In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is di...In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.展开更多
In this paper,we first initialize the S-product of tensors to unify the outer product,contractive product,and the inner product of tensors.Then,we introduce the separable symmetry tensors and separable anti-symmetry t...In this paper,we first initialize the S-product of tensors to unify the outer product,contractive product,and the inner product of tensors.Then,we introduce the separable symmetry tensors and separable anti-symmetry tensors,which are defined,respectively,as the sum and the algebraic sum of rank-one tensors generated by the tensor product of some vectors.We offer a class of tensors to achieve the upper bound for rank(A)≤6 for all tensors of size 3×3×3.We also show that each 3×3×3 anti-symmetric tensor is separable.展开更多
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
The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation...The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.展开更多
Appearance-based dynamic Hand Gesture Recognition(HGR)remains a prominent area of research in Human-Computer Interaction(HCI).Numerous environmental and computational constraints limit its real-time deployment.In addi...Appearance-based dynamic Hand Gesture Recognition(HGR)remains a prominent area of research in Human-Computer Interaction(HCI).Numerous environmental and computational constraints limit its real-time deployment.In addition,the performance of a model decreases as the subject’s distance from the camera increases.This study proposes a 3D separable Convolutional Neural Network(CNN),considering the model’s computa-tional complexity and recognition accuracy.The 20BN-Jester dataset was used to train the model for six gesture classes.After achieving the best offline recognition accuracy of 94.39%,the model was deployed in real-time while considering the subject’s attention,the instant of performing a gesture,and the subject’s distance from the camera.Despite being discussed in numerous research articles,the distance factor remains unresolved in real-time deployment,which leads to degraded recognition results.In the proposed approach,the distance calculation substantially improves the classification performance by reducing the impact of the subject’s distance from the camera.Additionally,the capability of feature extraction,degree of relevance,and statistical significance of the proposed model against other state-of-the-art models were validated using t-distributed Stochastic Neighbor Embedding(t-SNE),Mathew’s Correlation Coefficient(MCC),and the McNemar test,respectively.We observed that the proposed model exhibits state-of-the-art outcomes and a comparatively high significance level.展开更多
Novel visible light magnetically separable graphene-based BiOBr composite photocatalysts were prepared for the first time. The structures, morphologies and optical properties were characterized by field emission scann...Novel visible light magnetically separable graphene-based BiOBr composite photocatalysts were prepared for the first time. The structures, morphologies and optical properties were characterized by field emission scanning electron microscopy, transmission electron microscopy, X-ray diffraction and ultravioletvisible spectroscopy, respectively. The photocatalytic activity of the resulting samples was evaluated by degradation of tetracycline under visible light irradiation. An appropriate amount of introduced graphene can significantly enhance the photocatalytic activities. The enhanced activities were mainly attributed to the enhanced light absorption and the interfacial transfer of electrons. The corresponding photocatalytic mechanism was proposed based on the results.展开更多
In this paper, the maximal length of maximal distance separable (MDS) codes is studied, and a new upper bound formula of the maximal length of MDS codes is obtained. Especially, the exact values of the maximal length ...In this paper, the maximal length of maximal distance separable (MDS) codes is studied, and a new upper bound formula of the maximal length of MDS codes is obtained. Especially, the exact values of the maximal length of MDS codes in some parameters are given.展开更多
The nonlinear multidimensional knapsack problem is defined as the minimization of a convex function with multiple linear constraints. The methods developed for nonlinear multidimensional programming problems are often...The nonlinear multidimensional knapsack problem is defined as the minimization of a convex function with multiple linear constraints. The methods developed for nonlinear multidimensional programming problems are often applied to solve the nonlinear multidimensional knapsack problems, but they are inefficient or limited since most of them do not exploit the characteristics of the knapsack problems. In this paper, by establishing structural properties of the continuous separable nonlinear multidimensional knapsack problem, we develop a multi-tier binary solution method for solving the continuous nonlinear multidimensional knapsack problems with general structure. The computational complexity is polynomial in the number of variables. We presented two examples to illustrate the general application of our method and we used statistical results to show the effectiveness of our method.展开更多
One of the most obvious clinical reasons of dementia or The Behavioral and Psychological Symptoms of Dementia(BPSD)are the lack of emotional expression,the increased frequency of negative emotions,and the impermanence...One of the most obvious clinical reasons of dementia or The Behavioral and Psychological Symptoms of Dementia(BPSD)are the lack of emotional expression,the increased frequency of negative emotions,and the impermanence of emotions.Observing the reduction of BPSD in dementia through emotions can be considered effective and widely used in the field of non-pharmacological therapy.At present,this article will verify whether the image recognition artificial intelligence(AI)system can correctly reflect the emotional performance of the elderly with dementia through a questionnaire survey of three professional elderly nursing staff.The ANOVA(sig.=0.50)is used to determine that the judgment given by the nursing staff has no obvious deviation,and then Kendall's test(0.722**)and spearman's test(0.863**)are used to verify the judgment severity of the emotion recognition system and the nursing staff unanimously.This implies the usability of the tool.Additionally,it can be expected to be further applied in the research related to BPSD elderly emotion detection.展开更多
Magnetically separable mesoporous activated carbon was prepared from brown coal in the presence of Fe3O4 as a bi-functional additive.Magnetic activated carbon(MAC)was characterized by lowtemperature nitrogen adsorptio...Magnetically separable mesoporous activated carbon was prepared from brown coal in the presence of Fe3O4 as a bi-functional additive.Magnetic activated carbon(MAC)was characterized by lowtemperature nitrogen adsorption,scanning electron microscopy(SEM),transmission electron microscopy(TEM),X-ray diffraction(XRD),X-ray photoelectron spectroscopy(XPS)and vibrating sample magnetometry(VSM).The evolution behaviors and transition mechanism of Fe3O4 during the preparation of MAC were investigated.The results show that prepared MAC with 6 wt%Fe3O4 addition having a specific surface area and mesopore ratio of 370 m^2·g^-1 and 55.7%,which meet the requirements of adsorption application and magnetic recovery.Highly dispersed iron-containing aggregates with the size of 0.1 lm in the MAC were observed.During the preparation of MAC,Fe3O4 could enhance the escape of volatiles during the carbonization.Fe3O4 could also accelerate burning off the carbon wall during activation,which leads to enlarging micropore size,then resulting in the generation of mesopore and macropore.As a result,a part of Fe3O4 converted into FeO,FeOOH,a-Fe,c-Fe,Fe2SiO4 and compound of Aluminum-iron-silicon.The prepared activated carbon,which was magnetized by both of residual Fe3O4,reduced a-Fe and c-Fe,can be easily separated from the original solution by external magnetic field.展开更多
Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. How...Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. However, identifying the parameters of these models is challenging, especially when sparse models with better interpretability are desired by practitioners. Previous theoretical and practical studies have shown that variable projection (VP) is an efficient method for identifying separable nonlinear models, but these are based on \(L_2\) penalty of model parameters, which cannot be directly extended to deal with sparse constraint. Based on the exploration of the structural characteristics of separable models, this paper proposes gradient-based and trust-region-based variable projection algorithms, which mainly solve two key problems: how to eliminate linear parameters under sparse constraint;and how to deal with the coupling relationship between linear and nonlinear parameters in the model. Finally, numerical experiments on synthetic data and real time series data are conducted to verify the effectiveness of the proposed algorithms.展开更多
In recent years,persulfate(PS)-based advanced oxidation processes(AOPs)have become a hot research topic for degrading environmental pollutants due to their excellent oxidation capacity,selectivity,and stability.PS-AOP...In recent years,persulfate(PS)-based advanced oxidation processes(AOPs)have become a hot research topic for degrading environmental pollutants due to their excellent oxidation capacity,selectivity,and stability.PS-AOPs can generate sulfate radicals(SO^(·-)_(4))with strong oxidation ability,but single PS produces limited or no radicals.Therefore,activation of PS by energy input or catalyst dosing is used to improve its oxidation performance.However,the addition of disposable catalyst not only causes a waste of resources,but also may lead to secondary pollution.Therefore,magnetically separable catalysts for activating PS have received widespread attention due to their reusability.Although there are few literature reviews on the activation of PS by carbon-or iron-based magnetic materials,the mechanism analysis of the activation of PS by magnetic materials to degrade pollut-ants is not deep enough,and the discussion of material types is not comprehensive and detailed.Moreover,the discussion of magnetic materials in terms of recycling properties is lacking.Therefore,this review firstly sum-marizes and analyzes the mechanism of magnetically separable catalysts activating PS to degrade pollutants.Then,the research progress of zero-valent iron(ZVI,Fe^(0))-based,iron oxide-based,bimetallic oxide-based,and other magnetically separable catalyst is introduced,and the tailoring engineering approaches and reusability of magnetically separable catalysts are discussed.Finally,some possible material optimization suggestions are proposed in this paper.In conclusion,this review is expected to provide useful insights for improving the per-formance and reusability of magnetically separable materials activated PS in the future.展开更多
Proximal point algorithm(PPA)is a useful algorithm framework and has good convergence properties.Themain difficulty is that the subproblems usually only have iterative solutions.In this paper,we propose an inexact cus...Proximal point algorithm(PPA)is a useful algorithm framework and has good convergence properties.Themain difficulty is that the subproblems usually only have iterative solutions.In this paper,we propose an inexact customized PPA framework for twoblock separable convex optimization problem with linear constraint.We design two types of inexact error criteria for the subproblems.The first one is absolutely summable error criterion,under which both subproblems can be solved inexactly.When one of the two subproblems is easily solved,we propose another novel error criterion which is easier to implement,namely relative error criterion.The relative error criterion only involves one parameter,which is more implementable.We establish the global convergence and sub-linear convergence rate in ergodic sense for the proposed algorithms.The numerical experiments on LASSO regression problems and total variation-based image denoising problem illustrate that our new algorithms outperform the corresponding exact algorithms.展开更多
Separable multi-block convex optimization problem appears in many mathematical and engineering fields.In the first part of this paper,we propose an inertial proximal ADMM to solve a linearly constrained separable mult...Separable multi-block convex optimization problem appears in many mathematical and engineering fields.In the first part of this paper,we propose an inertial proximal ADMM to solve a linearly constrained separable multi-block convex optimization problem,and we show that the proposed inertial proximal ADMM has global convergence under mild assumptions on the regularization matrices.Affine phase retrieval arises in holography,data separation and phaseless sampling,and it is also considered as a nonhomogeneous version of phase retrieval,which has received considerable attention in recent years.Inspired by convex relaxation of vector sparsity and matrix rank in compressive sensing and by phase lifting in phase retrieval,in the second part of this paper,we introduce a compressive affine phase retrieval via lifting approach to connect affine phase retrieval with multi-block convex optimization,and then based on the proposed inertial proximal ADMM for 3-block convex optimization,we propose an algorithm to recover sparse real signals from their(noisy)affine quadratic measurements.Our numerical simulations show that the proposed algorithm has satisfactory performance for affine phase retrieval of sparse real signals.展开更多
With the widespread use of Internet of Things(IoT)technology in daily life and the considerable safety risks of falls for elderly individuals,research on IoT-based fall detection systems has gainedmuch attention.This ...With the widespread use of Internet of Things(IoT)technology in daily life and the considerable safety risks of falls for elderly individuals,research on IoT-based fall detection systems has gainedmuch attention.This paper proposes an IoT-based spatiotemporal data processing framework based on a depthwise separable convolution generative adversarial network using skip-connection(Skip-DSCGAN)for fall detection.The method uses spatiotemporal data from accelerometers and gyroscopes in inertial sensors as input data.A semisupervised learning approach is adopted to train the model using only activities of daily living(ADL)data,which can avoid data imbalance problems.Furthermore,a quantile-based approach is employed to determine the fall threshold,which makes the fall detection frameworkmore robust.This proposed fall detection framework is evaluated against four other generative adversarial network(GAN)models with superior anomaly detection performance using two fall public datasets(SisFall&MobiAct).The test results show that the proposed method achieves better results,reaching 96.93% and 92.75% accuracy on the above two test datasets,respectively.At the same time,the proposed method also achieves satisfactory results in terms ofmodel size and inference delay time,making it suitable for deployment on wearable devices with limited resources.In addition,this paper also compares GAN-based semisupervised learning methods with supervised learning methods commonly used in fall detection.It clarifies the advantages of GAN-based semisupervised learning methods in fall detection.展开更多
With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the netw...With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious code.Therefore,it is important to identify malicious codes on computer systems efficiently.However,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited resources.Therefore,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution module.The feature slicing module reduces the number of parameters by grouping features.The multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel sizes.In addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model LCMISNet.The malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,respectively.It proves that LCMISNet has a powerful malicious code recognition performance.In addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.展开更多
A silylated melamine sponge(SMS)was prepared by two simple steps,namely,immersion and dehydration of a melamine sponge coated with methyltrichlorosilane.The silylated structure of SMS was characterized by FT-IR(Fourie...A silylated melamine sponge(SMS)was prepared by two simple steps,namely,immersion and dehydration of a melamine sponge coated with methyltrichlorosilane.The silylated structure of SMS was characterized by FT-IR(Fourier-transform infrared)spectroscopy,SEM(Scanning electron microscopy)and in terms of water contact angles.Its oil-water absorption and separation capacities were measured by FT-IR and UV-visible spectrophoto-metry.The experimental results have shown that oligomeric silanol covalently bonds by Si-N onto the surface of melamine sponge skeletons.SMS has shown superhydrophobicity with a water contact angle exceeding 150°±1°,a better separation efficiency with regard to diesel oil(by 99.31%(wt/wt%)in oil-water mixture and even up to 99.99%(wt/wt%)for diesel oil in its saturated aqueous solution.Moreover,SMS inherited the intrinsicflame retardancy of the melamine sponge.In general,SMS has shown superhydrophobicity,high porosity,excellent selectivity,remarkable recyclability,and better absorption capacity for various oils and organic solvents,and a high separation efficiency for oil in saturated aqueous solutions.展开更多
Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion s...Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.展开更多
文摘In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.
文摘In this paper,we first initialize the S-product of tensors to unify the outer product,contractive product,and the inner product of tensors.Then,we introduce the separable symmetry tensors and separable anti-symmetry tensors,which are defined,respectively,as the sum and the algebraic sum of rank-one tensors generated by the tensor product of some vectors.We offer a class of tensors to achieve the upper bound for rank(A)≤6 for all tensors of size 3×3×3.We also show that each 3×3×3 anti-symmetric tensor is separable.
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supported by the Hunan Provincial Natural Science Foundation of China(2021JJ50074)the Scientific Research Fund of Hunan Provincial Education Department(19B082)+6 种基金the Science and Technology Development Center of the Ministry of Education-New Generation Information Technology Innovation Project(2018A02020)the Science Foundation of Hengyang Normal University(19QD12)the Science and Technology Plan Project of Hunan Province(2016TP1020)the Subject Group Construction Project of Hengyang Normal University(18XKQ02)theApplication Oriented SpecialDisciplines,Double First ClassUniversity Project of Hunan Province(Xiangjiaotong[2018]469)the Hunan Province Special Funds of Central Government for Guiding Local Science and Technology Development(2018CT5001)the First Class Undergraduate Major in Hunan Province Internet of Things Major(Xiangjiaotong[2020]248,No.288).
文摘The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.
文摘Appearance-based dynamic Hand Gesture Recognition(HGR)remains a prominent area of research in Human-Computer Interaction(HCI).Numerous environmental and computational constraints limit its real-time deployment.In addition,the performance of a model decreases as the subject’s distance from the camera increases.This study proposes a 3D separable Convolutional Neural Network(CNN),considering the model’s computa-tional complexity and recognition accuracy.The 20BN-Jester dataset was used to train the model for six gesture classes.After achieving the best offline recognition accuracy of 94.39%,the model was deployed in real-time while considering the subject’s attention,the instant of performing a gesture,and the subject’s distance from the camera.Despite being discussed in numerous research articles,the distance factor remains unresolved in real-time deployment,which leads to degraded recognition results.In the proposed approach,the distance calculation substantially improves the classification performance by reducing the impact of the subject’s distance from the camera.Additionally,the capability of feature extraction,degree of relevance,and statistical significance of the proposed model against other state-of-the-art models were validated using t-distributed Stochastic Neighbor Embedding(t-SNE),Mathew’s Correlation Coefficient(MCC),and the McNemar test,respectively.We observed that the proposed model exhibits state-of-the-art outcomes and a comparatively high significance level.
基金Funded by National Science Funds for Creative Research Groups of China(No.51421006)Program for Changjiang Scholars and Innovative Research Team in University(No.IRT13061)+6 种基金the National Science Fundation of China for Excellent Young Scholars(No.51422902)the Key Program of National Natural Science Foundation of China(No.41430751)National Science Fund for Distinguished Young Scholars(No.51225901)the National Natural Science Foundation of China(No.51579073)Natural Science Foundation of Jiangsu Province(No.BK20141417)Fundamental Research Funds(No.2016B43814)PAPD
文摘Novel visible light magnetically separable graphene-based BiOBr composite photocatalysts were prepared for the first time. The structures, morphologies and optical properties were characterized by field emission scanning electron microscopy, transmission electron microscopy, X-ray diffraction and ultravioletvisible spectroscopy, respectively. The photocatalytic activity of the resulting samples was evaluated by degradation of tetracycline under visible light irradiation. An appropriate amount of introduced graphene can significantly enhance the photocatalytic activities. The enhanced activities were mainly attributed to the enhanced light absorption and the interfacial transfer of electrons. The corresponding photocatalytic mechanism was proposed based on the results.
文摘In this paper, the maximal length of maximal distance separable (MDS) codes is studied, and a new upper bound formula of the maximal length of MDS codes is obtained. Especially, the exact values of the maximal length of MDS codes in some parameters are given.
文摘The nonlinear multidimensional knapsack problem is defined as the minimization of a convex function with multiple linear constraints. The methods developed for nonlinear multidimensional programming problems are often applied to solve the nonlinear multidimensional knapsack problems, but they are inefficient or limited since most of them do not exploit the characteristics of the knapsack problems. In this paper, by establishing structural properties of the continuous separable nonlinear multidimensional knapsack problem, we develop a multi-tier binary solution method for solving the continuous nonlinear multidimensional knapsack problems with general structure. The computational complexity is polynomial in the number of variables. We presented two examples to illustrate the general application of our method and we used statistical results to show the effectiveness of our method.
文摘One of the most obvious clinical reasons of dementia or The Behavioral and Psychological Symptoms of Dementia(BPSD)are the lack of emotional expression,the increased frequency of negative emotions,and the impermanence of emotions.Observing the reduction of BPSD in dementia through emotions can be considered effective and widely used in the field of non-pharmacological therapy.At present,this article will verify whether the image recognition artificial intelligence(AI)system can correctly reflect the emotional performance of the elderly with dementia through a questionnaire survey of three professional elderly nursing staff.The ANOVA(sig.=0.50)is used to determine that the judgment given by the nursing staff has no obvious deviation,and then Kendall's test(0.722**)and spearman's test(0.863**)are used to verify the judgment severity of the emotion recognition system and the nursing staff unanimously.This implies the usability of the tool.Additionally,it can be expected to be further applied in the research related to BPSD elderly emotion detection.
基金supported by the Fund of 863 High-Tech Research and Development Program of China and the Poten research project No. YA-2016-003
文摘Magnetically separable mesoporous activated carbon was prepared from brown coal in the presence of Fe3O4 as a bi-functional additive.Magnetic activated carbon(MAC)was characterized by lowtemperature nitrogen adsorption,scanning electron microscopy(SEM),transmission electron microscopy(TEM),X-ray diffraction(XRD),X-ray photoelectron spectroscopy(XPS)and vibrating sample magnetometry(VSM).The evolution behaviors and transition mechanism of Fe3O4 during the preparation of MAC were investigated.The results show that prepared MAC with 6 wt%Fe3O4 addition having a specific surface area and mesopore ratio of 370 m^2·g^-1 and 55.7%,which meet the requirements of adsorption application and magnetic recovery.Highly dispersed iron-containing aggregates with the size of 0.1 lm in the MAC were observed.During the preparation of MAC,Fe3O4 could enhance the escape of volatiles during the carbonization.Fe3O4 could also accelerate burning off the carbon wall during activation,which leads to enlarging micropore size,then resulting in the generation of mesopore and macropore.As a result,a part of Fe3O4 converted into FeO,FeOOH,a-Fe,c-Fe,Fe2SiO4 and compound of Aluminum-iron-silicon.The prepared activated carbon,which was magnetized by both of residual Fe3O4,reduced a-Fe and c-Fe,can be easily separated from the original solution by external magnetic field.
基金supported in part by the National Nature Science Foundation of China(Nos.62173091,62073082)in part by the Natural Science Foundation of Fujian Province(No.2023J01268)in part by the Taishan Scholar Program of Shandong Province.
文摘Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. However, identifying the parameters of these models is challenging, especially when sparse models with better interpretability are desired by practitioners. Previous theoretical and practical studies have shown that variable projection (VP) is an efficient method for identifying separable nonlinear models, but these are based on \(L_2\) penalty of model parameters, which cannot be directly extended to deal with sparse constraint. Based on the exploration of the structural characteristics of separable models, this paper proposes gradient-based and trust-region-based variable projection algorithms, which mainly solve two key problems: how to eliminate linear parameters under sparse constraint;and how to deal with the coupling relationship between linear and nonlinear parameters in the model. Finally, numerical experiments on synthetic data and real time series data are conducted to verify the effectiveness of the proposed algorithms.
基金supported by the National Natural Science Foundation of China(No.51508228)Guangdong Basic and Applied Basic Research Foundation(No.2021A1515011804)+1 种基金Zhongshan Social Public Welfare and Basic Research Project(No.210723154031576)the Fundamental Research Funds for the Central Universities.
文摘In recent years,persulfate(PS)-based advanced oxidation processes(AOPs)have become a hot research topic for degrading environmental pollutants due to their excellent oxidation capacity,selectivity,and stability.PS-AOPs can generate sulfate radicals(SO^(·-)_(4))with strong oxidation ability,but single PS produces limited or no radicals.Therefore,activation of PS by energy input or catalyst dosing is used to improve its oxidation performance.However,the addition of disposable catalyst not only causes a waste of resources,but also may lead to secondary pollution.Therefore,magnetically separable catalysts for activating PS have received widespread attention due to their reusability.Although there are few literature reviews on the activation of PS by carbon-or iron-based magnetic materials,the mechanism analysis of the activation of PS by magnetic materials to degrade pollut-ants is not deep enough,and the discussion of material types is not comprehensive and detailed.Moreover,the discussion of magnetic materials in terms of recycling properties is lacking.Therefore,this review firstly sum-marizes and analyzes the mechanism of magnetically separable catalysts activating PS to degrade pollutants.Then,the research progress of zero-valent iron(ZVI,Fe^(0))-based,iron oxide-based,bimetallic oxide-based,and other magnetically separable catalyst is introduced,and the tailoring engineering approaches and reusability of magnetically separable catalysts are discussed.Finally,some possible material optimization suggestions are proposed in this paper.In conclusion,this review is expected to provide useful insights for improving the per-formance and reusability of magnetically separable materials activated PS in the future.
基金the National Natural Science Foundation of China(Nos.11971238 and 11871279)。
文摘Proximal point algorithm(PPA)is a useful algorithm framework and has good convergence properties.Themain difficulty is that the subproblems usually only have iterative solutions.In this paper,we propose an inexact customized PPA framework for twoblock separable convex optimization problem with linear constraint.We design two types of inexact error criteria for the subproblems.The first one is absolutely summable error criterion,under which both subproblems can be solved inexactly.When one of the two subproblems is easily solved,we propose another novel error criterion which is easier to implement,namely relative error criterion.The relative error criterion only involves one parameter,which is more implementable.We establish the global convergence and sub-linear convergence rate in ergodic sense for the proposed algorithms.The numerical experiments on LASSO regression problems and total variation-based image denoising problem illustrate that our new algorithms outperform the corresponding exact algorithms.
基金Supported by the Natural Science Foundation of China(Grant Nos.12271050,12201268)CAEP Foundation(Grant No.CX20200027)+2 种基金Key Laboratory of Computational Physics Foundation(Grant No.6142A05210502)Science and Technology Program of Gansu Province of China(Grant No.21JR7RA511)the National Science Foundation(DMS 1816313)。
文摘Separable multi-block convex optimization problem appears in many mathematical and engineering fields.In the first part of this paper,we propose an inertial proximal ADMM to solve a linearly constrained separable multi-block convex optimization problem,and we show that the proposed inertial proximal ADMM has global convergence under mild assumptions on the regularization matrices.Affine phase retrieval arises in holography,data separation and phaseless sampling,and it is also considered as a nonhomogeneous version of phase retrieval,which has received considerable attention in recent years.Inspired by convex relaxation of vector sparsity and matrix rank in compressive sensing and by phase lifting in phase retrieval,in the second part of this paper,we introduce a compressive affine phase retrieval via lifting approach to connect affine phase retrieval with multi-block convex optimization,and then based on the proposed inertial proximal ADMM for 3-block convex optimization,we propose an algorithm to recover sparse real signals from their(noisy)affine quadratic measurements.Our numerical simulations show that the proposed algorithm has satisfactory performance for affine phase retrieval of sparse real signals.
基金supported partly by the Natural Science Foundation of Zhejiang Province,China(LGF21F020017).
文摘With the widespread use of Internet of Things(IoT)technology in daily life and the considerable safety risks of falls for elderly individuals,research on IoT-based fall detection systems has gainedmuch attention.This paper proposes an IoT-based spatiotemporal data processing framework based on a depthwise separable convolution generative adversarial network using skip-connection(Skip-DSCGAN)for fall detection.The method uses spatiotemporal data from accelerometers and gyroscopes in inertial sensors as input data.A semisupervised learning approach is adopted to train the model using only activities of daily living(ADL)data,which can avoid data imbalance problems.Furthermore,a quantile-based approach is employed to determine the fall threshold,which makes the fall detection frameworkmore robust.This proposed fall detection framework is evaluated against four other generative adversarial network(GAN)models with superior anomaly detection performance using two fall public datasets(SisFall&MobiAct).The test results show that the proposed method achieves better results,reaching 96.93% and 92.75% accuracy on the above two test datasets,respectively.At the same time,the proposed method also achieves satisfactory results in terms ofmodel size and inference delay time,making it suitable for deployment on wearable devices with limited resources.In addition,this paper also compares GAN-based semisupervised learning methods with supervised learning methods commonly used in fall detection.It clarifies the advantages of GAN-based semisupervised learning methods in fall detection.
文摘With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so on.While this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious code.Therefore,it is important to identify malicious codes on computer systems efficiently.However,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited resources.Therefore,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution module.The feature slicing module reduces the number of parameters by grouping features.The multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel sizes.In addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model LCMISNet.The malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,respectively.It proves that LCMISNet has a powerful malicious code recognition performance.In addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.
基金funded by Qingyang Science and Technology Support Project(KT2019-03)。
文摘A silylated melamine sponge(SMS)was prepared by two simple steps,namely,immersion and dehydration of a melamine sponge coated with methyltrichlorosilane.The silylated structure of SMS was characterized by FT-IR(Fourier-transform infrared)spectroscopy,SEM(Scanning electron microscopy)and in terms of water contact angles.Its oil-water absorption and separation capacities were measured by FT-IR and UV-visible spectrophoto-metry.The experimental results have shown that oligomeric silanol covalently bonds by Si-N onto the surface of melamine sponge skeletons.SMS has shown superhydrophobicity with a water contact angle exceeding 150°±1°,a better separation efficiency with regard to diesel oil(by 99.31%(wt/wt%)in oil-water mixture and even up to 99.99%(wt/wt%)for diesel oil in its saturated aqueous solution.Moreover,SMS inherited the intrinsicflame retardancy of the melamine sponge.In general,SMS has shown superhydrophobicity,high porosity,excellent selectivity,remarkable recyclability,and better absorption capacity for various oils and organic solvents,and a high separation efficiency for oil in saturated aqueous solutions.
基金supported by the Henan Provincial Science and Technology Research Project under Grants 232102211006,232102210044,232102211017,232102210055 and 222102210214the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205+1 种基金the Undergraduate Universities Smart Teaching Special Research Project of Henan Province under Grant Jiao Gao[2021]No.489-29the Doctor Natural Science Foundation of Zhengzhou University of Light Industry under Grants 2021BSJJ025 and 2022BSJJZK13.
文摘Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.