Search

Oversampling ratio N and the minority class' nearest neighboring number k are key hyperparameters of synthetic minority oversampling technique (SMOTE) to reconstruct the class distribution of dataset. No optimal default value exists there. Therefore, it is of necessity to discuss the influence of the output dataset on the classification performance when SMOTE adopts various hyperparameter combinations. In this paper, we propose a hyperparameter optimization algorithm for imbalanced data. By iterating to find reasonable N and k for SMOTE, so as to build a balanced and high-quality dataset. As a result, a model with outstanding performance and strong generalization ability is trained, thus effectively solving imbalanced classification. The proposed algorithm is based on the hybridization of simulated annealing mechanism (SA) and particle swarm optimization algorithm (PSO). In the optimization, Cohen's Kappa is used to construct the fitness function, and AdaRBFNN, a new classifier, is integrated by multiple trained RBF neural networks based on AdaBoost algorithm. Kappa of each generation is calculated according to the classification results, so as to evaluate the quality of candidate solution. Experiments are conducted on seven groups of KEEL datasets. Results show that the proposed algorithm delivers excellent performance and can significantly improve the classification accuracy of the minority class. [ABSTRACT FROM AUTHOR]

Faced with the rapid update of nonlinear and irregular big data from the environmental monitoring system, both the public and managers urgently need reliable methods to predict possible air pollutions in the future. Therefore, a multi-scale deep learning (MDL) and optimal combination ensemble (OCE) approach for hourly air quality index (AQI) forecasting is proposed in this paper, named MDL-OCE model. Before normal modeling, all original data are preprocessed through missing data filling and outlier testing to ensure smooth computation. Due to the complexity of such big data, slope-based ensemble empirical mode decomposition (EEMD) is adopted to decompose the time series of AQI and meteorological conditions into a finite number of simple intrinsic mode function (IMF) components and one residue component. Then, to unify the number of components of different variables, the fine-to-coarse (FC) technique is used to reconstruct all components into high frequency component (HF), low frequency component (LF), and trend component (TC). For purpose of extracting the underlying relationship between AQI and meteorological conditions, the three components are respectively trained and predicted by different deep learning architectures (stacked sparse autoencoder (SSAE)) with a multilayer perceptron (MLP). The corresponding forecasting results of three components are merged by OCE method to better achieve the ultimate AQI forecasting outputs. The empirical results clearly demonstrate that our proposed MDL-OCE model outperforms other advanced benchmark models in terms of forecasting performances in all cases. [ABSTRACT FROM AUTHOR]

Background: Alzheimer's disease (AD) is the most common type of dementia, causing a huge socioeconomic burden. In parallel with the widespread uptake of single-cell RNA sequencing (scRNA-seq) technology, there has been a rapid accumulation of data produced by researching AD at single-cell resolution, which is more conductive to explore the neuroimmune-related mechanism of AD. Objective: To explore the potential features of T cells in the peripheral blood and cerebrospinal fluid of AD patients. Methods: Two datasets, GSE181279 and GSE134578, were integrated from GEO database. Seurat, Monocle, CellChat, scRepertoire, and singleR packages were mainly employed for data analysis. Results: Our analysis demonstrated that in peripheral blood, T cells were significantly expanded, and these expanded T cells were possessed effector function, such as CD8+TEMRA, CD4+TEMRA, and CD8+TEM. Interestingly, CD8+TEMRA and CD4+TEMRA cells positioned adjacently after dimensions reduction and clustering. Notably, we identified that the expanded T cells were developed from Naïve T cells and TCM cells, and TEM cells was in the intermediate state of this developing process. Additionally, in cerebrospinal fluid of AD patients, the amplified T cells were mainly CD8+TEMRA cells, and the number and strength of communication between CD4+TEM, CD8+TEM, and CD8+TEMRA were decreased in AD patients. Conclusions: Our comprehensive analyses identified the cells in cerebrospinal fluid from AD patients are expanded TEMRA or TEM cells and the TEMRA cells communicating with other immune cells is weakened, which may be an important immune feature that leads to AD. [ABSTRACT FROM AUTHOR]

Circular RNAs (circRNAs) are the emerging informative RNAs, involved in cardiovascular diseases including atherosclerosis (AS). Endothelial injury is the initial qualitative change of AS. Thus, the objective of this study was to confirm the dysregulation and mechanism of circ_0000231 in cell model of AS at early stage in human umbilical vein endothelial cells (HUVECs) induced by oxidized low-density lipoprotein (ox-LDL).The expression of circ_0000231, miR-590-5p and programmed cell death 4 (PDCD4) was detected using real-time quantitative PCR and western blot. Cell injury was measured with MTT, flow cytometry, caspase-3 activity assay and enzyme-linked immunosorbent assay (ELISA). The interaction among circ_0000231, miR-590-5p and PDCD4 was validated by dual-luciferase reporter assay, RNA immunoprecipitation (RIP) and pull-down assays.Stress ox-LDL decreased cell viability, and increased apoptosis rate and caspase-3 activity in HUVECs in a dose- and time-dependent manner in concomitant with promotions of interleukin-6, interleukin-1β, tumor necrosis factor-α, LC3-II/I and Beclin-1 levels. Besides, circ_0000231 and PDCD4 expressions were upregulated, and miR-590-5p was downregulated in ox-LDL-stimulated HUVECs. Functionally, knockdown of circ_0000231 and overexpression of miR-590-5p could suppress ox-LDL-elicited above effects on apoptosis, autophagy and inflammatory response, accompanied with PDCD4 downregulation. Physically, miR-590-5p could directly interact with circ_0000231 and PDCD4.Downregulation of circ_0000231 suppresses HUVECs from ox-LDL-induced injury partially through regulating miR-590-5p/PDCD4 axis via competing endogenous RNA mechanism, showing a novel potential target for the pathology and treatment of endothelial injury in AS. [ABSTRACT FROM AUTHOR]