检索结果-南通市图书馆

A PREDICTION SCHEME FOR THE PRECIPITATION OF SPR BASED ON THE DATA MINING ALGORITHM AND CIRCULATION ANALYSIS

在线全文

学校读者我要写书评

暂无评论

Journal of Tropical Meteorology 2019年第4期25卷 519-527页

作者： LI Chao SHI Da・wei CHEN Yu-tian ZHANG Hong-hua geng huan-tong WANG Peng Jiangsu Meteorological Observatory Nanjing 210008 China Meteorological Bureau of Lianyungang City Lianyungang 222000 China College of Geography Nanjing University of Information Science and TechnologyNanjing 210044 China College of Continuing Education Nanjing University of Infbnnation Science and TechnologyNanjing 210044 China

Based on the 74 circulation indexes provided by National Climate Center of China(NCC) and the 24 indexes compiled by National Oceanic and Atmospheric Administration(NOAA) of the US, the study used the C4.5 algorithm in data mining to establish a decision tree prediction model to predict whether the spring persistent rains(SPR) of 55 years(from 1961 to 2015) is more than the normal, and obtained 5 rules to determine whether the SPR is more than the normal. The accuracy rate of the test set, namely "whether the SPR is more than the normal", is 98.18%. After the evaluation of the model by conducting ten 10-fold cross validations to take the average value, the test accuracy rate gained is 84%. There are differences between the three types of years with a SPR more than the normal when it comes to intensity and distribution. In spring, they have respective anomalous 850 hPa monthly mean wind fields and water-vapor flux distribution, and 700 hPa forms the zone where the vertical speed is anomalously negative. As indicated by the results, the SPR prediction model based on the C4.5 algorithm has a high prediction accuracy rate, the model is reasonably and effectively constructed, and the decision rules take comprehensive factors into consideration. The anomalous rainfall and circulation distribution characteristics obtained based on the decision classification results provide new ideas and methods for the prediction of SPR.

关键词： spring persistent rains data mining C4.5 algorithm prediction model model analysis

Decision Cost Feature Weighting and Its Application in Intrusion Detection

在线全文

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2004年第5期9卷 765-769页

作者： QIANQuan genghuan-tong WANGXu-fa DepartmentofComputerScience.UniversityofSciene＆TechnologyofChina Hefei230027AnhuiChina

This paper introduces the cost-sensitive feature weighting strategy and its application in intrusion detection. Cost factors and cost matrix are proposed to demonstrate the misclassification cost for IDS. How to get the whole minimal risk, is mainly discussed in this paper in detail. From experiments, it shows that although decision cost based weight learning exists somewhat attack misclassification, it can achieve relatively low misclassification costs on the basis of keeping relatively high rate of recognition precision. Key words decision cost - feature weighting - intrusion detection CLC number TP 393. 08 Foundation item: Supported by the National Natural Science Foundation Key Research Plan of China (90104030) and “20 Century Education Development Plan”Biography: QIAN Quan(1972-), male, Ph. D. research direction: computer network, network security and artificial intelligence

关键词： decision cost feature weighting intrusion detection

Automatic car license plate recognition based on edges and color

在线全文

学校读者我要写书评

暂无评论

通讯和计算机（中英文版） 2009年第4期6卷 47-50,59页

作者： JIAO Feng BI Shuo-ben geng huan-tong Computer and Software Institute Nanjing University of Information Science and Technology Nanjing 210044 China

In this paper we present a scheme for fast detection of the car license plates area and recognition of characters in 2D color images. In this scheme we first get the possible license plates area in the image with two kinds of information -- rectangle edges and connected ribbon area. And then, according to the size, color and shape characteristics, the area of car license plate can be decided. This scheme has less affection caused by light and blur. At the same time, a smart algorithm to detect and revise the oblique of characters is also introduced. Experiment results prove its good efficiency.

关键词：汽车牌照平面识别矩形边缘颜色

Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model

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 Tropical Meteorology 2023年第4期29卷 482-492页

作者：耿焕同谢博洋葛晓燕闵锦忠庄潇然 School of Software Nanjing University of Information Science and TechnologyNanjing 210044 China China Meteorological Administration Radar Meteorology Key Laboratory Nanjing 210023 China Jiangsu Meteorological Observatory Nanjing 210008 China

Weather radar echo extrapolation plays a crucial role in weather ***,traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical *** learning algorithms based on Recurrent Neural Networks also have the problem of accumulating ***,it is difficult to obtain higher accuracy by relying on a single historical radar echo ***,in this study,we constructed the Fusion GRU module,which leverages a cascade structure to effectively combine radar echo data and mean wind *** also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the *** on the Jiangsu Province dataset,we compared some *** results show that our proposed model,Cascade Fusion Spatiotemporal Network(CFSN),improved the critical success index(CSI)by 10.7%over the baseline at the threshold of 30 *** experiments further validated the effectiveness of our ***,the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.

关键词： deep learning spatiotemporal prediction radar echo extrapolation recurrent neural network multimodal fusion

MnO-pillared graphene blocks enabling the ultrastable and ultrafast aqueous zinc ion batteries

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2024年第9期67卷 2930-2940页

作者： Zheng Liu Zhipeng Qiu Zhiyuan Li tong Wei Zhuangjun Fan huan Pang School of Chemistry and Chemical Engineering Yangzhou UniversityYangzhou 225002China School of Materials Science and Engineering China University of PetroleumQingdao 266580China

Due to the low cost,high theoretical capacity,and environmental friendliness,manganese-based cathodes are regarded as promising alternatives for aqueous zinc ion batteries(AZIBs).However,the practicality of the zinc-manganese system is faced with great challenges,such as the inevitable structural collapse of the cathode and controversial energy storage ***,we propose a novel concept of spatial deposition mechanism through the addition of MnSO_(4) additives in the Mn O-pillared graphene blocks(G-MnO).The covalent interface between MnO nanoparticles and multilayered graphene nanosheets can construct an in-built micro-electric field,which is beneficial for consecutive electron transfer(in both horizontal and vertical directions).On this basis,the surficial activity of MnO confined in the interlayered nano-space is greatly enhanced and provides enough spatial deposition and subsequent reaction site for MnSO_(4) additives,thus firstly extending the surficial controlled process to stereoscopic space,effectively improving the electrochemical performance of ***,the assembled Zn//G-Mn O battery exhibits an excellent rate capability of 281.5 mAhg^(-1)at 0.1 A g^(-1)and 106 mAhg^(-1)at 20 Ag^(-1),and impressive cycling stability(93 mAhg^(-1)remaining after 5,000 cycles).This finding may provide a new opportunity for the rational design of surficial controlled energy storage and conversion devices.

关键词： zinc-ion battery manganese monoxide laminated constructure ultrahigh rate performance graphene

在线全文

学校读者我要写书评

暂无评论

范例推理在网络自动答疑系统中应用

计算机工程与应用 2008年第3期44卷 31-33,74页

作者：耿焕同毕硕本南京信息工程大学计算机与软件学院

针对教育快速发展与教师资源相对紧缺间的突出矛盾,利用计算机网络技术,提出了一种基于范例推理的网络自动答疑专家系统。该系统能综合多位优秀教师的知识,克服了传统面对面答疑方式受时空限制的缺陷。实验表明,基于范例推理技术的自动... 详细信息

针对教育快速发展与教师资源相对紧缺间的突出矛盾,利用计算机网络技术,提出了一种基于范例推理的网络自动答疑专家系统。该系统能综合多位优秀教师的知识,克服了传统面对面答疑方式受时空限制的缺陷。实验表明,基于范例推理技术的自动答疑系统是非常有效地、较好地满足答疑准确性的要求,而且具有很强的学习性。

关键词：范例推理计算机网络文本处理自动答疑

在线全文

学校读者我要写书评

暂无评论

基于双重贡献分配的多目标混合算子进化算法

控制与决策 2022年第5期37卷 1195-1202页

作者：耿焕同许可戴中斌徐小涵南京信息工程大学计算机与软件学院南京210044 江苏省气象局南京大气科学联合研究中心南京210009

针对多目标混合算子进化算法中各算子有效选择的自适应问题,提出一种基于双重贡献分配的多目标混合算子进化算法(DCA-MOEA/D).首先,将两种现有的进化算子与两种基于方向引导的差分进化组成算子池,每代个体以轮盘赌的方式从中选择一种进... 详细信息

针对多目标混合算子进化算法中各算子有效选择的自适应问题,提出一种基于双重贡献分配的多目标混合算子进化算法(DCA-MOEA/D).首先,将两种现有的进化算子与两种基于方向引导的差分进化组成算子池,每代个体以轮盘赌的方式从中选择一种进化算子产生子代;然后,根据子代的表现,结合两种方法为各算子分配贡献值,从而确定算子的选择概率;接着,引入外部归档集,根据非支配关系与拥挤度策略对其进行维护;最后,将整个进化过程划分为5个阶段,以达到算子选择中“探索”与“探究”之间的平衡.以IGD与HV为性能评价指标,通过与其他4种多目标进化算法在23个测试函数上的对比,验证所提出算法在收敛性和分布性上的显著优势.

关键词：多目标优化混合算子贡献分配算子选择

Possible Role of Cellular Polyamine Metabolism in Neuronal Apoptosis

在线全文

学校读者我要写书评

暂无评论

Current Medical Science 2024年第2期44卷 281-290页

作者： Xin-tong JI Wen-lei YU Meng-jia JIN Lin-jie LU Hong-ping YIN huan-huan WANG School of Basic Medical Sciences Affiliated Hospital of Hangzhou Normal UniversityHangzhou Normal UniversityHangzhou 311121China School of Medicine Chongqing UniversityChongqing 400030China Department of Stomatology Huzhou Wuxing District People's HospitalHuzhou Wuxing District Maternal and Child Health HospitalHuzhou 313008China School of Pharmacy Zhejiang UniversityHangzhou 310030China Department of Stomatology Haining Hospital of Traditional Chinese MedicineJiaxing 314400China

Recent studies have shown that cellular levels of polyamines(PAs)are significantly altered in neurodegenerative *** from in vivo animal and in vitro cell experiments suggests that the cellular levels of various PAs may play important roles in the central nervous system through the regulation of oxidative stress,mitochondrial metabolism,cellular immunity,and ion channel *** of PA metabolism related enzymes also contributes to neuronal injury and cognitive impairment in many neurodegenerative ***,in the current work,evidence was collected to determine the possible associations between cellular levels of PAs,and related enzymes and the development of several neurodegenerative diseases,which could provide a new idea for the treatment of neurodegenerative diseases in the future.

关键词： polyamine apoptosis mitochondria neurodegenerative disease

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

基于分解的预测型动态多目标粒子群优化算法

控制与决策 2019年第6期34卷 1307-1318页

作者：耿焕同周山胜陈哲韩伟民南京信息工程大学计算机与软件学院南京210044

针对动态多目标问题求解,提出一种基于分解的预测型动态多目标粒子群优化算法.首先借助分解思想,将目标问题划分为多个不同的子问题,当问题动态变化时,选择对应于不同子问题的优化个体检测环境变化程度,以提高算法对不同动态问题的适应... 详细信息

针对动态多目标问题求解,提出一种基于分解的预测型动态多目标粒子群优化算法.首先借助分解思想,将目标问题划分为多个不同的子问题,当问题动态变化时,选择对应于不同子问题的优化个体检测环境变化程度,以提高算法对不同动态问题的适应与响应能力;然后,设计一种群体预测策略,通过将目标空间中相同收敛方向上不同时刻的个体位置转换为时间序列,引入时间序列预测方法预测下一刻位置,从而提高预测种群的多样性和有效性,进而有效减少算法在问题变化后的收敛时间;最后,为避免问题发生变化后个体与子问题不匹配,设计一种再匹配策略,以提高预测策略的准确性.实验结果表明,在6个标准动态多目标测试问题上,与2个动态多目标优化算法进行比较,所提出算法在收敛性、分布性与稳定性上均具有显著优势.

关键词：动态多目标优化预测粒子群优化分解