A general method of constructing proxy blind signature is proposed based on multilinear transform. Based on this method, the four proxy blind signature schemes are correspondently generated with four different signatu...A general method of constructing proxy blind signature is proposed based on multilinear transform. Based on this method, the four proxy blind signature schemes are correspondently generated with four different signature equations, and each of them has four forms of variations of signs. Hence there are sixteen signatures in all, and all of them are proxy stronglyblind signature schemes. Furthermore, the two degenerated situations of multi-linear transform are discussed. Their corresponding proxy blind signature schemes are shown, too. But some schemes come from one of these degenerate situations are proxy weakly-blind signature scheme.The security for proposed scheme is analyzed in details. The results indicate that these signature schemes have many good properties such as unforgeability, distinguish-ability of proxy signature,non-repudiation and extensive value of application etc.展开更多
Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting(STLF).Existing forecasting models,unfortunately,are often inaccurate and computationally demanding.To overcome these...Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting(STLF).Existing forecasting models,unfortunately,are often inaccurate and computationally demanding.To overcome these challenges,a novel hybrid model,combining both linear regression and machine learning techniques,is proposed in this study.The hybrid model,MLR-LSTM-FFNN,captures both temporal and non-linear de-pendencies in load data by integrating multi-linear regression(MLR)with long short-term memory(LSTM)networks and feed-forward neural networks(FFNN).Using datasets from Qatar,with 5 min,15 min,30 min,and 1 h time intervals and from Panama City with a 1 h interval,experiments were conducted to thoroughly test the robustness of the model.The results showed that the MLR-LSTM-FFNN hybrid model outperformed the baseline and state-of-the-art hybrid models for each of the datasets,in terms of lower RMSE,MAE,and MAPE values along with a faster training time.This superior performance across different datasets underscores the model’s scal-ability and reliability as an STLF approach,providing a practical solution to energy demand prediction tasks.The improvement in short-term forecasting accuracy provides utilities with a practical tool to optimize demand-side management,reduce operational costs,and enhance grid reliability.展开更多
简单线性模型的时间序列预测质量通常超过Transformer等深度模型;而在具有大量通道的数据集上,深度模型尤其是多层感知器(MLP)的性能反而可超过简单线性模型。针对简单线性模型和MLP在时间序列预测中的误差功率谱差异,提出一种基于MLP...简单线性模型的时间序列预测质量通常超过Transformer等深度模型;而在具有大量通道的数据集上,深度模型尤其是多层感知器(MLP)的性能反而可超过简单线性模型。针对简单线性模型和MLP在时间序列预测中的误差功率谱差异,提出一种基于MLP的高频增强型时间序列预测模型HiFNet(High-Frequency Network)。首先,利用MLP在低频段的拟合能力;其次,通过自适应序列分解(ASD)模块及分组线性层解决MLP高频段易过拟合以及通道独立策略不能有效应对通道冗余的问题,从而增强MLP在高频段的鲁棒性;最后,对HiFNet在气象、电力和交通等领域的标准数据集上进行实验。结果表明:HiFNet的均方误差(MSE)在最佳情况下相较于NLinear、RLinear、SegRNN(Segment Recurrent Neural Network)和PatchTST(Patch Time Series Transformer)分别降低了23.6%、10.0%、35.1%和6.5%,而分组线性层通过学习通道相关性的低秩表达减轻了通道冗余的影响。展开更多
基金Supported by the Fundamental Research Program of Commission of Science Technology and Industry for National Defence (No.J1300D004)
文摘A general method of constructing proxy blind signature is proposed based on multilinear transform. Based on this method, the four proxy blind signature schemes are correspondently generated with four different signature equations, and each of them has four forms of variations of signs. Hence there are sixteen signatures in all, and all of them are proxy stronglyblind signature schemes. Furthermore, the two degenerated situations of multi-linear transform are discussed. Their corresponding proxy blind signature schemes are shown, too. But some schemes come from one of these degenerate situations are proxy weakly-blind signature scheme.The security for proposed scheme is analyzed in details. The results indicate that these signature schemes have many good properties such as unforgeability, distinguish-ability of proxy signature,non-repudiation and extensive value of application etc.
基金support from the Qatar National Research Fund through grant AICC05-0508-230001(Solar Trade(ST):An Equitable and Efficient Blockchain-Enabled Renewable Energy Ecosystem-“Oppor-tunities for Fintech to Scale up Green Finance for Clean Energy”)and from Qatar Environment and Energy Research Institute is gratefully acknowledged.
文摘Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting(STLF).Existing forecasting models,unfortunately,are often inaccurate and computationally demanding.To overcome these challenges,a novel hybrid model,combining both linear regression and machine learning techniques,is proposed in this study.The hybrid model,MLR-LSTM-FFNN,captures both temporal and non-linear de-pendencies in load data by integrating multi-linear regression(MLR)with long short-term memory(LSTM)networks and feed-forward neural networks(FFNN).Using datasets from Qatar,with 5 min,15 min,30 min,and 1 h time intervals and from Panama City with a 1 h interval,experiments were conducted to thoroughly test the robustness of the model.The results showed that the MLR-LSTM-FFNN hybrid model outperformed the baseline and state-of-the-art hybrid models for each of the datasets,in terms of lower RMSE,MAE,and MAPE values along with a faster training time.This superior performance across different datasets underscores the model’s scal-ability and reliability as an STLF approach,providing a practical solution to energy demand prediction tasks.The improvement in short-term forecasting accuracy provides utilities with a practical tool to optimize demand-side management,reduce operational costs,and enhance grid reliability.
文摘简单线性模型的时间序列预测质量通常超过Transformer等深度模型;而在具有大量通道的数据集上,深度模型尤其是多层感知器(MLP)的性能反而可超过简单线性模型。针对简单线性模型和MLP在时间序列预测中的误差功率谱差异,提出一种基于MLP的高频增强型时间序列预测模型HiFNet(High-Frequency Network)。首先,利用MLP在低频段的拟合能力;其次,通过自适应序列分解(ASD)模块及分组线性层解决MLP高频段易过拟合以及通道独立策略不能有效应对通道冗余的问题,从而增强MLP在高频段的鲁棒性;最后,对HiFNet在气象、电力和交通等领域的标准数据集上进行实验。结果表明:HiFNet的均方误差(MSE)在最佳情况下相较于NLinear、RLinear、SegRNN(Segment Recurrent Neural Network)和PatchTST(Patch Time Series Transformer)分别降低了23.6%、10.0%、35.1%和6.5%,而分组线性层通过学习通道相关性的低秩表达减轻了通道冗余的影响。
