Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation pr...Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation profiling techniques,new developments in this field determined four molecular subtypes for SHH-MB.SHH-MB subtypes show distinct DNAmethylation patterns that allow their discrimination fromoverlapping subtypes and predict clinical outcomes.Class overlapping occurs when two or more classes share common features,making it difficult to distinguish them as separate.Using the DNA methylation dataset,a novel classification technique is presented to address the issue of overlapping SHH-MBsubtypes.Penalizedmultinomial regression(PMR),Tomek links(TL),and singular value decomposition(SVD)were all smoothly integrated into a single framework.SVD and group lasso improve computational efficiency,address the problem of high-dimensional datasets,and clarify class distinctions by removing redundant or irrelevant features that might lead to class overlap.As a method to eliminate the issues of decision boundary overlap and class imbalance in the classification task,TL enhances dataset balance and increases the clarity of decision boundaries through the elimination of overlapping samples.Using fivefold cross-validation,our proposed method(TL-SVDPMR)achieved a remarkable overall accuracy of almost 95%in the classification of SHH-MB molecular subtypes.The results demonstrate the strong performance of the proposed classification model among the various SHH-MB subtypes given a high average of the area under the curve(AUC)values.Additionally,the statistical significance test indicates that TL-SVDPMR is more accurate than both SVM and random forest algorithms in classifying the overlapping SHH-MB subtypes,highlighting its importance for precision medicine applications.Our findings emphasized the success of combining SVD,TL,and PMRtechniques to improve the classification performance for biomedical applications with many features and overlapping subtypes.展开更多
The existing wireless power transfer(WPT)systems for gastrointestinal capsule robot have the prob-lems of small coupling coefficient and low power transmission efficiency(PTE).The reasons are due to the long distance ...The existing wireless power transfer(WPT)systems for gastrointestinal capsule robot have the prob-lems of small coupling coefficient and low power transmission efficiency(PTE).The reasons are due to the long distance between the transmitting coil and the receiving coil and the large difference in size.A new type of WPT system is designed,which uses three sets of small coil pairs to form a power supply unit(PSU),and utilizes multiple PSUs to form a multi-coil WPT system.Compared with single-coil system,the multi-coil system can achieve higher power utilization by switching between PSUs,instead of opening all PSUs.ANSYS Maxwell is used to perform finite element modeling on the PSU,analyzing the characteristics of the transmitting magnetic field.The results of the experiment show that when the distance between the small coil pairs in the PSU is 180mm,the magnetic field has relatively good uniformity,and the magnetic strength change relative to the center point is less than 5%.The average received power of the system is greater than 800mW,and the PTE is up to 5.1%.展开更多
In the class imbalanced learning scenario, traditional machine learning algorithms focusing on optimizing the overall accuracy tend to achieve poor classification performance especially for the minority class in which...In the class imbalanced learning scenario, traditional machine learning algorithms focusing on optimizing the overall accuracy tend to achieve poor classification performance especially for the minority class in which we are most interested. To solve this problem, many effective approaches have been proposed. Among them, the bagging ensemble methods with integration of the under-sampling techniques have demonstrated better performance than some other ones including the bagging ensemble methods integrated with the over-sampling techniques, the cost-sensitive methods, etc. Although these under-sampling techniques promote the diversity among the generated base classifiers with the help of random partition or sampling for the majority class, they do not take any measure to ensure the individual classification performance, consequently affecting the achievability of better ensemble performance. On the other hand, evolutionary under-sampling EUS as a novel under- sampling technique has been successfully applied in searching for the best majority class subset for training a good- performance nearest neighbor classifier. Inspired by EUS, in this paper, we try to introduce it into the under-sampling bagging framework and propose an EUS based bagging ensemble method EUS-Bag by designing a new fitness function considering three factors to make EUS better suited to the framework. With our fitness function, EUS-Bag could generate a set of accurate and diverse base classifiers. To verify the effectiveness of EUS-Bag, we conduct a series of comparison experiments on 22 two-class imbalanced classification problems. Experimental results measured using recall, geometric mean and AUC all demonstrate its superior performance.展开更多
Credit risk assessment is an important task of risk management for financial institutions.Machine learning-based approaches have made promising progress in credit risk assessment by treating it as imbalanced binary cl...Credit risk assessment is an important task of risk management for financial institutions.Machine learning-based approaches have made promising progress in credit risk assessment by treating it as imbalanced binary classification tasks.However,few efforts have been made to deal with the class overlap problem that accompanies imbalances simultaneously.To this end,this study proposes a Tomek link and genetic algorithm(GA)-based under-sampling framework(TEUS)to address the class imbalance and overlap issues in binary credit classification by eliminating majority class instances with considering multi-perspective factors.TEUS first determines boundary majority instances with Tomek link,then take the distance from each majority instance to its nearest boundary as the radius and assigns the density of opposite class samples within the radius as the overlap potential of that majority instance.Second,TEUS weighs each non-borderline majority instance based on its information contribution in estimating class labels.After partitioning non-borderline majority instances into subgroups according to overlap potential and information contribution,TEUS applies GA to select samples from subgroups and merge them with the minority samples into a new training set.Innovatively,the design of the fitness function in GA and the grouping of the non-borderline majority not only trade off the multi-perspective characteristics of instances but also help reduce the computational complexity of the sampling optimization search.Numerical experiments on real-world credit data sets demonstrate the effectiveness of the proposed TEUS.展开更多
The Energy Climate Package is the EU response to the Global Warming Challenge.Induction heating processes can contribute to the energy saving goal:20%saving within 2020.European induction manufacturer already propose ...The Energy Climate Package is the EU response to the Global Warming Challenge.Induction heating processes can contribute to the energy saving goal:20%saving within 2020.European induction manufacturer already propose many efficient solutions at industrial scale.To improve induction devices for an always better energy efficiency, EDF R&D set up a French cooperative project called ISIS with a financial support of the French National Research Agency.Its objective is to promote induction heating as Best Available Technology(BAT)and to develop innovative solutions to increase its efficiency.The ISIS innovations concern the electroheat conversion of induction devices(auto-adaptive multi-coil power supply,low losses coils)and the recovering of fatally lost energy.This paper shows the mid-term results of this project.Firsts control algorithms were successfully tested on a 100 kW 3-coil power supply.A homogenization technique is proposed to model a multi-strand coil.A heat recovery test bench is build and equipped with a PFC control loop to fit with the production fluctuations.展开更多
The state-of-the-art approaches for image reconstruction using under-sampled k-space data are compressed sensing based.They are iterative algorithms that optimize objective functions with spatial and/or temporal const...The state-of-the-art approaches for image reconstruction using under-sampled k-space data are compressed sensing based.They are iterative algorithms that optimize objective functions with spatial and/or temporal constraints.This paper proposes a non-iterative algorithm to estimate the un-measured data and then to reconstruct the image with the efficient filtered backprojection algorithm.The feasibility of the proposed method is demonstrated with a patient magnetic resonance imaging study.The proposed method is also compared with the state-of-the-art iterative compressed-sensing image reconstruction method using the total-variation optimization norm.展开更多
Magnetorheological(MR) cell with multi-coil was designed to enlarge the range of controllable transmission torque by increasing the effective length. Individual input current was proposed to maximize its potential for...Magnetorheological(MR) cell with multi-coil was designed to enlarge the range of controllable transmission torque by increasing the effective length. Individual input current was proposed to maximize its potential for reducing power consumption and generating large yield stress. Finite element analysis was performed to analyze magnetic field distribution, based on which a prototype MR cell was fabricated and tested to investigate the performance of various combinations of individual input currents. A good correlation was identified between experimental results and FEA predications. The results show that the power consumption can be reduced to 42.4%, maintaining large transmission torque, by distributing the total current(2 A) to three individual magnetic coils. In addition, optimal results of four input currents considering a multi-objective function are obtained by changing the weighting factor λ. The advantage of this design, such as lower power consumption and more control flexibility, makes it more competitive in engineering applications that require large energy consumption.展开更多
Check dams have been widely constructed in the Chinese Loess Plateau and has played an important role in controlling soil loss during last 70 years.However,the large-scale and automatic mapping of the check dams and t...Check dams have been widely constructed in the Chinese Loess Plateau and has played an important role in controlling soil loss during last 70 years.However,the large-scale and automatic mapping of the check dams and the resulting silted fields are lacking.In this study,we present a novel methodological framework to extract silted fields and to estimate the location of the check dams at a pixel level in the Wuding River catchment by remote sensing and ensemble learning models.The random under-sampling method and 23 features were used to train and validate three ensemble learning models,namely Random Forest,Extreme Gradient Boosting and EasyEnsemble,based on a large number of samples.The established optimal model was then applied to the whole study area to map check dams and silted fields.Our results indicate that the imbalance ratio of the samples has a significant impact on the performance of the models.Validation of the results on the testing set show that the F1-score of silted fields of three models is higher than 0.75 at the pixel level.Finally,we produced a map of silted fields and check dams at 10 m-spatial resolution by the optimal model with an accuracy of ca.90%at the object level.The proposed framework can be used for the large-scale and high-precision mapping of check dams and silted fields,which is of great significance for the monitoring and management of the dynamics of check dams and the quantitative evaluation of their eco-environmental benefits.展开更多
High magnetic field homogeneity is critical for magnetic resonance imaging(MRI),functional MRI,and magnetic resonance spectroscopy(MRS)applications.B_(0)inhomogeneity during MR scans is a long-standing problem resulti...High magnetic field homogeneity is critical for magnetic resonance imaging(MRI),functional MRI,and magnetic resonance spectroscopy(MRS)applications.B_(0)inhomogeneity during MR scans is a long-standing problem resulting from magnet imperfections and site conditions,with the main issue being the inhomogeneity across the human body caused by differences in magnetic susceptibilities between tissues,resulting in signal loss,image distortion,and poor spectral resolution.Through a combination of passive and active shim techniques,as well as technological advances employing multi-coil techniques,optimal coil design,motion tracking,and real-time modifications,improved field homogeneity and image quality have been achieved in MRI/MRS.The integration of RF and shim coils brings a high shim efficiency due to the proximity of participants.This technique will potentially be applied to high-density RF coils with a high-density shim array for improved B_(0)homogeneity.Simultaneous shimming and image encoding can be achieved using multi-coil array,which also enables the development of novel encoding methods using advanced magnetic field control.Field monitoring enables the capture and real-time compensation for dynamic field perturbance beyond the static background inhomogeneity.These advancements have the potential to better use the scanner performance to enhance diagnostic capabilities and broaden applications of MRI/MRS in a variety of clinical and research settings.The purpose of this paper is to provide an overview of the latest advances in B_(0)magnetic field shimming and magnetic field control techniques as well as MR hardware,and to emphasize their significance and potential impact on improving the data quality of MRI/MRS.展开更多
Compared with conventional cameras, spectral imagers provide many more features in the spectral do- main. They have been used in various fields such as material identification, remote sensing, precision agriculture, a...Compared with conventional cameras, spectral imagers provide many more features in the spectral do- main. They have been used in various fields such as material identification, remote sensing, precision agriculture, and surveillance. Traditional imaging spectrometers use generally scanning systems. They cannot meet the demands of dynamic scenarios. This limits the practical applications for spectral imaging. Recently, with the rapid development in computational photography theory and semiconductor techniques, spectral video acquisition has become feasible. This paper aims to offer a review of the state-of-the-art spectral imaging technologies, especially those capable of capturing spectral videos. Finally, we evaluate the performances of the existing spectral acquisition systems and discuss the trends for future work.展开更多
A clustering-based undersampling(CUS)and distance-based near-miss method are widely used in current imbalanced learning algorithms,but this method has certain drawbacks.In particular,the CUS does not consider the infl...A clustering-based undersampling(CUS)and distance-based near-miss method are widely used in current imbalanced learning algorithms,but this method has certain drawbacks.In particular,the CUS does not consider the influence of the distance factor on the majority of instances,and the near-miss method omits the inter-class(es)within the majority of samples.To overcome these drawbacks,this study proposes an undersampling method combining distance measurement and majority class clustering.Resampling methods are used to develop an ensemble-based imbalanced-learning algorithm called the clustering and distance-based imbalance learning model(CDEILM).This algorithm combines distance-based undersampling,feature selection,and ensemble learning.In addition,a cluster size-based resampling(CSBR)method is proposed for preserving the original distribution of the majority class,and a hybrid imbalanced learning framework is constructed by fusing various types of resampling methods.The combination of CDEILM and CSBR can be considered as a specific case of this hybrid framework.The experimental results show that the CDEILM and CSBR methods can achieve better performance than the benchmark methods,and that the hybrid model provides the best results under most circumstances.Therefore,the proposed model can be used as an alternative imbalanced learning method under specific circumstances,e.g.,for providing a solution to credit evaluation problems in financial applications.展开更多
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01137).
文摘Sonic Hedgehog Medulloblastoma(SHH-MB)is one of the four primary molecular subgroups of Medulloblastoma.It is estimated to be responsible for nearly one-third of allMB cases.Using transcriptomic and DNA methylation profiling techniques,new developments in this field determined four molecular subtypes for SHH-MB.SHH-MB subtypes show distinct DNAmethylation patterns that allow their discrimination fromoverlapping subtypes and predict clinical outcomes.Class overlapping occurs when two or more classes share common features,making it difficult to distinguish them as separate.Using the DNA methylation dataset,a novel classification technique is presented to address the issue of overlapping SHH-MBsubtypes.Penalizedmultinomial regression(PMR),Tomek links(TL),and singular value decomposition(SVD)were all smoothly integrated into a single framework.SVD and group lasso improve computational efficiency,address the problem of high-dimensional datasets,and clarify class distinctions by removing redundant or irrelevant features that might lead to class overlap.As a method to eliminate the issues of decision boundary overlap and class imbalance in the classification task,TL enhances dataset balance and increases the clarity of decision boundaries through the elimination of overlapping samples.Using fivefold cross-validation,our proposed method(TL-SVDPMR)achieved a remarkable overall accuracy of almost 95%in the classification of SHH-MB molecular subtypes.The results demonstrate the strong performance of the proposed classification model among the various SHH-MB subtypes given a high average of the area under the curve(AUC)values.Additionally,the statistical significance test indicates that TL-SVDPMR is more accurate than both SVM and random forest algorithms in classifying the overlapping SHH-MB subtypes,highlighting its importance for precision medicine applications.Our findings emphasized the success of combining SVD,TL,and PMRtechniques to improve the classification performance for biomedical applications with many features and overlapping subtypes.
基金the National Natural Science Founda-tion of China(Nos.61673271 and 81971767)the Shang-hai Research Project(Nos.19441910600,19441913800 and 19142203800)the Project of Institute of Medical Robotics,Shanghai Jiao Tong University(No.IMR2018KY05)。
文摘The existing wireless power transfer(WPT)systems for gastrointestinal capsule robot have the prob-lems of small coupling coefficient and low power transmission efficiency(PTE).The reasons are due to the long distance between the transmitting coil and the receiving coil and the large difference in size.A new type of WPT system is designed,which uses three sets of small coil pairs to form a power supply unit(PSU),and utilizes multiple PSUs to form a multi-coil WPT system.Compared with single-coil system,the multi-coil system can achieve higher power utilization by switching between PSUs,instead of opening all PSUs.ANSYS Maxwell is used to perform finite element modeling on the PSU,analyzing the characteristics of the transmitting magnetic field.The results of the experiment show that when the distance between the small coil pairs in the PSU is 180mm,the magnetic field has relatively good uniformity,and the magnetic strength change relative to the center point is less than 5%.The average received power of the system is greater than 800mW,and the PTE is up to 5.1%.
基金Acknowledgements We would like to express our gratitude to both the associate editor and the anonymous reviewers for their constructive comments that improved the quality of our manuscript to a large extent. This work was supported by the National Natural Science Foundation of China （Grant No.61501229） and the Fundamental Research Funds for the Central Universities （NS2015091, NS2014067, NJ20160013）.
文摘In the class imbalanced learning scenario, traditional machine learning algorithms focusing on optimizing the overall accuracy tend to achieve poor classification performance especially for the minority class in which we are most interested. To solve this problem, many effective approaches have been proposed. Among them, the bagging ensemble methods with integration of the under-sampling techniques have demonstrated better performance than some other ones including the bagging ensemble methods integrated with the over-sampling techniques, the cost-sensitive methods, etc. Although these under-sampling techniques promote the diversity among the generated base classifiers with the help of random partition or sampling for the majority class, they do not take any measure to ensure the individual classification performance, consequently affecting the achievability of better ensemble performance. On the other hand, evolutionary under-sampling EUS as a novel under- sampling technique has been successfully applied in searching for the best majority class subset for training a good- performance nearest neighbor classifier. Inspired by EUS, in this paper, we try to introduce it into the under-sampling bagging framework and propose an EUS based bagging ensemble method EUS-Bag by designing a new fitness function considering three factors to make EUS better suited to the framework. With our fitness function, EUS-Bag could generate a set of accurate and diverse base classifiers. To verify the effectiveness of EUS-Bag, we conduct a series of comparison experiments on 22 two-class imbalanced classification problems. Experimental results measured using recall, geometric mean and AUC all demonstrate its superior performance.
基金supported by National Key R&D Programof ChinaunderGrant No.2019YFB1404600Beijing Natural Science Funds under Grant No.9162003Beijing's"High-grade,Precision and Advanced Discipline Construction(Municipal)-Business Administration"project under Grant No.19008022065.
文摘Credit risk assessment is an important task of risk management for financial institutions.Machine learning-based approaches have made promising progress in credit risk assessment by treating it as imbalanced binary classification tasks.However,few efforts have been made to deal with the class overlap problem that accompanies imbalances simultaneously.To this end,this study proposes a Tomek link and genetic algorithm(GA)-based under-sampling framework(TEUS)to address the class imbalance and overlap issues in binary credit classification by eliminating majority class instances with considering multi-perspective factors.TEUS first determines boundary majority instances with Tomek link,then take the distance from each majority instance to its nearest boundary as the radius and assigns the density of opposite class samples within the radius as the overlap potential of that majority instance.Second,TEUS weighs each non-borderline majority instance based on its information contribution in estimating class labels.After partitioning non-borderline majority instances into subgroups according to overlap potential and information contribution,TEUS applies GA to select samples from subgroups and merge them with the minority samples into a new training set.Innovatively,the design of the fitness function in GA and the grouping of the non-borderline majority not only trade off the multi-perspective characteristics of instances but also help reduce the computational complexity of the sampling optimization search.Numerical experiments on real-world credit data sets demonstrate the effectiveness of the proposed TEUS.
基金Item Sponsored by French Research National Agency (ANR) Through "Efficacite Energetique et Reduction des Emissions de CO_2 Dans les Systemes Industriels" Program(Project ISIS n°ANR-09-EESI-004)
文摘The Energy Climate Package is the EU response to the Global Warming Challenge.Induction heating processes can contribute to the energy saving goal:20%saving within 2020.European induction manufacturer already propose many efficient solutions at industrial scale.To improve induction devices for an always better energy efficiency, EDF R&D set up a French cooperative project called ISIS with a financial support of the French National Research Agency.Its objective is to promote induction heating as Best Available Technology(BAT)and to develop innovative solutions to increase its efficiency.The ISIS innovations concern the electroheat conversion of induction devices(auto-adaptive multi-coil power supply,low losses coils)and the recovering of fatally lost energy.This paper shows the mid-term results of this project.Firsts control algorithms were successfully tested on a 100 kW 3-coil power supply.A homogenization technique is proposed to model a multi-strand coil.A heat recovery test bench is build and equipped with a PFC control loop to fit with the production fluctuations.
基金supported by American Heart Association,No.18AJML34280074.
文摘The state-of-the-art approaches for image reconstruction using under-sampled k-space data are compressed sensing based.They are iterative algorithms that optimize objective functions with spatial and/or temporal constraints.This paper proposes a non-iterative algorithm to estimate the un-measured data and then to reconstruct the image with the efficient filtered backprojection algorithm.The feasibility of the proposed method is demonstrated with a patient magnetic resonance imaging study.The proposed method is also compared with the state-of-the-art iterative compressed-sensing image reconstruction method using the total-variation optimization norm.
基金Projects(51175265,51305207)supported by the National Natural Science Foundation of China
文摘Magnetorheological(MR) cell with multi-coil was designed to enlarge the range of controllable transmission torque by increasing the effective length. Individual input current was proposed to maximize its potential for reducing power consumption and generating large yield stress. Finite element analysis was performed to analyze magnetic field distribution, based on which a prototype MR cell was fabricated and tested to investigate the performance of various combinations of individual input currents. A good correlation was identified between experimental results and FEA predications. The results show that the power consumption can be reduced to 42.4%, maintaining large transmission torque, by distributing the total current(2 A) to three individual magnetic coils. In addition, optimal results of four input currents considering a multi-objective function are obtained by changing the weighting factor λ. The advantage of this design, such as lower power consumption and more control flexibility, makes it more competitive in engineering applications that require large energy consumption.
基金supported by the National Natural Science Foundation of China(No.41907048)The Fundamental Research Funds for the Central Universities,CHD(No.300102260206)The Shannxi Academy of Forestry(No.SXLK2023-02-15).
文摘Check dams have been widely constructed in the Chinese Loess Plateau and has played an important role in controlling soil loss during last 70 years.However,the large-scale and automatic mapping of the check dams and the resulting silted fields are lacking.In this study,we present a novel methodological framework to extract silted fields and to estimate the location of the check dams at a pixel level in the Wuding River catchment by remote sensing and ensemble learning models.The random under-sampling method and 23 features were used to train and validate three ensemble learning models,namely Random Forest,Extreme Gradient Boosting and EasyEnsemble,based on a large number of samples.The established optimal model was then applied to the whole study area to map check dams and silted fields.Our results indicate that the imbalance ratio of the samples has a significant impact on the performance of the models.Validation of the results on the testing set show that the F1-score of silted fields of three models is higher than 0.75 at the pixel level.Finally,we produced a map of silted fields and check dams at 10 m-spatial resolution by the optimal model with an accuracy of ca.90%at the object level.The proposed framework can be used for the large-scale and high-precision mapping of check dams and silted fields,which is of great significance for the monitoring and management of the dynamics of check dams and the quantitative evaluation of their eco-environmental benefits.
基金supported by the National Institute of Neurological Disorders and Stroke(NINDS)and the National Institutes of Health(NIH)grants R01NS121544 and R01HL156818Additionally,support was provided by NIH SBIR grant R43NS120795+1 种基金We acknowledge data collection and sharing from the project funded by the Frontotemporal Lobar Degeneration Neuroimaging Initiative(National Institutes of Health Grant R01 AG032306)Hsin-Jung Yang and Hui Han hold equity in Lucidity Medical LLC.
文摘High magnetic field homogeneity is critical for magnetic resonance imaging(MRI),functional MRI,and magnetic resonance spectroscopy(MRS)applications.B_(0)inhomogeneity during MR scans is a long-standing problem resulting from magnet imperfections and site conditions,with the main issue being the inhomogeneity across the human body caused by differences in magnetic susceptibilities between tissues,resulting in signal loss,image distortion,and poor spectral resolution.Through a combination of passive and active shim techniques,as well as technological advances employing multi-coil techniques,optimal coil design,motion tracking,and real-time modifications,improved field homogeneity and image quality have been achieved in MRI/MRS.The integration of RF and shim coils brings a high shim efficiency due to the proximity of participants.This technique will potentially be applied to high-density RF coils with a high-density shim array for improved B_(0)homogeneity.Simultaneous shimming and image encoding can be achieved using multi-coil array,which also enables the development of novel encoding methods using advanced magnetic field control.Field monitoring enables the capture and real-time compensation for dynamic field perturbance beyond the static background inhomogeneity.These advancements have the potential to better use the scanner performance to enhance diagnostic capabilities and broaden applications of MRI/MRS in a variety of clinical and research settings.The purpose of this paper is to provide an overview of the latest advances in B_(0)magnetic field shimming and magnetic field control techniques as well as MR hardware,and to emphasize their significance and potential impact on improving the data quality of MRI/MRS.
基金Project supported by the National Natural Science Foundation of China （Nos. 61627804, 61371166, 61422107, 61571215, and 61671236） and the Natural Science Foundation of Jiangsu Province, China （Nos. BK20140610 and BK20160634）
文摘Compared with conventional cameras, spectral imagers provide many more features in the spectral do- main. They have been used in various fields such as material identification, remote sensing, precision agriculture, and surveillance. Traditional imaging spectrometers use generally scanning systems. They cannot meet the demands of dynamic scenarios. This limits the practical applications for spectral imaging. Recently, with the rapid development in computational photography theory and semiconductor techniques, spectral video acquisition has become feasible. This paper aims to offer a review of the state-of-the-art spectral imaging technologies, especially those capable of capturing spectral videos. Finally, we evaluate the performances of the existing spectral acquisition systems and discuss the trends for future work.
文摘A clustering-based undersampling(CUS)and distance-based near-miss method are widely used in current imbalanced learning algorithms,but this method has certain drawbacks.In particular,the CUS does not consider the influence of the distance factor on the majority of instances,and the near-miss method omits the inter-class(es)within the majority of samples.To overcome these drawbacks,this study proposes an undersampling method combining distance measurement and majority class clustering.Resampling methods are used to develop an ensemble-based imbalanced-learning algorithm called the clustering and distance-based imbalance learning model(CDEILM).This algorithm combines distance-based undersampling,feature selection,and ensemble learning.In addition,a cluster size-based resampling(CSBR)method is proposed for preserving the original distribution of the majority class,and a hybrid imbalanced learning framework is constructed by fusing various types of resampling methods.The combination of CDEILM and CSBR can be considered as a specific case of this hybrid framework.The experimental results show that the CDEILM and CSBR methods can achieve better performance than the benchmark methods,and that the hybrid model provides the best results under most circumstances.Therefore,the proposed model can be used as an alternative imbalanced learning method under specific circumstances,e.g.,for providing a solution to credit evaluation problems in financial applications.
