检索结果-南通市图书馆

Enhanced Answer Selection in CQA Using Multi-Dimensional Features Combination

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2019年第3期24卷 346-359页

作者： Hongjie Fan Zhiyi Ma Hongqiang Li Dongsheng Wang junfei liu the School of Electronics Engineering and Computer Science Peking University the School of Software and Microelectronics Peking University he School of Software and Microelectronics Peking University National Engineering Research Center for Software Engineering Peking University

Community Question Answering(CQA) in web forums, as a classic forum for user communication,provides a large number of high-quality useful answers in comparison with traditional question *** of methods to get good, honest answers according to user questions is a challenging task in natural language processing. Many answers are not associated with the actual problem or shift the subjects,and this usually occurs in relatively long answers. In this paper, we enhance answer selection in CQA using multidimensional feature combination and similarity order. We make full use of the information in answers to questions to determine the similarity between questions and answers, and use the text-based description of the answer to determine whether it is a reasonable one. Our work includes two subtasks:(a) classifying answers as good, bad, or potentially associated with a question, and(b) answering YES/NO based on a list of all answers to a question. The experimental results show that our approach is significantly more efficient than the baseline model, and its overall ranking is relatively high in comparison with that of other models.

关键词： community question answering information retrieval multi-dimensional features extraction similarity computation

Densely-connected neural networks for aspect term extraction

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第6期65卷 264-266页

作者： Chen CHEN Houfeng WANG Qingqing ZHU junfei liu School of Software and Microelectronics Peking University MOE Key Lab of Computational Linguistics School of Electronics Engineering and Computer SciencePeking University National Engineering Research Center for Software Engineering (Peking University)

Dear editor,Aspect term extraction(ATE) is a sub-task of aspect-based sentiment analysis, which aims to extract opinionated aspect terms from user reviews. For example, in a laptop domain review: “Boot time is super ... 详细信息

关键词： aspect term extraction recurrent neural network self-attention densely-connected network double word embeddings Aspect-Based Sentiment Analysis deep learning sequence labeling

猕猴桃细菌性溃疡病菌的分离鉴定与致病性分析

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

合肥工业大学学报（自然科学版） 2024年第2期47卷 257-262页

作者：吴仲秋牛向丽汪雯静李璇刘骏菲邬杰涛合肥工业大学食品与生物工程学院安徽合肥230601

溃疡病是猕猴桃主要细菌性病害,其病原为丁香假单胞菌猕猴桃致病变种(Pseudomonas syringae ***,Psa)。文章利用不同猕猴桃种植园的溃疡病发病植株进行Psa菌株分离、鉴定及致病性分析;结果显示,获得了6个具有丁香假单胞菌形态特征的菌株... 详细信息

溃疡病是猕猴桃主要细菌性病害,其病原为丁香假单胞菌猕猴桃致病变种(Pseudomonas syringae ***,Psa)。文章利用不同猕猴桃种植园的溃疡病发病植株进行Psa菌株分离、鉴定及致病性分析;结果显示,获得了6个具有丁香假单胞菌形态特征的菌株,经聚合酶链式反应(polymerase chain reaction,PCR)鉴定与序列同源比对,所分离菌株为Psa,该菌株在‘红阳’猕猴桃的接种检测中显示不同致病性,其中ScYbH2、ScDjyH2、ScYbH1接种植株出现溃疡病症状,而ScMbJ1、ScDjyH3、ScYaH2未表现显著致病性。烟草叶片超敏反应也显示它们具有不同的植物免疫系统激活能力。该研究获得了猕猴桃溃疡病分离菌株,其表型差异为后续的致病基因遗传分析奠定了基础。

关键词：猕猴桃丁香假单胞菌猕猴桃致病变种(Psa) 病原菌分离致病性超敏反应

在线全文

学校读者我要写书评

暂无评论

航天产品整机的线缆布线研究

今日自动化 2024年第2期 35-37页

作者：胡婕卢治兵吕明刘骏飞北京遥感设备研究所北京100000

新一代航天产品整机的体积小、装填密度大,为线缆布线方式带来了新的挑战。文章结合几个故障案例,介绍了航天产品整机在线束绑扎固定过程中应遵循的原则和工艺要求,列举了常见的线缆固定标准件及工具,指出了具体的操作及检验要求。经过... 详细信息

新一代航天产品整机的体积小、装填密度大,为线缆布线方式带来了新的挑战。文章结合几个故障案例,介绍了航天产品整机在线束绑扎固定过程中应遵循的原则和工艺要求,列举了常见的线缆固定标准件及工具,指出了具体的操作及检验要求。经过多型号航天产品实践验证,这些工艺措施应用效果较好。

关键词：线束绑扎整机装配布线一致性提高布线工艺质量

Neural basis of Chinese phonological processing under picture stimulus A functional magnetic resonance imaging study

维普期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2011年第11期6卷 821-825页

作者： junfei liu Jiangsu Key Laboratory of Language and Cognitive Neuroscience Xuzhou 221009 Jiangsu Province China Institute of Linguistics Xuzhou Normal University Xuzhou 221009 Jiangsu Province China

Studies concerning phonological processing mainly use written stimuli. Functional magnetic resonance imaging was used to investigate the brain regions related to the phonological processing under the picture stimulus in the rhyme task of Chinese language. Results of the test in 13 healthy college students whose native language is Chinese showed the extensive activation in the frontal lobe, parietal lobe and the occipitotemporal cortex, including the inferior frontal gyrus, middle frontal gyrus, supramarginal gyrus and medial occipitotemporal gyrus under the picture stimuli. Moreover, phonological processing induced activation in the superior temporal gyrus （BA 22） under the picture stimuli, but activation was not found in the middle temporal gyrus.

关键词： functional magnetic resonance imaging phonological processing picture stimuli middle frontal gyrus medial occipitotemporal gyrus

A hybrid attention model based on first-order statistical features for smoke recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第3期67卷 809-822页

作者： GUO Nan liu JiaHui DI KeXin GU Ke QIAO junfei Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Artificial Intelligence InstituteBeijing 100124China Faculty of Information Technology Beijing University of TechnologyBeijing 100124China

Smoke and fire recognition are of great importance on foreseeing fire disasters and preventing environmental pollution by monitoring the burning process of objects(e.g., straw, fuels). However, since fire images suffer from problems like the variability of the features, complexity of scenarios, interference from background, changeable weather conditions as well as image quality problems, identifying smoke and fire accurately and promptly from a given image still remains a substantial challenge. Automatically learning the features of smoke images by CNNs has improved the target recognition ability compared to traditional approaches,nonetheless, convolutions and pooling operations in CNNs may cause severe information loss which may lead to *** tackle the above problems, this paper proposed a hybrid attention model based on the characteristics of smoke images. This model adopted multiple optimized attention mechanism in several stages to quickly and precisely capture the important features,achieving state-of-the-art performance on smoke and fire recognition in terms of accuracy and speed. Our proposed module mainly consists of two stages: pooling and attention. In the first stage, we conducted several newly proposed first-order pooling methods. Through traversing the data space in a larger scope, features are better reserved, thus constructing a more intact feature space of smoke and fire in an image. In the second stage, feature maps are aggregated together to perform channel and spatial attention. The channel and spatial dependencies allow us to quickly catch the important features presented in an image. By fully exploring the feature space and prominent salient features, characteristics of smoke and fire are better presented so as to obtain better smoke and fire detection results. Experiments have been conducted on public smoke detection dataset and new proposed fine-grained smoke and fire detection database. Experimental results revealed that the propose

关键词： hybrid attention first-order pooling smoke and fire detection deep convolutional neural networks

High-performance formaldehyde prediction for indoor air quality assessment using time series deep learning

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2024年第3期17卷 415-429页

作者： liu Lu Xinyu Huang Xiaojun Zhou junfei Guo Xiaohu Yang Jinyue Yan School of Human Settlements and Civil Engineering Xi’an Jiaotong UniversityXi’anChina Department of Building Environment and Energy Engineering The Hong Kong Polytechnic UniversityKowloonHong KongChina Future Energy Profile School of BusinessSocietyand EngineeringMälardalen UniversityVästeråsSweden

Indoor air pollution resulting from volatile organic compounds(VOCs),especially formaldehyde,is a significant health concern needed to predict indoor formaldehyde concentration(Cf)in green intelligent building *** study develops a thermal and wet coupling calculation model of porous fabric to account for the migration of formaldehyde molecules in indoor air and cotton,silk,and polyester fabric with heat flux in Harbin,Beijing,Xi’an,Shanghai,Guangzhou,and Kunming,*** time-by-time indoor dry-bulb temperature(T),relative humidity(RH),and Cf,obtained from verified simulations,were collated and used as input data for the long short-term memory(LSTM)of the deep learning model that predicts indoor multivariate time series Cf from the secondary source effects of indoor fabrics(adsorption and release of formaldehyde).The trained LSTM model can be used to predict multivariate time series Cf at other emission times and *** LSTM-based model also predicted Cf with mean absolute percentage error(MAPE),symmetric mean absolute percentage error(SMAPE),mean absolute error(MAE),mean square error(MSE),and root mean square error(RMSE)that fell within 10%,10%,0.5,0.5,and 0.8,*** addition,the characteristics of the input dataset,model parameters,the prediction accuracy of different indoor fabrics,and the uncertainty of the data set are *** results show that the prediction accuracy of single data set input is higher than that of temperature and humidity input,and the prediction accuracy of LSTM is better than recurrent neural network(RNN).The method’s feasibility was established,and the study provides theoretical support for guiding indoor air pollution control measures and ensuring human health and safety.

关键词： multivariate time series formaldehyde concentration deep learning heat-humidity coupling mass transfer secondary source effect

Intelligent construction technology of railway engineering in China

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

Frontiers of Engineering Management 2019年第4期6卷 503-516页

作者： Chunfang LU junfei liu Yanhong liu Yuming liu China Railway Society Beijing 100844China Engineering Management Center China Railway CorporationBeijing 100844China School of Economics and Management Beijing Jiaotong UniversityBeijing 100044China

Intelligent construction technology has been widely used in the field of railway *** work first analyzes the connotation,function,and characteristics of intelligent construction of railway engineering(ICRE)and establishes its system structure from three dimensions,namely,life cycle,layers of management,and intelligent function,to deeply understand the development situation of intelligent railway construction in ***,seven key technical support systems of ICRE,which include building information modeling(BIM)standard system for China’s railway sector,technology management platform and life cycle management based on BIM-hGIS(geography information system),ubiquitous intelligent perception system,intelligent Intemet-of-Things(IoT)communication system based on mobile interconnection,construction management platform based on cloud computing and big data,unmanned operation system based on artificial intelligence,intelligent machinery and robot,and intelligent operation and maintenance system based on BIM and PHM(prediction and health management),are ***,ICRE is divided into three development stages:primary(perception),intermediate(substitution),and advanced(intelligence).The evaluation index system of each stage is provided from the aspects of technology and ***,this work summarizes and analyzes the application situation of ICRE in the entire railway sector of China,represented by Beijing-Zhangjiakou and Beijing-Xiong’an high-speed *** shows that the technical support systems of the ICRE have emerged in China and are still in the process of deepening basic technology research and preliminary *** the future,the ICRE of China’s railway sector will develop toward a higher stage.

关键词： China railway sector intelligent construction railway engineering informatization development stage

The response of roots and the rhizosphere environment to integrative cultivation practices in paddy rice

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

Journal of Integrative Agriculture 2024年第6期23卷 1879-1896页

作者： Hanzhu Gu Xian Wang Minhao Zhang Wenjiang Jing Hao Wu Zhilin Xiao Weiyang Zhang junfei Gu Lijun liu Zhiqin Wang Jianhua Zhang Jianchang Yang Hao Zhang Jiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology/Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops/Agricultural College Yangzhou UniversityYangzhou 225009China Taizhou Institute of Agricultural Science Jiangsu Academy of Agricultural SciencesTaizhou 225300China State Key Laboratory of Agrobiotechnology School of Life SciencesThe Chinese University of Hong KongShatinHong Kong 999077China Department of Biology Faculty of ScienceHong Kong Baptist UniversityKowloonHong Kong 999077China

Integrative cultivation practices(ICPs)are essential for enhancing cereal yield and resource use ***,the effects of ICP on the rhizosphere environment and roots of paddy rice are still poorly *** this study,four rice varieties were produced in the *** variety was treated with six different cultivation techniques,including zero nitrogen application(0 N),local farmers’practice(LFP),nitrogen reduction(NR),and three progressive ICP techniques comprised of enhanced fertilizer N practice and increased plant density(ICP1),a treatment similar to ICP1 but with alternate wetting and moderate drying instead of continuous flooding(ICP2),and the same practices as ICP2 with the application of organic fertilizer(ICP3).The ICPs had greater grain production and nitrogen use efficiency than the other three *** length,dry weight,root diameter,activity of root oxidation,root bleeding rate,zeatin and zeatin riboside compositions,and total organic acids in root exudates were elevated with the introduction of the successive cultivation *** enhanced nitrate nitrogen,the activities of urease and invertase,and the diversity of microbes(bacteria)in rhizosphere and non-rhizosphere soil,while reducing the ammonium nitrogen *** nutrient contents(ammonium nitrogen,total nitrogen,total potassium,total phosphorus,nitrate,and available phosphorus)and urease activity in rhizosphere soil were reduced in all treatments in comparison with the non-rhizosphere soil,but the invertase activity and bacterial diversity were *** main root morphology and physiology,and the ammonium nitrogen contents in rhizosphere soil at the primary stages were closely correlated with grain yield and internal nitrogen use *** findings suggest that the coordinated enhancement of the root system and the environment of the rhizosphere under integrative cultivation approaches may lead to higher rice production.

关键词： rice(Oryza sativa L.) nitrogen use efficiency grain yield integrative cultivation practices roots