检索结果-南通市图书馆

Effective short text classification via the fusion of hybrid features for IoT social data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2022年第6期8卷 942-954页

作者： Xiong Luo Zhijian Yu zhigang zhao Wenbing zhao Jenq-Haur Wang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Shunde Innovation School University of Science and Technology BeijingFoshan528399China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083China Department of Electrical Engineering and Computer Science Cleveland State UniversityClevelandOH44115USA Department of Computer Science and Information Engineering National Taipei University of TechnologyTaipei10608China

Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Previous studies mainly tackle these problems by enhancing the semantic information or the statistical information individually. However, the improvement achieved by a single type of information is limited, while fusing various information may help to improve the classification accuracy more effectively. To fuse various information for short text classification, this article proposes a feature fusion method that integrates the statistical feature and the comprehensive semantic feature together by using the weighting mechanism and deep learning models. In the proposed method, we apply Bidirectional Encoder Representations from Transformers (BERT) to generate word vectors on the sentence level automatically, and then obtain the statistical feature, the local semantic feature and the overall semantic feature using Term Frequency-Inverse Document Frequency (TF-IDF) weighting approach, Convolutional Neural Network (CNN) and Bidirectional Gate Recurrent Unit (BiGRU). Then, the fusion feature is accordingly obtained for classification. Experiments are conducted on five popular short text classification datasets and a 5G-enabled IoT social dataset and the results show that our proposed method effectively improves the classification performance.

关键词： Information fusion Short text classi fication BERT Bidirectional encoder representations fr 0om transformers Deep learning Social data

Pattern recognition of messily grown nanowire morphologies applying multi-layer connected self-organized feature maps

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2019年第5期35卷 946-956页

作者： Qing Liu Hejun Li Yulei Zhang zhigang zhao State Key Laboratory of Solidification Processing Carbon/Carbon Composites Technology Research Center Northwestern Polytechnical University

Multi-layer connected self-organizing feature maps(SOFMs) and the associated learning procedure were proposed to achieve efficient recognition and clustering of messily grown nanowire morphologies. The network is made up by several paratactic 2-D SOFMs with inter-layer connections. By means of Monte Carlo simulations, virtual morphologies were generated to be the training samples. With the unsupervised inner-layer and inter-layer learning, the neural network can cluster different morphologies of messily grown nanowires and build connections between the morphological microstructure and geometrical features of nanowires within. Then, the as-proposed networks were applied on recognitions and quantitative estimations of the experimental morphologies. Results show that the as-trained SOFMs are able to cluster the morphologies and recognize the average length and quantity of the messily grown nanowires within. The inter-layer connections between winning neurons on each competitive layer have significant influence on the relations between the microstructure of the morphology and physical parameters of the nanowires within.

关键词： Artificial neural networks Self-organizing feature maps Monte Carlo simulation Pattern recognition Messily grown nanowire morphologies

Ablation Mechanism of HfC-HfO2Protective Coating for SiC-Coated C/C Composites in an Oxyacetylene Torch Environment

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2017年第10期33卷 1195-1202页

作者： Yang Yang Kezhi Li Guanxi Liu zhigang zhao State Key Laboratory of Solidification Processing Carbon/Carbon Composites Research Center Northwestern Polytechnical University Xi'an 710072 China

To prevent the C/C composites from ablation, HfC-HfO2 protective coating was prepared by supersonic atmospheric plasma spraying. The morphology and microstructure of HfC-HfO2 coating were characterized by X-ray diffraction and scanning electron microscopy. The ablation resistance test was carried out by an oxyacetylene torch. The results show that the as-prepared coating is dense with little pinholes and crack free. The elements Hf, C and O were uniformly distributed in the cross-section. After ablation for different time, the mass ablation rate fluctuated along with the change of ablation time. The ablation process of the surface coating could be divided into rapid oxidation and solid state sintering stages. During ablation, an Hf CxOy-HfO2 transitional layer was generated in the coating, which resulted from the active oxidation of Hf C. After cooling, some microcracks were observed on the surface of coating, and the structure of cross-section was broken, which were due to the phase transition of HfO2.

关键词： Carbon/carbon composites Supersonic atmospheric plasma spraying Protective coating Ablation property

A smart cluster paradigm based Mo-containing polyoxometalate as a new therapeutic strategy for tumor-specific photothermal therapy

在线全文

学校读者我要写书评

暂无评论

Science Bulletin 2018年第14期63卷 877-878页

作者： Yuan Yong Shengtao Yang zhigang zhao College of Chemistry and Environment Protection Engineering. Southwest Minzu University. Chengdu 610041 China

A desirable near-infrared(NIR)photothermal agent based on Mo-based polyoxometalate cluster with self-adaptive electronic structure for tumor acidity/reducibility-specific therapy was reported in a paper on Journal of the American Chemical Society[1].This‘‘small-big"cluster paradigm displayed the capacity of self-assemble to big molecules under activation both the

关键词：治疗学肿瘤瞬间簇电子结构微型环境红外线代理人

Efficient high harmonics generation by enhancement cavity driven with a post-compressed FCPA laser at 10 MHz

在线全文

学校读者我要写书评

暂无评论

High Power Laser Science and Engineering 2018年第2期6卷 45-50页

作者： zhigang zhao Akira Ozawa Makoto Kuwata-Gonokami Yohei Kobayashi The Institute for Solid State Physics The University of Tokyo Department of Physics Graduate School of Science The University of Tokyo

Efficient high harmonics generation(HHG) was demonstrated at 10 MHz repetition rate with an external femtosecond enhancement cavity, seeded by a ～70 fs post-compressed 10 MHz fiber chirped pulse amplifier(FCPA) laser. Operation lasting over 30 min with 0.1 m W outcoupled power at 149 nm was demonstrated. It was found that shorter pulse was beneficial for alleviating the nonlinear plasma effect and improving the efficiency of HHG. Low finesse cavity can relax the plasma nonlinearity clamped intra-cavity power and improve the cavity-locking stability. The pulse duration is expected to be below 100 fs for both 1040 nm and 149 nm outputs, making it ideal for applications such as time-resolved photoemission spectroscopy.

关键词： enhancement cavity high harmonics generation ultrafast fiber lasers

A review on co-pyrolysis of coal and oil shale to produce coke

在线全文

学校读者我要写书评

暂无评论

Frontiers of Chemical Science and Engineering 2020年第4期14卷 504-512页

作者： Xiangchun Liu Ping Cui Qiang Ling zhigang zhao Ruilun Xie Anhui Key Laboratory of Coal Clean Conversion and Utilization School of Chemistry and Chemical EngineeringAnhui University of TechnologyMa'anshanAnhui 243002China

It has become the top priority for coking industry to rationally use and enlarge coking coal resources because of the shortage of the *** review focuses on the potential utilization of oil shale(OS)as a feedstock for coal-blending coking,in which the initial and basic step is ***,OS has a high ash *** such OS is directly used for coal-blending coking,the coke product will not meet market ***,this review firstly summarizes separation and beneficiation techniques for organic matter in OS,and provides an overview on coal and OS pyrolysis through several viewpoints(e.g.,pyrolysis process,phenomena,and products).Then the exploratory studies on co-pyrolysis of coal with OS,including co-pyrolysis phenom-ena and process mechanism,are ***,co-pyrolysis of different ranks of coals with OS in terms of coal-blending coking,where further research deserves to be performed,is suggested.

关键词： coal oil shale co-pyrolysis coal blending coking coke

Simulating the heartwood formation process of Erythrophleum fordii in South 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

Journal of Forestry Research 2015年第4期26卷 1049-1055页

作者： zhigang zhao Junjie Guo Chunsheng Wang Jie Zeng Research Institute of Tropical Forestry CAF

We studied the formation of heartwood in Ery- throphleumfordii Oliv., an endangered rosewood species, by cross-section analysis on 52 stumps aged 28-57 years and arbitrarily sampled from natural forests in South China. Width and area of heartwood were positively correlated with age and xylem width （XW）, and were independent of annual radial growth. The proportions of heartwood and sapwood areas were equal at about 40 years. The heartwood formation pro- cess was simulated by linear regression of age and XW.

关键词： Erythrophleum fordii Growth process Heartwood formation Heartwood width Rosewoodspecies

A Survey of Knowledge Graph Construction Using Machine Learning

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 225-257页

作者： zhigang zhao Xiong Luo Maojian Chen Ling Ma School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Shunde Innovation School University of Science and Technology BeijingFoshan528399China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083China

Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured *** framework facilitates a transformation in information retrieval,transitioning it from mere string matching to far more sophisticated entity *** this transformative process,the advancement of artificial intelligence and intelligent information services is ***,the role ofmachine learningmethod in the construction of KG is important,and these techniques have already achieved initial *** article embarks on a comprehensive journey through the last strides in the field of KG via machine *** a profound amalgamation of cutting-edge research in machine learning,this article undertakes a systematical exploration of KG construction methods in three distinct phases:entity learning,ontology learning,and knowledge ***,a meticulous dissection of machine learningdriven algorithms is conducted,spotlighting their contributions to critical facets such as entity extraction,relation extraction,entity linking,and link ***,this article also provides an analysis of the unresolved challenges and emerging trajectories that beckon within the expansive application of machine learning-fueled,large-scale KG construction.

关键词： Knowledge graph(KG) semantic network relation extraction entity linking knowledge reasoning

Research on Chemical Reactivity of Nitrotriazolam in Its Process of Preparation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chemical Research in Chinese Universities 2019年第4期35卷 680-685页

作者： YANG Bowen AN Qiufeng zhao zhigang SHAO Kaiyuan HU Wenxiang Shaanxi Key Laboratory of Chemical Additives for Industry College of Chemistry and Chemical Engineering Shaanxi University of Science and Technology Xi'an 710021 P. R. China College of Chemistry and Environment Protection Engineering Southwest University for NationalitiesChengdu 610041P.R.China Jingdong Xianghu Microwave Chemistry Union Laboratory Beijing Excalibur Space Military Academy of Medical SciencesBeijing 101601P.R.China Aerospace Systems Division Strategic Support TroopsChinese People's Liberation ArmyBeijing 100101P. R.China

Chemical reaction possibility was described quantitatively for the case of nitrotriazolam preparation with 2-clonazepam by using the data of two quantum chemical reactivity indices: net electrophilicity index and Wiberg bond order. Furthennore, relevant reaction mechanism was derived from tlie aspect of quantum chemistry. The results show that the indices used can quantitatively explain the chemical reactivity and reaction mechanism of the nitrotriazolam preparation. To validate the universal applicability of the proposed approach, the authors continued to use the quantum chemical reactivity indices to describe some classic chemical reactions, expecting to predict major issues related to physical organic chemistry, such as new chemical reactions and their mechanisms.

关键词： Density functional tlieory Net electrophilicity index Wiberg bond order Chemical reactivity Reaction mechanism