Search Results (2)

In this paper, a reliability assessment and prediction method based on bearing vibration signals is proposed, which combines Adaptive Cyclostationary Blind Deconvolution (ACYCBD) and AdaBoost-Mixed Kernel Relevance Vector Machine. Firstly, CYCBD parameters were optimized by the Ivy optimization algorithm to enhance the noise reduction effect, and then multidimensional features were extracted and dimensionalization was reduced by PaCMAP. Based on dimensionality reduction features, logistic regression was used to evaluate reliability, and AdaBoost-MKRVM was combined to predict reliability. The experimental results show that the mean absolute error (MAE) of the proposed method on the bearing life dataset of Xi’an Jiaotong University is 0.052, which is better than the traditional method, and provides a new idea for the performance prediction of rolling bearings. Full article

Dimensionality reduction techniques are often used by researchers in order to make high dimensional data easier to interpret visually, as data visualization is only possible in low dimensional spaces. Recent research in nonlinear dimensionality reduction introduced many effective algorithms, including t-distributed stochastic neighbor embedding (t-SNE), uniform manifold approximation and projection (UMAP), dimensionality reduction technique based on triplet constraints (TriMAP), and pairwise controlled manifold approximation (PaCMAP), aimed to preserve both the local and global structure of high dimensional data while reducing the dimensionality. The UMAP algorithm has found its application in bioinformatics, genetics, genomics, and has been widely used to improve the accuracy of other machine learning algorithms. In this research, we compare the performance of different fuzzy information discrimination measures used as loss functions in the UMAP algorithm while constructing low dimensional embeddings. In order to achieve this, we derive the gradients of the considered losses analytically and employ the Adam algorithm during the loss function optimization process. From the conducted experimental studies we conclude that the use of either the logarithmic fuzzy cross entropy loss without reduced repulsion or the symmetric logarithmic fuzzy cross entropy loss with sufficiently large neighbor count leads to better global structure preservation of the original multidimensional data when compared to the loss function used in the original UMAP algorithm implementation. Full article