Approximating the CIECAM02 color appearance model by means of neural networks

An artificial neural network used to realize the approximating problem of the color appearance model (CAM) CIECAM02 in color management is demonstrated. GretagMacbeth ColorChecker Charts, which now are widely used in calibration of digital camera, are chosen as sanples to implement the forward and reverse color appearance models. When the predictive results are evaluated, for forward model, the output color appearance space is converted to the uniform color space based on CAM and is evaluated, while for reverse model, because the prediction precision is insufficient, we try to convert the color appearance space, which is the cylinder space, to the cube space similar to the red, green, and blue (RGB) space, and the results show that the precision is obviously improved.     

基于SOM和RBF网络的软测量方法研究

针对氢粉碎过程中钕铁硼粉碎状态不可知,为有效预测合金的反应状态,提出了一种基于自组织特征映射(SOM)神经网络和径向基函数(RBF)神经网络结合构建的网络模型。在该模型中,SOM神经网络作为聚类网络,采用无教师学习算法对输入样本进行自组织分类,并将分类中心及其对应的权值向量传递给RBF神经网络,作为径向基函数的中心;RBF神经网络作为基础网络,采用高斯函数作为径向基函数实现从输入到隐含层的非线性映射,输出层则采用有教师学习算法训练网络的权值,从而实现输入层到输出层的线性映射。并以钕铁硼氢粉碎过程合金中氢含量为检测对象,运用上述方法在MATLAB平台上建立了合金中氢含量预测模型,并完成了仿真验证。     

A Recurrent Quantum Neural Network Model to Describe Eye Tracking of Moving Targets

A theoretical quantum neural network model is proposed using a nonlinear Schrödinger wave equation. The model proposes that there exists a nonlinear Schrödinger wave equation that mediates the collective response of a neural lattice. The model is used to explain eye movements when tracking moving targets. Using a recurrent quantum neural network(RQNN) while simulating the eye tracking model, two very interesting phenomena are observed. First, as eye sensor data is processed in a classical neural network, a wave packet is triggered in the quantum neural network.This wave packet moves like a particle. Second, when the eye tracks a fixed target, this wave packet moves not in a continuous but rather in a discrete mode. This result reminds one of the saccadic movements of the eye consisting of ‘jumps’ and ‘rests’. However, such a saccadic movement is intertwined with smooth pursuit movements when the eye has to track a dynamic trajectory. In a sense, this is the first theoretical model explaining the experimental observation reported concerning eye movements in a static scene situation. The resulting prediction is found to be very precise and efficient in comparison to classical objective modeling schemes such as the Kalman filter.     

基于神经网络的大孔径厚针孔成像复原算法研究

为了更好地获取低强度辐射源空间分布图像,提出一种使用神经网络算法将大孔径厚针孔退化图像复原的方法。建立了孔径5 mm、10 mm、15 mm的厚针孔模型,获得了3600个汉字形状辐射源的厚针孔退化图像集。基于DnCNN神经网络模型,建立了大孔径厚针孔退化图像复原神经网络,并与维纳滤波、Lucy-Richardson这些传统算法进行了比较。在考虑噪声影响后,利用迁移学习理论,对原神经网络模型进行迁移训练,再对含噪大孔径厚针孔退化图像进行复原。神经网络算法复原的RMSE明显低于传统方法,迁移学习显著减小了噪声的影响。证明了神经网络算法在大孔径厚针孔退化图像复原领域的优越性,并验证了神经网络方法复原含噪大孔径厚针孔退化图像的可行性。     

Neural networks for prediction of acoustical properties of polyurethane foams

This paper presents a study of neural networks for prediction of acoustical properties of polyurethane foams. The proposed neural network model of the foam uses easily measured parameters such as frequency, airflow resistivity and density to predict multiple acoustical properties including the sound absorption coefficient and the surface impedance. Such a model is quite robust in the sense that it can be used to develop models for many different classes of materials with different sets of input and output parameters. The current neural network model of the foam is empirical and provides a useful complement to the existing analytical and numerical approaches.     

Predicting and optimising the airborne sound transmission of floor-ceiling constructions using computational intelligence

Computational intelligence (CI) techniques offer powerful alternatives for investigating acoustical issues and providing acoustical solutions to problems. This paper presents information on two CI techniques by applying them to the sound transmission performance prediction and design of floor-ceiling constructions.First a simple neural network (NN) model for predicting the airborne sound transmission of typical floor-ceiling constructions is presented and explained in detail. This model is accessible to researchers with knowledge of neural network analysis (NNA) for further sophistication, specialisation or hybridisation. The model may also be used by architects and others with no knowledge of NNA and no access to any specialised neural network software. Evolutionary algorithms (EAs) were then applied to search the multidimensional space created by the neural network model in order to optimise the airborne sound transmission of floor-ceiling constructions within the range of design parameters utilised in buildings.     

Sensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN

This paper proposes a data-driven method-based fault diagnosis method using the deep convolutional neural network (DCNN). The DCNN is used to deal with sensor and actuator faults of robot joints, such as gain error, offset error, and malfunction for both sensors and actuators, and different fault types are diagnosed using the trained neural network. In order to achieve the above goal, the fused data of sensors and actuators are used, where both types of fault are described in one formulation. Then, the deep convolutional neural network is applied to learn characteristic features from the merged data to try to find discriminative information for each kind of fault. After that, the fully connected layer does prediction work based on learned features. In order to verify the effectiveness of the proposed deep convolutional neural network model, different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), conventional neural network (CNN) using the LeNet-5 method, and long-term memory network (LTMN) are investigated and compared with DCNN method. The results show that the DCNN fault diagnosis method can realize high fault recognition accuracy while needing less model training time.     

人工神经网络结合多光谱遥感数据用于立地质量评价

多光谱遥感数据蕴含着大量的地表立地信息,而传统立地质量评价体系主要使用了人工地面调查数据。为了建立一套有效的立地质量评价体系,以内蒙古赤峰市旺业甸林场为研究对象,基于研究区域的多光谱遥感数据结合地面小班调查数据,采用一种改进的反向传播人工神经网络(back Propagation artificial neural network,BPANN)模型,以落叶松为例,建立了遥感光谱因子结合立地因子与地位指数关系的神经网络模型,对研究区域的小班进行立地质量评价研究。通过训练数据集的敏感度分析剔除弱相关或不相关的因子,简化了神经网络的规模,提高了网络的训练效率,得到了最优的地位指数预测模型,模型的预测精度达到95.36%,与使用传统小班调查数据建立的神经网络模型的预测结果进行了比较,精度提高了9.83%,说明使用多光谱遥感数据+小班调查数据确定的落叶松地位指数预测模型具有最高的预测精度。多光谱遥感数据十分适用于森林立地质量评价,改进BP神经网络具有理想的预测精度,充分证实了该方法的有效性和优越性。     

基于LM-BP神经网络的气阀故障诊断方法

提出一种基于LM（Levenberg-Marquardt）算法优化的 BP (Back Propagation)神经网络的多级往复式压缩机压缩机气阀故障诊断方法。以6M25-185/314氢氮气压缩机的 6级压差和6级温差作为网络的输入向量,建立可对往复式压缩机一至六级气阀故障进行在线监测及故障诊断的LM-BP神经网络模型。以100组故障数据作为网络训练样本,30组数据作为网络检测样本进行故障诊断,结果表明,LM-BP神经网络相比于变梯度BP神经网络和RBF神经网络诊断更快速稳定且准确率达到96%以上。利用Matlab软件平台建立的LM-BP 神经网络故障诊断模型,模型简单便于在工程实际中应用。     

基于径向基函数的多目标旋转不变分类及其光电实现

提出利用径向基函数构造广义判别函数及神经网络模型，显示了模式识别与神经网络之间的密切联系.利用此函数和模型实现了多目标的面内(二维旋转)、面外(三维空间旋转)旋转不变识别，计算机模拟表明，对于旋转不变识别这是一个很有效的方法.一个光电混合系统被提出实现此旋转不变识别方法. 关键词：     

基于人工神经网络的制冷系统工况模拟

针对人工神经网络技术在制冷空调系统中的仿真应用,本文建立了单回路制冷系统的性能仿真系统。通过实验模拟制冷系统在夏季的负荷变动情况,得到了用于神经网络模型训练的样本数据。对制冷系统进行多种神经网络结构的建模,并进行了神经网络中各种结构参数对模型精度影响的分析。利用训练好的双隐层神经网络模型,研究了空调机组性能的影响因素,包括压缩机频率、室内外温度等。模拟结果表明,机组EER随着压缩机频率增加先增加后减少,随着室内温度升高而增加,随着室外温度升高而减少。结果表明,人工神经网络方法是分析制冷机组性能的一种有效途径。     

多状态,多阈值神经网络模型的光电混合实现

提出了一种采用高分辨率液晶电视（ＬＣＴＶ）实现Ｈｏｐｆｉｅｌｄ神经网络多值算法的光电系统，文章给出了平面多状态，多阈值的全互连Ｈｏｐｆｉｅｄ神经网络模型，并采用该系统对颜色进行了联想和记忆的实验，初步的实验结果可以证实，此种高分辨率液晶电视神经网络系统是可行的。     

Neural-net based modeling of velocity and concentration fields

This paper proposes a novel algorithm using an artificial neural network for modeling simultaneously both a 3-D flow velocity vector and a concentration field. The neural network is trained so that four outputted values of the network, three components of a 3-D velocity vector and a concentration of substances such as air pollutants or bacilli, agree with measured ones and additionally the continuity and diffusion equations are satisfied in the flow field. An approximate model for the velocity and concentration field can be constructed in the neural network from sparsely measured data. When any 3-D position, (x, y, z), is inputted to the neural network model, it outputs a 3-D velocity vector and a concentration at the position. The entire 3-D velocity vector and concentration field, therefore, can be easily estimated using the model. To validate the algorithm, the smoke concentration distribution estimated from a very limited set of measured data is compared with the measured one in which most of the data is unused for the modeling. Even from sparsely measured velocity vectors and smoke concentrations, the novel algorithm gives the entire concentration distribution whose flow characteristics are almost similar to the experimental result.     

人工神经网络在配煤过程状态建模中的应用研究

本文详细介绍了人工神经网络应用于状态建模的方法．对神经网络应用中的一些难点提出了切实可行且有效的解决措施，并举例作了应用示范．同时还介绍了神经网络方法应用于优化动力配煤的情况，并就神经网络方法在优化动力配煤中的进一步应用作了展望．     

Feasibility of gem identification using reflectance spectra coupled with artificial intelligence

Abstract

Standard traditional gem identification requires expert supervision, while sophisticated modern methods are time-consuming and expensive. In contrast, reflectance spectroscopy coupled with artificial intelligence is economical and convenient and does not require specialist supervision. This study established an artificial neural network model that consists of standard multilayered, feed-forward, and back-propagation neural networks, and obtained reflectance spectra of a transparent gem (almandine), an opaque gem (turquoise), several almandine imitations (agate, plastic, and glass), and several treated turquoise samples (dyed, impregnated, and Zachery treated) using an Analytical Spectral Devices spectrometer. The acquired spectra were used to train and test the artificial neural network model. The results show that the model can effectively discriminate between genuine and imitation gems of different classes. However, discrimination between natural and treated gems of same class is not as effective as discrimination of gems of different classes. The results suggest that an artificial neural network based on reflectance spectroscopy could serve as a useful tool for preliminary gem identification, and the advanced identification needs further training and investigation.     

Detection of whale calls in noise: performance comparison between a beluga whale, human listeners, and a neural network

This article examines the masking by anthropogenic noise of beluga whale calls. Results from human masking experiments and a software backpropagation neural network are compared to the performance of a trained beluga whale. The goal was to find an accurate, reliable, and fast model to replace lengthy and expensive animal experiments. A beluga call was masked by three types of noise, an icebreaker's bubbler system and propeller noise, and ambient arctic ice-cracking noise. Both the human experiment and the neural network successfully modeled the beluga data in the sense that they classified the noises in the same order from strongest to weakest masking as the whale and with similar call-detection thresholds. The neural network slightly outperformed the humans. Both models were then used to predict the masking of a fourth type of noise, Gaussian white noise. Their prediction ability was judged by returning to the aquarium to measure masked-hearing thresholds of a beluga in white noise. Both models and the whale identified bubbler noise as the strongest masker, followed by ramming, then white noise. Natural ice-cracking noise masked the least. However, the humans and the neural network slightly overpredicted the amount of masking for white noise. This is neglecting individual variation in belugas, because only one animal could be trained. Comparing the human model to the neural network model, the latter has the advantage of objectivity, reproducibility of results, and efficiency, particularly if the interference of a large number of signals and noise is to be examined.     

The application of neural networks to forecast fuzzy time series

Fuzzy time series models have been applied to handle nonlinear problems. To forecast fuzzy time series, this study applies a backpropagation neural network because of its nonlinear structures. We propose two models: a basic model using a neural network approach to forecast all of the observations, and a hybrid model consisting of a neural network approach to forecast the known patterns as well as a simple method to forecast the unknown patterns. The stock index in Taiwan for the years 1991–2003 is chosen as the forecasting target. The empirical results show that the hybrid model outperforms both the basic and a conventional fuzzy time series models.     

基于神经网络的托卡马克能量约束时间预测

使用机器学习理论中的神经网络方法,根据通用逼近原理对能量约束时间的复杂函数进行逼近,采用托卡马克装置的典型实验数据,设计一种组合结构的神经网络。通过大量的调参试验,给出一套性能最好的参数组合,并与传统幂指数形式的多元线性回归方法进行准确性和数据集迁移能力的比较。结果表明：神经网络模型对于能量约束时间的预测准确率更高,回归性能更好,且具有一定的抗噪声能力,更适合作为能量约束时间的定标或预测工具。     

结合人工神经网络的翅片管式冷凝器快速仿真模型

为了提高翅片管式冷凝器仿真精度和计算速度，提出了含基本数学模型与两个神经网络的复合冷凝器模型．基本数学模型采用分区集中参数模型，简化用神经网络用以反映分区集中参数模型与分布参数模型间的非线性关系，精度改进用神经网络通过分析比较模型与实验值的差别，提高复合模型的精度．实际应用表明，复合模型的计算速度比分布参数     

小波变换与神经网络融合法在油页岩近红外光谱分析中的应用

便携式近红外光谱分析技术可实现油页岩含油率的原位检测,在油页岩资源现场勘查中发挥着重要作用。但是,由于其测得的原始光谱数据量大、冗余信息多,直接建模会影响速度与精度。因此提出一种小波变换与神经网络融合法,先将油页岩全谱数据进行db8小波3级分解,提取其近似系数形成输入矩阵,然后再进行神经网络建模。为了验证有效性,利用30个油页岩合成样品,从中随机选择20个用于训练,另外10个用于预测,并分别使用全谱数据与小波特征数据进行了10次神经网络建模。结果表明,全谱数据建模速度均值为570.33 s,预测残差平方和及相关系数均值分别为0.006 012及0.843 75;而小波神经网络法对应的以上均值为3.15 s, 0.002 048及0.953 19。由此说明小波神经网络法优于全谱数据建模法,为油页岩含油率的快速、高精度检测提供了一种新方法。