5 April 2022 in IEEE Journal of Biomedical and Health Informatics
Early diagnosis is currently the most effective way of saving the life of patients with neuropsychiatric systemic lupus erythematosus (NPSLE). However, it is rather difficult to detect this terrible disease at the early stage, due to the subtle and elusive symptomatic signals. Recent studies show that the $^{1}$ H-MRS (proton magnetic resonance spectroscopy) imaging technique can capture more information reflecting the early appearance of this disease than conventional magnetic resonance imaging techniques. $^{1}$ H-MRS data, however, also presents more noises that can bring serious diagnosis bias. We hence proposed a noise-immune extreme ensemble learning technique for effectively leveraging $^{1}$ H-MRS data for advancing the early diagnosis of NPSLE. Our main results are that 1) by developing generalized maximum correntropy criterion in the kernel extreme learning setting, many types of non-Gaussian noises can be distinguished, and 2) weighted recursive feature elimination, using maximal information coefficient to weight feature’s importance, helps to further alleviate the bad impact of noises on the diagnosis performance. The proposed method is assessed on a publicly available dataset with 97.5% accuracy, 95.8% sensitivity and 99.9% specificity, which well demonstrates its efficacy.
12 October 2023 in IEEE Transactions on Industrial Informatics
Data-driven machine learning is increasingly involved in human life and industrial development due to its large-scale testing and low time cost. However, existing learning algorithms are not suitable for real-world applications with data dilemmas, such as extremely high-dimension-low-sample-size problems, non-Gaussian noise, and uncertainty. In this article, we propose a novel fuzzy multikernel subspace learning (FMKSL) to address these problems, which provides a robust multikernel representation with a fuzzy constraint and sparse coding. We then develop an adaptive learner chain optimization method based on the iterative process of FMKSL to speed up learning and achieve the best performance. Different from previous methods, we also design a flexible data augmentation method, namely generalized correntropy-based adaptive data augmentation (GC-ADA), to effectively use the $\alpha$ -order statistics between samples to transform the exact value prediction task into a simpler classification one. It is important that our general framework only needs an extremely small dataset to predict the related ranking of the sample since the exact label value measured by different institutions in reality varies largely. A typical scenario is the drug screening task, i.e., the inhibitory potency prediction of the nicotinamide phosphoribosyltransferase inhibitors. Extensive experiments on nine real-world datasets (four tasks) show that our framework outperforms state-of-the-art methods in prioritizing candidate samples and chemicals for experimental research and analysis via a data-driven computational approach.