检索结果-南通市图书馆

Intracranial Epileptic Seizures Detection Based on an Optimized Neural Network Classifier

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第3期30卷 419-425页

作者： gong chen LIU Jiahui NIU Yunyun School of Information Engineering China University of Geosciences in Beijing Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences

Automatic identification of intracranial electroencephalogram(i EEG) signals has become more and more important in the field of medical *** this paper, an optimized neural network classifier is proposed based on an improved feature extraction method for the identification of i EEG epileptic *** kinds of entropy, Sample entropy, Approximate entropy, Shannon entropy, Log energy entropy are extracted from the database as the feature vectors of Neural network(NN) during the identification *** kinds of classification tasks, namely Pre-ictal v Post-ictal(CD), Pre-ictal v Epileptic(CE), Post-ictal v Epileptic(DE), Pre-ictal v Post-ictal v Epileptic(CDE),are used to test the effect of our classification *** experimental results show that our algorithm achieves higher performance in all tasks than previous *** effect of hidden layer nodes number is investigated by a constructive approach named growth method. We obtain the optimized number ranges of hidden layer nodes for the binary classification problems CD, CE, DE, and the multitask classification problem CDE, respectively.

关键词： improved feature extraction method medical signal processing optimized neural network classifier classification method classification tasks identification process intracranial electroencephalogram signals feature extraction medical diagnostics entropy feature vectors intracranial Epileptic seizures detection optimized number ranges Approximate entropy Log energy entropy neural nets Pre-ictal v Post-ictal medical signal detection constructive approach named growth method automatic identification pattern classification Shannonentropy electroencephalography Sample entropy

Dynamic and Numerical Study of Waves in the Tibetan Plateau Vortex

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2014年第1期31卷 131-138页

作者： chen gong LI Guoping Institute of Plateau Meteorology China Meteorological Administration College of Atmospheric Sciences Chengdu University of Information Technology and The Key Laboratory of Plateau Atmosphere and Environment of Sichuan Province

In terms of its dynamics, The Tibetan Plateau Vortex （TPV） is assumed to be a vortex in the botmdary layer forced by diabatic heating and friction. In order to analyze the basic characteristics of waves in the vortex, the governing equations for the vortex were established in column coordinates with the balance of gradient wind. Based on this, the type of mixed waves and their dispersion characteristics were deduced by solving the linear model. Two numerical simulations with triple-nested domains--one idealized large-eddy simulation and one of a TPV that took place on 14 August 2006---were also carried out. The aim of the simulations was to validate the mixed wave deduced from the governing equations. The high-resolution model output data were analyzed and the results showed that the tangential flow field of the TPV in the form of center heating was cyclonic and convergent in the lower levels and anticyclonic and divergent in the upper levels. The simulations also showed that the vorticity of the vortex is uneven and might have shear flow along the radial direction. The changing vorticity causes the formation and spreading of vortex Rossby （VR） waves, and divergence will cause changes to the n^otion of the excitation and evolution of inertial gravity （IG） waves. Therefore, the vortex may contain what we call mixed ：inertial gravity-vortex Rossby （IG-VR） waves. It is suggested that some strongly developed TPVs should be studied in the future, because of their effects on weather in downstream areas.

关键词： Tibetan Plateau Vortex thermal forcing tangential flow field mixed inertial gravity-vortex Rossby waves

Bleeding canker of pear-An emerging devastating disease

在线全文

学校读者我要写书评

暂无评论

Journal of Integrative Agriculture 2020年第4期19卷 887-888页

作者： chen gong-you Department of Environment and Resource School of Agriculture and BiologyShanghai Jiao Tong UniversityShanghai 200240P.R.China

Bleeding canker (BC) of pear trees, is a devastating disease in China. The disease was originally observed in Jiangsu Province and its causal agent was identified first as Erwinia sp. in the early 1970's and latter as a novel species, Dickeya fangzhongdai. BC is epidemically emerging prevalently from April to September annually in pear-growing regions in Zhejiang, Anhui and Shandong provinces, and threatening pear industry currently in China. To better control BC disease, it is crucial to know BC symptomatology, epidemics, etiology, and diagnostics first. The special topic of the three papers have well illustrated the points mentioned above.

关键词： annually Anhui mentioned

Hierarchical LSTM with char-subword-word tree-structure representation for Chinese named entity recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第10期63卷 74-88页

作者： chen gong Zhenghua LI Qingrong XIA Wenliang chen Min ZHANG School of Computer Science and Technology Soochow University

Chinese named entity recognition(CNER) aims to identify entity names such as person names and organization names from Chinese raw text and thus can quickly extract the entity information that people are concerned about from large-scale texts. Recent studies attempt to improve performance by integrating lexicon words into char-based CNER models. These existing studies, however, usually focus on leveraging the context-free words in lexicon without considering the contextual information of words and subwords in the sentences. To address this issue, in addition to utilizing the lexicon words, we further propose to construct a hierarchical tree structure representation composed of characters, subwords and context-aware predicted words from segmentor to represent each sentence for CNER. Based on the tree-structure representation, we propose a hierarchical long short-term memory(HiLSTM) framework, which consists of hierarchical encoding layer, fusion layer and CRF layer, to capture linguistic knowledge at different levels. On the one hand, the interactions within each level help to obtain the contextual information. On the other hand, the propagations from the lower-levels to the upper-levels can provide additional semantic knowledge for CNER. Experimental results on three widely used CNER datasets show that our proposed HiLSTM model achieves significant improvement over several strong benchmark methods.

关键词： natural language processing named entity recognition representation learning neural networks

Preparation of activated carbons and their adsorption properties for greenhouse gases:CH_4 and CO_2

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Natural Gas Chemistry 2011年第5期20卷 460-464页

作者： Hao Yang Maochu gong Yaoqiang chen Key Laboratory of Green Chemistry ＆ Technology of Ministry of Education College of Chemistry Sichuan University Chengdu 610064 Sichuan China

Three kinds of activated carbons were prepared using coconut-shells as carbon precursors and characterized by XRD, FT-IR and texture property test. The results indicate that the prepared activated carbons were mainly amorphous and only a few impurity groups were adsorbed on their surfaces. The texture property test reveals that the activated carbons displayed different texture properties, especially the micropore size distribution. The adsorption capacities of the activated carbons were investigated by adsorbing CH4, CO2, N2 and O2 at 25 ？C in the pressure range of 0-200 kPa. The results reveal that all the activated carbons had high CO2 adsorption capacity, one of which had the highest CO2 adsorption value of 2.55 mmol/g at 200 kPa. And the highest adsorption capacity for CH4 of the activated carbons can reach 1.93 mmol/g at 200 kPa. In the pressure range of 0-200 kPa, the adsorption capacities for N2 and O2 were increased linearly with the change of pressure and K-AC is an excellent adsorbent towards the adsorption separation of greenhouse gases.

关键词： activated carbon greenhouse gas adsorption property CH4 CO2

Synthesis of β-alkynyl α-amino acids via palladium-catalyzed alkynylation of unactivated C(sp^3)-H bonds

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2015年第8期58卷 1345-1348页

作者： Bo Wang Gang He gong chen Department of Chemistry the Pennsylvania State University University Park

β-Di-substituted α-amino acids(AAs) contain adjacent carbon stereogenic centers and pose considerable synthetic challenge. Complementary to the conventional synthesis strategies based on the transformation of existing functional groups, we envisioned these molecules could be quickly accessed via selective functionalization of sp3 hybridized C-H bonds on the side chains of common α-AA precursors. We report a readily applicable method to prepare β-alkynyl α-amino acids via Pd-catalyzed diastereoselective C(sp3)-H alkynylation of common α-amino acids precursors with acetylene bromide.

关键词： α-amino acids C-H functionalization palladium

Building,Integrating,and Sharing Our Aging Society:Improving Older Adults’Health Together

在线全文

学校读者我要写书评

暂无评论

China CDC weekly 2021年第40期3卷 835-836页

作者： gong chen Peking University Institute of Population Research Peking University Institute of Ageing Study

This year marks the 20th anniversary of China becoming an aging society and the follow-up year of the 30th International Year of Older *** key policy of active response to population aging has been elevated to a national strategy(1).Thus,now is an important time for China CDC Weekly to publish a series of studies on health status and ways to improve the health of older Chinese adults.

关键词： Together policy becoming

A study on specialist or special disease clinics based on big data

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 Medicine 2014年第3期8卷 376-381页

作者： Zhuyuan Fang Xiaowei Fan gong chen Jiangsu Province Ho spital of TCM Nanjing 210029 China

Correlation analysis and processing of massive medical information can be implemented through big data technology to find the relevance of different factors in the life cycle of a disease and to provide the basis for scientific research and clinical practice. This paper explores the concept of constructing a big medical data platform and introduces the clinical model construction. Medical data can be collected and consolidated by distributed computing technology. Through analysis technology, such as artificial neural network and grey model, a medical model can be built. Big data analysis, such as Hadoop, can be used to construct early prediction and intervention models as well as clinical decision-making model for specialist and special disease clinics. It establishes a new model for common clinical research for specialist and special disease clinics.

关键词： big data correlation analysis medical information integration data analysis clinical model

Self-assembly and electrochromic property of electroactive tetraaniline-b-PEG diblock copolymer

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

Science China Chemistry 2017年第1期60卷 99-104页

作者： Linyu Cao Jiping Yang chen gong Meng Wang Key Laboratory of Aerospace Advanced Materials and Performance Ministry of Education School of Materials Science and Engineering Beihang University Beijing 100083 China

A kind of amphiphilic rod-coil diblock copolymer consisting both of tetraaniline(TAni)and polyethylene glycol(PEG)blocks,TAni-b-PEG,was *** diblock copolymer shows excellent electrochromic properties,especially,in switching time and coloration efficiency compared with ***-b-PEG is able to self-assemble into spherical structure,which is attributed to the formation of conducting channels and increase of ion-exchange capacity of TAni-b-PEG,implying that a block copolymer with electrochromic block and high ionic conductive block simultaneously possesses improving electrochromic properties.

关键词： tetraaniline PEG block copolymer self-assembly electrochromic property