The asymptotic optimization of pre-edited ANN classifier

The generalization problem of an artificial neural network (ANN) classifier with unlimited size of training sample, namely asymptotic optimization in probability, is discussed in this paper. As an improved ANN network model, the pre-edited ANN classifier shows better practical performance than the standard one. However, it has not been widely applied due to the absence of the related theoretical support. To further promote its application in practice, the asymptotic optimization of the pre-edited ANN classifier is studied in this paper. To help study ANN asymptotic optimization in probability, we gives a review of the previous research works on asymptotic optimization in probability of non-parametric classifier, and grouped the main methods into four classes: two-step method, one-step method, generalization method and hypothesis method. In this paper, we adopt generalization/hypothesis mixed method to prove that pre-edited ANN is asymptotically optimal in probability. Furthermore, a simulation is presented to provide an experimental support for our theoretical work.     

Land cover classification in rugged areas using simulated moderateresolution remote sensor data and an artificial neural network

Rugged land cover classification accuracies produced by an artificial neural network (ANN) using simulated moderate-resolution remote sensor data exceed overall accuracies produced using the maximum likelihood rule (MLR). Land cover in spatially-complex areas and at broad spatial scales may be difficult to monitor due to ambiguities in spectral reflectance information produced from cloud-related and topographic effects, or from sampling constraints. Such ambiguities may produce inconsistent estimates of changes in vegetation status, surface energy balance, run-off yields, or other land cover characteristics. By use of a 'back-classification' protocol, which uses the same pixels for testing as for training the classifier, tests of ANN versus MLR-based classifiers demonstrated the ANNbased classifier equalled or exceeded classification accuracies produced by the MLR-based classifier in five of six land cover classes evaluated.     

On the behavior of artificial neural network classifiers inhigh-dimensional spaces

It is widely believed in the pattern recognition field that when a fixed number of training samples is used to design a classifier, the generalization error of the classifier tends to increase as the number of features gets larger. In this paper, we discuss the generalization error of the artificial neural network (ANN) classifiers in high-dimensional spaces, under a practical condition that the ratio of the training sample size to the dimensionality is small. Experimental results show that the generalization error of ANN classifiers seems much less sensitive to the feature size than 1-NN, Parzen and quadratic classifiers     

Adaptive resonance neural classifier for identification of gases/odours using an integrated sensor array

A new approach to intelligent gas sensor (IGS) design using a classifier based on adaptive resonance theory (ART) artificial neural network (ANN) is presented. Using published data of sensor arrays fabricated and characterised at our laboratory, we demonstrate excellent gas/odour identification performance of our classifier for a 4-gas, 4-sensor system to identify individual gas/odour. Since the ART neural network is a self-organising classifier trained in the unsupervised mode, it avoids the drawbacks associated with static feedforward neural networks trained with a locally optimal backpropagation-type training algorithms applied by researchers in the recent past. The ART neural network offers easy implementability and real time performance in addition to giving excellent classification accuracy as demonstrated by our experiments.     

Empirical results of using back-propagation neural networks toseparate single echoes from multiple echoes

Empirical results illustrate the pitfalls of applying an artificial neural network (ANN) to classification of underwater active sonar returns. During training, a back-propagation ANN classifier learns to recognize two classes of reflected active sonar waveforms: waveforms having two major sonar echoes or peaks and those having one major echo or peak. It is shown how the classifier learns to distinguish between the two classes. Testing the ANN classifier with different waveforms of each type generated unexpected results: the number of echo peaks was nor the feature used to separate classes.     

Estimation of chemical oxygen demand by ultraviolet spectroscopic profiling and artificial neural networks

A simple method based on the mathematical treatment of spectral absorbance profiles in conjunction with artificial neural networks (ANNs) is demonstrated for rapidly estimating chemical oxygen demand (COD) values of wastewater samples. In order to improve spectroscopic analysis and ANN training time as well as to reduce the storage space of the trained ANN algorithm, it is necessary to decrease the ANN input vector size by extracting unique characteristics from the raw input pattern. Key features from the spectral absorbance pattern were therefore selected to obtain the spectral absorbance profile, reducing the ANN input vector from 160 to 10 selected inputs. The results indicate that the COD values obtained from the selected absorbance profiles agreed well with those obtained from the entire absorbance pattern. The spectral absorbance profile technique was also compared to COD values estimated by a multiple linear regression (MLR) model to validate whether ANNs were better and more robust models for rapid COD analysis. It was found that the ANN model predicted COD values closer to standard COD values than the MLR model.     

一种神经网络文本分类器的设计与实现

论文着重介绍了一种基于神经网络的文本分类器,分类器使用神经网络作为分类工具,特征词的词频组成原始特征向量,和神经网络输入层的神经元一一对应。并引入了信息检索中的常用技术——潜在语义索引,训练过程中结合遗传算法,优化神经网络的初始权值。最后对分类器进行了开放性测试,实验表明分类器对文本分类具有较高的平均查全率和平均精度。     

Recognition of control chart patterns using multi-resolution wavelets analysis and neural networks☆

Control charts pattern recognition is one of the most important tools in statistical process control to identify process problems. Unnatural patterns exhibited by such charts can be associated with certain assignable causes affecting the process. In this paper, multi-resolution wavelets analysis (MRWA) is used to extract distinct features for unnatural patterns by providing distinct time–frequency coefficients. A reduced set of parameters is derived from these coefficients and used as input to an artificial neural network (ANN) classifier. Results show that the performance of the proposed technique in classifying shift, trend and cyclic patterns is superior to that of ANN classifier, which operated on coded observed data.     

A comparison of texture measures for the per-field classification of Mediterranean land cover

Land cover of a Mediterranean region was classified within an artificial neural network (ANN) on a per-field basis using Landsat Thematic Mapper (TM) imagery. In addition to spectral information, the classifier used geostatistical structure functions and texture measures extracted from the co-occurrence matrix. Geostatistical measures of texture resulted in a more accurate classification of Mediterranean land cover than statistics derived from the co-occurrence matrix. The primary advantage of geostatistical measures was their robustness over a wide range of land cover types, field sizes and forms of class mixing. Spectral information and the variogram (geostatistical texture measure) resulted in the highest overall classification accuracies.     

Spectral prediction of Phytophthora infestans infection on tomatoes using artificial neural network (ANN)

Late blight (LB) is one of the most aggressive tomato diseases in California. Accurately detecting the disease will increase the efficiency of properly controlling the disease infestations to ensure the crop production. In this study, we developed a method to spectrally predict late blight infections on tomatoes based on artificial neural network (ANN). The ANN was designed as a back‐propagation (BP) neural network that used gradient‐descent learning algorithm. Through comparing different network structures, we selected a 3‐25‐9‐1 network structure. Two experimental samples, from field experiments and remotely sensed image data sets, were used to train the ANN to predict healthy and diseased tomato canopies with various infection stages for any given spectral wavelength (µm) intervals. Results of discrete data indicated different levels of disease infestations. The correlation coefficients of prediction values and observed data were 0.99 and 0.82 for field data and remote sensing image data, respectively. In addition, we predicted the field data based on the remote sensing image data and predicted the remote sensing image data with field data using the same network structure, and the results showed that the coefficient of determination was 0.62 and 0.66, respectively. Our study suggested an ANN with back‐propagation training could be used in spectral prediction in the study.     

Performance of artificial neural networks in nearshore wave power prediction

In this paper the assessment of the wave energy potential in nearshore coastal areas is investigated by means of artificial neural networks (ANNs). The performance of the ANNs is compared with in situ measurements and spectral numerical modelling (the conventional tool for wave energy assessment). For this purpose, 13 years of records of two buoys, one offshore and one inshore, with an hourly frequency are used to develop an ANN model for predicting the nearshore wave power. The best suited architecture was selected after assessing the performance of 480 ANN models involving twelve different architectures. The results predicted by the ANN model were compared with the measured data and those obtained by means of the SWAN (Simulating Waves Nearshore) spectral model. The quality in the predictions of the ANN model shows that this type of artificial intelligence models constitutes a powerful tool to forecast the wave energy potential at particular coastal site with great accuracy, and one that overcomes some of the disadvantages of the conventional tools for nearshore wave power prediction.     

An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring

Accurate equipment remaining useful life prediction is critical to effective condition based maintenance for improving reliability and reducing overall maintenance cost. In this paper, an artificial neural network (ANN) based method is developed for achieving more accurate remaining useful life prediction of equipment subject to condition monitoring. The ANN model takes the age and multiple condition monitoring measurement values at the present and previous inspection points as the inputs, and the life percentage as the output. A function generalized from the Weibull failure rate function is used to fit each condition monitoring measurement series for a failure history, and the fitted measurement values are used to form the ANN training set so as to reduce the effects of the noise factors that are irrelevant to the equipment degradation. A validation mechanism is introduced in the ANN training process to improve the prediction performance of the ANN model. The proposed ANN method is validated using real-world vibration monitoring data collected from pump bearings in the field. A comparative study is performed between the proposed ANN method and an adapted version of a reported method, and the results demonstrate the advantage of the proposed method in achieving more accurate remaining useful life prediction.     

A bootstrap technique for nearest neighbor classifier design

A bootstrap technique for nearest neighbor classifier design is proposed. Our primary interest in designing a classifier is in small training sample size situations. Conventional bootstrapping techniques sample the training samples with replacement. On the other hand, our technique generates bootstrap samples by locally combining original training samples. The nearest neighbor classifier is designed on the bootstrap samples and is tested on the test samples independent of training samples. The performance of the proposed classifier is demonstrated on three artificial data sets and one real data set. Experimental results show that the nearest neighbor classifier designed on the bootstrap samples outperforms the conventional k-NN classifiers as well as the edited 1-NN classifiers, particularly in high dimensions     

Fast and improved backpropagation learning of multi-layer artificial neural network using adaptive activation function

In the conventional backpropagation (BP) learning algorithm used for the training of the connecting weights of the artificial neural network (ANN), a fixed slope−based sigmoidal activation function is used. This limitation leads to slower training of the network because only the weights of different layers are adjusted using the conventional BP algorithm. To accelerate the rate of convergence during the training phase of the ANN, in addition to updates of weights, the slope of the sigmoid function associated with artificial neuron can also be adjusted by using a newly developed learning rule. To achieve this objective, in this paper, new BP learning rules for slope adjustment of the activation function associated with the neurons have been derived. The combined rules both for connecting weights and slopes of sigmoid functions are then applied to the ANN structure to achieve faster training. In addition, two benchmark problems: classification and nonlinear system identification are solved using the trained ANN. The results of simulation-based experiments demonstrate that, in general, the proposed new BP learning rules for slope and weight adjustments of ANN provide superior convergence performance during the training phase as well as improved performance in terms of root mean square error and mean absolute deviation for classification and nonlinear system identification problems.     

Feature dimensionality reduction for the verification of handwritten numerals

A novel method based on multi-modal discriminant analysis is proposed to reduce feature dimensionality. First, each class is divided into several clusters by the k-means algorithm. The optimal discriminant analysis is implemented by multi-modal mapping. Our method utilizes only those training samples on and near the effective decision boundary to generate a between-class scatter matrix, which requires less CPU time than other nonparametric discriminant analysis (NDA) approaches [Fukunaga and Mantock in IEEE Trans PAMI 5(6):671–677, 1983; Bressan and Vitria in Pattern Recognit Lett 24(5):2473–2749, 2003]. In addition, no prior assumptions about class and cluster densities are needed. In order to achieve a high verification performance of confusing handwritten numeral pairs, a hybrid feature extraction scheme is developed, which consists of a set of gradient-based wavelet features and a set of geometric features. Our proposed dimensionality reduction algorithm is used to congregate features, and it outperforms the principal component analysis (PCA) and other NDA approaches. Experiments proved that our proposed method could achieve a high feature compression performance without sacrificing its discriminant ability for classification. As a result, this new method can reduce artificial neural network (ANN) training complexity and make the ANN classifier more reliable.     

Spectral mixture analysis for mapping abundance of urban surface components from the Terra/ASTER data

Using a linear unconstrained least squares (LSS) method and a non-linear artificial neural network (ANN) algorithm, we conducted a spectral mixture analysis to the Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) image data in Yokohama city, Japan, for mapping the abundance of the urban surface components. ASTER is a newly developed research facility instrument. The regions of interest of four endmembers (Vegetation, Soil, High/Low albedo impervious surfaces) were determined in Maximum Noise Fraction (MNF) feature spaces. The spectral signatures of the four endmembers were then extracted from the ASTER VNIR (15-m resolution) and SWIR (30-m resolution) imagery by referring to high spatial resolution airborne imagery (The Airborne Imaging Spectrometer, AISA, with 2-m resolution) and land use/land cover map for training and testing the LSS and ANN algorithms. Experimental results indicate that ASTER VNIR and SWIR image data are capable of mapping the abundances of urban surface components with a reasonable accuracy and that the ANN outperforms the unconstrained LSS in this spectral mixture analysis.     

Robust radar target classifier using artificial neural networks

In this paper an artificial neural network (ANN) based radar target classifier is presented, and its performance is compared with that of a conventional minimum distance classifier. Radar returns from realistic aircraft are synthesized using a thin wire time domain electromagnetic code. The time varying backscattered electric field from each target is processed using both a conventional scheme and an ANN-based scheme for classification purposes. It is found that a multilayer feedforward ANN, trained using a backpropagation learning algorithm, provides a higher percentage of successful classification than the conventional scheme. The performance of the ANN is found to be particularly attractive in an environment of low signal-to-noise ratio. The performance of both methods are also compared when a preemphasis filter is used to enhance the contributions from the high frequency poles in the target response.     

Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery

Improvement in remote sensing techniques in spatial/spectral resolution strengthens their applicability for urban environmental study. Unfortunately, high spatial resolution imagery also increases internal variability in land cover units and can cause a ‘salt-and-pepper’ effect, resulting in decreased accuracy using pixel-based classification results. Region-based classification techniques, using an image object (IO) rather than a pixel as a classification unit, appear to hold promise as a method for overcoming this problem. Using IKONOS high spatial resolution imagery, we examined whether the IO technique could significantly improve classification accuracy compared to the pixel-based method when applied to urban land cover mapping in Tampa Bay, FL, USA. We further compared the performance of an artificial neural network (ANN) and a minimum distance classifier (MDC) in urban detailed land cover classification and evaluated whether the classification accuracy was affected by the number of extracted IO features. Our analysis methods included IKONOS image data calibration, data fusion with the pansharpening (PS) process, Hue–Intensity–Saturation (HIS) transferred indices and textural feature extraction, and feature selection using a stepwise discriminant analysis (SDA). The classification results were evaluated with visually interpreted data from high-resolution (0.3 m) digital aerial photographs. Our results indicate a statistically significant difference in classification accuracy between pixel- and object-based techniques; ANN outperforms MDC as an object-based classifier; and the use of more features (27 vs. 9 features) increases the IO classification accuracy, although the increase is statistically significant for the MDC but not for the ANN.     

结合纹理与轮廓特征的多通道行人检测算法

针对在复杂场景下,聚合通道特征（ACF）的行人检测算法存在检测精度较低、误检率较高的问题,提出一种结合纹理和轮廓特征的多通道行人检测算法。算法由训练分类器和检测两部分组成。在训练阶段,首先提取ACF特征、局部二值模式（LBP）纹理特征和ST（Sketch Tokens）轮廓特征,然后对提取的三类特征均采用Real AdaBoost分类器进行训练;在检测阶段,应用了级联检测的思想,初期使用ACF分类器处理所有实例,保留下来的少数实例应用复杂的LBP及ST分类器进行逐次筛选。实验采用INRIA数据集对算法进行仿真,该算法的平均对数漏检率为13.32%,与ACF算法相比平均对数漏检率降低了3.73个百分点。实验结果表明LBP特征与ST特征能有对ACF特征进行信息互补,从而在复杂场景下去掉部分误判,提高了行人检测的精度,同时应用级联检测保证了多特征算法的计算效率。     

Parallel supervised land-cover classification system for hyperspectral and multispectral images

Hyperspectral and multispectral imagery allows remote-sensing applications such as the land-cover mapping, which is a significant baseline to understand and to monitor the Earth. Furthermore, it is a relevant process for socio-economic activities. For that reason, high land-classification accuracies are imperative, and minor image processing time is essential. In addition, the process of gathering classes’ documented samples is complicated. This implies that the classification system is required to perform with a limited number of training observations. Another point worth mentioning is that there are hardly any methods that can be used analogously for hyperspectral or multispectral images. This paper aims to propose a novel classification system that can be used for both types of images. The designed classification system is composed of a novel parallel feature extraction algorithm, which utilises a cluster of two graphics processing units in combination with a multicore central processing unit (CPU), and an artificial neural network (ANN) particularly devised for the classification of the features ensued by the implemented feature extraction method. To prove the performance of the proposed classification system, it is compared with non-parallel and CPU-only-parallel implementations employing multispectral and hyperspectral databases. Moreover, experiments with different number of samples for training the classifier are performed. Finally, the proposed ANN is compared with a state-of-the-art support vector machine in classification and processing time results.