This paper presents an improved BP algorithm. The approach can reduce the amount of computation by using the logarithmic objective function. The learning rate μ(k) per iteration is determined by dynamic o...This paper presents an improved BP algorithm. The approach can reduce the amount of computation by using the logarithmic objective function. The learning rate μ(k) per iteration is determined by dynamic optimization method to accelerate the convergence rate. Since the determination of the learning rate in the proposed BP algorithm only uses the obtained first order derivatives in standard BP algorithm(SBP), the scale of computational and storage burden is like that of SBP algorithm,and the convergence rate is remarkably accelerated. Computer simulations demonstrate the effectiveness of the proposed algorithm展开更多
For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and de...For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.展开更多
A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely no...A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely not all jobs can be scheduled within specified scheduling horizons due to the limited machine capacity. The objective is thus to maximize the overall profits of processed jobs while respecting machine constraints. A first-in- first-out heuristic is applied to find an initial solution, and then a large neighborhood search procedure is employed to relax and re- optimize cumbersome solutions. A machine learning mechanism is also introduced to converge on the most efficient neighborhoods for the problem. Extensive computational results are presented based on data from an application involving the daily observation scheduling of a fleet of earth observing satellites. The method rapidly solves most problem instances to optimal or near optimal and shows a robust performance in sensitive analysis.展开更多
Previous studies have found that drivers’physiological conditions can deteriorate under noise conditions,which poses a potential hazard when driving.As a result,it is crucial to identify the status of drivers when ex...Previous studies have found that drivers’physiological conditions can deteriorate under noise conditions,which poses a potential hazard when driving.As a result,it is crucial to identify the status of drivers when exposed to different noises.However,such explo-rations are rarely discussed with short-term physiological indicators,especially for rail transit drivers.In this study,an experiment involving 42 railway transit drivers was conducted with a driving simulator to assess the impact of noise on drivers’physiological responses.Considering the individuals’heterogeneity,this study introduced drivers’noise annoyance to measure their self-noise-adaption.The variances of drivers’heart rate variability(HRV)along with different noise adaptions are explored when exposed to different noise conditions.Several machine learning approaches(support vector machine,K-nearest neighbour and random forest)were then used to classify their physiological status under different noise conditions according to the HRV and drivers’self-noise adaptions.Results indicate that the volume of traffic noise negatively affects drivers’performance in their routines.Drivers with different noise adaptions but exposed to a fixed noise were found with discrepant HRV,demonstrating that noise adaption is highly associated with drivers’physiological status under noises.It is also found that noise adaption inclusion could raise the accuracy of classifications.Overall,the random forests classifier performed the best in identifying the physiological status when exposed to noise conditions for drivers with different noise adaptions.展开更多
由于跟踪过程目标不规则形变的影响,采用固定纵横比的尺度模型无法精确地估计目标的尺度.为解决该问题,本文提出基于纵横比自适应的相关滤波跟踪算法.基于fDSST(fast Discriminative Scale Space Tracking)算法,训练学习纵横比模型,更...由于跟踪过程目标不规则形变的影响,采用固定纵横比的尺度模型无法精确地估计目标的尺度.为解决该问题,本文提出基于纵横比自适应的相关滤波跟踪算法.基于fDSST(fast Discriminative Scale Space Tracking)算法,训练学习纵横比模型,更新目标的纵横比,获取更精确的目标尺度.在此基础上,本文设计了平滑修正方案以及学习率自适应机制,可以有效地缓解因目标出现遮挡导致的模型漂移问题.在OTB100、VOT2016和VOT2018数据集上与其他跟踪算法进行对比实验,结果表明本文算法改善了基准算法的性能,特别是在OTB100上的总体准确率和成功率比fDSST提高了9.6%和6.2%.展开更多
文摘This paper presents an improved BP algorithm. The approach can reduce the amount of computation by using the logarithmic objective function. The learning rate μ(k) per iteration is determined by dynamic optimization method to accelerate the convergence rate. Since the determination of the learning rate in the proposed BP algorithm only uses the obtained first order derivatives in standard BP algorithm(SBP), the scale of computational and storage burden is like that of SBP algorithm,and the convergence rate is remarkably accelerated. Computer simulations demonstrate the effectiveness of the proposed algorithm
基金Supported by the National Natural Science Foundation of China (60904018, 61203040)the Natural Science Foundation of Fujian Province of China (2009J05147, 2011J01352)+1 种基金the Foundation for Distinguished Young Scholars of Higher Education of Fujian Province of China (JA10004)the Science Research Foundation of Huaqiao University (09BS617)
文摘For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.
基金supported by the National Natural Science Foundation of China (7060103570801062)
文摘A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely not all jobs can be scheduled within specified scheduling horizons due to the limited machine capacity. The objective is thus to maximize the overall profits of processed jobs while respecting machine constraints. A first-in- first-out heuristic is applied to find an initial solution, and then a large neighborhood search procedure is employed to relax and re- optimize cumbersome solutions. A machine learning mechanism is also introduced to converge on the most efficient neighborhoods for the problem. Extensive computational results are presented based on data from an application involving the daily observation scheduling of a fleet of earth observing satellites. The method rapidly solves most problem instances to optimal or near optimal and shows a robust performance in sensitive analysis.
基金supported by the Sichuan Mineral Resources Research Center(Gr ant No.SCKCZY2023-ZC010)the Gansu Tec h-nological Innovation Guidance Plan(Grant No.22CX8JA142)+2 种基金the Sc hool Enter prise Cooperation Program of Southwest Jiao-tong Univ ersity(Grant No.LG-YY-CW-2020010)the Open Fund of Key Laboratory of Flight Techniques and Flight Safety(Grant No.FZ2021KF05)the Key Research Base of Humanistic and Social Sciences of Deyang-Psychology and Behavior Science Research Center(Grant No.XLYXW2023202).
文摘Previous studies have found that drivers’physiological conditions can deteriorate under noise conditions,which poses a potential hazard when driving.As a result,it is crucial to identify the status of drivers when exposed to different noises.However,such explo-rations are rarely discussed with short-term physiological indicators,especially for rail transit drivers.In this study,an experiment involving 42 railway transit drivers was conducted with a driving simulator to assess the impact of noise on drivers’physiological responses.Considering the individuals’heterogeneity,this study introduced drivers’noise annoyance to measure their self-noise-adaption.The variances of drivers’heart rate variability(HRV)along with different noise adaptions are explored when exposed to different noise conditions.Several machine learning approaches(support vector machine,K-nearest neighbour and random forest)were then used to classify their physiological status under different noise conditions according to the HRV and drivers’self-noise adaptions.Results indicate that the volume of traffic noise negatively affects drivers’performance in their routines.Drivers with different noise adaptions but exposed to a fixed noise were found with discrepant HRV,demonstrating that noise adaption is highly associated with drivers’physiological status under noises.It is also found that noise adaption inclusion could raise the accuracy of classifications.Overall,the random forests classifier performed the best in identifying the physiological status when exposed to noise conditions for drivers with different noise adaptions.
文摘由于跟踪过程目标不规则形变的影响,采用固定纵横比的尺度模型无法精确地估计目标的尺度.为解决该问题,本文提出基于纵横比自适应的相关滤波跟踪算法.基于fDSST(fast Discriminative Scale Space Tracking)算法,训练学习纵横比模型,更新目标的纵横比,获取更精确的目标尺度.在此基础上,本文设计了平滑修正方案以及学习率自适应机制,可以有效地缓解因目标出现遮挡导致的模型漂移问题.在OTB100、VOT2016和VOT2018数据集上与其他跟踪算法进行对比实验,结果表明本文算法改善了基准算法的性能,特别是在OTB100上的总体准确率和成功率比fDSST提高了9.6%和6.2%.
