When Broad Learning System Meets Label Noise Learning: A Reweighting Learning Framework.

Broad learning system (BLS) is a novel neural network with efficient learning and expansion capacity, but it is sensitive to noise. Accordingly, the existing robust broad models try to suppress noise by assigning each sample an appropriate scalar weight to tune down the contribution of noisy samples in network training. However, they disregard the useful information of the noncorrupted elements hidden in the noisy samples, leading to unsatisfactory performance. To this end, a novel BLS with adaptive reweighting (BLS-AR) strategy is proposed in this article for the classification of data with label noise. Different from the previous works, the BLS-AR learns for each sample a weight vector rather than a scalar weight to indicate the noise degree of each element in the sample, which extends the reweighting strategy from sample level to element level. This enables the proposed network to precisely identify noisy elements and thus highlight the contribution of informative ones to train a more accurate representation model. Thanks to the separability of the model, the proposed network can be divided into several subnetworks, each of which can be trained efficiently. In addition, three corresponding incremental learning algorithms of the BLS-AR are developed for adding new samples or expanding the network. Substantial experiments are conducted to explicate the effectiveness and robustness of the proposed BLS-AR model.

Study on the Characteristics of Trackside Acoustic Flow Field of High-Speed Train under the Influence of Crosswind.

During the on-track acoustic detection process, a potential flow model and an acoustic finite element mathematical model based on synthetic wind are utilized, taking into account the combined effects of vehicle speed, wind direction angle, and crosswind speed. Simulation and modeling are achieved using Automatic Matching of Acoustic Radiation Boundary Conditions (AML) technology, enabling obtaining a distribution map and sound pressure frequency response curve of the trackside acoustic field under crosswind conditions by setting up field point grids. It is found that sound pressure values at the same location gradually increase as the vehicle speed increases in the frequency range of 10 Hz to 70 Hz, at different vehicle speeds. The sound pressure values and distribution area of the trackside acoustic field are the largest when the crosswind speed is 10 m/s (wind force at level five), allowing for easier location of the sound source when a fault occurs. The study also reveals that under different wind direction angles, the same location's sound pressure value on the trackside gradually decreases as the wind direction angle increases, to lower than that of the non-crosswind condition, severely hindering the reception and diagnosis of acoustic signals.

A Review of Convex Clustering From Multiple Perspectives: Models, Optimizations, Statistical Properties, Applications, and Connections.

Traditional partition-based clustering is very sensitive to the initialized centroids, which are easily stuck in the local minimum due to their nonconvex objectives. To this end, convex clustering is proposed by relaxing K -means clustering or hierarchical clustering. As an emerging and excellent clustering technology, convex clustering can solve the instability problems of partition-based clustering methods. Generally, convex clustering objective consists of the fidelity and the shrinkage terms. The fidelity term encourages the cluster centroids to estimate the observations and the shrinkage term shrinks the cluster centroids matrix so that their observations share the same cluster centroid in the same category. Regularized by the lpn -norm ( pn ∈ {1,2,+∞} ), the convex objective guarantees the global optimal solution of the cluster centroids. This survey conducts a comprehensive review of convex clustering. It starts with the convex clustering as well as its nonconvex variants and then concentrates on the optimization algorithms and the hyperparameters setting. In particular, the statistical properties, the applications, and the connections of convex clustering with other methods are reviewed and discussed thoroughly for a better understanding the convex clustering. Finally, we briefly summarize the development of convex clustering and present some potential directions for future research.

Noise Robust Face Hallucination Based on Smooth Correntropy Representation.

Face hallucination technologies have been widely developed during the past decades, among which the sparse manifold learning (SML)-based approaches have become the popular ones and achieved promising performance. However, these SML methods always failed in handling noisy images due to the least-square regression (LSR) they used for error approximation. To this end, we propose, in this article, a smooth correntropy representation (SCR) model for noisy face hallucination. In SCR, the correntropy regularization and smooth constraint are combined into one unified framework to improve the resolution of noisy face images. Specifically, we introduce the correntropy induced metric (CIM) rather than the LSR to regularize the encoding errors, which admits the proposed method robust to noise with uncertain distributions. Besides, the fused LASSO penalty is added into the feature space to ensure similar training samples holding similar representation coefficients. This encourages the SCR not only robust to noise but also can well exploit the inherent typological structure of patch manifold, resulting in more accurate representations in noise environment. Comparison experiments against several state-of-the-art methods demonstrate the superiority of SCR in super-resolving noisy low-resolution (LR) face images.

Identification and Nanomechanical Characterization of the HIV Tat-Amyloid ß Peptide Multifibrillar Structures.

HIV transactivator of transcription (Tat) protein could interact with amyloid ß (Aß) peptide which cause the growth of Aß plaques in the brain and result in Alzheimer's disease in HIV-infected patients. Herein, we employ high-resolution atomic force microscopy and quantitative nanomechanical mapping to investigate the effects of Tat protein in Aß peptide aggregation. Our results demonstrate that the Tat protein could bind to the Aß fibril surfaces and result in the formation of Tat-Aß multifibrillar structures. The resultant Tat-Aß multifibrillar aggregates represent an increase in stiffness compared with Aß fibrils due to the increase in ß-sheet formation. The identification and characterization of the Tat-Aß intermediate aggregates is important to understanding the interactions between Tat protein and Aß peptide, and the development of novel therapeutic strategy for Alzheimer's disease-like disorder in HIV infected individuals.