Proceedings ArticleDOI
Learning with multiple Gaussian distance kernels for time series classification
Lei Liu,Wangmeng Zuo,David Zhang,Dongyu Zhang +3 more
- pp 624-628
TLDR
A multiple kernel learning (MKL) method to integrate multiple Gaussian distance kernels to further improve time series classification accuracy and results show that the proposed method is superior to SVM with individual Gaussiandistance kernel.Abstract:
Various distance measures have been proposed for time series classification, and several of them have been used to construct Gaussian distance kernels for support vector machine (SVM) - based classification. Considering that different Gaussian distance kernels may carry complementary information for classification, in this paper, we propose a multiple kernel learning (MKL) method to integrate multiple Gaussian distance kernels to further improve time series classification accuracy. We first adopt the classical Gaussian RBF (GRBF) kernel and the recently developed Gaussian elastic metric distance kernel (i.e. GERP kernel and GTWED kernel), and then use an efficient MKL, SimpleMKL, to learn the kernel classifier. Our experimental results on 12 UCR time series data sets show that the proposed method is superior to SVM with individual Gaussian distance kernel.read more
Citations
More filters
Proceedings ArticleDOI
A comparison of three types of pulse signals: Physical meaning and diagnosis performance
TL;DR: The physical meanings and sensitivities of signals sampled by these three types of sensors, i.e., the pressure sensor, the photoelectric sensor, and the ultrasound sensor are analyzed to guide the sensor selection for computational pulse diagnosis.
Book ChapterDOI
Characterization of Inter-Cycle Variations for Wrist Pulse Diagnosis
TL;DR: This chapter proposes three feature extraction methods, i.e., simple combination, multi-scale entropy, and complex network, which are effective in characterizing both inter- and intra-cycle variations and can obtain better performance in pulse diagnosis.
References
More filters
Journal ArticleDOI
Learning the Kernel Matrix with Semidefinite Programming
Gert R. G. Lanckriet,Nello Cristianini,Peter L. Bartlett,Laurent El Ghaoui,Michael I. Jordan +4 more
TL;DR: This paper shows how the kernel matrix can be learned from data via semidefinite programming (SDP) techniques and leads directly to a convex method for learning the 2-norm soft margin parameter in support vector machines, solving an important open problem.
Proceedings ArticleDOI
Multiple kernel learning, conic duality, and the SMO algorithm
TL;DR: Experimental results are presented that show that the proposed novel dual formulation of the QCQP as a second-order cone programming problem is significantly more efficient than the general-purpose interior point methods available in current optimization toolboxes.
Journal Article
Large Scale Multiple Kernel Learning
TL;DR: It is shown that the proposed multiple kernel learning algorithm can be rewritten as a semi-infinite linear program that can be efficiently solved by recycling the standard SVM implementations, and generalize the formulation and the method to a larger class of problems, including regression and one-class classification.
Journal ArticleDOI
On Comparing Classifiers: Pitfalls toAvoid and a Recommended Approach
TL;DR: Several phenomena that can, if ignored, invalidate an experimental comparison and the conclusions that follow apply not only to classification, but to computational experiments in almost any aspect of data mining.
Book ChapterDOI
On the marriage of Lp-norms and edit distance
Lei Chen,Raymond T. Ng +1 more
TL;DR: A new distance function, which is a marriage of L1- norm and the edit distance, ERP, which can support local time shifting, and is a metric, and dominates all existing strategies.
Related Papers (5)
Weighted Gaussian Kernel with Multiple Widths and Support Vector Classifications
Jing Tian,Lifeng Zhao +1 more