• Smart Structures and Systems
• /
• v.34 no.2
• /
• pp.97-116
• /
• 2024

The standard l₁-norm regularization is recently introduced for impact force identification, but generally underestimates the peak force. Compared to l₁-norm regularization, l_p-norm (0 ≤ p < 1) regularization, with a nonconvex penalty function, has some promising properties such as enforcing sparsity. In the framework of sparse regularization, if the desired solution is sparse in the time domain or other domains, the under-determined problem with fewer measurements than candidate excitations may obtain the unique solution, i.e., the sparsest solution. Considering the joint sparse structure of impact force in temporal and spatial domains, we propose a general l_p-norm (0 ≤ p < 1) regularization methodology for simultaneous identification of the impact location and force time-history from highly incomplete measurements. Firstly, a nonconvex optimization model based on l_p-norm penalty is developed for regularizing the highly under-determined problem of impact force identification. Secondly, an iteratively reweighed l₁-norm algorithm is introduced to solve such an under-determined and unconditioned regularization model through transforming it into a series of l₁-norm regularization problems. Finally, numerical simulation and experimental validation including single-source and two-source cases of impact force identification are conducted on plate structures to evaluate the performance of l_p-norm (0 ≤ p < 1) regularization. Both numerical and experimental results demonstrate that the proposed l_p-norm regularization method, merely using a single accelerometer, can locate the actual impacts from nine fixed candidate sources and simultaneously reconstruct the impact force time-history; compared to the state-of-the-art l₁-norm regularization, l_p-norm (0 ≤ p < 1) regularization procures sufficiently sparse and more accurate estimates; although the peak relative error of the identified impact force using l_p-norm regularization has a decreasing tendency as p is approaching 0, the results of l_p-norm regularization with 0 ≤ p ≤ 1/2 have no significant differences.

• The Korean Journal of Applied Statistics
• /
• v.28 no.1
• /
• pp.9-21
• /
• 2015

The support vector machine has been successfully applied to various classification areas due to its flexibility and a high level of classification accuracy. However, when analyzing imbalanced data with uneven class sizes, the classification accuracy of SVM may drop significantly in predicting minority class because the SVM classifiers are undesirably biased toward the majority class. The weighted $L_2$-norm SVM was developed for the analysis of imbalanced data; however, it cannot identify irrelevant input variables due to the characteristics of the ridge penalty. Therefore, we propose the weighted $L_1$-norm SVM, which uses lasso penalty to select important input variables and weights to differentiate the misclassification of data points between classes. We demonstrate the satisfactory performance of the proposed method through simulation studies and a real data analysis.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.203-212
• /
• 2024

The area under the ROC curve (AUC) is one of the most common criteria used to measure the overall performance of binary classifiers for a wide range of machine learning problems. In this article, we propose a L₁-penalized AUC-optimization classifier that directly maximizes the AUC for high-dimensional data. Toward this, we employ the AUC-consistent surrogate loss function and combine the L₁-norm penalty which enables us to estimate coefficients and select informative variables simultaneously. In addition, we develop an efficient optimization algorithm by adopting k-means clustering and proximal gradient descent which enjoys computational advantages to obtain solutions for the proposed method. Numerical simulation studies demonstrate that the proposed method shows promising performance in terms of prediction accuracy, variable selectivity, and computational costs.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.209-215
• /
• 2009

In regression problem, the SCAD estimator proposed by Fan and Li (2001), has many desirable property such as continuity, sparsity and unbiasedness. In this paper, we extend SCAD penalized regression framework to quantile regression and hence, we propose new SCAD penalized quantile estimator on high-dimensions and also present an efficient algorithm. From the simulation and real data set, the proposed estimator performs better than quantile regression estimator with $L_1$ norm.

• Smart Structures and Systems
• /
• v.25 no.3
• /
• pp.369-384
• /
• 2020

A wavefield sparse reconstruction technique based on compressed sensing is developed in this work to dramatically reduce the number of measurements. Firstly, a severely underdetermined representation of guided wavefield at a snapshot is established in the spatial domain. Secondly, an optimal compressed sensing model of guided wavefield sparse reconstruction is established based on l₁-norm penalty, where a suite of discrete cosine functions is selected as the dictionary to promote the sparsity. The regular, random and jittered undersampling schemes are compared and selected as the undersampling matrix of compressed sensing. Thirdly, a gradient projection method is employed to solve the compressed sensing model of wavefield sparse reconstruction from highly incomplete measurements. Finally, experiments with different excitation frequencies are conducted on an aluminum plate to verify the effectiveness of the proposed sparse reconstruction method, where a scanning laser Doppler vibrometer as the true benchmark is used to measure the original wavefield in a given inspection region. Experiments demonstrate that the missing wavefield data can be accurately reconstructed from less than 12% of the original measurements; The reconstruction accuracy of the jittered undersampling scheme is slightly higher than that of the random undersampling scheme in high probability, but the regular undersampling scheme fails to reconstruct the wavefield image; A quantified mapping relationship between the sparsity ratio and the recovery error over a special interval is established with respect to statistical modeling and analysis.