linear discriminant analysis
Recently Published Documents





2022 ◽  
Vol 16 (4) ◽  
pp. 1-18
Min-Ling Zhang ◽  
Jing-Han Wu ◽  
Wei-Xuan Bao

As an emerging weakly supervised learning framework, partial label learning considers inaccurate supervision where each training example is associated with multiple candidate labels among which only one is valid. In this article, a first attempt toward employing dimensionality reduction to help improve the generalization performance of partial label learning system is investigated. Specifically, the popular linear discriminant analysis (LDA) techniques are endowed with the ability of dealing with partial label training examples. To tackle the challenge of unknown ground-truth labeling information, a novel learning approach named Delin is proposed which alternates between LDA dimensionality reduction and candidate label disambiguation based on estimated labeling confidences over candidate labels. On one hand, the (kernelized) projection matrix of LDA is optimized by utilizing disambiguation-guided labeling confidences. On the other hand, the labeling confidences are disambiguated by resorting to k NN aggregation in the LDA-induced feature space. Extensive experiments over a broad range of partial label datasets clearly validate the effectiveness of Delin in improving the generalization performance of well-established partial label learning algorithms.

2022 ◽  
Meelad Amouzgar ◽  
David R Glass ◽  
Reema Baskar ◽  
Inna Averbukh ◽  
Samuel C Kimmey ◽  

Single-cell technologies generate large, high-dimensional datasets encompassing a diversity of omics. Dimensionality reduction enables visualization of data by representing cells in two-dimensional plots that capture the structure and heterogeneity of the original dataset. Visualizations contribute to human understanding of data and are useful for guiding both quantitative and qualitative analysis of cellular relationships. Existing algorithms are typically unsupervised, utilizing only measured features to generate manifolds, disregarding known biological labels such as cell type or experimental timepoint. Here, we repurpose the classification algorithm, linear discriminant analysis (LDA), for supervised dimensionality reduction of single-cell data. LDA identifies linear combinations of predictors that optimally separate a priori classes, enabling users to tailor visualizations to separate specific aspects of cellular heterogeneity. We implement feature selection by hybrid subset selection (HSS) and demonstrate that this flexible, computationally-efficient approach generates non-stochastic, interpretable axes amenable to diverse biological processes, such as differentiation over time and cell cycle. We benchmark HSS-LDA against several popular dimensionality reduction algorithms and illustrate its utility and versatility for exploration of single-cell mass cytometry, transcriptomics and chromatin accessibility data.

Sensors ◽  
2022 ◽  
Vol 22 (1) ◽  
pp. 367
Janez Lapajne ◽  
Matej Knapič ◽  
Uroš Žibrat

Hyperspectral imaging is a popular tool used for non-invasive plant disease detection. Data acquired with it usually consist of many correlated features; hence most of the acquired information is redundant. Dimensionality reduction methods are used to transform the data sets from high-dimensional, to low-dimensional (in this study to one or a few features). We have chosen six dimensionality reduction methods (partial least squares, linear discriminant analysis, principal component analysis, RandomForest, ReliefF, and Extreme gradient boosting) and tested their efficacy on a hyperspectral data set of potato tubers. The extracted or selected features were pipelined to support vector machine classifier and evaluated. Tubers were divided into two groups, healthy and infested with Meloidogyne luci. The results show that all dimensionality reduction methods enabled successful identification of inoculated tubers. The best and most consistent results were obtained using linear discriminant analysis, with 100% accuracy in both potato tuber inside and outside images. Classification success was generally higher in the outside data set, than in the inside. Nevertheless, accuracy was in all cases above 0.6.

2021 ◽  
Vol 2 (2) ◽  
pp. 95-103
Siti Khotimatul Wildah ◽  
Sarifah Agustiani ◽  
Ali Mustopa ◽  
Nanik Wuryani ◽  
Hendri Mahmud Nawawi ◽  

Wajah merupakan bagian dari sistem biometric dimana wajah manusia memiliki bentuk dan karakteristik yang berbeda antara satu dengan lainnya sehingga wajah dapat dijadikan sebagai alternatif pengamanan suatu sistem. Proses pengenalan wajah didasarkan pada proses pencocokan dan perbandingan citra yang dimasukan dengan citra yang telah tersimpan di database. Akan tetapi pengenalan wajah menjadi permasalahan yang cukup menantang dikarenakan illuminasi, pose dan ekspresi wajah serta kualitas citra. Oleh sebab itu pada penelitian ini bertujuan untuk melakukan pengenalan wajah dengan menggunakan metode machine learning seperti Logistic Regression (LR), Linear Discriminant Analysis (LDA), Decision Tree Classifier, Random Forest Classifier (RF), Gaussian NB, K Neighbors Classifier (KNN) dan Support Vector Machine (SVM) dan beberapa metode ekstraksi fitur Hu-Moment, HOG dan Haralick pada dataset Yale Face. Berdasarkan pengujian yang dilakukan metode ekstraksi fitur gabungan Hu-Moment, HOG dan Haralick dengan algoritma Linear Discriminant Analysis (LDA) menghasilkan nilai akurasi tertinggi sebesar 79,71% dibandingkan dengan metode ekstraksi fitur dan algoritma klasifikasi lainnya.

Sign in / Sign up

Export Citation Format

Share Document