深度学习在射频指纹识别(Radio Frequency Fingerprinting,RFF)中的应用常受限于繁琐且依赖人工经验的超参数调整过程。Optuna框架提供了替代方案,但其策略易产生大量无效采样点并过度消耗计算资源于非关键区域。为解决此问题,本文提出...深度学习在射频指纹识别(Radio Frequency Fingerprinting,RFF)中的应用常受限于繁琐且依赖人工经验的超参数调整过程。Optuna框架提供了替代方案,但其策略易产生大量无效采样点并过度消耗计算资源于非关键区域。为解决此问题,本文提出一种基于Optuna框架的渐进式参数空间加权调节(PWM)算法,该算法通过分阶段优化策略动态引导搜索方向,首先利用历史试验的统计相关性自适应收缩参数范围,其次结合混合权重机制强化关键参数优化,最后用固定最优分类参数和安全约束的方式加速收敛,得以改进Optuna框架。通过实验结果表明PWM-Optuna集成系统既有效替代了人工超参数调整,也能够提高射频指纹识别效率以及缩短训练时间,为模型快速收敛与性能提升提供了可靠的技术支撑。展开更多
Accurate prediction of electricity price(EP)is crucial for energy utilities and gridoperators for enhancing the energy trading,grid stability studies,resource allocationsand pricing strategies,thereby improving the ov...Accurate prediction of electricity price(EP)is crucial for energy utilities and gridoperators for enhancing the energy trading,grid stability studies,resource allocationsand pricing strategies,thereby improving the overall grid reliability,efficiency,and cost-effectiveness.This study introduces a novel D3Net model for half-hourly EP prediction,integrating Seasonal-Trend decomposition using LOESS(STL)and Variational ModeDecomposition(VMD)with Multi-Layer Perceptron(MLP),Random Forest Regression(RFR),and Tabular Neural Network(TabNet).The methodology involves applying STL tothe EP time-series to extract trend,seasonal,and residual components.The trend ispredicted using an MLP model,the seasonal component is further decomposed withVMD into 20 Variational Mode Functions(VMFs)and predicted using an RFR model,andthe residual component is decomposed with VMD and predicted using the TabNet model.Input features are identified using the Partial Autocorrelation Function,and models areoptimized using the Optuna algorithm.The final prediction combines the trend,seasonal,and residual components'predictions.Explainable Artificial Intelligence(xAI)methodswere used to enhance model interpretability and trustworthiness,with optimization viathe Optuna algorithm.Comparative analysis with seven standalone and seven decomposition-based models confirmed the superior performance and statisticalsignificance of the D3Net model.The D3Net achieved the highest global performanceindicator for South Australia(GPI≈11.068)and Tasmania(GPI≈12.206).Theseresults validate the efficacy and statistical significance of the D3Net model,demonstrating the viability of integrating STL and VMD decomposition approaches withMLP,RFR,and TabNet for EP prediction.展开更多
文摘深度学习在射频指纹识别(Radio Frequency Fingerprinting,RFF)中的应用常受限于繁琐且依赖人工经验的超参数调整过程。Optuna框架提供了替代方案,但其策略易产生大量无效采样点并过度消耗计算资源于非关键区域。为解决此问题,本文提出一种基于Optuna框架的渐进式参数空间加权调节(PWM)算法,该算法通过分阶段优化策略动态引导搜索方向,首先利用历史试验的统计相关性自适应收缩参数范围,其次结合混合权重机制强化关键参数优化,最后用固定最优分类参数和安全约束的方式加速收敛,得以改进Optuna框架。通过实验结果表明PWM-Optuna集成系统既有效替代了人工超参数调整,也能够提高射频指纹识别效率以及缩短训练时间,为模型快速收敛与性能提升提供了可靠的技术支撑。
文摘Accurate prediction of electricity price(EP)is crucial for energy utilities and gridoperators for enhancing the energy trading,grid stability studies,resource allocationsand pricing strategies,thereby improving the overall grid reliability,efficiency,and cost-effectiveness.This study introduces a novel D3Net model for half-hourly EP prediction,integrating Seasonal-Trend decomposition using LOESS(STL)and Variational ModeDecomposition(VMD)with Multi-Layer Perceptron(MLP),Random Forest Regression(RFR),and Tabular Neural Network(TabNet).The methodology involves applying STL tothe EP time-series to extract trend,seasonal,and residual components.The trend ispredicted using an MLP model,the seasonal component is further decomposed withVMD into 20 Variational Mode Functions(VMFs)and predicted using an RFR model,andthe residual component is decomposed with VMD and predicted using the TabNet model.Input features are identified using the Partial Autocorrelation Function,and models areoptimized using the Optuna algorithm.The final prediction combines the trend,seasonal,and residual components'predictions.Explainable Artificial Intelligence(xAI)methodswere used to enhance model interpretability and trustworthiness,with optimization viathe Optuna algorithm.Comparative analysis with seven standalone and seven decomposition-based models confirmed the superior performance and statisticalsignificance of the D3Net model.The D3Net achieved the highest global performanceindicator for South Australia(GPI≈11.068)and Tasmania(GPI≈12.206).Theseresults validate the efficacy and statistical significance of the D3Net model,demonstrating the viability of integrating STL and VMD decomposition approaches withMLP,RFR,and TabNet for EP prediction.
