检索结果-南通市图书馆

Journal of Computer Science & Technology 2017年第4期32卷 828-842页

作者： Ting Bai Hong-Jian Dou Xin Zhao Ding-yi yang Ji-rong Wen School of Information Renmin University of China Beijing 100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing 100872 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006 China

Nowadays, many e-commerce websites allow users to login with their existing social networking accounts. When a new user comes to an e-commerce website, it is interesting to study whether the information from external social media platforms can be utilized to alleviate the cold-start problem. In this paper, we focus on a specific task on cross-site information sharing, i.e., leveraging the text posted by a user on the social media platform (termed as social text) to infer his/her purchase preference of product categories on an e-commerce platform. To solve the task, a key problem is how to effectively represent the social text in a way that its information can be utilized on the e-commerce platform. We study two major kinds of text representation methods for predicting cross-site purchase preference, including shallow textual features and deep textual features learned by deep neural network models. We conduct extensive experiments on a large linked dataset, and our experimental results indicate that it is promising to utilize the social text for predicting purchase preference. Specially, the deep neural network approach has shown a more powerful predictive ability when the number of categories becomes large.

关键词： social media e-commerce website purchase preference deep neural network

Enzyme Activity in Water-Stable Soil Aggregates as Affected by Long-Term Application of Organic Manure and Chemical Fertiliser

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Pedosphere 2013年第1期23卷 111-119页

作者： LIU yi-Ren LI Xiang SHEN Qi-rong XU yang-Chun Jiangsu Provincial Key Laboratory for Solid Organic Waste Utilization College of Resources and Environmental SciencesNanjing Agricultural University Institute of Soil Fertilizer and Resource Environment Jiangxi Academy of Agricultural Sciences

The activities of invertase, protease, urease, acid phosphomonoesterase, dehydrogenase, and catalase in different fractions of waterstable aggregates (WSA) were examined in long-term (26 years) fertilised soils. The long-term application of organic manure (OM) with chemical fertiliser (CF) significantly increased macroaggregate and decreased microaggregate percentages, enhanced the mean weight diameter, and significantly increased soil total carbon (TC) and total nitrogen (TN) contents of WSA in different size fractions. Combined fertilisation with OM and CF also increased invertase, protease, urease, acid phosphomonoesterase, dehydrogenase, and catalase activities of WSA in different size fractions. Enzyme activities were higher in macroaggregates than in microaggregates. The distribution of enzyme activities generally followed the distribution of TC and TN in WSA. The geometric mean of the enzyme activities in different WSA of OM-treated soils was significantly higher than that in soils treated with 100% CF or no fertiliser. The results indicated that the long-term combined application of OM with CF increased the aggregate stability and enzyme activity of different WSA sizes, and consequently, improved soil physical structure and increased soil microbial activity.

关键词： distribution mean weight diameter stability total carbon total nitrogen

Removal of virus aerosols by the combination of filtration and UV-c irradiation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2023年第3期17卷 1-9页

作者： Min Shang Yadong Kong Zhijuan yang rong Cheng Xiang Zheng yi Liu Tongping Chen School of Environment and Natural Resources Renmin University of ChinaBeijing 100872China Sichuan Solid Waste and Chemicals Management Center Chengdu 610031China Biogas Institute of Ministry of Agriculture and Rural Affairs Chengdu 610041China

The COVID-19 pandemic remains ever prevalent and afflicting—partially because one of its transmission pathways is *** the widely used central air conditioning systems worldwide,indoor virus aerosols can rapidly migrate,thus resulting in rapid infection *** is therefore important to install microbial aerosol treatment units in the air conditioning systems,and we herein investigated the possibility of combining such filtration with UV irradiation to address virus *** showed that the removal efficiency of filtration towards f2 and MS2 phages depended on the type of commercial filter material and the filtration speed,with an optimal velocity of 5 cm/s for virus ***,it was found that UV irradiation had a significant effect on inactivating viruses enriched on the surfaces of filter materials;MS2 phages had greater resistance to UV-C irradiation than f2 *** optimal inactivation time for UV-C irradiation was 30 min,with higher irradiation times presenting no substantial increase in inactivation ***,excessive virus enrichment on the filters decreased the inactivation *** inactivation is therefore *** general,the combined system involving filtration with UV-C irradiation demonstrated a significant removal effect on virus ***,the system is simple and economical,making it convenient for widespread implementation in air-conditioning systems.

关键词： Filtration system UV-C irradiation Virus aerosol Public health COVID-19

Weighted approximation of functions with singularities by Bernstein operators

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2008年第10期9卷 1451-1456页

作者： Bao-rong WEI yi ZHAO Department of Mathematics Hangzhou Normal University Hangzhou 310036 China Institute of Mathematics Hangzhou Dianzi University Hangzhou 310018 China

As an important type of polynomial approximation, approximation of functions by Bernstein operators is an important topic in approximation theory and computational theory. This paper gives global and pointwise estimates for weighted approximation of functions with singularities by Bernstein operators. The main results are the Jackson＇s estimates of functions f∈ （Wwλ）2 andre Cw, which extends the result of （Della Vecchia et al., 2004）.

关键词： Bemstein operators Functions with singularities Weighted approximation Pointwise estimates

Towards accurate mapping of loess waterworn gully by integrating google earth imagery and DEM using deep learning

在线全文

学校读者我要写书评

暂无评论

International Soil and Water Conservation Research 2024年第1期12卷 13-28页

作者： rong Chen yi Zhou Zetao Wang ying Li Fan Li Feng yang School of Geography and Tourism Shaanxi Normal UniversityXi'an710119China National Experiment and Teaching Demonstration Center for Geography Xi'an710119China SuperMap Software Co. Ltd.Beijing100015China School of Environmental Science and Engineering Southern University of Science and TechnologyShenzhen518055China

Accurate mapping of loess waterworn gully(LWG)is essential to further study gully erosion and geomorphological evolution for the Chinese Loess Plateau(CLP).Due to the vertical joint and collapsibility of loess,LWGs have the characteristics of zigzag and unique slope abruptness under synthetic action of hydraulic force and *** forces existing LWG mapping methods to either focus on the improvement of mapping accuracy or center on the increase of mapping ***,simultaneously achieving accurate and efficient mapping of LWG is still in its infancy under complex topographic ***,we proposed a method that innovatively integrates the loess slope abruptness feature into an improved deep learning semantic segmentation framework for LWG mapping using 0.6 m Google imagery and 5 m DEM *** selected four study areas representing typical loess landforms to test the performance of our *** proposed method can achieve satisfactory mapping results,with the F1 score,mean Intersection-over-Union(mIoU),and overall accuracy of 90.5%,85.3%,and 92.3%,*** addition,the proposed model also showed significant accuracy improvement by inputting additional topographic information(especially the slope of slope).Compared with existing algorithms(Random forests,original DeepLabV3+,and Unet),the proposed approach in this study achieved a better accuracy-efficiency ***,the method can ensure high accuracy and efficiency of the LWG mapping for different loess landform types and can be extended to study various loess gully mapping and water and soil conservation.

关键词： Loess waterworn gully Topographic information Mapping Deep learning Soil erosion Loess plateau

Application of the improved dung beetle optimizer,muti-head attention and hybrid deep learning algorithms to groundwater depth prediction in the Ningxia area,China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Atmospheric and Oceanic Science Letters 2025年第1期18卷 18-23页

作者： Jiarui Cai Bo Sun Huijun Wang yi Zheng Siyu Zhou Huixin Li Yanyan Huang Peishu Zong Collaborative Innovation Center on forecast and Evaluation of Meteorological Disasters/Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment ChangeNanjing University of Information Science and TechnologyNanjingChina Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) ZhuhaiChina China Meteorological Administration Key Laboratory of Transportation MeteorologyNanjingChina Jiangsu Meteorological Observatory NanjingChina

Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical *** learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many *** this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,*** two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction *** addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.

关键词： Groundwater depth Multi-head attention Improved dung beetle optimizer CNN-LSTM CNN-GRU Ningxia

Mechanical Properties of Railway High-strength Manufactured Sand Concrete: Typical Lithology, Stone Powder Content and Strength Grade

在线全文

学校读者我要写书评

暂无评论

Journal of Wuhan University of Technology(Materials Science) 2025年第1期40卷 194-203页

作者： WANG Zhen LI Huajian HUANG Fali yang Zhiqiang WEN Jiaxin SHI Henan Railway Engineering Research Institute China Academy of Railway Science Corporation LimitedBeijing 100081China State Key Laboratory for Track Technology of High-Speed Railway Beijing 100081China

In order to achieve the large-scale application of manufactured sand in railway high-strength concrete structure,a series of high-strength manufactured sand concrete(HMC)are prepared by taking the manufactured sand lithology(tuff,limestone,basalt,granite),stone powder content(0,5%,10%,15%)and concrete strength grade(C60,C80,C100)as *** evolution of mechanical properties of HMC and the correlation between cubic compressive strength and other mechanical properties are *** to river sand,manufactured sand enhances the cubic compressive strength,axial compressive strength and elastic modulus of concrete,while its potential microcracks weaken the flexural strength and splitting tensile strength of *** powder content displays both positive and negative effects on mechanical properties of HMC,and the stone powder content is suggested to be less than 10%.The empirical formulas between cubic compressive strength and other mechanical properties are proposed.

关键词： manufactured sand concrete railway mechanical property lithology stone powder content

Targets capture by distributed active swarms via bio-inspired reinforcement learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期Mechanics & Astronomy) .卷 210-221页

作者： Kun Xu Yue Li Jun Sun Shuyuan Du Xinpeng Di Yuguang yang Bo Li Institute of Biomechanics and Medical Engineering Applied Mechanics Laboratory Department of Engineering MechanicsTsinghua University Institute of Nuclear and New Energy Technology Tsinghua University Shanghai Aerospace Control Technology Institute Shanghai Key Laboratory of Aerospace Intelligent Control Technology College of Automation Engineering Nanjing University of Aeronautics and Astronautics

Natural swarms arranged from cells to herds are usually decentralized but display intriguing collective intelligence in coordinating individuals across large scales to efficiently achieve their common goals. Learning from nature may provide new strategies for controlling collective dynamics of synthetic swarms to accomplish specific functions. Here, we present a bioinspired computational framework that steers distributed active swarms to collectively capture and merge targets via reinforcement learning. We exploit collective milling structures of natural herds to cage the targets, and adopt a switching control policy inspired by sperms' chiral dynamics to optimize the trajectories of individuals, through which the active swarms can selforganize to enclose single or multiple distant targets in a dynamical, adaptive and scalable manner. There exists a critical swarm size, beyond which the excessive competition between agents would generate large mechanical forces, leading to capture instability but enabling the transition from short-distance to long-distance merging capture of multiple targets. This work provides physical insights into distributed active swarms and could offer a multilevel, decentralized strategy toward controlling swarm robotics in wide applications such as bio-medical devices, machine immunity, and target clearance.

关键词： swarm intelligence robotics multi-tasks artificial intelligence bionics

Bilevel Optimal Scheduling of Island Integrated Energy System Considering Multifactor Pricing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2025年第1期122卷 349-378页

作者： Xin Zhang Mingming Yao Daiwen He Jihong Zhang Peihong yang Xiaoming Zhang School of Automation and Electrical Engineering Inner Mongolia University of Science and TechnologyBaotou014010China

In this paper,a bilevel optimization model of an integrated energy operator(IEO)–load aggregator(LA)is constructed to address the coordinate optimization challenge of multiple stakeholder island integrated energy system(IIES).The upper level represents the integrated energy operator,and the lower level is the electricity-heatgas load *** to the benefit conflict between the upper and lower levels of the IIES,a dynamic pricing mechanism for coordinating the interests of the upper and lower levels is proposed,combined with factors such as the carbon emissions of the IIES,as well as the lower load interruption *** price of selling energy can be dynamically adjusted to the lower LA in the mechanism,according to the information on carbon emissions and load interruption *** benefits and win-win situations are achieved between the upper and lower ***,CPLEX is used to iteratively solve the bilevel optimization *** optimal solution is selected according to the joint optimal discrimination *** results indicate that the sourceload coordinate operation can reduce the upper and lower operation *** the proposed pricingmechanism,the carbon emissions and load interruption power of IEO-LA are reduced by 9.78%and 70.19%,respectively,and the capture power of the carbon capture equipment is improved by 36.24%.The validity of the proposed model and method is verified.

关键词： Bilevel optimal scheduling load aggregator integrated energy operator carbon emission dynamic pricing mechanism

Engine Misfire Fault Detection Based on the Channel Attention Convolutional Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 843-862页

作者： Feifei Yu Yongxian Huang Guoyan Chen Xiaoqing yang Canyi Du Yongkang Gong School of Mechatronic Engineering Guangdong Polytechnic Normal UniversityGuangzhou510665China School of Automotive and Transportation Engineering Guangdong Polytechnic Normal UniversityGuangzhou510665China

To accurately diagnosemisfire faults in automotive engines,we propose a Channel Attention Convolutional Model,specifically the Squeeze-and-Excitation Networks(SENET),for classifying engine vibration signals and precisely pinpointing misfire *** the experiment,we established a total of 11 distinct states,encompassing the engine’s normal state,single-cylinder misfire faults,and dual-cylinder misfire faults for different *** collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,*** collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and prevent overlap between the two *** results revealed that,with a vibration acceleration sequence of 1000 time steps(approximately 50 ms)as input,the SENET model achieved a misfire fault detection accuracy of 99.8%.For comparison,we also trained and tested several commonly used models,including Long Short-Term Memory(LSTM),Transformer,and Multi-Scale Residual Networks(MSRESNET),yielding accuracy rates of 84%,79%,and 95%,*** underscores the superior accuracy of the SENET model in detecting engine misfire faults compared to other ***,the F1 scores for each type of recognition in the SENET model surpassed 0.98,outperforming the baseline *** analysis indicated that the misclassified samples in the LSTM and Transformer models’predictions were primarily due to intra-class misidentifications between single-cylinder and dual-cylinder misfire *** delve deeper,we conducted a visual analysis of the features extracted by the LSTM and SENET models using T-distributed Stochastic Neighbor Embedding(T-SNE)*** findings revealed that,in the LSTMmodel,data points of the same type tended to cluster together with significant ***,in the SENET model,data points of various types were more widely and evenly dispersed,demonstra

关键词： Channel attention SENET model engine misfire fault fault detection