Timely detection of forest wildfires is of great significance to the early prevention and control of large-scale forest fires. Unmanned Aerial Vehicle(UAV) with cameras has the characteristics of wide monitoring range and strong flexibility, making it very suitable for early detection of forest fire. However, the visual angle/distance of UAV in the process of image sampling and the limited sample size of UAV labeled images limit the accuracy of forest fire recognition based on UAV images. This paper proposes a FT-ResNet50 model based on transfer learning. The model migrates the ResNet network trained on an ImageNet dataset and its initialization parameters into the target dataset of forest fire identification based on UAV images. Combined with the characteristics of the target data set, Adam and Mish functions are used to fine tune the three convolution blocks of ResNet, and focal loss function and network structure parameters are added to optimize the ResNet network, to extract more effectively deep semantic information from fire images. The experimental results show that compared with baseline models, FT-ResNet50 achieved better accuracy in forest fire identification. The recognition accuracy of the FT-ResNet50 model was 79.48%; 3.87% higher than ResNet50 and 6.22% higher than VGG16.
Background: More and more new surgical procedures for the treatment of benign prostate hyperplasia (BPH) are proposed creatively. However, the existing clinical evidence shows that the effectiveness and safety of various procedures exist inconsistent.
Methods:The randomized controlled trials comparing the international prostate score, length of hospital stay, maximum urinary flow rate, operation time, and complication rates of prostatic artery embolization (PAE), Greenlight-XPS Laser prostate vaporization procedure (GLL PVP), diode laser enucleation of prostate (DILEP) and plasmakinetic resection of the prostate (PKRP), transurethral resection of the prostate (TURP) in patients with BPH were screened out in databases. The primary outcome was pooled using a restricted maximum likelihood-based random-effect model and inverse variance-based fixed-effect model.Cochrane Q statistics and I2 statistics were computed to quantify between-study heterogeneity. The risk of bias of each included study was assessed using the revised Cochrane risk of bias tool.Results: This meta-analysis ultimately included 14 original research papers, with 1,940 participants enrolled. Eight studies were considered to be at moderate risk of bias, while the others were at mild risk of bias. Although the improvement in functional outcome of the DILEP procedure was equivalent to that of the PKRP procedure, the DILEP procedure group had fewer hospital stays than the PKRP group (P=0.01).In addition, even though the performance of the GLL PVP procedure in the improvement of functional outcome was inferior to the counterpart of TURP (P=0.64), it had a much fewer hospital stays (P=0.01).
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.