Affine-Constrained Group Sparse Coding and Its Application to Image-Based Classifications

2021

Tinshhua Sci. Technol.

A Brain-Computer Interface (BCI) aims to produce a new way for people to communicate with computers.Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio (SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition III Dataset II.

Section: Ngsc From the Sample Set Perspectivementioning

confidence: 99%

Exploiting sparse representation in the P300 speller paradigm

Liu

2021

Tinshhua Sci. Technol.

“…The discriminative terms include softmax discriminative cost function [14], Fisher discrimination function [15], linear classification errors [9], [16], [17] and hinge loss function [18]. With the assumption that samples in the same class tend to share some atoms, the structural sparsity information is explored to learn discriminative dictionaries [19], [20]. The above dictionary learning methods are linear and thus are inadequate for dealing with highly nonlinear datasets.…”

Section: Introductionmentioning

confidence: 99%

Self-Taught Semisupervised Dictionary Learning With Nonnegative Constraint

Zhang

Liu

et al. 2020

IEEE Trans. Ind. Inf.

This paper investigates classification by dictionary learning. A novel unified framework termed self-taught semisupervised dictionary learning with non-negative constraint (NNST-SSDL) is proposed for simultaneously optimizing the components of a dictionary and a graph Laplacian. Specifically, an atom graph Laplacian regularization is built by using sparse coefficients to effectively capture the underlying manifold structure. It is more robust to noisy samples and outliers because atoms are more concise and representative than training samples. A non-negative constraint imposed on the sparse coefficients guarantees that each sample is in the middle of its related atoms. In this way the dependency between samples and atoms is made explicit. Furthermore, a self-taught mechanism is introduced to effectively feed back the manifold structure induced by atom graph Laplacian regularization and the supervised information hidden in unlabeled samples in order to learn a better dictionary. An efficient algorithm, combining a block coordinate descent method with the alternating direction method of multipliers is derived to optimize the unified framework. Experimental results on several benchmark datasets show the effectiveness of the proposed model.

“…Mixed regularization can promotes the use of a small subset of atoms for each class. Thus, sharing of dictionary atoms for data in the same class could increase the discriminative power of the dictionary (Bengio et al 2009;Chi et al 2013b;2013a). Bengio et al (Bengio et al 2009) propose the method of group sparse coding by using the same dictionary words for all the images in a class, which provides a discriminative signal in the construction of image representations.…”

Section: Introductionmentioning

confidence: 99%

“…Bengio et al (Bengio et al 2009) propose the method of group sparse coding by using the same dictionary words for all the images in a class, which provides a discriminative signal in the construction of image representations. Chi et al (Chi et al 2013b) propose an intra-block coherence suppression dictionary learning algorithm by employing the block and group regularized sparse modeling. They also present a novel affine-constrained group sparse coding framework (Chi et al 2013a) to extend the current sparse representation-based classification (SRC) framework for classification problems with multiple inputs.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Dictionary Learning via Structural Sparse Preserving

Zhang

Fan

et al. 2016

AAAI

While recent techniques for discriminative dictionary learning have attained promising results on the classification tasks, their performance is highly dependent on the number of labeled samples available for training. However, labeling samples is expensive and time consuming due to the significant human effort involved. In this paper, we present a novel semi- supervised dictionary learning method which utilizes the structural sparse relationships between the labeled and unlabeled samples. Specifically, by connecting the sparse reconstruction coefficients on both the original samples and dictionary, the unlabeled samples can be automatically grouped to the different labeled samples, and the grouped samples share a small number of atoms in the dictionary via mixed l2p- norm regularization. This makes the learned dictionary more representative and discriminative since the shared atoms are learned by using the labeled and unlabeled samples potentially from the same class. Minimizing the derived objective function is a challenging task because it is non-convex and highly non-smooth. We propose an efficient optimization algorithm to solve the problem based on the block coordinate descent method. Moreover, we have a rigorous proof of the convergence of the algorithm. Extensive experiments are presented to show the superior performance of our method in classification applications.