper,a class-guided coupled dictionary learning method is proposed,which is obviously distinguished from the current methods.Specifically,the proposed method utilizes the labels of training samples to construct discriminative sparse representation coefficient error and classification error as regularization terms,so as to enforce the learned coupled dictionaries to be both representational and discriminative.The learned coupled dictionaries facilitate pixels from the same category have similar sparse represent coefficients,while pixels from different categories have different sparse represent coefficients.The experiments on three pairs of HSI and MSI have shown better classification performance.
