Application of the back-error propagation artificial neural network(BPANN) on genetic variants in the PPAR-γ and RXR-α gene and risk of metabolic syndrome in a Chinese Han population

This study was aimed to explore the associations between the combined effects of several polymorphisms in the PPAR-γ and RXR-α gene and environmental factors with the risk of metabolic syndrome by back-error propaga- tion artificial neural network （BPANN）. We established the model based on data gathered from metabolic syndrome patients （n = 1012） and normal controls （n = 1069） by BPANN. Mean impact value （MIV） for each input variable was calculated and the sequence of factors was sorted according to their absolute MIVs. Generalized multifactor dimensionality reduction （GMDR） confirmed a joint effect of PPAR-9＂ and RXR-a based on the results from BPANN. By BPANN analysis, the sequences according to the importance of metabolic syndrome risk fac- tors were in the order of body mass index （BMI）, serum adiponectin, rs4240711, gender, rs4842194, family history of type 2 diabetes, rs2920502, physical activity, alcohol drinking, rs3856806, family history of hypertension, rs1045570, rs6537944, age, rs17817276, family history of hyperlipidemia, smoking, rs1801282 and rs3132291. However, no polymorphism was statistically significant in multiple logistic regression analysis. After controlling for environmental factors, A1, A2, B1 and B2 （rs4240711, rs4842194, rs2920502 and rs3856806） models were the best models （cross-validation consistency 10/10, P = 0.0107） with the GMDR method. In conclusion, the interaction of the PPAR-γ and RXR-α gene could play a role in susceptibility to metabolic syndrome. A more realistic model is obtained by using BPANN to screen out determinants of diseases of multiple etiologies like metabolic syndrome.

Temperature compensation method of silicon microgyroscope based on BP neural network

The temperature characteristics of a silicon microgyroscope are studied, and the temperature compensation method of the silicon microgyroscope is proposed. First, an open-loop circuit is adopted to test the entire microgyroscope＇s resonant frequency and quality factor variations over temperature, and the zero bias changing trend over temperature is measured via a closed-loop circuit. Then, in order to alleviate the temperature effects on the performance of the microgyroscope, a kind of temperature compensated method based on the error back propagation（BP）neural network is proposed. By the Matlab simulation, the optimal temperature compensation model based on the BP neural network is well trained after four steps, and the objective error of the microgyroscope＇s zero bias can achieve 0.001 in full temperature range. By the experiment, the real time operation results of the compensation method demonstrate that the maximum zero bias of the microgyroscope can be decreased from 12.43 to 0.75（°）/s after compensation when the ambient temperature varies from -40 to 80℃, which greatly improves the zero bias stability performance of the microgyroscope.

Wireless location algorithm using digital broadcasting signals based on neural network

In order to enhance the accuracy and reliability of wireless location under non-line-of-sight （NLOS） environments,a novel neural network （NN） location approach using the digital broadcasting signals is presented. By the learning ability of the NN and the closely approximate unknown function to any degree of desired accuracy,the input-output mapping relationship between coordinates and the measurement data of time of arrival （TOA） and time difference of arrival （TDOA） is established. A real-time learning algorithm based on the extended Kalman filter （EKF） is used to train the multilayer perceptron （MLP） network by treating the linkweights of a network as the states of the nonlinear dynamic system. Since the EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights,the convergence is improved in comparison with the backwards error propagation （BP） algorithm. Numerical results illustrate thatthe proposedalgorithmcanachieve enhanced accuracy,and the performance ofthe algorithmis betterthanthat of the BP-based NN algorithm and the least squares （LS） algorithm in the NLOS environments. Moreover,this location method does not depend on a particular distribution of the NLOS error and does not need line-of-sight （ LOS ） or NLOS identification.

Estimation and Prediction of Gas Chromatography Retention Indices of Hydrocarbons in Straight-run Gasoline by Using Artificial Neural Network and Structural Coding Method

The molecular structures of hydrocarbons in straight run gasoline were numerically coded. The nonlinear quantitative relationship(QSRR) between gas chromatography(GC) retention indices of the hydrocarbons and their molecular structures were established by using an error back propagation(BP) algorithm. The GC retention indices of 150 hydrocarbons were then predicted by removing 15 compounds(as a test set) and using the 135 remained molecules as a calibration set. Through this procedure, all the compounds in the whole data set were then predicted in groups of 15 compounds. The results obtained by BP with the correlation coefficient and the standard deviation 0 993 4 and 16 54, are satisfied.

Artificial Neural Networks for Event Based Rainfall-Runoff Modeling

The Artificial Neural Network (ANN) approach has been successfully used in many hydrological studies especially the rainfall-runoff modeling using continuous data. The present study examines its applicability to model the event-based rainfall-runoff process. A case study has been done for Ajay river basin to develop event-based rainfall-runoff model for the basin to simulate the hourly runoff at Sarath gauging site. The results demonstrate that ANN models are able to provide a good representation of an event-based rainfall-runoff process. The two important parameters, when predicting a flood hydrograph, are the magnitude of the peak discharge and the time to peak discharge. The developed ANN models have been able to predict this information with great accuracy. This shows that ANNs can be very efficient in modeling an event-based rainfall-runoff process for determining the peak discharge and time to the peak discharge very accurately. This is important in water resources design and management applications, where peak discharge and time to peak discharge are important input

基于贝叶斯神经网络的船用惯导定位修正方法

船用惯性导航系统(inertial navigation system, INS)通常采用与全球卫星导航系统(global navigation satellite system, GNSS)组合导航的方式提高其长时间工作的定位精度。当GNSS失效时,其定位误差将随时间迅速发散。针对这一问题,设计了采用反向传播神经网络(back propagate neural network, BPNN)、根据INS原始输出数据拟合修正经纬度的定位修正方案,提出了基于Bayesian算法更新网络权重系数的方法,结合理论分析和试验研究确定了神经元个数与训练数据集的分配方案。实船试验结果表明,当GNSS失效时,在后续2 h,通过24 h历史数据训练得到的神经网络修正INS位置,相比INS独立工作时的定位误差,修正后误差均值下降了63%,误差最大值下降约50%,最小值下降至0。

改进GA-BPNN在短期电力负荷预测中的应用

为了避免传统方法预测短期电力负荷建模复杂性,将改进遗传算法(GA)和误差反向传播(BP)算法相结合构成的混合算法用于训练人工神经网络,结合电力负荷历史数据,对短期电力负荷进行仿真预测。仿真结果表明,该混合算法有效地解决了常规BP算法学习网络权值收敛速度慢、易陷入局部极小和GA算法独立训练神经网络速度缓慢等问题,具有较快的收敛速度和较高的预测精度。

基于GA-BP网络的数控机床动态误差预测研究

动态误差是高速高精度数控机床的重要误差源,针对实际加工过程中动态误差对工件精度影响较大的问题,提出了一种基于遗传算法优化的反向传播(GA-BP)神经网络以预测动态误差。首先,为了提高神经网络对动态误差的预测精度,从线性特征与非线性特征两方面对动态误差影响因素进行了深入分析,确定了神经网络输入输出参数;然后,采用了遗传算法对BP神经网络进行了优化,建立了动态误差模型,获得了最优网络学习参数,从而实现了对动态跟随误差的精准预测;之后,采用三次样条插值的方法对理想轨迹与实际轨迹之间的轮廓误差进行了计算,有效提高了轮廓误差估算精度;最后,采用了五轴数控机床进行了实验,对模型的有效性进行了验证。研究结果表明:所建神经网络模型可以精准预测机床反向越冲特性对轮廓误差的影响,各轴的动态误差预测精度为±3μm,复杂轨迹轮廓误差预测精度为±1.5μm。实验结果验证了所建模型的可靠性,为后续机床动态误差建模与控制研究提供了一定的参考价值。

人工神经网络在果蔬干燥领域应用进展

果蔬干燥是农产品加工中的重要环节,构建精确的干燥动力学模型成为干燥领域的重点方向。综述人工神经网络在果蔬干燥过程中的应用现状、分析存在的问题和做出展望。针对神经网络在干燥过程中的各种场景分类为四个部分:含水率预测、品质检测、工艺优化和控制系统方面,总结各部分的应用类型及发展创新;再对比传统干燥模型和人工神经网络模型;最后介绍混合神经网络的应用场景。发现人工神经网络比传统干燥模型更精确,且混合神经网络结合专家系统、模糊逻辑等理论能够提供准确的预测,作为一种新颖高效的建模技术,可以广泛应用于果蔬加工的优化、控制、自动化等领域。其中应用最广泛的就是与遗传算法结合的GA-BP神经网络,BP负责预测、GA负责寻优,在这样的算法中不仅可以精确预测结果还可以优化工艺。这样的模型更适合果蔬干燥且在未来有更广阔的发展空间,以期这些探讨和分析对果蔬干燥领域具有参考意义。

基于ACO-BP算法的熔融沉积成型翘曲变形量的预测方法

针对熔融沉积成型翘曲变形量预测问题,提出了一种基于蚁群算法(ACO)-误差反向传播(BP)神经网络算法的预测方法。采用ACO算法优化BP神经网络的初始权值、阈值,防止其训练时收敛于局部极小。基于正交试验分别设计4因素4水平的训练样本集和4因素3水平的验证样本集。训练样本集用于预测模型的学习,验证样本集用于验证预测方法的精度。基于极差法分析了各工艺参数对翘曲变形量的影响程度。结果表明,工艺参数对翘曲变形量的影响程度从大到小分别为层高、填充率、喷头挤出温度和打印速度。采用训练样本集充分训练预测模型后,验证基于ACO-BP算法的翘曲变形量预测方法的效果。基于均方根误差(RMSE)、均方误差(MSE)、平均绝对误差(MAE)和平均绝对百分比误差(MAPE)评价模型预测精度。对于RMSE,BP算法的预测精度约为ACO-BP算法的1.7倍;对于MSE,BP算法的预测精度约为ACO-BP算法的2.9倍;对于MAE,BP算法的预测精度约为ACO-BP算法的1.6倍;对于MAPE,BP算法的预测精度约为ACO-BP算法的2.2倍。基于ACO算法优化的BP神经网络预测精度更高。

人工神经网络在电力营销系统中的应用与实现

在电力行业信息化发展背景下,收集与存储大量电力数据,可为电力企业营销决策制定提供依据。该文提出采用人工神经网络构建电力营销系统BP神经网络模型,通过智能决策树分类算法预处理模型数据,得到最优化的模型数据,并改进神经网络隐含层节点数目算法,结合应用分时段预测方法及共轭梯度算法分别进行网络训练及网络结构优化,为网络收敛速度加快提供保障,得出相对准确的电力营销年度电量预测结论,说明电力营销系统中人工神经网络具有较高的应用价值。

Approach of Improving the Inertial Navigation System Error for Large Transport Aircraft

The corresponding corrected method is proposed for the INS ( INS-Inertial Navigation System ) accumulated error of large transport aircraft. System errors contain aircraft position error, altitude error and speed error,one is increasing the accuracy of hardw are; the other is development of low cost softw are algorithms. Because of improving hardw are is more difficult in my country at present, developing softw are algorithms is essential w ay,w hich have been validated in my types of airplane. The combined heuristic algorithms ( ABPNN,Advanced Back-propagation neural netw orks algorithm and LSM -least square method) are presented,w hich incorporates the effects of flight region and measured terrain height data by radar and barometer. Based on this algorithm,the appropriate match region w as gotten by recognition of fiducial digital map in real time online. In process of w ork,the minimum of position error as a cost function and the constraint conditions are gave,the flight positions are recognized in real time and continuously,least sum of square is calculated based on LSM ,in other w ords,the optimized result is obtained. The simulation case demonstrate that the method is very successful,the correct rate of recognition is more 90 percent. In w ords,the algorithm presented is economical,validation and effective.

大数据环境下的船舶中间产品装配工时预测模型

基于大数据环境提出考虑误差修正的两阶段船舶中间产品装配工时预测模型。从船舶设计软件中提取中间产品装配工艺信息,建立反向传播神经网络(Back Propagation Neural Network,BPNN)模型,实现装配工时的初步预测。采集对装配工时预测可能造成影响的外界因素大数据,建立基于极端梯度提升(Extreme Gradient Boosting,XGBoost)算法的装配工时预测误差修正模型。两阶段预测结果相加得到装配工时预测值。实例验证该预测模型的有效性,可为船舶企业完善装配工时管理提供切实可行的解决思路。

基于热传导和卷积神经网络的磨床主轴热误差预测

热变形是影响磨床加工精度的主要因素,严重制约了机床精度的进一步提高。为了提高热误差预测的精度,提出了一种基于热传导和卷积神经网络的磨床主轴热误差预测方法。根据热传导理论推导出主轴表面和外部环境的温差和热变量的映射关系,揭示了材料热变形本质。然后,建立了以温差为输入和主轴热变形量为输出的神经网络热误差预测模型。该模型拥有4个神经网络层,分别对应温差、热能增量、时间变量以及热变形量。运用反向传播算法对该预测模型进行训练并计算模型参数。最后,基于SINUMERIK 840D数控控制器开发了一套磨床主轴热误差补偿系统,并在某一数控磨床上进行了验证。结果表明,通过主轴热误差补偿后,磨床的加工精度提升了41.7%,验证了本文提出的主轴热误差预测模型的有效性和可行性。

基于SSA-BP的电主轴热误差优化建模

为解决某加工中心电主轴的热误差补偿问题,建立预测精度高、鲁棒性强的热误差补偿模型。搭建实验台,利用美国雄狮回转误差分析仪采集电主轴的温度场和热误差数据。介绍麻雀搜索算法(SSA)原理、具体优化流程。采用SSA优化BP神经网络的权值和阈值,建立SSA-BP神经网络预测模型。与之前建立的BP神经网络预测模型相比,优化后预测效果更优,为电主轴热误差建模提供新的思路。

基于图神经网络的程序脆弱性指数评估方法

软错误会导致隐性偏差,严重影响计算机系统的可靠性。计算程序脆弱性指数是防护隐性偏差的先决条件。针对传统方法中程序语义提取不足,无法全面反映错误传播机理的问题,提出了一种基于图注意力网络的程序脆弱性指数评估方法EpicGNN。将脆弱性指数预测的任务转换为图神经网络的图回归任务,应用不同类型的边来表示不同的指令关系;引入结构化多头自注意力机制量化节点间、节点到图在错误传播中的重要程度;依据该重要性聚合节点信息、图信息形成图的表示向量,并利用回归模型预测脆弱性指数。实验结果表明,EpicGNN在spec2000、spec2006、rodinia等数据集上的平均绝对误差相比现有模型减少了0.037~0.258,对未见过的图仍然有良好的泛化性能。

基于人工神经网络构建的赤潮短期预报模型及应用

利用大数据赤潮预报方法,基于福建沿岸24个生态浮标和5个大浮标历史数据及实时监测数据,采用人工神经网络实现福建沿岸赤潮的业务化预报。赤潮短期预报模型由误差反向传播网络(BP)和径向基神经网络(RBF)构成,结合福建沿岸所有赤潮事件的高频采样数据样本,每天可算出480个预报结果,最后对预报结果进行发生概率等级判断,最终实现福建沿岸10个赤潮监测区赤潮发生概率等级的业务化预报。赤潮短期预报模型成功预报出2019年5月下旬福建北部发生的多起赤潮事件,2019年和2020年24 h时效的赤潮预报结果正确率达到95%和99%,赤潮识别率达到60%和55%。

基于改进粒子群优化的BP神经网络图像压缩方法

为了改善反向传播(BP)神经网络算法过度依赖初始参数,导致网络收敛速度慢,容易陷入局部极小值的问题,提出利用改进的粒子群优化(IPSO)算法,对BP神经网络的参数进行优化,找出合适的初始权值和阈值。该文算法在基本粒子群优化(PSO)算法中增加了基于四分位数的选择策略,引入遗传算法的自适应变异概率作为扰动概率,加入基于个体自身适应度值与种群平均适应度值比值的自适应扰动策略。该文算法IPSO-BP对训练图像Lena、测试图像Cameraman和验证图像Peppers效果都有明显的提高,经过IPSO-BP训练的模型峰值信噪比(PSNR)和均方误差(MSE)明显好于惯性权重线性递减的粒子群优化-反向传播(LDWPSO-BP)、基于动态加速因子的粒子群优化-反向传播(PSO-DAC-BP)、基于正态分布衰减惯性权重的粒子群优化-反向传播(NDPSO-BP)、自适应变异粒子群优化-反向传播(ADVPSO-BP)、遗传算法-反向传播(GA-BP)以及天牛须搜索-反向传播(BAS-BP),PSNR在7种算法中最大,MSE在7种算法中最小。虽然IPSO-BP在图像Lena上的压缩率(CR)小于PSO-DAC-BP和BAS-BP,在Cameraman上的CR小于NDPSO-BP、ADVPSO-BP和GA-BP,但相差不超过0.01和0.006。

Stewart载物平台位姿误差估计模型

提出了一种通过单目结构光相机测量Stewart载物平台位姿的方法,搭建了位姿误差测量试验台,对Stewart载物平台位姿误差进行了测量。建立了一种使用多元宇宙优化算法(multi-verse optimizer,MVO)优化反向传播(back propagation,BP)神经网络的Stewart载物平台误差估计模型,并利用测量得到的误差数据对模型进行了训练。通过测试数据对误差估计模型的有效性进行了验证。实验结果表明,模型可以更好地估计沿z轴方向的位移误差以及绕x轴和绕y轴的旋转误差,为Stewart平台的位姿测量研究提供了一种新方法。

ARTIFICIAL NEURAL NETWORK CORRECTION OF ROUGH ERRORS OF OBSERVATIONS

In the context of tower measured radiation datasets.following the correction principle meeting a diagnostic equation in data quality control and in terms of a technique for model construction on data and ANN(artificial neural network)retrieval for BP correction of radiation measurements with rough errors available,a BP model is presented.Evidence suggests that the developed model works well and is superior to a convenient multivariate linear regression model,indicating its wide applications.