As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power predictio...As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power prediction is essential for algorithms like scheduling and optimization control.Based on the spatio-temporal features of Numerical Weather Prediction(NWP)data,it proposes the WVMD_DSN(Whale Optimization Algorithm,Variational Mode Decomposition,Dual Stream Network)model.The model first applies Pearson correlation coefficient(PCC)to choose some NWP features with strong correlation to wind power to form the feature set.Then,it decomposes the feature set using Variational Mode Decomposition(VMD)to eliminate the nonstationarity and obtains Intrinsic Mode Functions(IMFs).Here Whale Optimization Algorithm(WOA)is applied to optimise the key parameters of VMD,namely the number of mode components K and penalty factor a.Finally,incorporating attention mechanism(AM),Squeeze-Excitation Network(SENet),and Bidirectional Gated Recurrent Unit(BiGRU),it constructs the dual-stream network(DSN)for short-term wind power prediction.Comparative experiments demonstrate that the WVMD_DSN model outperforms existing baseline algorithms and exhibits good generalization performance.The relevant code is available at https://github.com/ruanyuyuan/Wind-power-forecast.git(accessed on 20 August 2024).展开更多
Scene text detection is an important task in computer vision.In this paper,we present YOLOv5 Scene Text(YOLOv5ST),an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection.Our primary goal ...Scene text detection is an important task in computer vision.In this paper,we present YOLOv5 Scene Text(YOLOv5ST),an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection.Our primary goal is to enhance inference speed without sacrificing significant detection accuracy,thereby enabling robust performance on resource-constrained devices like drones,closed-circuit television cameras,and other embedded systems.To achieve this,we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation,including replacing standard convolution with depth-wise convolution,adopting the C2 sequence module in place of C3,employing Spatial Pyramid Pooling Global(SPPG)instead of Spatial Pyramid Pooling Fast(SPPF)and integrating Bi-directional Feature Pyramid Network(BiFPN)into the neck.Experimental results demonstrate a remarkable 26%improvement in inference speed compared to the baseline,with only marginal reductions of 1.6%and 4.2%in mean average precision(mAP)at the intersection over union(IoU)thresholds of 0.5 and 0.5:0.95,respectively.Our work represents a significant advancement in scene text detection,striking a balance between speed and accuracy,making it well-suited for performance-constrained environments.展开更多
As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empi...As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empirical analysis.Researchers in the field of machine learning have proved that random forest can form better judgements on this kind of problem,and it has an auxiliary role in the prediction of stock trend.This study uses historical trading data of four listed companies in the USA stock market,and the purpose of this study is to improve the performance of random forest model in medium-and long-term stock trend prediction.This study applies the exponential smoothing method to process the initial data,calculates the relevant technical indicators as the characteristics to be selected,and proposes the D-RF-RS method to optimize random forest.As the random forest is an ensemble learning model and is closely related to decision tree,D-RF-RS method uses a decision tree to screen the importance of features,and obtains the effective strong feature set of the model as input.Then,the parameter combination of the model is optimized through random parameter search.The experimental results show that the average accuracy of random forest is increased by 0.17 after the above process optimization,which is 0.18 higher than the average accuracy of light gradient boosting machine model.Combined with the performance of the ROC curve and Precision–Recall curve,the stability of the model is also guaranteed,which further demonstrates the advantages of random forest in medium-and long-term trend prediction of the stock market.展开更多
Three high dimensional spatial standardization algorithms are used for diffusion tensor image(DTI)registration,and seven kinds of methods are used to evaluate their performances.Firstly,the template used in this paper...Three high dimensional spatial standardization algorithms are used for diffusion tensor image(DTI)registration,and seven kinds of methods are used to evaluate their performances.Firstly,the template used in this paper was obtained by spatial transformation of 16 subjects by means of tensor-based standardization.Then,high dimensional standardization algorithms for diffusion tensor images,including fractional anisotropy(FA)based diffeomorphic registration algorithm,FA based elastic registration algorithm and tensor-based registration algorithm,were performed.Finally,7 kinds of evaluation methods,including normalized standard deviation,dyadic coherence,diffusion cross-correlation,overlap of eigenvalue-eigenvector pairs,Euclidean distance of diffusion tensor,and Euclidean distance of the deviatoric tensor and deviatoric of tensors,were used to qualitatively compare and summarize the above standardization algorithms.Experimental results revealed that the high-dimensional tensor-based standardization algorithms perform well and can maintain the consistency of anatomical structures.展开更多
With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in...With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry.To improve the effectiveness of stock trend prediction and solve the problems in time series data processing,this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index.Meanwhile,in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge,this paper combines the deep forest model to train the stock data separately.The experimental results show that(1)the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit(GRU)model when the un-fuzzy index-adjusted dataset is used as features for input,(2)the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input,(3)the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and(4)the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.展开更多
The mutual-interference phenomenon among multiple applications delivered as services through Cloud Services Delivery Network(CSDN)influences their QoS seriously.In order to deploy multiple applications dependably and ...The mutual-interference phenomenon among multiple applications delivered as services through Cloud Services Delivery Network(CSDN)influences their QoS seriously.In order to deploy multiple applications dependably and efficiently,we propose the Multiple Applications Co-Exist(MACE)method.MACE classifies multiple applications into different types and deploys them using isolation to some extent.Meanwhile,resource static allocation,dynamic supplement and resource reserved mechanism to minimize mutual-interference and maximize resource utilization are designed.After MACE is applied to a real large-scale CSDN and evaluated through 6-month measurement,we find that the CSDN load is more balanced,the bandwidth utilization increases by about 20%,the multiple applications'potential statistical multiplexing ratio decreases from 12% to 5%,and the number of complaint events affecting the dependability of CSDN services caused by multiple applications'mutual-interference has dropped to 0.Obviously,MACE offers a tradeoff and improvement for the dependability and efficiency goals of CSDN.展开更多
Internet of things(IoT) imposes new challenges on service composition as it is difficult to manage a quick instantiation of a complex services from a growing number of dynamic candidate services. A cross-modified Arti...Internet of things(IoT) imposes new challenges on service composition as it is difficult to manage a quick instantiation of a complex services from a growing number of dynamic candidate services. A cross-modified Artificial Bee Colony Algorithm(CMABC) is proposed to achieve the optimal solution services in an acceptable time and high accuracy. Firstly, web service instantiation model was established. What is more, to overcome the problem of discrete and chaotic solution space, the global optimal solution was used to accelerate convergence rate by imitating the cross operation of Genetic algorithm(GA). The simulation experiment result shows that CMABC exhibited faster convergence speed and better convergence accuracy than some other intelligent optimization algorithms.展开更多
A novel attribute-based framework is proposed to tackle the problem of halftone water- marking in combination of the spatial/transformation domain. The challenge is that the host image is continuous, while the waterma...A novel attribute-based framework is proposed to tackle the problem of halftone water- marking in combination of the spatial/transformation domain. The challenge is that the host image is continuous, while the watermarked halftone is bi-level. To search for a solution, an attribute image is defined as a good connection between the original grayscale image and its halftone image. When the attribute image is used as a watermark carrier, it helps to fred the watermarked halftone efficiently by solving a constrained modified direct binary search problem. Experimental results demonstrate that the proposed scheme in comparison with other similar methods maintains high watermark capacity with good image quality, high robustness, processing efficiency and easy decoding. Especially it has a good performance in printing application.展开更多
Unsupervised feature selection has become an important and challenging problem faced with vast amounts of unlabeled and high-dimension data in machine learning. We propose a novel unsupervised feature selection method...Unsupervised feature selection has become an important and challenging problem faced with vast amounts of unlabeled and high-dimension data in machine learning. We propose a novel unsupervised feature selection method using Structured Self-Representation( SSR) by simultaneously taking into account the selfrepresentation property and local geometrical structure of features. Concretely,according to the inherent selfrepresentation property of features,the most representative features can be selected. Mean while,to obtain more accurate results,we explore local geometrical structure to constrain the representation coefficients to be close to each other if the features are close to each other. Furthermore,an efficient algorithm is presented for optimizing the objective function. Finally,experiments on the synthetic dataset and six benchmark real-world datasets,including biomedical data,letter recognition digit data and face image data,demonstrate the encouraging performance of the proposed algorithm compared with state-of-the-art algorithms.展开更多
Improving short-term wind speed prediction accuracy and stability remains a challenge for wind forecasting researchers.This paper proposes a new variational mode decomposition(VMD)-attention-based spatio-temporal netw...Improving short-term wind speed prediction accuracy and stability remains a challenge for wind forecasting researchers.This paper proposes a new variational mode decomposition(VMD)-attention-based spatio-temporal network(VASTN)method that takes advantage of both temporal and spatial correlations of wind speed.First,VASTN is a hybrid wind speed prediction model that combines VMD,squeeze-and-excitation network(SENet),and attention mechanism(AM)-based bidirectional long short-term memory(BiLSTM).VASTN initially employs VMD to decompose the wind speed matrix into a series of intrinsic mode functions(IMF).Then,to extract the spatial features at the bottom of the model,each IMF employs an improved convolutional neural network algorithm based on channel AM,also known as SENet.Second,it combines BiLSTM and AM at the top layer to extract aggregated spatial features and capture temporal dependencies.Finally,VASTN accumulates the predictions of each IMF to obtain the predicted wind speed.This method employs VMD to reduce the randomness and instability of the original data before employing AM to improve prediction accuracy through mapping weight and parameter learning.Experimental results on real-world data demonstrate VASTN’s superiority over previous related algorithms.展开更多
基金the Science and Technology Project of State Grid Corporation of China under Grant 5400-202117142A-0-0-00the National Natural Science Foundation of China under Grant 62372242.
文摘As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power prediction is essential for algorithms like scheduling and optimization control.Based on the spatio-temporal features of Numerical Weather Prediction(NWP)data,it proposes the WVMD_DSN(Whale Optimization Algorithm,Variational Mode Decomposition,Dual Stream Network)model.The model first applies Pearson correlation coefficient(PCC)to choose some NWP features with strong correlation to wind power to form the feature set.Then,it decomposes the feature set using Variational Mode Decomposition(VMD)to eliminate the nonstationarity and obtains Intrinsic Mode Functions(IMFs).Here Whale Optimization Algorithm(WOA)is applied to optimise the key parameters of VMD,namely the number of mode components K and penalty factor a.Finally,incorporating attention mechanism(AM),Squeeze-Excitation Network(SENet),and Bidirectional Gated Recurrent Unit(BiGRU),it constructs the dual-stream network(DSN)for short-term wind power prediction.Comparative experiments demonstrate that the WVMD_DSN model outperforms existing baseline algorithms and exhibits good generalization performance.The relevant code is available at https://github.com/ruanyuyuan/Wind-power-forecast.git(accessed on 20 August 2024).
基金the National Natural Science Foundation of PRChina(42075130)Nari Technology Co.,Ltd.(4561655965)。
文摘Scene text detection is an important task in computer vision.In this paper,we present YOLOv5 Scene Text(YOLOv5ST),an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection.Our primary goal is to enhance inference speed without sacrificing significant detection accuracy,thereby enabling robust performance on resource-constrained devices like drones,closed-circuit television cameras,and other embedded systems.To achieve this,we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation,including replacing standard convolution with depth-wise convolution,adopting the C2 sequence module in place of C3,employing Spatial Pyramid Pooling Global(SPPG)instead of Spatial Pyramid Pooling Fast(SPPF)and integrating Bi-directional Feature Pyramid Network(BiFPN)into the neck.Experimental results demonstrate a remarkable 26%improvement in inference speed compared to the baseline,with only marginal reductions of 1.6%and 4.2%in mean average precision(mAP)at the intersection over union(IoU)thresholds of 0.5 and 0.5:0.95,respectively.Our work represents a significant advancement in scene text detection,striking a balance between speed and accuracy,making it well-suited for performance-constrained environments.
基金National Natural Science Foundation of China,Grant/Award Numbers:61673084,National Natural Science Foundation of ChinaThe Fundamental Research Foundation for Universities of Heilongjiang Province,Grant/Award Number:LGYC2018JC017。
文摘As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empirical analysis.Researchers in the field of machine learning have proved that random forest can form better judgements on this kind of problem,and it has an auxiliary role in the prediction of stock trend.This study uses historical trading data of four listed companies in the USA stock market,and the purpose of this study is to improve the performance of random forest model in medium-and long-term stock trend prediction.This study applies the exponential smoothing method to process the initial data,calculates the relevant technical indicators as the characteristics to be selected,and proposes the D-RF-RS method to optimize random forest.As the random forest is an ensemble learning model and is closely related to decision tree,D-RF-RS method uses a decision tree to screen the importance of features,and obtains the effective strong feature set of the model as input.Then,the parameter combination of the model is optimized through random parameter search.The experimental results show that the average accuracy of random forest is increased by 0.17 after the above process optimization,which is 0.18 higher than the average accuracy of light gradient boosting machine model.Combined with the performance of the ROC curve and Precision–Recall curve,the stability of the model is also guaranteed,which further demonstrates the advantages of random forest in medium-and long-term trend prediction of the stock market.
基金Supported by the National Key Research and Development Program of China(2016YFC0100300)the National Natural Science Foundation of China(61402371,61771369)+1 种基金the Natural Science Basic Research Plan in Shaanxi Province of China(2017JM6008)the Fundamental Research Funds for the Central Universities of China(3102017zy032,3102018zy020)
文摘Three high dimensional spatial standardization algorithms are used for diffusion tensor image(DTI)registration,and seven kinds of methods are used to evaluate their performances.Firstly,the template used in this paper was obtained by spatial transformation of 16 subjects by means of tensor-based standardization.Then,high dimensional standardization algorithms for diffusion tensor images,including fractional anisotropy(FA)based diffeomorphic registration algorithm,FA based elastic registration algorithm and tensor-based registration algorithm,were performed.Finally,7 kinds of evaluation methods,including normalized standard deviation,dyadic coherence,diffusion cross-correlation,overlap of eigenvalue-eigenvector pairs,Euclidean distance of diffusion tensor,and Euclidean distance of the deviatoric tensor and deviatoric of tensors,were used to qualitatively compare and summarize the above standardization algorithms.Experimental results revealed that the high-dimensional tensor-based standardization algorithms perform well and can maintain the consistency of anatomical structures.
基金Fundamental Research Foundation for Universities of Heilongjiang Province,Grant/Award Number:LGYC2018JQ003。
文摘With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry.To improve the effectiveness of stock trend prediction and solve the problems in time series data processing,this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index.Meanwhile,in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge,this paper combines the deep forest model to train the stock data separately.The experimental results show that(1)the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit(GRU)model when the un-fuzzy index-adjusted dataset is used as features for input,(2)the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input,(3)the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and(4)the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.
基金National Basic Research Program of China under Grant No. 2011CB302600National Natural Science Foundation of China under Grant No. 90818028,No. 61003226National Science Fund for Distinguished Young Scholars under Grant No. 60625203
文摘The mutual-interference phenomenon among multiple applications delivered as services through Cloud Services Delivery Network(CSDN)influences their QoS seriously.In order to deploy multiple applications dependably and efficiently,we propose the Multiple Applications Co-Exist(MACE)method.MACE classifies multiple applications into different types and deploys them using isolation to some extent.Meanwhile,resource static allocation,dynamic supplement and resource reserved mechanism to minimize mutual-interference and maximize resource utilization are designed.After MACE is applied to a real large-scale CSDN and evaluated through 6-month measurement,we find that the CSDN load is more balanced,the bandwidth utilization increases by about 20%,the multiple applications'potential statistical multiplexing ratio decreases from 12% to 5%,and the number of complaint events affecting the dependability of CSDN services caused by multiple applications'mutual-interference has dropped to 0.Obviously,MACE offers a tradeoff and improvement for the dependability and efficiency goals of CSDN.
基金supported by a grant from the Project "Multifunctional mobile phone R & D and industrialization of the Internet of things" supported by the Project of the Provincial Department of research (2011A090200008)partly supported by National Science and Technology Major Project (No. 2010ZX07102-006)+3 种基金the National Basic Research Program of China (973 Program) (No. 2011CB505402)the Major Program of the National Natural Science Foundation of China (No. 61170117)the National Natural Science Foundation of China (No.61432004)the National Key Research and Development Program (No.2016YFB1001404)
文摘Internet of things(IoT) imposes new challenges on service composition as it is difficult to manage a quick instantiation of a complex services from a growing number of dynamic candidate services. A cross-modified Artificial Bee Colony Algorithm(CMABC) is proposed to achieve the optimal solution services in an acceptable time and high accuracy. Firstly, web service instantiation model was established. What is more, to overcome the problem of discrete and chaotic solution space, the global optimal solution was used to accelerate convergence rate by imitating the cross operation of Genetic algorithm(GA). The simulation experiment result shows that CMABC exhibited faster convergence speed and better convergence accuracy than some other intelligent optimization algorithms.
基金Supported by the National Natural Science Foundation of China(61100156)the National 12th Five-Year Plan Item of China(513160702)the Fundamental Research Funds for the Central Universities(JB150317,JB140311,K5051303014)
文摘A novel attribute-based framework is proposed to tackle the problem of halftone water- marking in combination of the spatial/transformation domain. The challenge is that the host image is continuous, while the watermarked halftone is bi-level. To search for a solution, an attribute image is defined as a good connection between the original grayscale image and its halftone image. When the attribute image is used as a watermark carrier, it helps to fred the watermarked halftone efficiently by solving a constrained modified direct binary search problem. Experimental results demonstrate that the proposed scheme in comparison with other similar methods maintains high watermark capacity with good image quality, high robustness, processing efficiency and easy decoding. Especially it has a good performance in printing application.
基金Sponsored by the Major Program of National Natural Science Foundation of China(Grant No.13&ZD162)the Applied Basic Research Programs of China National Textile and Apparel Council(Grant No.J201509)
文摘Unsupervised feature selection has become an important and challenging problem faced with vast amounts of unlabeled and high-dimension data in machine learning. We propose a novel unsupervised feature selection method using Structured Self-Representation( SSR) by simultaneously taking into account the selfrepresentation property and local geometrical structure of features. Concretely,according to the inherent selfrepresentation property of features,the most representative features can be selected. Mean while,to obtain more accurate results,we explore local geometrical structure to constrain the representation coefficients to be close to each other if the features are close to each other. Furthermore,an efficient algorithm is presented for optimizing the objective function. Finally,experiments on the synthetic dataset and six benchmark real-world datasets,including biomedical data,letter recognition digit data and face image data,demonstrate the encouraging performance of the proposed algorithm compared with state-of-the-art algorithms.
基金supported by the undergraduate training program for innovation and entrepreneurship of NUIST(XJDC202110300239).
文摘Improving short-term wind speed prediction accuracy and stability remains a challenge for wind forecasting researchers.This paper proposes a new variational mode decomposition(VMD)-attention-based spatio-temporal network(VASTN)method that takes advantage of both temporal and spatial correlations of wind speed.First,VASTN is a hybrid wind speed prediction model that combines VMD,squeeze-and-excitation network(SENet),and attention mechanism(AM)-based bidirectional long short-term memory(BiLSTM).VASTN initially employs VMD to decompose the wind speed matrix into a series of intrinsic mode functions(IMF).Then,to extract the spatial features at the bottom of the model,each IMF employs an improved convolutional neural network algorithm based on channel AM,also known as SENet.Second,it combines BiLSTM and AM at the top layer to extract aggregated spatial features and capture temporal dependencies.Finally,VASTN accumulates the predictions of each IMF to obtain the predicted wind speed.This method employs VMD to reduce the randomness and instability of the original data before employing AM to improve prediction accuracy through mapping weight and parameter learning.Experimental results on real-world data demonstrate VASTN’s superiority over previous related algorithms.
