基于ELM理论的昆虫分类

机器视觉技术应用在昆虫分类领域,取代传统人眼观察识别过程、提高了工作效率。自动识别技术包含昆虫特征提取和分类器设计两个主要步骤。根据整个识别过程,文中提出了一种基于混合特征的ELM理论昆虫识别方法。在特征提取阶段,提取混合特征包括颜色特征、形态特征、空域纹理特征和频谱纹理特征。在分类器设计阶段采用具有学习速度快且泛化性能好的极限学习机。实验结果表明,该方法使昆虫识别的正确率达到97%,且分类器训练时间短,优于传统的自动识别方法。     

Classification of malignant and benign masses based on hybrid ART2LDA approach

A new type of classifier combining an unsupervised and a supervised model was designed and applied to classification of malignant and benign masses on mammograms. The unsupervised model was based on an adaptive resonance theory (ART2) network which clustered the masses into a number of separate classes. The classes were divided into two types: one containing only malignant masses and the other containing a mix of malignant and benign masses. The masses from the malignant classes were classified by ART2. The masses from the mixed classes were input to a supervised linear discriminant classifier (LDA). In this way, some malignant masses were separated and classified by ART2 and the less distinguishable benign and malignant masses were classified by LDA. For the evaluation of classifier performance, 348 regions of interest (ROI's) containing biopsy proven masses (169 benign and 179 malignant) were used. Ten different partitions of training and test groups were randomly generated using an average of 73% of ROI's for training and 27% for testing. Classifier design, including feature selection and weight optimization, was performed with the training group. The test group was kept independent of the training group. The performance of the hybrid classifier was compared to that of an LDA classifier alone and a backpropagation neural network (BPN). Receiver operating characteristics (ROC) analysis was used to evaluate the accuracy of the classifiers. The average area under the ROC curve (A(z)) for the hybrid classifier was 0.81 as compared to 0.78 for the LDA and 0.80 for the BPN. The partial areas above a true positive fraction of 0.9 were 0.34, 0.27 and 0.31 for the hybrid, the LDA and the BPN classifier, respectively. These results indicate that the hybrid classifier is a promising approach for improving the accuracy of classification in CAD applications.     

A multilevel hybrid anomaly detection scheme for industrial wireless sensor networks

Real-time sensing plays an important role in ensuring the reliability of industrial wireless sensor networks (IWSNs). Sensor nodes in IWSNs have inherent limitations that give rise to different anomalies in the network. These anomalies can lead to disastrous and harmful situations or even serious system failures. This article presents a formulation to the design of an anomaly detection scheme for detecting the anomalous node along with the type of anomaly. The proposed scheme is divided into two major parts. First, spatiotemporal correlation within a cluster is obtained for the normal and anomalous behavior of sensor nodes. Second, the multilevel hybrid classifier is used by combining the sequential minimal optimization support vector machine (SMO-SVM) as a binary classifier with optimally pruned extreme learning machine (OP-ELM) as a multiclass classifier for detection of an anomalous node and type of anomalies, respectively. Mahalanobis distance-based lightweight K-Medoid clustering is used to build a new set of training datasets that represents the original training dataset, by significantly reducing the training time of a multilevel hybrid classifier. Results are analyzed using standard WSN datasets. The proposed model shows high accuracy, i.e., 94.79% and detection rate, i.e., 94.6% with a reduced false positive rate as compared to existing hybrid methods.     

Blind signal-type classification using a novel robust feature subset selection method and neural network classifier

Automatic modulation recognition plays an important role for many novel computer and communication technologies. Most of the proposed systems can only identify a few kinds of digital signal and/or low order of them. They usually require high levels of signal-to-noise ratio. In this paper, we present a novel hybrid intelligent system that automatically recognizes a variety of digital signals. In this recognizer, a multilayer perceptron neural network with resilient back propagation learning algorithm is proposed as the classifier. For the first time, a combination set of spectral features and higher order moments up to eighth and higher order cumulants up to eighth are proposed as the effective features. Then we have optimized the classifier design by bees algorithm (BA) for selection of the best features that are fed to the classifier. This optimization method is new for this area. Simulation results show that the proposed technique has very high recognition accuracy with seven features selected by BA.     

Recognition of the Communication Signals Using Particle Swarm Optimization and Support Vector Machine Based on the Multi-Resolution Wavelet Analysis

Automatic recognition of the communication signals plays an important role for various applications. This paper presents a novel intelligent system for recognition of digital communication signals. This system includes three main modules: feature extraction module, classifier module and optimization module. In the feature extraction module, multi-resolution wavelet analysis is proposed for extraction the suitable features. In the classifier module, a multi-class support vector machine (SVM) based classifier is proposed as the multi-class classifier. For optimization module, a particle swarm optimization algorithm is proposed to improve the generalization performance of the recognizer. In this module, it is optimized the SVM classifier design by searching for the best value of the parameters that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. Simulation results show that the proposed hybrid intelligent system has high performance even at very low signal to noise ratios (SNRs).     

Improving the performance of fuzzy classifier systems for patternclassification problems with continuous attributes

In this paper, various methods are introduced for improving the ability of fuzzy classifier systems to automatically generate fuzzy if-then rules for pattern classification problems with continuous attributes. First, we describe a simple fuzzy classifier system where a randomly generated initial population of fuzzy if-then rules is evolved by typical genetic operations, such as selection, crossover, and mutation. By computer simulations on a real-world pattern classification problem with many continuous attributes, we show that the search ability of such a simple fuzzy classifier system is not high. Next, we examine the search ability of a hybrid algorithm where a learning procedure of fuzzy if-then rules is combined with the fuzzy classifier system. Then, we introduce two heuristic procedures for improving the performance of the fuzzy classifier system. One is a heuristic rule generation procedure for an initial population where initial fuzzy if-then rules are directly generated from training patterns. The other is a heuristic population update procedure where new fuzzy if-then rules are generated from misclassified and rejected training patterns, as well as from existing fuzzy if-then rules by genetic operations. By computer simulations, we demonstrate that these two heuristic procedures drastically improve the search ability of the fuzzy classifier system. We also examine a variant of the fuzzy classifier system where the population size (i.e., the number of fuzzy if-then rules) varies depending on the classification performance of fuzzy if-then rules in the current population     

最小化支持向量数分类器的云检测

针对。感卫星图像的云检测,提出了基于最小化支持向量数分类器的云检测方案,解决传统分类器训练样本多、易陷入局部最优的问题。使用该分类器对QuickBird高分辨率。感图像进行云检测,检测正确率达99%以上。实验表明:在确定分类器内部结构参数过程中,与传统的交叉验证法相比,基于支持向量数的方法不仅能够准确预测分类器推广性能的变化趋势,从而确立最优化的参数组合,并且实现简单,大大减少了计算的复杂度。与传统的BP神经网络相比,该方法所需训练样本少,分类性能好。     

Distinguishing between natural and recolored images via lateral chromatic aberration

With the development of image colorization technique, the recolored images (RIs) become more and more authentic, making it very difficult to visually distinguish from natural images (NIs). Recently, researchers have proposed the detection methods towards recolored images. However, the current detection still has limitations such as poor generalization, large-scale training samples, high-dimensional features for training, and high computation cost. To address those issues, this paper proposes a novel method based on the lateral chromatic aberration (LCA) inconsistency and its statistical differences. Generally, RIs have fewer numbers of LCA characteristics than that of NIs, that inspire us to design the classifier for distinguishing two types of images. In particular, we propose to adopt very low 5-dimensional features to feed a classical SVM mechanism. The baseline ImageNet and Oxford datasets are used to verify the effectiveness of the proposed method, in which the performance of our proposed method rivals the prior arts.     

Classifying gene expression data of cancer using classifier ensemble with mutually exclusive features

The explosion of DNA and protein sequence data in public and private databases has been encouraging interdisciplinary research on biology and information technology. Gene expression profiles are just sequences of numbers, and the necessity of tools analyzing them to get useful information has risen significantly. In order to predict the cancer class of patients from the gene expression profile, this paper presents a classification framework that combines a pair of classifiers trained with mutually exclusive features. The idea behind feature selection with nonoverlapping correlation is to encourage classifier ensemble, which consists of multiple classifiers, to learn different aspects of training data, so that classifiers can search in a wide solution space. Experimental results show that the classifier ensemble produces higher recognition accuracy than conventional classifiers.     

基于CPSO－AdaBoost算法的人脸检测方法

Ada Boost分类器训练算法对特征搜索的时间复杂度较高,改进的PSO-Ada Boost算法采用最佳特征搜索方式训练耗时减少,但在迭代过程中容易陷入局部最优解。为此,提出用混沌粒子群优化Ada Boost训练算法的CPSO-Ada Boost算法。通过引入混沌优化序列增加种群的多样性并扩大粒子搜索范围,帮助粒子克服"惰性"摆脱局部最优解,从而在训练分类器时可以快速寻找到性能更好的弱分类器。在MIT样本库上训练人脸检测分类器结果表明,CPSO-Ada Boost算法减少了训练过程中所需要的特征数量,缩短了训练时间,有效地提高了人脸检测率。     

基于BitBP特征的多重级联人脸检测器

结合Haar和MB-LBP特征,提出了一种采用BitBP特征描述图像局部信息的方法,该特征可有效描述图像局部区域的灰度像素分布情况,具有比Haar和MB-LBP特征更强的分类能力。且可有效地克服Haar特征数目巨大、训练时间长的缺点。根据BitBP特性,提出一种多重级联的分类器。该分类器的每层均由单一BitBP特征的次级级联分类器构成。而次级级联分类器中的每层分类器均是一个小型的联分类器。利用多重级联结构,可获得更快的检测速度。     

Automatic image orientation detection

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how principal component analysis (PCA) and linear discriminant analysis (LDA) can be used as a feature extraction mechanism to remove redundancies in the high-dimensional feature vectors used for classification. The proposed method is compared with four different commonly used classifiers, namely k-nearest neighbor, support vector machine (SVM), a mixture of Gaussians, and hierarchical discriminating regression (HDR) tree. Experiments on a database of 16 344 images have shown that our proposed algorithm achieves an accuracy of approximately 98% on the training set and over 97% on an independent test set. A slight improvement in classification accuracy is achieved by employing classifier combination techniques.     

Size-reduction and band-broadening design technique of uniplanarhybrid ring coupler using phase inverter for M(H)MIC's

The hybrid coupler is one of the most fundamental building blocks in microwave and millimeter-wave systems. Ring topology can be often found in the hybrid microwave integrated-circuit design of narrow and broad-band integrated couplers and mixers. In this paper, we propose a new design theory using a phase inverter for systematic size reduction and band broadening of a uniplanar hybrid ring coupler. The features and design criteria of broad-band reverse-phase hybrid ring couplers are presented. Effective bandwidth of a new reverse-phase hybrid ring coupler can be increased by 28% with a return loss of 20 dB. In addition, we present a class of uniplanar phase inverters and discuss their technical aspects. Experimental results show that the bandwidth of the proposed phase inverter is greater than 1.9 octaves with insertion loss below 1 dB and phase shift error of less than ±20°. Measurements confirm that the new uniplanar hybrid ring coupler provides attractive features. Its isolation is better than 20 dB over a 1.8-octave bandwidth attributed to the phase inverter providing almost a frequency-independent phase shift     

Wavelet Transformation and Signal Discrimination for HRR Radar Target Recognition

This paper explores the use of wavelets to improve the selection of discriminant features in the target recognition problem using High Range Resolution (HRR) radar signals in an air to air scenario. We show that there is statistically no difference between four different wavelet families in extracting discriminatory features. Since similar results can be obtained from any of the four wavelet families and wavelets within the families, the simplest wavelet (Haar) should be used. We further show that a simple box classifier can be constructed from the extracted features and that any feature that classifies four or less training signals can be removed from the classifier without a statistically significant difference in the classifier performance. We use the box classifier to select the 128 most salient pseudo range bins and then apply the wavelet transform to this reduced set of bins. We show that by iteratively applying this approach, classifier performance is improved. The number of times the feature reduction and transformation can be performed while producing improved classifier performance is small and the transformed features are shown to quickly cause the performance to approach an asymptote.     

Group-sensitive multiple kernel learning for object recognition

In this paper, a group-sensitive multiple kernel learning (GS-MKL) method is proposed for object recognition to accommodate the intraclass diversity and the interclass correlation. By introducing the "group" between the object category and individual images as an intermediate representation, GS-MKL attempts to learn group-sensitive multikernel combinations together with the associated classifier. For each object category, the image corpus from the same category is partitioned into groups. Images with similar appearance are partitioned into the same group, which corresponds to the subcategory of the object category. Accordingly, intraclass diversity can be represented by the set of groups from the same category but with diverse appearances; interclass correlation can be represented by the correlation between groups from different categories. GS-MKL provides a tractable solution to adapt multikernel combination to local data distribution and to seek a tradeoff between capturing the diversity and keeping the invariance for each object category. Different from the simple hybrid grouping strategy that solves sample grouping and GS-MKL training independently, two sample grouping strategies are proposed to integrate sample grouping and GS-MKL training. The first one is a looping hybrid grouping method, where a global kernel clustering method and GS-MKL interact with each other by sharing group-sensitive multikernel combination. The second one is a dynamic divisive grouping method, where a hierarchical kernel-based grouping process interacts with GS-MKL. Experimental results show that performance of GS-MKL does not significantly vary with different grouping strategies, but the looping hybrid grouping method produces slightly better results. On four challenging data sets, our proposed method has achieved encouraging performance comparable to the state-of-the-art and outperformed several existing MKL methods.     

一种基于类Haar特征和改进AdaBoost分类器的车辆识别算法

 提出一种基于类haar特征和改进AdaBoost分类器的车辆图像识别算法,以解决当前基于SVM分类器或级联分类器存在的分类识别性能不足以及传统基于AdaBoost算法的训练所需时间过长的问题.首先,基于积分图提取图像的扩展类haar特征,然后对所提取的海量类haar特征应用改进的AdaBoost分类器训练方法进行特征选择及分类器训练,最后利用所选择的特征信息及训练得到的分类器进行两类分类识别.实验结果表明,文中方法无论是在识别性能还是训练所需时间方面均明显优于传统方法,具有较好的应用前景.     

Cardiorespiratory-based sleep staging in subjects with obstructive sleep apnea

A cardiorespiratory-based automatic sleep staging system for subjects with sleep-disordered breathing is described. A simplified three-state system is used: Wakefulness (W), rapid eye movement (REM) sleep (R), and non-REM sleep (S). The system scores the sleep stages in standard 30-s epochs. A number of features associated with the epoch RR-intervals, an inductance plethysmography estimate of rib cage respiratory effort, and an electrocardiogram-derived respiration (EDR) signal were investigated. A subject-specific quadratic discriminant classifier was trained, randomly choosing 20% of the subject's epochs (in appropriate proportions of W, S and R) as the training data. The remaining 80% of epochs were presented to the classifier for testing. An estimated classification accuracy of 79% (Cohen's kappa value of 0.56) was achieved. When a similar subject-independent classifier was trained, using epochs from all other subjects as the training data, a drop in classification accuracy to 67% (kappa = 0.32) was observed. The subjects were further broken in groups of low apnoea-hypopnea index (AHI) and high AHI and the experiments repeated. The subject-specific classifier performed better on subjects with low AHI than high AHI; the performance of the subject-independent classifier is not correlated with AHI. For comparison an electroencephalograms (EEGs)-based classifier was trained utilizing several standard EEG features. The subject-specific classifier yielded an accuracy of 87% (kappa = 0.75), and an accuracy of 84% (kappa = 0.68) was obtained for the subject-independent classifier, indicating that EEG features are quite robust across subjects. We conclude that the cardiorespiratory signals provide moderate sleep-staging accuracy, however, features exhibit significant subject dependence which presents potential limits to the use of these signals in a general subject-independent sleep staging system.     

Relevancy contemplation in medical data analytics and ranking of feature selection algorithms

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.     

An adaptive classifier design for high-dimensional data analysiswith a limited training data set

Proposes a self-learning and self-improving adaptive classifier to mitigate the problem of small training sample size that can severely affect the recognition accuracy of classifiers when the dimensionality of the multispectral data is high. This proposed adaptive classifier utilizes classified samples (referred to as semilabeled samples) in addition to original training samples iteratively. In order to control the influence of semilabeled samples, the proposed method gives full weight to the training samples and reduced weight to semilabeled samples. The authors show that by using additional semilabeled samples that are available without extra cost, the additional class label information may be extracted and utilized to enhance statistics estimation and hence improve the classifier performance, and therefore the Hughes phenomenon (peak phenomenon) may be mitigated. Experimental results show this proposed adaptive classifier can improve the classification accuracy as well as representation of estimated statistics significantly     

Supervised enhancement filters: application to fissure detection in chest CT scans

In medical image processing, many filters have been developed to enhance certain structures in 3-D data. In this paper, we propose to use pattern recognition techniques to design more optimal filters. The essential difference with previous approaches is that we provide a system with examples of what it should enhance and suppress. This training data is used to construct a classifier that determines the probability that a voxel in an unseen image belongs to the target structure(s). The output of a rich set of basis filters serves as input to the classifier. In a feature selection process, this set is reduced to a compact, efficient subset. We show that the output of the system can be reused to extract new features, using the same filters, that can be processed by a new classifier. Such a multistage approach further improves performance. While the approach is generally applicable, in this work the focus is on enhancing pulmonary fissures in 3-D computed tomography (CT) chest scans. A supervised fissure enhancement filter is evaluated on two data sets, one of scans with a normal clinical dose and one of ultra-low dose scans. Results are compared with those of a recently proposed conventional fissure enhancement filter. It is demonstrated that both methods are able to enhance fissures, but the supervised approach shows better performance; the areas under the receiver operating characteristic (ROC) curve are 0.98 versus 0.90, for the normal dose data and 0.97 versus 0.87 for the ultra low dose data, respectively.