Jianping Gou

A Local Mean-Based k-Nearest Centroid Neighbor Classifier

K-nearest neighbor (KNN) rule is a simple and effective algorithm in pattern classification. In this article, we propose a local mean-based k-nearest centroid neighbor classifier that assigns to each query pattern a class label with nearest local centroid mean vector so as to improve the classification performance. The proposed scheme not only takes into account the proximity and spatial distribution of k neighbors, but also utilizes the local mean vector of k neighbors from each class in making classification decision. In the proposed classifier, a local mean vector of k nearest centroid neighbors from each class for a query pattern is well positioned to sufficiently capture the class distribution information. In order to investigate the classification behavior of the proposed classifier, we conduct extensive experiments on the real and synthetic data sets in terms of the classification error. Experimental results demonstrate that our proposed method performs significantly well, particularly in the small sample size cases, compared with the state-of-the-art KNN-based algorithms.

Improved pseudo nearest neighbor classification

k-Nearest neighbor (KNN) rule is a very simple and powerful classification algorithm. In this article, we propose a new KNN-based classifier, called the local mean-based pseudo nearest neighbor (LMPNN) rule. It is motivated by the local mean-based k-nearest neighbor (LMKNN) rule and the pseudo nearest neighbor (PNN) rule, with the aim of improving the classification performance. In the proposed LMPNN, the k nearest neighbors from each class are searched as the class prototypes, and then the local mean vectors of the neighbors are yielded. Subsequently, we attempt to find the local mean-based pseudo nearest neighbor per class by employing the categorical k local mean vectors, and classify the unknown query patten according to the distances between the query and the pseudo nearest neighbors. To assess the classification performance of the proposed LMPNN, it is compared with the competing classifiers, such as LMKNN and PNN, in terms of the classification error on thirty-two real UCI data sets, four artificial data sets and three image data sets. The comprehensively experimental results suggest that the proposed LMPNN classifier is a promising algorithm in pattern recognition.

Locality-Based Discriminant Neighborhood Embedding

In this article, we develop a linear supervised subspace learning method called locality-based discriminant neighborhood embedding (LDNE), which can take advantage of the underlying submanifold-based structures of the data for classification. Our LDNE method can simultaneously consider both ‘locality’ of locality preserving projection (LPP) and ‘discrimination’ of discriminant neighborhood embedding (DNE) in manifold learning. It can find an embedding that not only preserveslocalinformationtoexploretheintrinsicsubmanifoldstructureofdatafromthesameclass, but also enhances the discrimination among submanifolds from different classes. To investigate the performance of LDNE, we compare it with the state-of-the-art dimensionality reduction techniques such as LPP and DNE on publicly available datasets. Experimental results show that our LDNE can be an effective and robust method for classification.

Two-Phase Representation Based Classification

In this paper, we propose the two-phase representation based classification called the two-phase linear reconstruction measure based classification (TPLRMC). It is inspired from the fact that the linear reconstruction measure (LRM) gauges the similarities among feature samples by decomposing each feature sample as a liner combination of the other feature samples with \(L_{p}\)-norm regularization. Since the linear reconstruction coefficients can fully reveal the feature’s neighborhood structure that is hidden in the data, the similarity measures among the training samples and the query sample are well provided in classifier design. In TPLRMC, it first coarsely seeks the K nearest neighbors for the query sample with LRM, and then finely represents the query sample as the linear combination of the determined K nearest neighbors and uses LRM to perform classification. The experimental results on face databases show that TPLRMC can significantly improve the classification performance.

Discriminative self-adapted locality-sensitive sparse representation for video semantic analysis

In recent years, sparse representation has attracted a blooming interest in the areas of pattern recognition, image processing, and computer vision. In video semantic analysis, the diversity of scene for the same semantic content in video always exists. Using dictionary learning in sparse representation can capture the latent relationship among the original diverse video semantic features. To enhance the discriminative ability of diverse video semantic features, the method of discriminative self-adapted locality-sensitive sparse representation for video semantic analysis is proposed. In the proposed method, a discriminative self-adaptive locality-sensitive dictionary learning method (DSALSDL) is designed. In DSALSDL, a self-adaptive local adapter is built to join in the process of dictionary learning for sparse representation, so as to obtain the potential information of the video data. Furthermore, in the self-adaptive locality-sensitive sparse representation, a discriminant loss function based on class-specific representation coefficients is imposed to further learn appropriate dictionary for video semantic analysis. Using the self-adaptive local adapter and discriminant loss function in dictionary learning, the sparse representation is exploited for video semantic concept detection. The proposed method is evaluated on the related video databases in comparison with existing relative sparse representation methods. Experimental results show that our method can improve the power of discrimination of video features and improve the accuracy of video semantic concept detection.

Discriminative sparsity preserving graph embedding

In this paper, we propose a new dimensionality reduction method called discriminative sparsity preserving graph embedding (DSPGE). Unlike many existing graph embedding methods such as locality preserving projections (LPP) and sparsity preserving projections (SPP), the aim of DSPGE is to preserve the sparse reconstructive relationships of data while simultaneously capture the geometric and discriminant structure of data in the embedding space. Through the sparse reconstruction and class-specific adjacent graphs, DSPGE characterizes the intra-class and inter-class sparsity preserving scatters, seeking to achieve the optimal projections that simultaneously maximize the inter-class sparsity preserving scatter and minimize intra-class sparsity preserving scatter. The effectiveness of the proposed DSPGE is demonstrated on two popular face databases, compared to up-to-date methods. The experimental results show that DSPGE outperforms the competing methods with the satisfactory classification performance.

Dynamical Properties of Discrete-Time Background Neural Networks with Uniform Firing Rate

The dynamics of a discrete-time background network with uniform firing rate and background input is investigated. The conditions for stability are firstly derived. An invariant set is then obtained so that the nondivergence of the network can be guaranteed. In the invariant set, it is proved that all trajectories of the network starting from any nonnegative value will converge to a fixed point under some conditions. In addition, bifurcation and chaos are discussed. It is shown that the network can engender bifurcation and chaos with the increase of background input. The computations of Lyapunov exponents confirm the chaotic behaviors.

An emotion-based responding model for natural language conversation

As an important task of artificial intelligence, natural language conversation has attracted wide attention of researchers in natural language processing. Existing works in this field mainly focus on consistency of neural response generation whilst ignoring the effect of emotion state on the response generation. In this paper, we propose an Emotion-based natural language Responding Model (ERM) to address the challenging issue in conversation. ERM encodes the emotion state of the conversation as distributed embedding into the process of response generation, redefines an objective function that jointly trains our model and introduces a novel re-rank function to select the appropriate response. Experimental results on Chinese conversation dataset show that our method yields qualitative performance improvements in the Perplexity (PPL), Word Error-rate (WER) and Bilingual Evaluation Understudy (BLEU) compared with the baseline sequence-to-sequence (Seq2Seq) model, and achieves better performance than the state-of-the-art in terms of emotion and content consistency of the response.

Least squares kernel ensemble regression in Reproducing Kernel Hilbert Space

Abstract Ensemble regression method shows better performance than single regression since ensemble regression method can combine several single regression methods together to improve accuracy and stability of a single regressor. In this paper, we propose a novel kernel ensemble regression method by minimizing total least square loss in multiple Reproducing Kernel Hilbert Spaces (RKHSs). Base kernel regressors are co-optimized and weighted to form an ensemble regressor. In this way, the problem of finding suitable kernel types and their parameters in base kernel regressor is solved in the ensemble regression framework. Experimental results on several datasets, such as artificial datasets, UCI regression and classification datasets, show that our proposed approach achieves the lowest regression loss among comparative regression methods such as ridge regression, support vector regression (SVR), gradient boosting, decision tree regression and random forest.

Group sparse based locality – sensitive dictionary learning for video semantic analysis

Sparse Representation-based Classifier (SRC) and Dictionary Learning (DL), have significantly impacted greatly on the classification performance of image recognition in recent times. In video semantic analysis, the locality structure of video semantic data containing more discriminative information is very essential for classification. However, this has not been fully considered by the current sparse representation-based approaches. Furthermore, similar coding outcomes are not being realized from video features with the same video category. To handle these issues, we propose a novel DL method, called Group Sparsity Locality-Sensitive Dictionary Learning (GSLSDL) for video semantic analysis. In the proposed GSLSDL, a discriminant loss function for the video category based on group sparse coding of sparse coefficients, is introduced into the structure of the Locality-Sensitive Dictionary Learning (LSDL) method. After solving the optimized dictionary, the sparse coefficients for the testing video feature samples are obtained. The classification result for video semantic is then realized by minimizing the error between the original and reconstructed samples. The experiment results show that, the proposed GSLSDL significantly improves the performance of video semantic detection compared with the competing methods, and robust in various diverse environments of video.