Disambiguation Enabled Linear Discriminant Analysis for Partial Label Dimensionality Reduction

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.

ANALISIS PREDIKSI FINANCIAL DISTRESS DENGAN MENGGUNAKAN MODEL SRINGATE PADA PERUSAHAAN PROPERTI DAN REAL ESTATE YANG TERDAFTAR DI BEI PERIODE 2019-2020

This study aims to financial distress predict and the level of accuracy using the Springate model in the property and real estate sector listed on the Indonesia Stock Exchange for the 2019-2020 period. The population of this study is all property and real estate companies listed on the Indonesia Stock Exchange for the 2019-2020 period, so the population of this study managed to find 66 companies. Samples were selected based on predetermined purposive sampling criteria. The sample selected according to the specified criteria is 37 companies. The data analysis technique used the Springate S-Score discriminant analysis technique. The results of the bankruptcy analysis using the Springate method, namely in 2019 before the onset of covid-19 there were 27 property and real estate companies in financial distress and 10 companies in healthy condition (non-financial distress). In 2020, during the COVID-19 pandemic, there were additional companies that were in financial distress, namely 34 companies and only 3 companies that remained in a healthy condition (non-financial distress). Based on the results of the analysis of the Springate method in predicting bankruptcy in property and real estate sector companies, it has an accuracy rate of 62.2%.

Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures

The differential diagnosis of epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) may be difficult, due to the lack of distinctive clinical features. The interictal electroencephalographic (EEG) signal may also be normal in patients with ES. Innovative diagnostic tools that exploit non-linear EEG analysis and deep learning (DL) could provide important support to physicians for clinical diagnosis. In this work, 18 patients with new-onset ES (12 males, 6 females) and 18 patients with video-recorded PNES (2 males, 16 females) with normal interictal EEG at visual inspection were enrolled. None of them was taking psychotropic drugs. A convolutional neural network (CNN) scheme using DL classification was designed to classify the two categories of subjects (ES vs. PNES). The proposed architecture performs an EEG time-frequency transformation and a classification step with a CNN. The CNN was able to classify the EEG recordings of subjects with ES vs. subjects with PNES with 94.4% accuracy. CNN provided high performance in the assigned binary classification when compared to standard learning algorithms (multi-layer perceptron, support vector machine, linear discriminant analysis and quadratic discriminant analysis). In order to interpret how the CNN achieved this performance, information theoretical analysis was carried out. Specifically, the permutation entropy (PE) of the feature maps was evaluated and compared in the two classes. The achieved results, although preliminary, encourage the use of these innovative techniques to support neurologists in early diagnoses.

A Linear Discriminant Analysis Model Based on the Changes of 7 Proteins in Plasma Predicts Response to Anlotinib Therapy in Advanced Non-Small Cell Lung Cancer Patients

BackgroundAnlotinib is a multi-targeted tyrosine kinase inhibitor mainly targeting angiogenesis signaling. The predictive marker of anlotinib’s efficacy remains elusive. This study was designed to explore the predictive marker of anlotinib in non-small cell lung cancer (NSCLC).MethodsWe prospectively enrolled 52 advanced NSCLC patients who underwent at least one line of targeted therapy or chemotherapy between August 2018 and March 2020. Patients were divided into durable responders (DR) and non-durable responders (NDR) based on the median progression-free survival (PFS, 176 days). The Olink Immuno-Oncology panel (92 proteins) was used to explore the predictive protein biomarkers in plasma samples before treatment (baseline) and on the first treatment evaluation (paired).ResultsAt baseline, the response to anlotinib was not significantly associated with age, gender, smoke history, histology, oligo-metastases, EGFR mutations, and other clinical characteristics. The results of PFS-related protein biomarkers at baseline were all not satisfying. Then we assessed the changes of 92 proteins levels in plasma on the first treatment evaluation. We obtained a Linear discriminant analysis (LDA) model based on 7 proteins, with an accuracy of 100% in the original data and an accuracy of 89.2% in cross validation. The 7 proteins were CD70, MIC-A/B, LAG3, CAIX, PDCD1, MMP12, and PD-L2. Multivariate Cox analysis further showed that the changes of CD70 (HR 25.48; 95% CI, 4.90–132.41, P=0.000) and MIC-A/B (HR 15.04; 95% CI, 3.81–59.36, P=0.000) in plasma were the most significant prognostic factors for PFS.ConclusionWe reported herein a LDA model based on the changes of 7 proteins levels in plasma before and after treatment, which could predict anlotinib responders among advanced NSCLC patients with an accuracy of 100%. Further studies are warranted to verify the prediction performance of the LDA model.

Supervised dimensionality reduction for exploration of single-cell data by Hybrid Subset Selection - Linear Discriminant Analysis

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.

Comparison of Selected Dimensionality Reduction Methods for Detection of Root-Knot Nematode Infestations in Potato Tubers Using Hyperspectral Imaging

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.

On the Question of Industrial Specialization of Megapolises

Most of the authors single out megacities as a special form of settlement, and speak of exceeding the level and pace of socio-economic development. Megacities attract enterprises of various business areas, as it is believed that this will have a positive impact on their development. In this paper, we assess the industry structure of the largest cities, analyze its differences from smaller territories, and conduct a discriminant analysis in order to identify the subjects of the Russian Federation that are predisposed to the appearance of a metropolis in them.