In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features i...In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).展开更多
在粳稻品种中花11的组培苗中发现1份可以稳定遗传的矮秆多分蘖突变体,相比野生型,突变体株高明显下降、分蘖能力明显增强。为定位控制该性状的基因,以该突变体和野生型杂交构建遗传群体,与籼稻黄华占构建定位群体,再利用SSR和In Del分...在粳稻品种中花11的组培苗中发现1份可以稳定遗传的矮秆多分蘖突变体,相比野生型,突变体株高明显下降、分蘖能力明显增强。为定位控制该性状的基因,以该突变体和野生型杂交构建遗传群体,与籼稻黄华占构建定位群体,再利用SSR和In Del分子标记定位该基因。遗传分析表明,矮秆多分蘖突变体受1对隐性核基因控制,暂命名为htd(t)。利用F2代定位群体将突变基因定位于第4号染色体标记RM1345和ZM4-12之间,遗传距离分别为3.9和2.6 c M。序列分析表明,htd(t)可能为HTD1的等位基因。展开更多
For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over ti...For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.展开更多
Based on the daily maximum temperature data covering the period 1961-2005, temporal and spatial characteristics and their changing in mean annual and monthly high temperature days（HTDs）and the mean daily maximum tem...Based on the daily maximum temperature data covering the period 1961-2005, temporal and spatial characteristics and their changing in mean annual and monthly high temperature days（HTDs）and the mean daily maximum temperature（MDMT）during annual and monthly HTDs in East China were studied.The results show that the mean annual HTDs were 15.1 and the MDMT during annual HTDs was 36.3℃in the past 45 years.Both the mean annual HTDs and the MDMT during annual HTDs were negative anomaly in the1980s and positive anomaly in the other periods of time,oscillating with a cycle of about 12-15 years.The mean annual HTDs were more in the southern part,but less in the northern part of East China.The MDMT during annual HTDs was higher in Zhejiang,Anhui and Jiangxi provinces in the central and western parts of East China.The high temperature process（HTP） was more in the southwestern part,but less in northeastern part of East China.Both the HTDs and the numbers of HTP were at most in July,and the MDMT during monthly HTDs was also the highest in July.In the first 5 years of the 21st century,the mean annual HTDs and the MDMT during annual HTDs increased at most of the stations,both the mean monthly HTDs and the MDMT during monthly HTDs were positive anomalies from April to October,the number of each type of HTP generally was at most and the MDMT in each type of HTP was also the highest.展开更多
文摘分蘖是水稻最重要的农艺性状之一,其决定水稻的最终产量。多蘖矮杆突变体htd7(t)是粳稻品种‘日本晴’经350 Gy的60Co-γ射线辐射处理后产生的突变体。为了克隆HTD7(t)基因,将htd7(t)与‘9311’配制正反杂交组合进行遗传分析发现,htd7(t)多蘖矮杆性状是受1对隐性核基因控制。利用SSR分子标记将HTD7(t)初步定位在第11染色体分子标记RM21与RM254之间,遗传距离分别为5.6 c M和3.2 c M。利用已经公布的水稻基因组数据,在该基因附近新发展了13对In Del标记,对HTD7(t)进行精细定位。根据定位结果构建覆盖HTD7(t)基因的BAC重叠群,最终将HTD7(t)定位在In Del11-3和In Del11-5之间的64.8 kb的物理距离内。
基金funded by the NSFC program with grant 60672117supported in part by Xian Desheng Scientific Tech. Inc., Xian, P. R. China
文摘In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).
文摘在粳稻品种中花11的组培苗中发现1份可以稳定遗传的矮秆多分蘖突变体,相比野生型,突变体株高明显下降、分蘖能力明显增强。为定位控制该性状的基因,以该突变体和野生型杂交构建遗传群体,与籼稻黄华占构建定位群体,再利用SSR和In Del分子标记定位该基因。遗传分析表明,矮秆多分蘖突变体受1对隐性核基因控制,暂命名为htd(t)。利用F2代定位群体将突变基因定位于第4号染色体标记RM1345和ZM4-12之间,遗传距离分别为3.9和2.6 c M。序列分析表明,htd(t)可能为HTD1的等位基因。
文摘For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.
基金Funded by R&D Special Fund for Public Welfare Industry(meteorology),No.GYHY(QX)2007-6-19Na-tional Scientific and Technical Supporting Programs,No.2006BAK13B05
文摘Based on the daily maximum temperature data covering the period 1961-2005, temporal and spatial characteristics and their changing in mean annual and monthly high temperature days（HTDs）and the mean daily maximum temperature（MDMT）during annual and monthly HTDs in East China were studied.The results show that the mean annual HTDs were 15.1 and the MDMT during annual HTDs was 36.3℃in the past 45 years.Both the mean annual HTDs and the MDMT during annual HTDs were negative anomaly in the1980s and positive anomaly in the other periods of time,oscillating with a cycle of about 12-15 years.The mean annual HTDs were more in the southern part,but less in the northern part of East China.The MDMT during annual HTDs was higher in Zhejiang,Anhui and Jiangxi provinces in the central and western parts of East China.The high temperature process（HTP） was more in the southwestern part,but less in northeastern part of East China.Both the HTDs and the numbers of HTP were at most in July,and the MDMT during monthly HTDs was also the highest in July.In the first 5 years of the 21st century,the mean annual HTDs and the MDMT during annual HTDs increased at most of the stations,both the mean monthly HTDs and the MDMT during monthly HTDs were positive anomalies from April to October,the number of each type of HTP generally was at most and the MDMT in each type of HTP was also the highest.
