Recently, many researchers have attempted to use convolutional neural networks (CNNs) for wildfire smoke detection. However, the application of CNNs in wildfire smoke detection still faces several issues, e.g., the high false-alarm rate of detection and the imbalance of training data. To address these issues, we propose a novel framework integrating conventional methods into CNN for wildfire smoke detection, which consisted of a candidate smoke region segmentation strategy and an advanced network architecture, namely wildfire smoke dilated DenseNet (WSDD-Net). Candidate smoke region segmentation removed the complex backgrounds of the wildfire smoke images. The proposed WSDD-Net achieved multi-scale feature extraction by combining dilated convolutions with dense block. In order to solve the problem of the dataset imbalance, an improved cross entropy loss function, namely balanced cross entropy (BCE), was used instead of the original cross entropy loss function in the training process. The proposed WSDD-Net was evaluated according to two smoke datasets, i.e., WS and Yuan, and achieved a high AR (99.20%) and a low FAR (0.24%). The experimental results demonstrated that the proposed framework had better detection capabilities under different negative sample interferences.
Grass-like Ni3S2 nanorod/nanowire arrays in situ grown on NF network are synthesized through simply regulating the pre-oxidation degree of NF precursor which demonstrate excellent electrochemical properties.
Bisphenol A-based benzoxazine (BOZ) was blended with cyanate ester (CE) to improve the properties of cyanate resin. The effects of the content of BOZ on the mechanical property and dielectric property of the blends have been investigated. The results show that a suitable addition of BOZ can enhance the impact strength and flexural strength as well as reduce the dielectric constant and the dielectric loss of CE. The mechanical properties are significantly improved when the content of BOZ is 10 wt%, and the dynamic mechanical analysis reveals that the cross-link density of the blend is lower than pure CE. Scanning electron microscopy analysis shows distinct characteristics of ductile fracture of the blends. In addition, the dielectric constant and the dielectric loss of modified system decreases, compared with the curing CE. The optimal addition amount of BOZ resin is 15 wt% for the dielectric properties. The blend of a suitable addition of BOZ still remains a good thermal resistance. All these changes in properties are closely correlated to the copolymerization between BOZ and CE.
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.