Article
Engineering, Electrical & Electronic
Samson Damilola Fabiyi, Paul Murray, Jaime Zabalza, Jinchang Ren
Summary: This article introduces a method called folded Linear Discriminant Analysis (F-LDA) for dimensionality reduction of remotely sensed HSI data in small sample size scenarios. The F-LDA allows selecting more discriminant features and significantly improves accuracy in pixel classification, outperforming conventional LDA in terms of classification accuracy, computational complexity, and memory requirements.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Chun-Na Li, Yi Li, Yan-Hui Meng, Pei-Wei Ren, Yuan-Hai Shao
Summary: Recently, a study focused on an absolute value inequalities discriminant analysis criterion with robustness and sparseness for supervised dimensionality reduction. However, its method of obtaining discriminant directions one by one through greedy search fails to explain the sparseness of multiple discriminant directions, and it also relies on solving a series of linear programming problems, which is time-consuming. In this paper, a novel linear discriminant analysis approach is proposed, integrating robustness and sparseness using the L-1-norm and L-2, L-1-norm. The proposed method obtains all the discriminant directions simultaneously and is solved using the more efficient alternating direction method of multipliers. Experimental results on various datasets validate the effectiveness of the proposed method.
Article
Operations Research & Management Science
Chun-Na Li, Pei-Wei Ren, Yan-Ru Guo, Ya-Fen Ye, Yuan-Hai Shao
Summary: This paper proposes a regularized linear discriminant analysis method called GCLDA, which uses a generalized capped norm to measure distances and includes a regularization term to improve adaptability and avoid singularity.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Mathematics
Muhammad Aminu, Noor A. Ahmad
Summary: Partial least squares discriminant analysis (PLS-DA) is a popular tool in chemometrics and bioinformatics for data analysis. PLS-DA aims to find a low-dimensional representation of high-dimensional data that separates different classes. However, its performance degrades under nonlinear conditions and its effectiveness in multi-class data is debated. In this paper, a new algorithm called Kernel Locality Preserving PLS-DA (KLPPLS-DA) is proposed, which combines nonlinear subspace learning with local structure preservation to improve discrimination.
BULLETIN OF THE MALAYSIAN MATHEMATICAL SCIENCES SOCIETY
(2023)
Article
Chemistry, Medicinal
Zhenqiu Shu, Qinghan Long, Luping Zhang, Zhengtao Yu, Xiao-Jun Wu
Summary: The progress in single-cell RNA sequencing (ScRNA-seq) technology allows for the accurate discovery of cell heterogeneity and diversity. Clustering is a crucial step in ScRNA-seq data analysis, but it faces challenges due to the high dimensionality and noise of the data. To overcome these challenges, we propose a novel ScRNA-seq data clustering model, RGNMF-DS, which incorporates similarity and dissimilarity regularizers for matrix decomposition and utilizes a graph regularizer to uncover the local geometric structure in the data. Experimental results demonstrate that our proposed model outperforms other state-of-the-art methods in clustering ScRNA-seq datasets.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Computer Science, Artificial Intelligence
Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens
Summary: This paper examines the asymptotic properties of regularized least squares with indefinite kernels in RKKS, showing a globally optimal solution on a sphere and deriving learning rates. It is the first work on the approximation analysis of regularized learning algorithms in RKKS.
Article
Acoustics
Zhonghua Tang, Ming Zan, Zhifei Zhang, Zhongming Xu, Enyong Xu
Summary: Operational transfer path analysis (OTPA) is an efficient and widely used method in various engineering fields. However, the accuracy of OTPA is reduced due to errors in operational responses. To improve the accuracy, a Tikhonov regularized total least-squares method (RTLSM) based on the Tikhonov regularized least-squares method (RLSM) is used to estimate the transmissibility matrix, and both simulation and experimental results show that RTLSM is better than RLSM in OTPA.
JOURNAL OF SOUND AND VIBRATION
(2022)
Article
Computer Science, Information Systems
Muhammad Aminu, Noor Atinah Ahmad
Summary: By incorporating a locality preserving feature, LPPLSDA enhances the performance of partial least squares discriminant analysis, especially in face recognition tasks. Experimental results consistently show that LPPLSDA outperforms the conventional PLS-DA method on various benchmarked face databases.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Feiping Nie, Xia Dong, Zhanxuan Hu, Rong Wang, Xuelong Li
Summary: This work proposes a parameter-free clustering model called discriminative projected clustering (DPC) for low-dimensional and discriminative projection learning and clustering. The connection between DPC and linear discriminant analysis (LDA) is theoretically analyzed, and experiments demonstrate the effectiveness and efficiency of DPC in real-world applications.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Alam Zaib, Tarig Ballal, Shahid Khattak, Tareq Y. Al-Naffouri
Summary: Linear discriminant analysis classifiers often face challenges with small training data or a high number of features, leading to poor performance. To address this, various regularized LDA methods have been proposed, with the R2LDA approach introduced as a doubly regularized classifier. By utilizing multiple regularization techniques to adjust parameters, R2LDA effectively handles noise contamination in test data and demonstrates consistency and effectiveness in both synthetic and real datasets.
Article
Engineering, Industrial
Lavi Rizki Zuhal, Ghifari Adam Faza, Pramudita Satria Palar, Rhea Patricia Liem
Summary: This study assesses the potential benefits of using KPLS for high-dimensional reliability analysis problems, finding that KPLS with four principal components significantly reduces CPU time compared to ordinary Kriging while still accurately estimating failure probability. In some cases, it was also observed that KPLS with four principal components reduces the number of function evaluations, which is beneficial for problems with expensive function evaluations.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Computer Science, Artificial Intelligence
Zheng Wang, Haojie Hu, Rong Wang, Qianrong Zhang, Feiping Nie, Xuelong Li
Summary: A novel robust trace ratio objective is proposed in this paper to reduce the negative effects of outliers on the objective function by converting the mean calculation method, showing superior performance on several benchmark datasets.
Article
Computer Science, Artificial Intelligence
Xinmin Tao, Yixuan Bao, Xiaohan Zhang, Tian Liang, Lin Qi, Zhiting Fan, Shan Huang
Summary: A semi-supervised kernel local Fisher discriminant analysis algorithm based on density peak clustering pseudo-labels (SDPCKLFDA) is proposed to effectively use both labeled and unlabeled data for learning. The algorithm generates pseudo cluster labels using the density peak clustering algorithm and constructs regularization strategies based on these pseudo-labels. The optimal projection vector is obtained by solving the objective function of the local Fisher discriminant analysis. The algorithm improves the discriminant performance of extracted features and is suitable for multimodal and noisy data.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Maaz Mahadi, Tarig Ballal, Muhammad Moinuddin, Ubaid M. Al-Saggaf
Summary: Recursive least-squares (RLS) algorithms are widely used in various applications. This paper focuses on time-varying regularized RLS (RRLS) techniques and proposes a low-complexity update method using an approximate recursive formula. Simulation results demonstrate the superiority of the time-varying RRLS strategy over the fixed one.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Zhen Qin, Jun Tao, Yili Xia, Le Yang
Summary: This paper proposes an enhanced sparse recursive least squares (RLS) adaptive filter algorithm by combining a sparse regularization term and a proportionate matrix. Theoretical performance analysis is conducted, and guidance for selecting adaptive parameters is obtained. A fast implementation method is also derived. Simulation results support the theoretical analysis.
DIGITAL SIGNAL PROCESSING
(2022)