检索结果-内蒙古大学图书馆

EMARec: a sequential recommendation with exponential moving average

Neural Computing and Applications 2024年第21期36卷 12917-12933页

作者： Chen, Rui Wang, Zonglin Tang, Cundong Zhang, Jianwei Li, Pu Kong, Xiangjie Huang, Min College of Software Engineering Zhengzhou University of Light Industry Zhengzhou450001 China Henan Joint International Research Laboratory of Computer Animation Implementation Technologies Zhengzhou450001 China School of Information Science and Technology Northwest University Xi’an710127 China Faculty of Information and Engineering Xuchang Vocational Technical College Xuchang461000 China College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China

Capturing dynamic preference features from user historical behavioral data is widely applied to improve the accuracy of recommendations in sequential recommendation tasks. However, existing deep neural network-based sequential recommendation methods often ignore the noise information in user behavioral data that influence recommendation effectiveness, making recommendation models sensitive to noisy data. Additionally, these deep learning-based recommendation models often require a large number of parameters to capture user behavior patterns, leading to higher time complexity and susceptibility to overfitting due to noise fluctuations. To address these issues, in this paper, we apply the moving average concept from the field of time-series analysis to sequential recommendation tasks. The approach smooths sequence data, removes noise, making the data more stable and reliable, increases the model’s insensitivity to noise information, and better understands the evolution of user interests and behavioral patterns. Specifically, in our experiments, the moving average algorithm effectively denoises sequential data with low time complexity. Therefore, we propose a Sequential Recommendation with Exponential Moving Average with MLP architecture that makes the model more competitive in terms of time complexity. Experimental results conducted on two datasets demonstrate that EMARec outperforms state-of-the-art sequential recommendation methods across various common evaluation metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Research on Optimal Preload Method of Controllable Rolling Bearing Based on Multisensor Fusion

引用

Computer Modeling in engineering & sciences 2024年第6期139卷 3329-3352页

作者： Kuosheng Jiang Chengrui Han Yasheng Chang School of Mechanical and Electrical Engineering Anhui University of Science and TechnologyHuainan232001China School of Optical and Electronic Information Suzhou City University&Suzhou Key Laboratory of BiophotonicsSuzhou215104China State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an710054China

Angular contact ball bearings have been widely used in machine tool spindles,and the bearing preload plays an important role in the performance of the *** order to solve the problems of the traditional optimal preload prediction method limited by actual conditions and uncertainties,a roller bearing preload test method based on the improved D-S evidence theorymulti-sensor fusion method was ***,a novel controllable preload system is proposed and ***,multiple sensors are employed to collect data on the bearing parameters during preload ***,a multisensor fusion algorithm is used to make predictions,and a neural network is used to optimize the fitting of the preload *** limitations of conventional preload testing methods are identified,and the integration of complementary information frommultiple sensors is used to achieve accurate predictions,offering valuable insights into the optimal preload *** results demonstrate that the multi-sensor fusion approach outperforms traditional methods in accurately measuring the optimal preload for rolling bearings.

关键词： Multi-sensor information fusion neural network preload force

来源：评论

学校读者我要写书评

暂无评论

Constructing lithiophilic sites-rich artificial solid electrolyte interphase to enable dendrite-free and corrosion-free lithium-sulfur batteries

引用

Green Energy & Environment 2024年第12期9卷 1891-1900页

作者： Wei Lu Anshun Zhao Qiuxu Chen Sihan Liu Mingxi Yu Zihao Wang Ze Gao Xue Zhao Guiru Sun Ming Feng Key Laboratory of Functional Materials Physics and Chemistry Ministry of Education Jilin Normal UniversityChangchunJilin130103China College of Information Technology Jilin Engineering Research Center of Optoelectronic Materials and DevicesJilin Normal UniversitySipingJilin136000China School of Science Changchun University of Science and TechnologyChangchunJilin130022China

An artificial solid electrolyte interphase(SEI)with lithiophilic sites and chemical bonds anchoring lithium polysulfides(LiPSs)has been developed as a potential solution to protect the lithium(Li)metal anode of Lithium-sulfur(Li-S)*** strategy aims to guide consistent Li deposition and relieve lithium ***,the evolution process of lithiophilic sites based on aluminum fluoride(AlF_(3))in an artificial SEI is disclosed in Li-S batteries with metal-based lithiophilic *** polyester polymer(PMMA and PPC)/AlF_(3) artificial SEI(MPAF-SEI)was homogeneously anchored on Li anode by in-situ *** conversion of AlF_(3) into Li-Al and LiF lithiophilic sites effectively reduce the Li nucleation overpotential and prevents the formation of Li *** the same time,the polymer can anchor LiPSs by chemical bonds and prevents Li *** optimized MPAF-SEI protected Li demonstrates excellent stability for over 3000 h at a capacity of 1 mAh cm^(-2) in Li||Li symmetric *** Li-S battery with low N/P(4)exhibits a capacity of 532.6 mAh g^(-1) over 300 cycles lifespan at 0.5 C.

关键词： Li anode SEI Lithiophilic sites Li-S battery AlF_(3)

来源：评论

学校读者我要写书评

暂无评论

Measurement-based Path Loss Prediction and Analysis in Water Scenarios

Measurement-based Path Loss Prediction and Analysis in Water...

引用

2024 IEEE International Conference on Computational Electromagnetics, ICCEM 2024

作者： Li, Hanpeng Chen, Xiaomin Li, Hangang Ma, Jian Ye, Xuchao Song, Lixin Zhang, Taotao Zhong, Weizhi Zhu, Qiuming Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China Aviation Key Laboratory of Science and Technology On Aero Electromechanical System Integration Nanjing211106 China State Key Lab. of Complex Electromagnetic Environment Effects On Electronics and Information System Luoyang471003 China

ISBN: (纸本)9798350383317

Unmanned aerial vehicles (UAVs) have enabled the unmanned management of water areas. Path loss (PL) serves as a critical factor that affects the UAV communication quality. In this work, a PL model for UAV channel in water scenarios is proposed, aiming to explore the multidimensional relationship between transceiver distance, carrier frequency, UAV height, and PL by constructing an Artificial Neural Network (ANN). Moreover, channel measurements are conducted in a river area, and the obtained data are analyzed using the proposed ANN model as well as the close-in (CI) model. The analysis results demonstrates that the PL increases initially and then declines as the UAV height increases. The proposed ANN model has higher prediction accuracy than the classic empirical model, and can achieve precise prediction of the PL in water scenarios. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Influence of TiO2 Space layer on plasmon enhanced Luminescence of Ag/TiO2/NaGdF4:Er3+/Yb3+/Al3+ composite Films

引用

Materials Research Innovations 2023年第5期27卷 289-295页

作者： Zheng, Piaopiao Chen, Mingjie Zhou, Haifang Wang, Chunxia Lai, Yunfeng Yu, Jinling Cheng, Shuying School of Physics and Information Engineering Institute of Micro-Nano Devices & Solar Cells Fuzhou University Fuzhou China Jiangsu Collaborative Innovation Center of Photovoltaic Science and Engineering Changzhou China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou China

Lanthanide-doped upconversion nanoparticles (UCNPs)have potential applications in optical and optoelectronic devices due to their novel optical properties. The surface plasmon is an effective method in improving the upconversion luminescence (UCL) properties, and it is essential to tunee the distance between the metal NPs and UCNPs for improving UCL. In this work, the Ag/TiO2/NaGdF4:Er3+/Yb3+/Al3+ composite films were fabricated, and the effect of the TiO2 layer thickness on spectral characteristics in the composite films was investigated. It is shown that the thickness of TiO2 film has a significant effect on the Ag NPs plasma resonance and fluorescence intensity. The maximum upconversion emission enhancement factors of the red and green emission were obtained for the sample with 15-nm-thickness TiO2 under the 980 nm excitation. That is mainly originated from the enhancement of the resonate energy transfer (Yb3+→Er3+) rate under the competition between non-radiative transition and local field effects. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

Bioinspired Polarized Skylight Orientation Determination Artificial Neural Network

引用

Journal of Bionic engineering 2023年第3期20卷 1141-1152页

作者： Huaju Liang Hongyang Bai Ke Hu Xinbo Lv School of Energy and Power Engineering Nanjing University of Science and TechnologyNanjing210094China Neuromorphic Computing Laboratory China Nanhu Academy of Electronics and Information TechnologyJiaxing314001China Guidance Radar General Department Xi’an Electronic Engineering Research InstituteXi’an710100China School of Automation Nanjing University of Science and TechnologyNanjing210094China

This paper proposes an artificial neural network to determine orientation using polarized skylight. This neural network has specific dilated convolution, which can extract light intensity information of different polarization directions. Then, the degree of polarization (DOP) and angle of polarization (AOP) are directly extracted in the network. In addition, the exponential function encoding of orientation is designed as the network output, which can better reflect the insect’s encoding of polarization information and improve the accuracy of orientation determination. Finally, training and testing were conducted on a public polarized skylight navigation dataset, and the experimental results proved the stability and effectiveness of the network.

关键词： Polarized light navigation Orientation determination Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

ML-Driven HR system: Candidate Assessment for Enhanced Recruitment Outcomes 3

ML-Driven HR System: Candidate Assessment for Enhanced Recru...

引用

3rd International Conference on Automation, Computing and Renewable systems, ICACRS 2024

作者： Dixon, G.C. Srithanujan, S. Ranaweera, H.D.T.N. Ariyarathne, R.M.P.M. Weerasinghe, K.L. Gamage, N. Department of Information Technology SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer System engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer Science and Software Engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka

ISBN: (纸本)9798331532420

This study developed and implemented a machine learning-driven HR system designed to enhance recruitment outcomes, particularly in online interviews. Challenges such as candidate impersonation, interview question memorization, and deepfake manipulations were addressed. The system incorporated several critical processes utilizing advanced algorithms: pre-interview shortlisting employed Support Vector Machines (SVM) achieving 92% accuracy;cognitive skills assessment utilized adaptive testing methods powered by fine-tuned Large Language Models (LLMs) with 88% accuracy;emotional intelligence evaluation was conducted using deep learning-based emotion detection algorithms attaining 85% accuracy;face verification leveraged Convolutional Neural Networks (CNNs) for identity and deepfake detection with 90% accuracy;online video interviews were analyzed through integrated audio-visual processing techniques;language proficiency testing employed Natural Language Processing (NLP) models reaching 87% accuracy;analysis of thinking patterns was performed using sentiment analysis algorithms with 83% accuracy;and candidate grading was facilitated by ensemble learning methods ensuring consistent and reliable evaluations. The results demonstrated the system’s effectiveness in verifying candidate authenticity and assessing competence, providing a robust solution for modern recruitment challenges. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Differences in spring precipitation over southern China associated with multiyear La Ni?a events

引用

Acta Oceanologica Sinica 2024年第2期43卷 1-10页

作者： Guangliang Li Licheng Feng Wei Zhuang Fei Liu Ronghua Zhang Cuijuan Sui National Marine Environmental Forecasting Center Ministry of Natural ResourcesBeijing 100081China State Key Laboratory of Marine Environmental Science College of Ocean and Earth SciencesXiamen UniversityXiamen 361102China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519082China Key Laboratory of Tropical Atmosphere-Ocean System of Ministry of Education/School of Atmospheric Sciences Sun Yat-Sen UniversityZhuhai 519082China School of Marine Sciences Nanjing University of Information Science and TechnologyNanjing 210044China

Composite analyses were performed in this study to reveal the difference in spring precipitation over southern China during multiyear La Ni?a events during 1901 to 2015. It was found that there is significantly below-normal precipitation during the first boreal spring, but above-normal precipitation during the second year. The difference in spring precipitation over southern China is correlative to the variation in western North Pacific anomalous cyclone(WNPC), which can in turn be attributed to the different sea surface temperature anomaly(SSTA) over the Tropical Pacific. The remote forcing of negative SSTA in the equatorial central and eastern Pacific and the local air-sea interaction in the western North Pacific are the usual causes of WNPC formation and *** in the first spring is stronger than those in the second spring. As a result, the intensity of WNPC in the first year is stronger, which is more likely to reduce the moisture in southern China by changing the moisture transport, leading to prolonged precipitation deficits over southern China. However, the tropical SSTA signals in the second year are too weak to induce the formation and maintenance of WNPC and the below-normal precipitation over southern China. Thus, the variation in tropical SSTA signals between two consecutive springs during multiyear La Ni?a events leads to obvious differences in the spatial pattern of precipitation anomaly in southern China by causing the different WNPC response.

关键词： multiyear La Nina precipitation anomaly anomalous western North Pacific cyclone southern China

来源：评论

学校读者我要写书评

暂无评论

Microstructure and dielectric properties of perovskite-structured high-entropy ceramics of Pb(Zr0.25Ti0.25Sn0.25Hf0.25)O3

引用

Ceramics International 2023年第12期49卷 20398-20405页

作者： Zhang, Han Yang, Qingqing Meng, Bin Lin, Wu Ping, Xinyu Chen, Yingquan Xia, Haijun Faculty of Materials Science and Engineering Kunming University of Science and Technology Yunnan Province Kunming650093 China Key Laboratory of Advanced Materials of Yunnan Province Kunming University of Science and Technology Yunnan Province Kunming650093 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Province Kunming650000 China

A dielectric high-entropy ceramic with a composition of Pb(Zr0.25Ti0.25Sn0.25Hf0.25)O3 was designed through B-site doping, and then prepared by solid phase reaction method combined with conventional sintering in air for 3 h at 1200 °C, 1250 °C and 1300 °C, respectively. All the high-entropy ceramics of Pb(Zr0.25Ti0.25Sn0.25Hf0.25)O3 possess a perovskite structure with uniform elemental distribution and their average grain size falls within the range of 3.19–5.5 μm. For the sample sintered at 1250 °C, the dielectric loss is less than 0.07 in the testing frequency of 1 kHz∼1 MHz in 30–350 °C, and the dielectric constant reaches a peak of 14356 at about 270 °C at 1 kHz. At room temperature, the remnant polarization Pr reaches 28.8 μC/cm2. The results demonstrate that the high-entropy ceramic of Pb(Zr0.25Ti0.25Sn0.25Hf0.25)O3 has great potentials in the dielectric and ferroelectric field. © 2023 Elsevier Ltd and Techna Group S.r.l.

关键词： Zirconium compounds

来源：评论

学校读者我要写书评

暂无评论

Annual Optimal Performance Analysis of Micro Heat Pipe PV/T under Different Angles in Northwest China

引用

Journal of Thermal science 2025年第2期34卷 400-412页

作者： LIU Xiaomin WU Qingbai LI Jinping Vojislav NOVAKOVIC School of Energy and Power Engineering Lanzhou University of TechnologyLanzhou730050China Collaborative Innovation Center for Supporting Technology of Northwest Low-Carbon Towns Lanzhou730050China Gansu Key Laboratory of Complementary Energy System of Biomass and Solar Energy Lanzhou730050China Gansu Natural Energy Research Institute Lanzhou730050China Department of Energy and Process Engineering Norwegian University of Science and TechnologyTrondheimNO-7491Norway

The exploitation of photovoltaic/thermal(PV/T)systems,which facilitate concurrent conversion of solar radiation into electrical and heat energies,presents substantial potential in the solar-abundant northwestern zone of *** investigation endeavors to evaluate the efficacy of a micro heat pipe(M-HP)PV/T system via exhaustive experimental analysis conducted in *** improve the performance of M-HP-PV/T system,a comparison was made between the optimal angles for each day and the entire *** system inside greenhouse exhibited an average photovoltaic conversion efficiency(PCE)and thermal conversion efficiency(TCE)of12.32%and 42.81%.The system of external environment registered average PCE and TCE values of 12.99%and21.08%.To further understand the system's operational results,a mathematical model was constructed through the integration of experimental data,exhibiting good agreement between the simulated outcomes and empirical *** average solar irradiance of daily optimum angle was 728.3 W/m^(2);the annual optimum angle was 29°with an average solar irradiance of 705.6 W/m^(2).The average annual total powers at the optimal angle outside the greenhouse and inside the greenhouse were 448.0 W and 398.7 *** average annual total efficiencies at the optimal angle outside the greenhouse and inside the greenhouse were 40.8%and 56.9%.The total power in the greenhouse was lower by 49.3 W,while total efficiency in the greenhouse was higher by 16.1%.

关键词： solar energy micro heat pipe PV/T system greenhouse optimal angle

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：