Deep learning has become increasingly popular in both academic and industrial areas in the past years. Various domains including pattern recognition, computer vision, and natural language processing have witnessed the great power of deep networks. However, current studies on deep learning mainly focus on data sets with balanced class labels, while its performance on imbalanced data is not well examined. Imbalanced data sets exist widely in real world and they have been providing great challenges for classification tasks. In this paper, we focus on the problem of classification using deep network on imbalanced data sets. Specifically, a novel loss function called mean false error together with its improved version mean squared false error are proposed for the training of deep networks on imbalanced data sets. The proposed method can effectively capture classification errors from both majority class and minority class equally. Experiments and comparisons demonstrate the superiority of the proposed approach compared with conventional methods in classifying imbalanced data sets on deep neural networks.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental results of using original and new features. In this paper, we propose a Relation Autoencoder model considering both data features and their relationships. We also extend it to work with other major autoencoder models including Sparse Autoencoder, Denoising Autoencoder and Variational Autoencoder. The proposed relational autoencoder models are evaluated on a set of benchmark datasets and the experimental results show that considering data relationships can generate more robust features which achieve lower construction loss and then lower error rate in further classification compared to the other variants of autoencoders.
Strong wind causes damages and losses around the world. The windborne debris carried by strong wind might impact on building and create openings on the building envelop, which might threaten the occupants and cause further damages to the building. To address this issue, some wind loading codes including the Australian Wind Loading Code (AS/NZS 1170:2:2011) give design requirements. The resistance capacity of oriented strand board skins structural insulated panel was investigated and proved having low resistance to the projectile impact, and could not meet the impact resistance requirement for application in cyclonic region C and D defined in Australian Wind Loading Code. In this study, basalt fibre cloth is used to strengthen oriented strand board structural insulated panel to increase its capacity to resist windborne debris impact. This paper presents experimental and numerical study of structural insulated panel with or without basalt fibre cloth strengthening under windborne debris impact. Five specimens with different configurations were tested. The dynamic responses were quantitatively compared in terms of residual speed of debris after impact. The results indicate that basalt fibre cloth enhanced the resistance capacity of oriented strand board structural insulated panel. A numerical model is developed in LS-DYNA to simulate the debris impact. The testing results are used to verify the accuracy of the numerical model, which can be used in subsequent parametric studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.