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.

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。

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.

数控机床工作台DSP定位误差系统设计及分析

为进一步优化数控机床对于测试误差的补偿功能,开发通过DSP硬件系统对误差进行准确预测并设置补偿措施。建立的定位误差模型预测补偿系统包含数控系统进给轴反馈结构、DSP建模预测系统以及数控系统。研究结果表明,采用Matlab软件运行得到的优化权值与阈值建立的GA-BP网络进行误差预测共需251μs;采用GA-BP网络构建的模型进行预测时达到了更高精度。该研究有助于提高数控机床加工精度,对提高加工参数的优化起到很好的指导意义以及控制效果。

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。

在线社交网络中基于多态信任融合的信任估计

为提高大型在线社交网络中信任计算方法的准确性和鲁棒性,采用共被引和转置信任传播操作,提出一种基于多态信任融合的信任估计方法估计连续信任/不信任值。结合信任者、被信任者的相邻用户的信息以及被信任者对信任者的信任,平均估计出两个用户信任或被其它用户信任的差异,以及一个用户信任另一个用户和被该用户信任的差异;利用这些差异,计算4种部分信任估计值,将这些部分估计值加权平均,得到信任者对被信任者的最终信任估计值。仿真结果表明,所提方法比其它最新的现有信任计算算法更准确和鲁棒,对应用于大型网络更高效。

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。

掘进机截割头截割特性数值模拟研究

为了解决掘进机各关键部件在工况环境下发生振动破坏的问题,利用数值模拟软件对掘进机截割头进行工况分析,发现随着模态的不断增加,此时的固有频率呈现逐步增大的趋势,当模态为31时,掘进机最大变形值出现在支撑架位置,在此位置的变形最大值为1.782 2 mm。同时对掘进机在钻进和横截工况下的振动特性以及受力特性进行分析,随着时间的变化,此时的横截和钻进工况下,截割头合外力均呈现无规律变化情况,两种工况下的合力最大值分别为86 kN和50 kN,钻进工况对于截割头截齿的影响要强于横截工况,为后续截割头截齿设计提供一定的参考。

基于GA优化BP神经网络的机床转台定位误差分析

为了提高数控机床转台误差补偿效果,设计了一种通过遗传算法(GA)来完成BP神经网络优化过程,并加入坐标参数、运动速度指标建立了转台定位误差模型。通过Matlab软件构建GA优化BP模型,得到优化权值与阈值后,将结果移植至DSP内开展建模与预测,促进预测速率的大幅提升。研究结果表明:机床转台处于各空间位置与速率下形成了不同定位误差,总体呈现较为复杂的变化特征采用GA优化BP神经网络构建的模型预测时达到了更高精度,误差残差范围在-0.5~0.5μm,满足实际需求。该研究有助于提高机床转台定位精度,增强加工精度。

Dual-threshold symbol selective relaying in cooperative networks

In order to efficiently mitigate error propagation and reduce computational complexity, this paper proposes a scheme for traditional cooperative networks, named as dual-threshold symbol selective demodulate-and-forward. In the scheme, two log likelihood ratio(LLR)-based thresholds are devised to measure the reliability of received signals for the relay and the destination, respectively. One of the threshold guarantees that the relay only forwards reliable symbols, thus less error will be propagated to the destination. The other threshold is used at the destination for determining the reliability of symbols received from the source.The destination will directly demodulate reliable symbols received from the source. Otherwise, when the symbols received from the source are not reliable, the maximum ratio combiner(MRC) is used to combine symbols received from the source and the relay.Closed-form expression of the bit error probability(BEP) of the proposed scheme is derived and analyzed under binary phase shift keying(BPSK) modulation. Then, the relationship and closed-form solutions of two LLR-based thresholds are derived. Simulation results prove that the theoretical BEP of the proposed scheme closely matches the simulated ones. The proposed scheme can achieve high performance with low computational complexity compared to existing schemes.

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

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。