Because of an unfortunate mistake during the production of this article,the Acknowledgements have been omitted.The Acknowledgements are added as follows:Sasan YAZDANI would like to thank the Scientific and Technologic...Because of an unfortunate mistake during the production of this article,the Acknowledgements have been omitted.The Acknowledgements are added as follows:Sasan YAZDANI would like to thank the Scientific and Technological Research Council of Turkey(TÜB˙ITAK)for receiving financial support for this work through the 2221 Fellowship Program for Visiting Scientists and Scientists on Sabbatical Leave(Grant ID:E 21514107-115.02-228864).Sasan YAZDANI also expresses his gratitude to Sahand University of Technology for granting him sabbatical leave to facilitate the completion of this research.展开更多
虽然异构计算系统的应用可以加快神经网络参数的处理,但系统功耗也随之剧增。良好的功耗预测方法是异构系统优化功耗和处理多类型工作负载的基础,基于此,通过改进多层感知机-注意力模型,提出一种面向CPU/GPU异构计算系统多类型工作负载...虽然异构计算系统的应用可以加快神经网络参数的处理,但系统功耗也随之剧增。良好的功耗预测方法是异构系统优化功耗和处理多类型工作负载的基础,基于此,通过改进多层感知机-注意力模型,提出一种面向CPU/GPU异构计算系统多类型工作负载的功耗预测算法。首先,考虑服务器功耗与系统特征,建立一种基于特征的工作负载功耗模型;其次,针对现有的功耗预测算法不能解决系统特征与系统功耗之间的长程依赖的问题,提出一种改进的基于多层感知机-注意力模型的功耗预测算法Prophet,该算法改进多层感知机实现各个时刻的系统特征的提取,并使用注意力机制综合这些特征,从而有效解决系统特征与系统功耗之间的长程依赖问题;最后,在实际系统中开展相关实验,将所提算法分别与MLSTM_PM(Power consumption Model based on Multi-layer Long Short-Term Memory)和ENN_PM(Power consumption Model based on Elman Neural Network)等功耗预测算法对比。实验结果表明,Prophet具有较高的预测精准性,与MLSTM_PM算法相比,在工作负载blk、memtest和busspd上将平均相对误差(MRE)分别降低了1.22、1.01和0.93个百分点,并且具有较低的复杂度,表明了所提算法的有效性及可行性。展开更多
为保证复杂仿真系统达到可信度要求和缩短开发周期,应在构建复杂仿真系统之初确定各个仿真子系统的可信度。为此,提出一种复杂仿真系统可信度智能分配方法,在明确复杂仿真系统总体可信度的情况下获取各仿真子系统的可信度分配结果。根...为保证复杂仿真系统达到可信度要求和缩短开发周期,应在构建复杂仿真系统之初确定各个仿真子系统的可信度。为此,提出一种复杂仿真系统可信度智能分配方法,在明确复杂仿真系统总体可信度的情况下获取各仿真子系统的可信度分配结果。根据复杂仿真系统的组成和结构,提出基于多层成对马尔可夫随机场(multi-layer pairwise Markov random field,ML-PMRF)的复杂仿真系统可信度分配模型构建方法。基于最大后验推理和离散萤火虫群优化,提出一种面向ML-PMRF的智能推理方法。通过实例应用及对比实验,验证了所提方法的有效性和合理性。展开更多
Under the scenario of dense targets in clutter, a multi-layer optimal data correlation algorithm is proposed. This algorithm eliminates a large number of false location points from the assignment process by rough corr...Under the scenario of dense targets in clutter, a multi-layer optimal data correlation algorithm is proposed. This algorithm eliminates a large number of false location points from the assignment process by rough correlations before we calculate the correlation cost, so it avoids the operations for the target state estimate and the calculation of the correlation cost for the false correlation sets. In the meantime, with the elimination of these points in the rough correlation, the disturbance from the false correlations in the assignment process is decreased, so the data correlation accuracy is improved correspondingly. Complexity analyses of the new multi-layer optimal algorithm and the traditional optimal assignment algorithm are given. Simulation results show that the new algorithm is feasible and effective.展开更多
Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributio...Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.展开更多
文摘Because of an unfortunate mistake during the production of this article,the Acknowledgements have been omitted.The Acknowledgements are added as follows:Sasan YAZDANI would like to thank the Scientific and Technological Research Council of Turkey(TÜB˙ITAK)for receiving financial support for this work through the 2221 Fellowship Program for Visiting Scientists and Scientists on Sabbatical Leave(Grant ID:E 21514107-115.02-228864).Sasan YAZDANI also expresses his gratitude to Sahand University of Technology for granting him sabbatical leave to facilitate the completion of this research.
文摘虽然异构计算系统的应用可以加快神经网络参数的处理,但系统功耗也随之剧增。良好的功耗预测方法是异构系统优化功耗和处理多类型工作负载的基础,基于此,通过改进多层感知机-注意力模型,提出一种面向CPU/GPU异构计算系统多类型工作负载的功耗预测算法。首先,考虑服务器功耗与系统特征,建立一种基于特征的工作负载功耗模型;其次,针对现有的功耗预测算法不能解决系统特征与系统功耗之间的长程依赖的问题,提出一种改进的基于多层感知机-注意力模型的功耗预测算法Prophet,该算法改进多层感知机实现各个时刻的系统特征的提取,并使用注意力机制综合这些特征,从而有效解决系统特征与系统功耗之间的长程依赖问题;最后,在实际系统中开展相关实验,将所提算法分别与MLSTM_PM(Power consumption Model based on Multi-layer Long Short-Term Memory)和ENN_PM(Power consumption Model based on Elman Neural Network)等功耗预测算法对比。实验结果表明,Prophet具有较高的预测精准性,与MLSTM_PM算法相比,在工作负载blk、memtest和busspd上将平均相对误差(MRE)分别降低了1.22、1.01和0.93个百分点,并且具有较低的复杂度,表明了所提算法的有效性及可行性。
文摘为保证复杂仿真系统达到可信度要求和缩短开发周期,应在构建复杂仿真系统之初确定各个仿真子系统的可信度。为此,提出一种复杂仿真系统可信度智能分配方法,在明确复杂仿真系统总体可信度的情况下获取各仿真子系统的可信度分配结果。根据复杂仿真系统的组成和结构,提出基于多层成对马尔可夫随机场(multi-layer pairwise Markov random field,ML-PMRF)的复杂仿真系统可信度分配模型构建方法。基于最大后验推理和离散萤火虫群优化,提出一种面向ML-PMRF的智能推理方法。通过实例应用及对比实验,验证了所提方法的有效性和合理性。
基金This project was supported by the National Natural Science Foundation of China (60672139, 60672140)the Excellent Ph.D. Paper Author Foundation of China (200237)the Natural Science Foundation of Shandong (2005ZX01).
文摘Under the scenario of dense targets in clutter, a multi-layer optimal data correlation algorithm is proposed. This algorithm eliminates a large number of false location points from the assignment process by rough correlations before we calculate the correlation cost, so it avoids the operations for the target state estimate and the calculation of the correlation cost for the false correlation sets. In the meantime, with the elimination of these points in the rough correlation, the disturbance from the false correlations in the assignment process is decreased, so the data correlation accuracy is improved correspondingly. Complexity analyses of the new multi-layer optimal algorithm and the traditional optimal assignment algorithm are given. Simulation results show that the new algorithm is feasible and effective.
文摘Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.
