Integrated assessment of sea water quality based on BP artificial neural network

In order to carry out an integrated assessment of sea water quality objectively, this paper based on the concept and principle of artificial neural network, generated appropriate training samples for BP artificial neural network model through the method of producing samples to the concentration of various pollution index of sea water quality from the viewpoint of threshold, established the BP artificial neural network model of sea water quality assessment using multi-layer neural network with error back-propagation algorithm. This model was used to assess water environment and obtain sea water quality categories of offshore area in Bohai Bay through calculating. The calculations shown that pollution index in river＇s wet season was higher than that in dry season from 2004 to 2007, and the pollution was particularly serious in 2005 and 2006, but a little better in 2007. The assessed results of cases shown that the model was reasonable in design and higher in generalization, meanwhile, it was common, objective and practical to sea water quality assessment.

Application of Artificial Neural Network to Battlefield Target Classification

To study the capacity of artificial neural network (ANN) applying to battlefield target classification and result of classification, according to the characteristics of battlefield target acoustic and seismic signals, an on the spot experiment was carried out to derive acoustic and seismic signals of a tank and jeep by special experiment system. Experiment data processed by fast Fourier transform(FFT) were used to train the ANN to distinguish the two battlefield targets. The ANN classifier was performed by the special program based on the modified back propagation (BP) algorithm. The ANN classifier has high correct identification rates for acoustic and seismic signals of battlefield targets, and is suitable for the classification of battlefield targets. The modified BP algorithm eliminates oscillations and local minimum of the standard BP algorithm, and enhances the convergence rate of the ANN.

基于TensorFlow的CNN自由手写数字识别研究

CNN卷积神经网络是图像识别和分类等领域的前沿研究方法。由于CNN模型训练效果与实际测试之间存在较大的差距,为提高自由手写数字的识别率,尝试使用TensorFlow搭构CNN网络模型,在完成MNIST数据集训练的基础上实现对自由手写数字的识别,并根据两种样本状态的差别和识别结果提出效果分析及改进方法,实验证明该改进方法获得明显效果。

RS-SVM forecasting model and power supply-demand forecast

A support vector machine (SVM) forecasting model based on rough set (RS) data preprocess was proposed by combining the rough set attribute reduction and the support vector machine regression algorithm, because there are strong complementarities between two models. Firstly, the rough set was used to reduce the condition attributes, then to eliminate the attributes that were redundant for the forecast, Secondly, it adopted the minimum condition attributes obtained by reduction and the corresponding original data to re-form a new training sample, which only kept the important attributes affecting the forecast accuracy. Finally, it studied and trained the SVM with the training samples after reduction, inputted the test samples re-formed by the minimum condition attributes and the corresponding original data, and then got the mapping relationship model between condition attributes and forecast variables after testing it. This model was used to forecast the power supply and demand. The results show that the average absolute error rate of power consumption of the whole society and yearly maximum load are 14.21% and 13.23%, respectively, which indicates that the RS-SVM forecast model has a higher degree of accuracy.

Adaptive WNN aerodynamic modeling based on subset KPCA feature extraction

In order to accurately describe the dynamic characteristics of flight vehicles through aerodynamic modeling, an adaptive wavelet neural network (AWNN) aerodynamic modeling method is proposed, based on subset kernel principal components analysis (SKPCA) feature extraction. Firstly, by fuzzy C-means clustering, some samples are selected from the training sample set to constitute a sample subset. Then, the obtained samples subset is used to execute SKPCA for extracting basic features of the training samples. Finally, using the extracted basic features, the AWNN aerodynamic model is established. The experimental results show that, in 50 times repetitive modeling, the modeling ability of the method proposed is better than that of other six methods. It only needs about half the modeling time of KPCA-AWNN under a close prediction accuracy, and can easily determine the model parameters. This enables it to be effective and feasible to construct the aerodynamic modeling for flight vehicles.

Novel Active Learning Method for Speech Recognition

In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning （AL） is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence （KLD） and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.

EEG classification based on probabilistic neural network with supervised learning in brain computer interface

Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented in this paper. It applies the recognition rate of training samples to the learning progress of network parameters. The learning vector quantization is employed to group training samples and the Genetic algorithm （GA） is used for training the network＇ s smoothing parameters and hidden central vector for detemlining hidden neurons. Utilizing the standard dataset I （a） of BCI Competition 2003 and comparing with other classification methods, the experiment results show that the best performance of pattern recognition Js got in this way, and the classification accuracy can reach to 93.8%, which improves over 5% compared with the best result （88.7 % ） of the competition. This technology provides an effective way to EEG classification in practical system of BCI.

Extending self-organizing maps for supervised classification of remotely sensed data

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.

An infrared human face recognition method based on 2DPCA

Aimed at the problems of infrared image recognition under varying illumination,face disguise,etc.,we bring out an infrared human face recognition algorithm based on 2DPCA.The proposed algorithm can work out the covariance matrix of the training sample easily and directly;at the same time,it costs less time to work out the eigenvector.Relevant experiments are carried out,and the result indicates that compared with the traditional recognition algorithm,the proposed recognition method is swift and has a good adaptability to the changes of human face posture.

Auto recognition of carbonate microfacies based on an improved back propagation neural network

Though traditional methods could recognize some facies, e.g. lagoon facies, backshoal facies and foreshoal facies, they couldn't recognize reef facies and shoal facies well. To solve this problem, back propagation neural network(BP-ANN) and an improved BP-ANN with better stability and suitability, optimized by a particle swarm optimizer(PSO) algorithm(PSO-BP-ANN) were proposed to solve the microfacies' auto discrimination of M formation from the R oil field in Iraq. Fourteen wells with complete core, borehole and log data were chosen as the standard wells and 120 microfacies samples were inferred from these 14 wells. Besides, the average value of gamma, neutron and density logs as well as the sum of squares of deviations of gamma were extracted as key parameters to build log facies(facies from log measurements)-microfacies transforming model. The total 120 log facies samples were divided into 12 kinds of log facies and 6 kinds of microfacies, e.g. lagoon bioclasts micrite limestone microfacies, shoal bioclasts grainstone microfacies, backshoal bioclasts packstone microfacies, foreshoal bioclasts micrite limestone microfacies, shallow continental micrite limestone microfacies and reef limestone microfacies. Furthermore, 68 samples of these 120 log facies samples were chosen as training samples and another 52 samples were gotten as testing samples to test the predicting ability of the discrimination template. Compared with conventional methods, like Bayes stepwise discrimination, both the BP-ANN and PSO-BP-ANN can integrate more log details with a correct rate higher than 85%. Furthermore, PSO-BP-ANN has more simple structure, smaller amount of weight and threshold and less iteration time.

Adaptive Nonlinear Model Predictive Control Using an On-line Support Vector Regression Updating Strategy

The performance of data-driven models relies heavily on the amount and quality of training samples, so it might deteriorate significantly in the regions where samples are scarce. The objective of this paper is to develop an online SVR model updating strategy to track the change in the process characteristics efficiently with affordable computational burden. This is achieved by adding a new sample that violates the Karush–Kuhn–Tucker conditions of the existing SVR model and by deleting the old sample that has the maximum distance with respect to the newly added sample in feature space. The benefits offered by such an updating strategy are exploited to develop an adaptive model-based control scheme, where model updating and control task perform alternately.The effectiveness of the adaptive controller is demonstrated by simulation study on a continuous stirred tank reactor. The results reveal that the adaptive MPC scheme outperforms its non-adaptive counterpart for largemagnitude set point changes and variations in process parameters.

Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns

In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.

The first all-season sample set for mapping global land cover with Landsat-8 data

We report the world's first all-season training and validation sample sets for global land cover classification with Landsat-8 data.Prior to this,such samples were only available at a single date primarily from the growing season.It is unknown how much limitation such a single-date sample has to mapping global land cover in other seasons of the year.To answer this question,we selected available Landsat-8 images from four seasons and collected training and validation samples from them.We compared the performances of training samples in different seasons using Random Forest algorithm.We found that the use of training samples from any individual season would result in the best overall classification accuracy when validated by samples in the same season.The global overall accuracy from combined best seasonal results was 67.2% when classifying the 11 Level-1 classes in the Finer Resolution Observation and Monitoring of Global Land Cover(FROM-GLC) classification system.The use of training samples from all seasons(named all-season training sample set hereafter) produced an overall accuracy of 67.0%.We also tested classification within 10° latitude 60° longitude zones using all-season training subsample within each zone and obtained an overall accuracy of 70.2%.This indicates that properly grouped subsamples in space can help improve classification accuracies.All the results in this study seem to suggest that it is possible to use an all-season training sample set to reach global optimality with universal applicability in classifying images acquired at any time of a year for global land cover mapping.

Application of Support Vector Machine to Ship Steering

System identification is an effective way for modeling ship manoeuvring motion and ship manoeuvrability prediction. Support vector machine is proposed to identify the manoeuvring indices in four different response models of ship steering motion, including the first order linear, the first order nonlinear, the second order linear and the second order nonlinear models. Predictions of manoeuvres including trained samples by using the identified parameters are compared with the results of free-running model tests. It is discussed that the different four categories are consistent with each other both analytically and numerically. The generalization of the identified model is verified by predicting different untrained manoeuvres. The simulations and comparisons demonstrate the validity of the proposed method.