This paper describes a new semi-supervised learning algorithm for intra-class clustering (ICC). ICC partitions each class into sub-classes in order to minimize overlap across clusters from different classes. This is a...
详细信息
This paper describes a new semi-supervised learning algorithm for intra-class clustering (ICC). ICC partitions each class into sub-classes in order to minimize overlap across clusters from different classes. This is achieved by allowing partitioning of a certain class to be assisted by data points from other classes in a context-dependent fashion. The result is that overlap across sub-classes (both within- and across class) is greatly reduced. ICC is particularly useful when combined with algorithms that assume that each class has a unimodal Gaussian distribution (e.g., Linear Discriminant Analysis (LDA), quadratic classifiers), an assumption that is not always true in many real-world situations. ICC can help partition non-Gaussian, multimodal distributions to overcome such a problem. In this sense, ICC works as a preprocessor. Experiments with our ICC algorithm on synthetic data sets and real-world data sets indicated that it can significantly improve the performance of LDA and quadratic classifiers. We expect our approach to be applicable to a broader class of pattern recognition problems where class-conditional densities are significantly non-Gaussian or multi-modal. (C) 2013 Elsevier B:V. All rights reserved.
Radar emitter recognition is an important part of the electronic attack and defense system, and its key task is to sort and identify various information of emitters from mixed pulse streams. Pulse descriptor word, as ...
详细信息
Radar emitter recognition is an important part of the electronic attack and defense system, and its key task is to sort and identify various information of emitters from mixed pulse streams. Pulse descriptor word, as an easily obtainable feature, is often used for sorting and recognition. Aiming at the problems of high complexity and difficulty in handling intra-class clustering and inter-class aliasing of existing sorting methods, a hierarchical clustering method based on Kernel Density Estimation-Kullback-Leibler Divergence-Template Matching (KDEKLD-TM) is proposed. Firstly, the down-sampled data is used to construct central clusters, greatly improving the processing speed. Then, with probability theory as the theoretical support, inter-classclustering on all samples is performed based on maximum posterior probability. Finally, based on cluster distribution similarity and periodic template matching, intra-class merging and inter-class deinterleaving are completed. After sorting, considering the periodic differences in pulse repetition intervals among different types of emitter and the insufficient attention paid by existing recognition methods to this feature, a time-frequency convolution network (TFCN) based emitter recognition method is proposed for the first time in terms of pulse description word. Using time-frequency analysis (TFA) to extract periodic features and using convolutional neural networks (CNN) for classification, the onedimensional sequence classification problem is treated as a two-dimensional image classification problem. The proposed method is simulated in a typical scenario with intra-class clustering and inter-class aliasing. The results show that the proposed method can sort a total of 2.06 million aliased samples composed of 10 classes within 58.61 s, and the recognition accuracy reaches 96.33%. The comparison with the baseline method proves the effectiveness and progressiveness of the proposed method. Finally, the sorting and recognition
Visible-infrared person re-identification (VI-ReID) aims to match pedestrian images from visible and near- infrared modalities. The pedestrian images of two modalities contain discriminative features indifferent sizes...
详细信息
Visible-infrared person re-identification (VI-ReID) aims to match pedestrian images from visible and near- infrared modalities. The pedestrian images of two modalities contain discriminative features indifferent sizes and positions, e.g., the global color of the cloth, the body's local pose, and the shoe's pixel size. However, existing methods mainly capture features at a single granularity, ignoring multi-granularity information contributing to pedestrian identification. Therefore, we propose a cross-modality multi-granularity Transformer (CM2GT) framework to solve this issue. CM2GT learns coarse-to-fine feature representations and integrates discriminative information across various granularities, which alleviates problems of the irrelevant matching and ambiguous alignment caused by matching single granularity features. Specifically, we first design a multi-granularity feature extractor (MGFE) module based on Transformer to capture the global-patch-pixel level features of each modality, which can flexibly represent semantic information at multiple scales. Secondly, a multi-granularity fusion Transformer (MGFT) module mines the hierarchical relationships between multi-granularity features by a saliency-enhanced Transformer, which ensures the identity-wise saliency consistency across different granularities and modalities. Furthermore, to further enhance cross-modality intra-class clustering in latent space, we design a cross-modality nearest-neighbor clustering (CNC) loss function to minimize the distance between the anchor sample and its cross-modality nearest neighbor. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods.
A new classification model, the fuzzy hybrid twin support vector machine(TWSVM), namely FHTWSVM, is proposed by combining the fuzzy TWSVM and the hypersphere support vector machine(SVM).The hypersphere SVM is utilized...
详细信息
A new classification model, the fuzzy hybrid twin support vector machine(TWSVM), namely FHTWSVM, is proposed by combining the fuzzy TWSVM and the hypersphere support vector machine(SVM).The hypersphere SVM is utilized for generating the hyperspheres for the positive and negative class with the smallest possible radius, so that the hyperspheres can contain as many samples as possible. The samples which the hyperspheres cover form a new sample set. Furthermore a distance-based fuzzy function is utilized to calculate the fuzzy factors for the samples. Finally FHTWSVM is used to train all samples with the parameters optimized by grid search. This method can maximize intra-class clustering for noise removal and reduce the influence of *** demonstrate the superiority of the performance of FHTWSVM over other classifiers, e.g., KNN, RF,Bayesian, TWSVM, Ada Boost and XGBoost, a series of experiments is conducted using eight gene expression datasets. The evaluation results show that the proposed approach can improve the classification performance as well as reduce prediction errors for the datasets.
暂无评论