线性神经网络在舰船磁场推算模型中的应用

针对舰艇内外磁场推算问题,从智能优化的角度出发,建立了内外磁场之间的线性神经网络预报模型。该方法避免了利用数值建模存在的诸多困难,可实现舰艇内外磁场有效推算。并利用船模实验验证了网络预测的准确性,其换算精度相较于数值建模有所提高,满足工程实际需求。     

基于神经网络的磁性目标磁矩反演方法

针对磁性目标定位中的磁矩反演问题,提出一种基于神经网络的磁矩反演技术。首先,基于最小二乘原理,建立了磁性目标磁矩反演模型;其次采用Hopfield网络进行了优化求解,并针对模型求解过程中鲁棒性差的弊端,对网络进化策略进行了自适应修正;最后设计了仿真实验对其有效性进行了检验,仿真结果表明利用修正后的网络求解磁矩反演问题结果令人满意,具有一定的实用性。     

基于神经网络的MUSIC计算方法

MUSIC方法是空间谱估计中经典的子空间方法,这类算法有个共同特点就是要对输出数据的协方差矩阵进行数学分解,其计算量较大,不适合实时处理。因此,文章提出了基于神经网络的高效迭代方法,不需进行数学分解,计算过程相对简单。仿真结果证明了该方法的有效性。     

基于BP神经网络轻型轿车排放模型的应用

本文利用BP神经网络理论,构造一个预测轻型轿车排放的BP神经网络模型,经验证,预测模型能较好地对一般轻型轿车排放结果进行定性预测,可以作为简易稳态工况法(ASM)尾气检测前的参考,对节约检测成本、提高一次检测通过率有着较高的实用价值;同时以南京市为例,研究了轻型汽油车行驶里程、使用年限等参数对排放的影响,为有针对性的维修治理提供可靠的依据。     

Impact of phytoplankton community size on a linked global ocean optical and ecosystem model

We isolated the effect phytoplankton cell size has on varying remote sensing reflectance spectra (R_rs(λ)) in the presence of optically active constituents by using optical and radiative transfer models linked in an offline diagnostic calculation to a global biogeochemical/ecosystem/circulation model with explicit phytoplankton size classes. Two case studies were carried out, each with several scenarios to isolate the effects of chlorophyll concentration, phytoplankton cell size, and size-varying phytoplankton absorption on R_rs(λ). The goal of the study was to determine the relative contribution of phytoplankton cell size and chlorophyll to overall R_rs(λ) and to understand where a standard band ratio algorithm (OC4) may under/overestimate chlorophyll due to R_rs(λ) being significantly affected by phytoplankton size. Phytoplankton cell size was found to contribute secondarily to R_rs(λ) variability and to amplify or dampen the seasonal cycle in R_rs(λ), driven by chlorophyll. Size and chlorophyll were found to change in phase at low to mid-latitudes, but were anti-correlated or poorly correlated at high latitudes. Phytoplankton size effects increased model calculated R_rs(443) in the subtropical ocean during local spring through early fall months in both hemispheres and decreased R_rs(443) in the Northern Hemisphere high latitude regions during local summer to fall months. This study attempts to tease apart when/where variability about the OC4 relationship may be associated with cell size variability. The OC4 algorithm may underestimate [Chl] when the fraction of microplankton is elevated, which occurs in the model simulations during local spring/summer months at high latitudes in both hemispheres.     

基于PSO-BP神经网络的船体分段任务包工时定额模型

为解决船体分段任务包工时定额的计算过度依赖线性公式而忽略工时定额与工艺参数之间的非线性关系的问题,提高工时定额计算的效率和精确度,将PSO-BP神经网络技术应用到船体分段任务包工时定额中。通过对影响船体分段中间产品额定工时的工艺参数进行分析,建立多输入单输出的PSO-BP神经网络模型,并应用实际数据对PSO-BP神经网络进行训练,测试仿真结果与实际值之间的误差在允许范围内。验证结果表明,采用PSO-BP神经网络建立船体分段任务包工时定额模型,能对任务包作业工时进行准确预测。     

基于组合预测模型的铁路货运量预测研究

为了进一步提高铁路货运量的预测精度,提出基于乘积季节模型与引入注意力机制(Attention Mechanism)的长短期记忆(Long Short-Term Memory)模型的组合预测模型。首先建立乘积季节模型、LSTM模型与引入注意力机制的LSTM模型,然后利用误差修正法分别将2种LSTM模型与乘积季节模型组合起来进行预测,最后将预测结果分别与单一模型进行对比。采用2005年至2018年全国铁路月度货运量进行预测分析,结果表明2种组合预测模型的预测精度均高于单一预测模型的预测精度,其中基于乘积季节模型与引入注意力机制的LSTM模型的组合预测模型精度最高,具有研究和实用价值。     

A new logit‐artificial neural network ensemble for mode choice modeling: a case study for border transport

Logit model is one of the statistical techniques commonly used for mode choice modeling, while artificial neural network (ANN) is a very popular type of artificial intelligence technique used for mode choice modeling. Ensemble learning has evolved to be very effective approach to enhance the performance for many applications through integration of different models. In spite of this advantage, the use of ANN‐based ensembles in mode choice modeling is under explored. The focus of this study is to investigate the use of aforementioned techniques for different number of transportation modes and predictor variables. This study proposes a logit‐ANN ensemble for mode choice modeling and investigates its efficiency in different situations. Travel between Khobar‐Dammam metropolitan area of Saudi Arabia and Kingdom of Bahrain is selected for mode choice modeling. The travel on this route can be performed mainly by air travel or private vehicle through King Fahd causeway. The results show that the proposed ensemble gives consistently better accuracies than single models for multinomial choice problems irrespective of number of input variables. Copyright © 2015 John Wiley & Sons, Ltd.     

Analyzing passenger train arrival delays with support vector regression

We propose machine learning models that capture the relation between passenger train arrival delays and various characteristics of a railway system. Such models can be used at the tactical level to evaluate effects of various changes in a railway system on train delays. We present the first application of support vector regression in the analysis of train delays and compare its performance with the artificial neural networks which have been commonly used for such problems. Statistical comparison of the two models indicates that the support vector regression outperforms the artificial neural networks. Data for this analysis are collected from Serbian Railways and include expert opinions about the influence of infrastructure along different routes on train arrival delays.     

Analysis of air traffic control operational impact on aircraft vertical profiles supported by machine learning

The Air Traffic Management system is under a paradigm shift led by NextGen and SESAR. The new trajectory-based Concept of Operations is supported by performance-based trajectory predictors as major enablers. Currently, the performance of ground-based trajectory predictors is affected by diverse factors such as weather, lack of integration of operational information or aircraft performance uncertainty.Trajectory predictors could be enhanced by learning from historical data. Nowadays, data from the Air Traffic Management system may be exploited to understand to what extent Air Traffic Control actions impact on the vertical profile of flight trajectories.This paper analyses the impact of diverse operational factors on the vertical profile of flight trajectories. Firstly, Multilevel Linear Models are adopted to conduct a prior identification of these factors. Then, the information is exploited by trajectory predictors, where two types are used: point-mass trajectory predictors enhanced by learning the thrust law depending on those factors; and trajectory predictors based on Artificial Neural Networks.Air Traffic Control vertical operational procedures do not constitute a main factor impacting on the vertical profile of flight trajectories, once the top of descent is established. Additionally, airspace flows and the flight level at the trajectory top of descent are relevant features to be considered when learning from historical data, enhancing the overall performance of the trajectory predictors for the descent phase.