检索结果-南通市图书馆

基于多准则决策和深度神经网络的电子商务推荐系统

在线全文

学校读者我要写书评

暂无评论

贵阳学院学报（自然科学版） 2024年第3期19卷 69-73,91页

作者：韩晓路周湘贞安徽职业技术学院现代商务学院安徽合肥451191 郑州升达经贸管理学院信息工程学院河南郑州230001

推荐系统在电子商务门户中发挥着重要作用。现有推荐算法通常基于单个评分标准进行推荐商品排序,未考虑到从不同标准的用户偏好上对用户和商品特征进行综合建模。为此,提出了基于多准则决策(MCD)和深度神经网络(DNN)的电商产品推荐系统... 详细信息

推荐系统在电子商务门户中发挥着重要作用。现有推荐算法通常基于单个评分标准进行推荐商品排序,未考虑到从不同标准的用户偏好上对用户和商品特征进行综合建模。为此,提出了基于多准则决策(MCD)和深度神经网络(DNN)的电商产品推荐系统。首先,设计上下文感知的DNN模型,从不同标准出发进行评分预测,并通过聚合函数得到综合评分预测值。其后,通过结合残差卷积神经网络(CNN)和双向长短时记忆(Bi-LSTM)的混合模型,基于用户评论预测用户对商品的情感倾向。最后,将评分预测与情感倾向结合,实现准确的商品推荐。实验结果表明,所提方法在亚马逊电商产品数据集上进行商品推荐的平均绝对误差(MAE)和均方根误差(RMSE)分别为0.953和1.129,优于其他比较方法,证明在推荐系统中结合MCD和情感分析,能够有效提高推荐系统性能。

关键词：电子商务推荐系统多准则决策深度神经网络情感分析双向长短时记忆

Fabricating high-performance sodium ion capacitors with P2-Na_(0.67)Co_(0.5)Mn_(0.5)O_2 and MOF-derived carbon

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2019年第1期28卷 79-84页

作者： Haichen Gu Lingjun Kong Huijuan Cui Xianlong zhou Zhaojun Xie zhen zhou School of Materials Science and Engineering National Institute for Advanced Materials Institute of New Energy Material Chemistry Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Nankai University

Sodium ion capacitors(SICs) have been considered as a kind of promising devices to achieve both high power and energy density. However, it is still a challenge to achieve high energy output at elevated power delivery due to the poor rate capability of battery-type electrode materials and the kinetic mismatch with capacitor-type electrode materials. In this work, to fabricate SICs, P2-Na_(0.67)Co_(0.5)Mn_(0.5)O_2(P2-NCM)was chosen as the battery-type cathode material, and a typical metal-organic framework(MOF) material,zeolitic imidazolate framework-8(ZIF-8) derived carbon(ZDC) was utilized as the capacitor-type anode material. Due to the kinetic match and high-rate performance of both electrodes, the ZDC//P2-NCM SICs exhibited an energy output of 18.8 Wh kg^(-1) at a high power delivery of 12.75 kW kg^(-1).

关键词： Energy density Power density P2-phase material Zeolitic imidazolate framework-8 Sodium ion capacitors

What is the promising anode material for Na ion batteries?

在线全文

学校读者我要写书评

暂无评论

Science Bulletin 2018年第3期63卷 146-148页

作者： Yangyang zhou Yali Yang Menggai Jiao zhen zhou School of Materials Science and Engineering National Institute for Advanced Materials Institute of New Energy Material Chemistry Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Nankai University

In the current world,people have ever-increasing demand for *** fuels are now the primary source of energy,and their excess use results in severe problems,such as environmental pollution and global ***,it is essential to develop a new society based on sustainable energies such as wind,tidal and solar energy *** to the intermittence and instability of the above new energies,smart grids with the core technology

关键词：阳极材料 Na 电池离子过量使用环境污染精力太阳能

刁口河生态补水对浅表土壤典型物化指标的影响研究

在线全文

学校读者我要写书评

暂无评论

中国水能及电气化 2024年第7期 57-61,66页

作者：宫晓东周振陈萍山东黄河河务局黄河河口管理局山东东营257091

2011—2023年,持续14年的生态补水,极大地改善了刁口河流路湿地生态环境。为科学判定生态补水对刁口河流路湿地特别是浅表土壤的改善效果,课题组在山东黄河三角洲国家级自然保护区一千二监测站内布设了监测断面,按频次对土壤典型物化指... 详细信息

2011—2023年,持续14年的生态补水,极大地改善了刁口河流路湿地生态环境。为科学判定生态补水对刁口河流路湿地特别是浅表土壤的改善效果,课题组在山东黄河三角洲国家级自然保护区一千二监测站内布设了监测断面,按频次对土壤典型物化指标(全盐量、碱解氮、速效钾、有效磷)进行了原型监测,结合气象资料,确定生态补水最大在0.8km内对刁口河流路湿地浅表土壤物化指标有良性影响,改善了生态环境,典型物化指标的变幅高低基本表现出离河距离越近变幅越大、离河距离越远变幅越小的规律。

关键词：刁口河生态补水浅表土壤物化指标

在线全文

学校读者我要写书评

暂无评论

光纤法珀传感器的改进型相位生成载波法解调

中国光学（中英文） 2024年第2期17卷 312-323页

作者：周朕蕊张国强邱宗甲郭少朋李群邵剑吴鹏陆云才中国科学院电工研究所北京100190 中国科学院大学北京100049 国网江苏省电力有限公司电力科学研究院江苏南京211102

为解决相位生成载波-反正切解调算法(PGC-Atan)的非线性失真问题,搭建了基于改进型PGC-Atan算法的非本征型法珀传感器(EFPI)解调系统。首先,理论分析了载波相位调制深度(C)偏离最优值、伴生调幅、载波相位延迟等非线性因素对经典PGC-Ata... 详细信息

为解决相位生成载波-反正切解调算法(PGC-Atan)的非线性失真问题,搭建了基于改进型PGC-Atan算法的非本征型法珀传感器(EFPI)解调系统。首先,理论分析了载波相位调制深度(C)偏离最优值、伴生调幅、载波相位延迟等非线性因素对经典PGC-Atan算法中参与反正切运算的正弦与余弦两路信号的影响。然后,针对外调制或伴生调幅较小的情况,提出了一种基于系数补偿的改进型PGC-Atan算法(PGC-CC-Atan)。该算法通过构造与C值和载波相位延迟有关的系数,消除反正切运算中的非线性参数。针对内调制情况,提出了一种基于椭圆拟合的改进型PGC-Atan算法(PGCEF-Atan)。该算法通过基于分块矩阵的最小二乘法拟合椭圆并提取3个椭圆参数,进而将受非线性因素影响的正弦与余弦两路信号校正为正交信号。最后,通过仿真验证了改进型算法的正确性,并采用高调制特性的垂直腔面发射激光器(VCSEL)和常规腔长的EFPI等搭建PGC解调系统,对比经典PGC-Atan算法与两种改进型算法的解调性能,证实了改进型算法非线性失真抑制的有效性。实验结果表明:一定C值范围内,两种改进型算法可在非线性因素影响下有效解调。PGC-EF-Atan算法相较于PGC-CC-Atan算法,解调信纳比提升了11.602 dB,总谐波失真降低了10.951%。两种改进型算法中,PGC-EF-Atan算法对非线性失真的抑制效果更好,且解调线性度良好,准确度高。

关键词：相位生成载波解调非线性失真椭圆拟合光纤法珀传感器

Scheme for Preparation of Macroscopic Multi-component Entanglement in Cavity QED

在线全文

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2008年第2期49卷 473-476页

作者： JIA Lian-Jun YANG zhen-Biao zhou zhen-Xiao Department of Physics Lanzhou University Lanzhou 730000 China Department of Electronic Science and Applied Physics Fuzhou University Fuzhou 350002 China School of Nuclear Science and Technology Lanzhou University Lanzhou 730000 China

We propose a scheme of generating multi-component entangled coherent states of cavity fields. In this scheme, the atoms pass through cavities one by one, simultaneously driven by a strong classical field in each cavity. Then the detection of the atomic states collapses the cavity fields onto multi-component entangled coherent states. It is shown that, with a judicious choice of the parameters of the classical field, we can conditionally produce macroscopic multi-dimensional maximal entanglement for the cavity modes.

关键词： resonant interaction strongly driven atom multi-component entanglement cavity QED

Machine learning:Accelerating materials development for energy storage and conversion

在线全文

学校读者我要写书评

暂无评论

InfoMat 2020年第3期2卷 553-576页

作者： An Chen Xu Zhang zhen zhou School of Materials Science and Engineering Nankai UniversityChina Computational Centre for Molecular Science Nankai UniversityChina Institute of New Energy Material Chemistry Nankai UniversityChina Key Laboratory of Advanced Energy Materials Chemistry(Ministry of Education) Nankai UniversityChina Renewable Energy Conversion and Storage Center(ReCast) Nankai UniversityChina

With the development of modern society,the requirement for energy has become increasingly important on a global ***,the exploration of novel materials for renewable energy technologies is urgently *** methods are difficult to meet the requirements for materials science due to long experimental period and high ***,machine learning(ML)is rising as a new research paradigm to revolutionize materials *** this review,we briefly introduce the basic procedure of ML and common algorithms in materials science,and particularly focus on latest progress in applying ML to property prediction and materials development for energyrelated fields,including catalysis,batteries,solar cells,and gas ***,contributions of ML to experiments are involved as *** highly expect that this review could lead the way forward in the future development of ML in materials science.

关键词： big data energy storage and conversion machine learning property prediction

Observation of Doppler shift f_(D) modulated by the internal kink mode using conventional reflectometry in the EAST tokamak

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plasma Science and Technology 2024年第3期26卷 1-9页

作者：李恭顺张涛耿康宁文斐叶凯萱徐立清朱翔张学习钟富彬周振杨书琪周子强喻琳兰婷王守信提昂张寿彪刘海庆李国强高翔 the EAST Team Institute of Plasma Physics Chinese Academy of SciencesHefei 230031People's Republic of China Advanced Energy Research Center Shenzhen UniversityShenzhen 518060People's Republic of China University of Science and Technology of China Hefei 230026People's Republic of China

In this paper we present a new experimental observation using a conventional reflectometry technique,poloidal correlation reflectometry(PCR),in the Experimental Advanced Superconducting Tokamak(EAST).The turbulence spectrum detected by the PCR system exhibits an asymmetry and induced Doppler shift f_(D)during the internal kink mode(IKM)rotation *** Doppler shift f_(D)is the target measurement of Doppler reflectometry,but captured by conventional *** show that the Doppler shift f_(D)is modulated by the periodic changes in the effective angle between the probing wave and cutoff layer normal,but not by plasma *** fishbone mode and saturated long-lived mode are typical IKMs,and this modulation phenomenon is observed in both ***,the value of the Doppler shift f_(D)is positively correlated with the amplitude of the IKM,even when the latter is ***,the positive and negative frequency components of the Doppler shift f_(D)can be asymmetric,which is related to the plasma configuration.A simulated analysis is performed by ray tracing to verify these *** results establish a clear link between f_(D)and IKM rotation,and are helpful for studying the characteristics of IKM and related physical phenomena.

关键词： microwave reflectometry Doppler shift internal kink mode

Fourier Self-deconvolution Using Approximation Obtained from Frequency Domain Wavelet Transform as a Linear Function

在线全文

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2006年第3期17卷 380-382页

作者： Yuan zhen zhou Jian Bin zhenG Institute of Analytical Science/Shaanxi Provincial Key Lab of Electroanalytical Chemistry Northwest University Xi＇an 710069

A new method of resolving overlapped peak, Fourier self-deconvolution （FSD） using approximation CN obtained from frequency domain wavelet transform of F（ω） yielded by Fourier transform of overlapped peak signals f（t） as the linear function, was presented in this paper. Compared with classical FSD, the new method exhibits excellent resolution for different overlapped peak signals such as HPLC signals, and have some characteristics such as an extensive applicability for any overlapped peak shape signals and a simple operation because of no selection procedure of the linear function. Its excellent resolution for those different overlapped peak signals is mainly because F（ω） obtained from Fourier transform of f（t） and CN obtained from wavelet transform of F（ω） have the similar linearity and peak width. The effect of those fake peaks can be eliminated by the algorithm proposed by authors. This method has good potential in the process of different overlapped peak signals.

关键词： Fourier deconvolution wavelet transform signal processing HPLC signal