In the research area of time series classification, the ensemble shapelet transform algorithm is one of state-of-the-art algorithms for classification. However, its high time complexity is an issue to hinder its application since its base classifier shapelet transform includes a high time complexity of a distance calculation and shapelet selection. Therefore, in this paper we introduce a novel algorithm, i.e. short isometric shapelet transform, which contains two strategies to reduce the time complexity. The first strategy of SIST fixes the length of shapelet based on a simplified distance calculation, which largely reduces the number of shapelet candidates as well as speeds up the distance calculation in the ensemble shapelet transform algorithm. The second strategy is to train a single linear classifier in the feature space instead of an ensemble classifier. The theoretical evidences of these two strategies are presented to guarantee a near-lossless accuracy under some preconditions while reducing the time complexity. Furthermore, empirical experiments demonstrate the superior performance of the proposed algorithm.

To cluster data that are not linearly separable in the original feature space, k -means clustering was extended to the kernel version. However, the performance of kernel k -means clustering largely depends on the choice of the kernel function. To mitigate this problem, multiple kernel learning has been introduced into the k -means clustering to obtain an optimal kernel combination for clustering. Despite the success of multiple kernel k -means clustering in various scenarios, few of the existing work update the combination coefficients based on the diversity of kernels, which leads to the result that the selected kernels contain high redundancy and would degrade the clustering performance and efficiency. We resolve this problem from the perspective of subset selection in this article. In particular, we first propose an effective strategy to select a diverse subset from the prespecified kernels as the representative kernels, and then incorporate the subset selection process into the framework of multiple k -means clustering. The representative kernels can be indicated as a significant combination weights. Due to the nonconvexity of the obtained objective function, we develop an alternating minimization method to optimize the combination coefficients of the selected kernels and the cluster membership alternatively. In particular, an efficient optimization method is developed to reduce the time complexity of optimizing the kernel combination weights. Finally, extensive experiments on benchmark and real-world data sets demonstrate the effectiveness and superiority of our approach in comparison with existing methods.

Ensemble pruning, selecting a subset of individual learners from an original ensemble, alleviates the deficiencies of ensemble learning on the cost of time and space. Accuracy and diversity serve as two crucial factors, while they usually conflict with each other. To balance both of them, we formalize the ensemble pruning problem as an objection maximization problem based on information entropy. Then we propose an ensemble pruning method, including a centralized version and a distributed version, in which the latter is to speed up the former. Finally, we extract a general distributed framework for ensemble pruning, which can be widely suitable for most of the existing ensemble pruning methods and achieve less time-consuming without much accuracy degradation. Experimental results validate the efficiency of our framework and methods, particularly concerning a remarkable improvement of the execution speed, accompanied by gratifying accuracy performance.

Multi-task learning aims to learn multiple tasks jointly by sharing information among related tasks such that the generalization performance over different tasks could be improved. Although multi-task learning has been demonstrated to obtain performance gain in comparison with the single task learning, the main challenge that learning what to share with whom is still not fully resolved. In this paper, we propose a robust clustered multi-task learning approach that clusters tasks into several groups by learning the representative tasks. The main assumption behind our approach is that each task can be represented by a linear combination of some representative tasks that can characterize all tasks. The correlation between tasks can be indicated by the corresponding combination coefficient. By imposing a row-sparse constraint on the correlation matrix, our approach could select the representative tasks and encourage information sharing among the related tasks. In addition, the $l_1,2 $-norm is applied to the representation loss to enhance the robustness of our approach. To solve the resulting bi-convex optimization problem, we design an efficient optimization method based on the alternating direction method of multipliers and accelerated proximal gradient method. Finally, experimental results on synthetic and real-world data sets validate the effectiveness of the proposed approach.

Human activity recognition is a challenging problem in computer vision due to large resemblance across classes and variance within an individual class. A routine way to recognize human activity from 3D skeleton sequences can be divided into two tasks, discriminative features representation and temporal dynamics modeling. During the past few years, temporal pyramid is widely used for capturing temporal dynamics after extracting discriminative features from frames. However, this uninformative dividing method could destroy the geometric structure of meaningful action snippets within skeleton sequence. To resolve this problem efficiently, we propose a novel and intuitive method in this paper. First, based on a more realistic assumption that adjacent postures in action sequences are more similar and activity can be depicted with several action snippets, a dividing algorithm is designed to encode the temporal information. Second, an interpretable and discriminative descriptor named posture tendency descriptor (PTD) is constructed to represent one action snippet. Finally, multiple PTDs along the entire skeleton sequence are concatenated in a hierarchical and temporal order forming the representation of a human activity. Experimental results on three benchmark datasets demonstrate that the proposed approach with an off-the-shelf classification algorithm achieves highly competitive performance in comparison with the state-of-the-art approaches.