Search

Accurate and real-time monitoring of the surface contamination status of insulators is of great significance for preventing pollution flashover accidents and maintaining system safety. This article introduces hyperspectral imaging technology to detect the contamination status of composite insulators. To address the impact of different outdoor lighting conditions on the detection of composite insulator contamination status, a composite insulator contamination status evaluation model is established based on the hyperspectral data collected indoors. Then, gradient spectral angle matching (GSAM) method is used to extract insulator images from the hyperspectral images collected under different outdoor lighting conditions, and the insulator image is segmented into multiple super-pixel regions using the energy-driven sampling method. The super-pixel average spectral data were used instead of the pixel spectral data, and the contamination state was evaluated after the series processing of the two model transfer methods of correlation alignment method and piecewise direct standardization (PDS). The results show that the use of super-pixel segmentation method reduces the amount of data to be measured by 98% while ensuring the visualization of insulator pollution distribution, and the model transfer method improves the classification accuracy of the model from 50% to 90%, effectively reducing the impact of changes in lighting conditions on hyperspectral detection.

Label distribution covers a certain number of labels, representing the degree to which each label describes the instance. Label enhancement (LE) is a procedure of recovering the label distribution from the logical labels in the training data, the purpose of which is to better depict the label ambiguity through label distribution. However, data annotation inevitably introduces label noise, and it is extremely challenging to implement LE on corrupted labels. To deal with this problem, one way to recover the label distribution from the corrupted labels is to be guided by a small batch of trusted data. In this article, a novel LE method named TALEN is proposed via recovering and progressively refining label distribution guided by trusted data. Specifically, an LE process is applied to the untrusted data to select samples with a clean label. In addition, a combined loss function is designed to train the predictive model for classification. Experiments on datasets with synthetic label noise validate the feasibility of identifying clean labels via the recovered label distribution. Furthermore, experimental results on both synthetic label noise and real-world label noise on image datasets and additional experiments on text datasets show a clear advantage of TALEN over several existing noise-robust learning methods.

Partial multi-label learning (PML) aims to learn a multilabel predictive model from the PML training examples, each of which is associated with a set of candidate labels where only a subset is valid. The common strategy to induce a predictive model is identifying the valid labels in each candidate label set. Nonetheless, this strategy ignores considering the essential label distribution corresponding to each instance as label distributions are not explicitly available in the training dataset. In this article, a novel partial multilabel learning method is proposed to recover the latent label distribution and progressively enhance it for predictive model induction. Specifically, the label distribution is recovered by considering the observation model for logical labels and the sharing topological structure from feature space to label distribution space. Besides, the latent label distribution is progressively enhanced by recovering latent labeling information and supervising predictive model training alternatively to make the label distribution appropriate for the induced predictive model. Experimental results on PML datasets clearly validate the effectiveness of the proposed method for solving partial multilabel learning problems. In addition, further experiments show the high quality of the recovered label distributions and the effectiveness of adopting label distributions for partial multilabel learning.