期刊文献+
共找到27篇文章
< 1 2 >
每页显示 20 50 100
右美沙芬对家兔急性脑外伤颅内压及坏死神经元数的影响 被引量:1
1
作者 刘献志 阎东明 +5 位作者 张志强 宋来君 保建基 徐国本 冯祖荫 王成裕 《郑州大学学报(医学版)》 CAS 北大核心 2002年第3期315-318,共4页
目的:探讨应用右美沙芬对急性脑外伤家兔颅内压及病理改变的影响。方法:将成年雄性家兔20只利用颅脑外伤自由落体打击器造成一侧脑外伤动物模型,伤后家兔被均分为外伤组10只及治疗组10只,另设未受外伤的对照组 6只。治疗组动物在外伤后... 目的:探讨应用右美沙芬对急性脑外伤家兔颅内压及病理改变的影响。方法:将成年雄性家兔20只利用颅脑外伤自由落体打击器造成一侧脑外伤动物模型,伤后家兔被均分为外伤组10只及治疗组10只,另设未受外伤的对照组 6只。治疗组动物在外伤后立即腹腔注射右美沙芬治疗,剂量为 50 mg·kg-1·d-1,对照组和外伤组给予腹腔注射等量生理盐水,连用7d采用颅内压监护仪监测不同时间段颅内压,7d后处死各组动物,显微镜下观察伤灶及其周围坏死神经元细胞数。结果:伤前和伤后 5 min治疗组、外伤组颅内压差异无显著性。但治疗组动物在 1d、3 d、7 d的颅内压较外伤组相应时间段显著降低,且伤灶及周围皮层坏死神经元数显著减少(P<0.01)。结论:右美沙芬能降低急性脑外伤家兔的颅内压,提高神经元存活率。 展开更多
关键词 急性颅脑损伤 颅内压 坏死神经元数 右美沙芬 动物实验
下载PDF
隐层神经元数对基于神经网络的自相关过程控制的影响 被引量:1
2
作者 何桢 刘冬生 《组合机床与自动化加工技术》 2007年第3期89-93,共5页
将传统修哈特控制图应用于自动化连续生产过程,经常会引发大量虚发报警。使用神经网络方法对存在相关性的连续生产过程进行研究时,取得了良好效果。本文在使用BP神经网络对自相关过程进行监控的基础之上,对隐层神经元数对于神经网络训... 将传统修哈特控制图应用于自动化连续生产过程,经常会引发大量虚发报警。使用神经网络方法对存在相关性的连续生产过程进行研究时,取得了良好效果。本文在使用BP神经网络对自相关过程进行监控的基础之上,对隐层神经元数对于神经网络训练收敛性及识别率的影响进行分析研究。针对一定的输入层神经元数,选择合适的隐层神经元数将极大的改善网络的训练效果并提高网络的识别率。 展开更多
关键词 自相关过程 统计过程控制(SPC) 神经网络 隐层神经元数
下载PDF
用BP神经网络预测土壤入渗参数时隐层神经元数分析 被引量:1
3
作者 张敬平 《山西水土保持科技》 2008年第3期20-22,共3页
为了用BP神经网络更准确地预测土壤入渗参数,分析了不同隐层神经元数下,预测值与实测值的关系曲线,以及在同一训练目标误差下,不同隐层神经元数、训练曲线的变化及能否达到训练目的,得出了最优隐层神经元数。隐层神经元数的确定,为土壤... 为了用BP神经网络更准确地预测土壤入渗参数,分析了不同隐层神经元数下,预测值与实测值的关系曲线,以及在同一训练目标误差下,不同隐层神经元数、训练曲线的变化及能否达到训练目的,得出了最优隐层神经元数。隐层神经元数的确定,为土壤传输函数的研究奠定了基础。 展开更多
关键词 BP神经网络 隐层神经元数 土壤入渗参
下载PDF
幂激励前向神经网络最优结构确定算法 被引量:16
4
作者 张雨浓 郭东生 谭宁 《计算机工程与应用》 CSCD 北大核心 2011年第2期29-31,共3页
针对一种以幂函数序列为各隐神经元激励函数的前向神经网络,提出了一种基于权值直接确定方法的网络最优结构确定算法。计算机仿真与验证结果表明,该算法能自动、快速、有效地确定网络的最优隐神经元数,达到网络的最佳逼近能力,从而实现... 针对一种以幂函数序列为各隐神经元激励函数的前向神经网络,提出了一种基于权值直接确定方法的网络最优结构确定算法。计算机仿真与验证结果表明,该算法能自动、快速、有效地确定网络的最优隐神经元数,达到网络的最佳逼近能力,从而实现网络结构的最优化。 展开更多
关键词 幂级 前向神经网络 神经元数 结构最优化 权值直接确定法
下载PDF
基于BP人工神经网络的纱线毛羽预测研究 被引量:7
5
作者 李惠军 朱磊 《棉纺织技术》 CAS CSCD 北大核心 2011年第1期32-34,共3页
研究基于BP人工神经网络的纱线毛羽预测问题。以棉纤维的7项品质指标作为输入参数,以棉纱的毛羽指数H指标作为输出参数,通过使用36组数据分别进行网络模型训练,最终将纱线毛羽指数预测模型的结构选定为7-10-1来进行纱线毛羽的预测,结果... 研究基于BP人工神经网络的纱线毛羽预测问题。以棉纤维的7项品质指标作为输入参数,以棉纱的毛羽指数H指标作为输出参数,通过使用36组数据分别进行网络模型训练,最终将纱线毛羽指数预测模型的结构选定为7-10-1来进行纱线毛羽的预测,结果表明:BP人工神经网络模型的预测速度和精度较好。 展开更多
关键词 BP人工神经网络 毛羽指 训练误差 隐含层神经元数 模型
下载PDF
基于Matlab的时序数据两种建模和预测方法比较 被引量:4
6
作者 孟娜 周以齐 《山东农业大学学报(自然科学版)》 CSCD 北大核心 2006年第3期471-476,共6页
利用Matlab工具箱,对时序数据进行了两种不同形式的建模和预测。一是利用系统辨识方法来建立AR模型,利用所建模型进行预测;二是利用单隐层BP神经网络,对数据进行非线性拟合和预测。通过可视化,比较了两种方法的优劣。
关键词 时序分析 AR模型 MATLAB编程 BP神经网络 隐含层神经元数
下载PDF
用改进GA-BP神经网络的设备故障维修时间预测 被引量:3
7
作者 邢毓华 李凡菲 《计算机仿真》 北大核心 2021年第8期97-102,166,共7页
光伏充电站中设备故障维修时间对运行效率有着重要影响。为提高光伏充电站设备维修时间的预测精度,考虑到神经网络算法中隐含层神经元数对算法预测精度的影响,提出了一种改进的GA-BP神经网络算法,并以光伏充电站60个设备维修时间为样本... 光伏充电站中设备故障维修时间对运行效率有着重要影响。为提高光伏充电站设备维修时间的预测精度,考虑到神经网络算法中隐含层神经元数对算法预测精度的影响,提出了一种改进的GA-BP神经网络算法,并以光伏充电站60个设备维修时间为样本验证了改进算法的有效性。结果表明,GA-BP神经网络结构中隐含层神经元数取5时算法预测精度最高,且采用改进GA-BP神经网络算法预测时平均相对误差仅为6.1%,较灰色模型与BP神经网络算法分别降低了90.4%与57%。改进后的GA-BP神经网络的预测准确度远高于灰色模型和BP神经网络,得到的预测时间可为维修人员调度提供依据。 展开更多
关键词 光伏充电站 维修时间预测 神经网络 隐含层神经元数 预测准确度
下载PDF
基于BP人工神经网络的纱线强度CV值预测研究 被引量:2
8
作者 聂琼 《轻纺工业与技术》 2011年第5期102-104,共3页
研究基于BP人工神经网络的纱线强度CV值预测问题。以棉纤维的七项品质指标作为输入参数,以纱线的强度CV值指标作为输出参数,通过使用28组数据分别进行网络模型训练,最终选定纱线强度CV值的模型结构进行预测,验证了BP人工神经网络模型的... 研究基于BP人工神经网络的纱线强度CV值预测问题。以棉纤维的七项品质指标作为输入参数,以纱线的强度CV值指标作为输出参数,通过使用28组数据分别进行网络模型训练,最终选定纱线强度CV值的模型结构进行预测,验证了BP人工神经网络模型的预测精度。 展开更多
关键词 BP人工神经网络 强度CV值 隐含层神经元数 MATLAB
下载PDF
有望控制帕金森氏病的新的特异性神经营养因子
9
作者 孙雷心 《生物技术通报》 CAS CSCD 1994年第1期21-22,共2页
Synergen Inc.公司(Boulder,CO)分离出一种新的、特异性刺激中脑多巴胺生产细胞的神经营养因子。公司打算用这种因子来治疗帕金森氏病。帕金森氏病的病因是由于这类多巴胺吸附和分泌细胞的降解。这种因子称为神经胶质细胞系衍生的神经... Synergen Inc.公司(Boulder,CO)分离出一种新的、特异性刺激中脑多巴胺生产细胞的神经营养因子。公司打算用这种因子来治疗帕金森氏病。帕金森氏病的病因是由于这类多巴胺吸附和分泌细胞的降解。这种因子称为神经胶质细胞系衍生的神经营养因子(GDNF)。 展开更多
关键词 帕金森氏病 神经营养因子 中脑多巴胺 多巴胺能 神经胶质细胞 GDNF 大鼠 神经元数 特异性 分泌细胞
下载PDF
面神经损伤吻合术手术时机研究
10
作者 胡炯炯 周梁 马兆鑫 《中国临床医学》 2011年第6期773-776,共4页
目的:探讨面神经损伤后最佳的修复时机。方法:以行面神经即时吻合术和延迟吻合术后豚鼠的辣根过氧化物酶(HRP)标记神经元数、有髓纤维数/HRP标记神经元等为观察指标,评价面神经即时吻合和延迟不同时期吻合术后面神经再生的情况。结果:... 目的:探讨面神经损伤后最佳的修复时机。方法:以行面神经即时吻合术和延迟吻合术后豚鼠的辣根过氧化物酶(HRP)标记神经元数、有髓纤维数/HRP标记神经元等为观察指标,评价面神经即时吻合和延迟不同时期吻合术后面神经再生的情况。结果:各组指标比较,延迟7 d缝合组和即时缝合组的治疗效果最佳,此2组间差异无统计学意义;延迟60 d缝合组和延迟90 d缝合组治疗效果最差。结论:在无法即时行面神经吻合术的情况下,可在神经断伤后7 d吻合面神经。尽量争取在神经离断伤后60 d内修补损伤的面神经。 展开更多
关键词 神经端端吻合术 手术时机 有髓纤维/HRP标记神经元 侧支生长
下载PDF
FAULT-TOLERANT INTEGRATED NAVIGATION SYSTEM BASED ON NEURONS 被引量:1
11
作者 马昕 袁信 《Transactions of Nanjing University of Aeronautics and Astronautics》 EI 1998年第2期4-7,共4页
In this paper, the multisensor data fusion technique of a fault tolerant integrated navigation system is discussed. A neural approach for data fusion is proposed for multisensor integrated systems. The simulation res... In this paper, the multisensor data fusion technique of a fault tolerant integrated navigation system is discussed. A neural approach for data fusion is proposed for multisensor integrated systems. The simulation results show that this neural approach for data fusion is feasible. 展开更多
关键词 navigation system NEURON data fusion fault tolerant
下载PDF
基于信息熵的DBN网络结构优化 被引量:2
12
作者 廖强 张杰 《信息通信》 2018年第1期44-48,共5页
对目前深度信念网络(Deep Belief Network,DBN)难以同时提取合适的网络深度和隐藏层神经元数的问题,在利用传统重构误差计算并判断网络深度的基础上,从信息表达的角度出发,分析了信息熵、输入层和隐藏层三者之间的内在联系,然后根据信... 对目前深度信念网络(Deep Belief Network,DBN)难以同时提取合适的网络深度和隐藏层神经元数的问题,在利用传统重构误差计算并判断网络深度的基础上,从信息表达的角度出发,分析了信息熵、输入层和隐藏层三者之间的内在联系,然后根据信息熵与隐藏层之间的关系,提出了一种基于信息熵确定隐藏层神经元数的优化方法,使DBN网络模型的的结构趋于更优。在手写数字识别上的实验结果表明,该方法能自组织地计算网络深度和隐藏层的神经元数量。与依据重构误差法确定网络深度的测试数据相比,平均误差减小了1.47%,有效地优化了DBN网络结构,降低了网络的训练时间,提高了网络精度和识别准确率。 展开更多
关键词 深度信念网络 DBN 信息熵 网络深度 隐藏层神经元数
下载PDF
分析器官生理学(感官生理学)
13
《国外科技资料目录(医药卫生)》 2000年第12期8-8,共1页
0043499 兔虹膜睫状体中∑识别位点:局部∑位点激动剂降低眼内压/Bucolo C//J Pharmacol Exp Ther.-1999,289(3).-1362~1369 医科情0043500 耳蜗核可以构成听力偏侧吗?神经元数目的立体评价/Agar E//Ann OtolRhinol Laryngol.-1999,108... 0043499 兔虹膜睫状体中∑识别位点:局部∑位点激动剂降低眼内压/Bucolo C//J Pharmacol Exp Ther.-1999,289(3).-1362~1369 医科情0043500 耳蜗核可以构成听力偏侧吗?神经元数目的立体评价/Agar E//Ann OtolRhinol Laryngol.-1999,108(7 Pt 1).-661~665 展开更多
关键词 感官生理学 神经元数 耳蜗核
下载PDF
Melt Index Prediction by Neural Soft-Sensor Based on Multi-Scale Analysis and Principal Component Analysis 被引量:11
14
作者 施健 刘兴高 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2005年第6期849-852,共4页
Prediction of melt index (MI), the most important parameter in determining the product's grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model ... Prediction of melt index (MI), the most important parameter in determining the product's grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model with principal component analysis (PCA), radial basis function (RBF) networks, and multi-scale analysis (MSA) is proposed to infer the MI of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, MSA is introduced to a^quire much more information and to reduce the uncertainty of the system, and RBF networks are used to characterize the nonlinearity of the process. The research results show that the proposed method provides promising prediction reliability and accuracy, and supposed to have extensive application prospects in propylene polymerization processes. 展开更多
关键词 propylene polymerization neural soft-sensor principal component analysis multi-scale analysis
下载PDF
Approach to Generalized Synchronization with Application to Chaos-Based Secure Communication 被引量:4
15
作者 MINLe-Quan CHENGuan-Rong +2 位作者 ZHANGXiao-Dan ZHANGXia-Hua YANGMiao 《Communications in Theoretical Physics》 SCIE CAS CSCD 2004年第4期632-640,共9页
A constructive theorem is established for generalized synchronization (GS) related to C<SUP>1</SUP> diffeomorphic transformations of unidirectionally coupled dynamical arrays. The theorem provides some int... A constructive theorem is established for generalized synchronization (GS) related to C<SUP>1</SUP> diffeomorphic transformations of unidirectionally coupled dynamical arrays. The theorem provides some interpretations about the underlying mechanism of various GS phenomena in nature. As a direct application of the theorem, a chaos-based secure Internet communication scheme is proposed. Moreover, a cellular neural network (CNN) of Chen's chaotic circuits with GS property is designed and studied. Numerical simulation shows that this Chen's CNN has high security and is fast and reliable for secure Internet communications. 展开更多
关键词 SYNCHRONIZATION neural network cellular chaos numerical using chaos numerical simulation
下载PDF
Improvement and Realization of Neuron PSD Control in Servo-Control System 被引量:2
16
作者 焦斌 顾辛生 《Journal of Shanghai Jiaotong university(Science)》 EI 2005年第2期143-146,共4页
Neuron PSD (proportion, sum and differentiation) controller has the ability of on-line change of weights to reach the purpose of regulating parameters of PID using neuron’s self-studying and self-organization and the... Neuron PSD (proportion, sum and differentiation) controller has the ability of on-line change of weights to reach the purpose of regulating parameters of PID using neuron’s self-studying and self-organization and the change of controlled plant, which overcomes the disadvantages of affecting a conventional PID’s accurate regulation because of the change of load, model and non-linearity. LF2407 DSP can reach the purpose of parallel running by using multi-sets of bus. So it can greatly increase operation speed and offer a set of flexible instruction system. The realization of PSD control on DSP can build an ideal electrical machine controller. 展开更多
关键词 digital signal processing (DSP) NEURON PSD propotional integral differential (PID)
下载PDF
Application and comparison of RNN, RBFNN and MNLR approaches on prediction of flotation column performance 被引量:8
17
作者 Nakhaei Fardis Irannajad Mehdi 《International Journal of Mining Science and Technology》 SCIE EI CSCD 2015年第6期983-990,共8页
Evaluation of grade and recovery plays an important role in process control and plant profitability in mineral processing operations, especially flotation. The accurate measurement or estimation of these two parameter... Evaluation of grade and recovery plays an important role in process control and plant profitability in mineral processing operations, especially flotation. The accurate measurement or estimation of these two parameters, based on the secondary variables, is a critical issue. Data-driven modeling techniques, which entail comprehensive data analysis and implementation of machine learning methods for system forecast, provide an attractive alternative. In this paper, two types of artificial neural networks(ANNs),namely radial basis function neural network(RBFNN) and layer recurrent neural network(RNN), and also a multivariate nonlinear regression(MNLR) model were employed to predict metallurgical performance of the flotation column. The training capacity and the accuracy of these three above mentioned types of models were compared. In order to acquire data for the simulation, a case study was conducted at Sarcheshmeh copper complex pilot plant. Based on the root mean squared error and correlation coefficient values, at training and testing stages, the RNN forecasted the metallurgical performance of the flotation column better than RBF and MNLR models. The RNN could predict Cu grade and recovery with correlation coefficients of 0.92 and 0.9, respectively in testing process. 展开更多
关键词 Flotation columnRadial basis functionRecurrent neural networkMultivariate nonlinear regressionMetallurgical performance
下载PDF
An attitude calculation algorithm based on WNN-EKF 被引量:1
18
作者 CHEN Guangwu FAN Ziyan +2 位作者 WEI Zongshou LI Wenyuan ZHANG Linjing 《Journal of Measurement Science and Instrumentation》 CAS CSCD 2022年第2期138-146,共9页
In the strapdown inertial navigation system,the attitude information is obtained through an inertial measurement unit(IMU)device,which mainly includes a triaxial gyroscope,a triaxial accelerometer and a triaxial magne... In the strapdown inertial navigation system,the attitude information is obtained through an inertial measurement unit(IMU)device,which mainly includes a triaxial gyroscope,a triaxial accelerometer and a triaxial magnetometer.However,IMU sensors have system noise and drift errors,and these errors can accumulate over time,which makes it difficult to control the attitude accuracy.In order to solve the problems of gyro drift over time and random errors generated by the surrounding environment,this paper presents an attitude calculation algorithm based on wavelet neural network-extended Kalman filter(WNN-EKF).The wavelet neural network(WNN)is used to optimize the model and compensate the extended Kalman filter’s own model error.Through the semi-physical simulation experiment,the results show that the algorithm improves the accuracy of attitude calculation and enhances the self-adaptability to the environment. 展开更多
关键词 inertial measurement unit(IMU) QUATERNION attitude calculation wavelet neural network(WNN) extended Kalman filter(EKF)
下载PDF
Neural Network Inversion for Multilayer Quaternion Neural Networks 被引量:1
19
作者 Takehiko Ogawa 《Computer Technology and Application》 2016年第2期73-82,共10页
Recently, solutions to inverse problems have been required in various engineering fields. The neural network inversion method has been studied as one of the neural network-based solutions. On the other hand, the exten... Recently, solutions to inverse problems have been required in various engineering fields. The neural network inversion method has been studied as one of the neural network-based solutions. On the other hand, the extension of the neural network to a higher-dimensional domain, e.g., complex-value or quaternion, has been proposed, and a number of higher-dimensional neural network models have been proposed. Using the quatemion, we have the advantage of expressing 3D (three-dimensional) object attitudes easily. In the quaternion domain, we can define inverse problems where the cause and the result are expressed by the quaternion. In this paper, we extend the neural network inversion method to the quatemion domain. Further, we provide the results of the computer experiments to demonstrate the process and effectiveness of our method. 展开更多
关键词 Inverse problems neural network inversion quatemion inverse mapping inverse kinematics.
下载PDF
Extending self-organizing maps for supervised classification of remotely sensed data 被引量:1
20
作者 CHEN Yongliang 《Global Geology》 2009年第1期46-56,共11页
An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the ... An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors : an input vector and a class codebook vector. When a training sample is input into the model, Kohonen's competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification. 展开更多
关键词 Self-organizing map modified competitive learning supervised classification remotely sensed data
下载PDF
上一页 1 2 下一页 到第
使用帮助 返回顶部