Let m and n be fixed, positive integers and P a space composed of real polynomials in m variables. The authors study functions f ： R →R which map Gram matrices, based upon n points of R^m, into matrices, which are n...Let m and n be fixed, positive integers and P a space composed of real polynomials in m variables. The authors study functions f ： R →R which map Gram matrices, based upon n points of R^m, into matrices, which are nonnegative definite with respect to P Among other things, the authors discuss continuity, differentiability, convexity, and convexity in the sense of Jensen, of such functions展开更多
对于用能数据不足的综合能源系统,借助相似系统的丰富数据可以为其建立高精度的多元负荷预测模型,然而,受数据安全等因素的限制,很多系统并不愿意共享自身数据。联邦学习为处理隐私保护下的少数据综合能源多元负荷预测问题提供了一个重...对于用能数据不足的综合能源系统,借助相似系统的丰富数据可以为其建立高精度的多元负荷预测模型,然而,受数据安全等因素的限制,很多系统并不愿意共享自身数据。联邦学习为处理隐私保护下的少数据综合能源多元负荷预测问题提供了一个重要的思路,但是现有方法依然存在相似参与方识别精度不高等不足。鉴于此,本文提出一种融合联邦学习和长短期记忆网络(long short-term memory,LSTM)的少数据综合能源多元负荷预测方法(multitask learning based on shared dot product confidentiality under federated learning,MT-SDPFL)。首先,给出一种基于共享向量点积保密协议的相似参与方识别方法,用来从诸多可用的综合能源系统中选出最为相似的参与方;接着,使用参数共享联邦学习算法对选中的各参与方联合训练,结合LSTM和finetune技术建立每个参与方的多元负荷预测模型。将所提方法应用于多个实际能源系统,实验结果表明,该方法可以在数据稀疏的情况下取得高精度的多源负荷预测结果。展开更多
Dot enzyme-linked immunosorbent assay （dot-ELISA）, indirect ELISA and Westem blot were performed to detect the virulent protease secreted by Vibrio anguillarum which was isolated from the diseased left-eyed flounder...Dot enzyme-linked immunosorbent assay （dot-ELISA）, indirect ELISA and Westem blot were performed to detect the virulent protease secreted by Vibrio anguillarum which was isolated from the diseased left-eyed flounder, Paralichthys olivaceous. Sensitivity results showed that dot-ELISA is a more sensitive, rapid and simple technique for the protease detection. The minimal detectable amount of protease is about 7 pg in the dot-ELISA test, while 7.8 ng in the indirect ELISA and 6.25 ng in the Westem blot respectively. Protease could be detected 2 h after incubation of V. anguillarum in the 2216E liquid medium but enzyme activity was very low at that period. From 6 to 12 h, the amount and enzyme activity of protease increased markedly and reached maximum at stationary phase. Analysis of serum samples periodically collected from the infected flounders showed that after 2 h of infection by V. anguillarum, the pathogenic bacteria could be detected in the blood of the infected flounders but no protease was found. It was 5-6 h after infection that the protease was detected in blood and then the amount increased as infection advanced. Quantitative detection of protease either incubation in the medium or from the blood of infected flounders could be accomplished in virtue of positive controls of quantificational protease standards （＂marker＂） so that the alterations ofprotease secretion both in vitro and in vivo could be understood generally. In addition, the indirect ELISA and dot-ELISA were also performed to detect V. anguillarum cells. Results indicated that the sensitivity of indirect ELISA to bacteria cells is higher than that of the dot-ELISA, and that the minimal detectable amount is approximately 10^4 cell/mL in the indirect ELISA, while 10^5 cell/mL in the dot-ELISA.展开更多
We investigate the time evolution of entanglement between two quantum dots in an engineered vacuum environment such that a metallic nanoring having a surface plasmon is placed near the quantum dots. Such engineering i...We investigate the time evolution of entanglement between two quantum dots in an engineered vacuum environment such that a metallic nanoring having a surface plasmon is placed near the quantum dots. Such engineering in environment results in oscillations in entanglement dynamics of the quantum dots systems. With proper adjustment of the separation between the quantum dots, entanglement decay can be stabilized and preserved for longer time than its decay without the surface plasmons interactions.展开更多
Spam emails pose a threat to individuals. The proliferation of spam emails daily has rendered traditional machine learning and deep learning methods for screening them ineffective and inefficient. In our research, we ...Spam emails pose a threat to individuals. The proliferation of spam emails daily has rendered traditional machine learning and deep learning methods for screening them ineffective and inefficient. In our research, we employ deep neural networks like RNN, LSTM, and GRU, incorporating attention mechanisms such as Bahdanua, scaled dot product (SDP), and Luong scaled dot product self-attention for spam email filtering. We evaluate our approach on various datasets, including Trec spam, Enron spam emails, SMS spam collections, and the Ling spam dataset, which constitutes a substantial custom dataset. All these datasets are publicly available. For the Enron dataset, we attain an accuracy of 99.97% using LSTM with SDP self-attention. Our custom dataset exhibits the highest accuracy of 99.01% when employing GRU with SDP self-attention. The SMS spam collection dataset yields a peak accuracy of 99.61% with LSTM and SDP attention. Using the GRU (Gated Recurrent Unit) alongside Luong and SDP (Structured Self-Attention) attention mechanisms, the peak accuracy of 99.89% in the Ling spam dataset. For the Trec spam dataset, the most accurate results are achieved using Luong attention LSTM, with an accuracy rate of 99.01%. Our performance analyses consistently indicate that employing the scaled dot product attention mechanism in conjunction with gated recurrent neural networks (GRU) delivers the most effective results. In summary, our research underscores the efficacy of employing advanced deep learning techniques and attention mechanisms for spam email filtering, with remarkable accuracy across multiple datasets. This approach presents a promising solution to the ever-growing problem of spam emails.展开更多
文摘Let m and n be fixed, positive integers and P a space composed of real polynomials in m variables. The authors study functions f ： R →R which map Gram matrices, based upon n points of R^m, into matrices, which are nonnegative definite with respect to P Among other things, the authors discuss continuity, differentiability, convexity, and convexity in the sense of Jensen, of such functions
文摘对于用能数据不足的综合能源系统,借助相似系统的丰富数据可以为其建立高精度的多元负荷预测模型,然而,受数据安全等因素的限制,很多系统并不愿意共享自身数据。联邦学习为处理隐私保护下的少数据综合能源多元负荷预测问题提供了一个重要的思路,但是现有方法依然存在相似参与方识别精度不高等不足。鉴于此,本文提出一种融合联邦学习和长短期记忆网络(long short-term memory,LSTM)的少数据综合能源多元负荷预测方法(multitask learning based on shared dot product confidentiality under federated learning,MT-SDPFL)。首先,给出一种基于共享向量点积保密协议的相似参与方识别方法,用来从诸多可用的综合能源系统中选出最为相似的参与方;接着,使用参数共享联邦学习算法对选中的各参与方联合训练,结合LSTM和finetune技术建立每个参与方的多元负荷预测模型。将所提方法应用于多个实际能源系统,实验结果表明,该方法可以在数据稀疏的情况下取得高精度的多源负荷预测结果。
文摘Dot enzyme-linked immunosorbent assay （dot-ELISA）, indirect ELISA and Westem blot were performed to detect the virulent protease secreted by Vibrio anguillarum which was isolated from the diseased left-eyed flounder, Paralichthys olivaceous. Sensitivity results showed that dot-ELISA is a more sensitive, rapid and simple technique for the protease detection. The minimal detectable amount of protease is about 7 pg in the dot-ELISA test, while 7.8 ng in the indirect ELISA and 6.25 ng in the Westem blot respectively. Protease could be detected 2 h after incubation of V. anguillarum in the 2216E liquid medium but enzyme activity was very low at that period. From 6 to 12 h, the amount and enzyme activity of protease increased markedly and reached maximum at stationary phase. Analysis of serum samples periodically collected from the infected flounders showed that after 2 h of infection by V. anguillarum, the pathogenic bacteria could be detected in the blood of the infected flounders but no protease was found. It was 5-6 h after infection that the protease was detected in blood and then the amount increased as infection advanced. Quantitative detection of protease either incubation in the medium or from the blood of infected flounders could be accomplished in virtue of positive controls of quantificational protease standards （＂marker＂） so that the alterations ofprotease secretion both in vitro and in vivo could be understood generally. In addition, the indirect ELISA and dot-ELISA were also performed to detect V. anguillarum cells. Results indicated that the sensitivity of indirect ELISA to bacteria cells is higher than that of the dot-ELISA, and that the minimal detectable amount is approximately 10^4 cell/mL in the indirect ELISA, while 10^5 cell/mL in the dot-ELISA.
基金supported by the National Natural Science Foundation of China(Grant Nos.11274132 and 11550110180)
文摘We investigate the time evolution of entanglement between two quantum dots in an engineered vacuum environment such that a metallic nanoring having a surface plasmon is placed near the quantum dots. Such engineering in environment results in oscillations in entanglement dynamics of the quantum dots systems. With proper adjustment of the separation between the quantum dots, entanglement decay can be stabilized and preserved for longer time than its decay without the surface plasmons interactions.
文摘Spam emails pose a threat to individuals. The proliferation of spam emails daily has rendered traditional machine learning and deep learning methods for screening them ineffective and inefficient. In our research, we employ deep neural networks like RNN, LSTM, and GRU, incorporating attention mechanisms such as Bahdanua, scaled dot product (SDP), and Luong scaled dot product self-attention for spam email filtering. We evaluate our approach on various datasets, including Trec spam, Enron spam emails, SMS spam collections, and the Ling spam dataset, which constitutes a substantial custom dataset. All these datasets are publicly available. For the Enron dataset, we attain an accuracy of 99.97% using LSTM with SDP self-attention. Our custom dataset exhibits the highest accuracy of 99.01% when employing GRU with SDP self-attention. The SMS spam collection dataset yields a peak accuracy of 99.61% with LSTM and SDP attention. Using the GRU (Gated Recurrent Unit) alongside Luong and SDP (Structured Self-Attention) attention mechanisms, the peak accuracy of 99.89% in the Ling spam dataset. For the Trec spam dataset, the most accurate results are achieved using Luong attention LSTM, with an accuracy rate of 99.01%. Our performance analyses consistently indicate that employing the scaled dot product attention mechanism in conjunction with gated recurrent neural networks (GRU) delivers the most effective results. In summary, our research underscores the efficacy of employing advanced deep learning techniques and attention mechanisms for spam email filtering, with remarkable accuracy across multiple datasets. This approach presents a promising solution to the ever-growing problem of spam emails.
