This study is among the first to investigate ozone levels in urban forests in China. It establishes that urban forest air quality in Yuanshan Forest Park (Shenzhen) is suitable for recreational activities and identifies spatial, seasonal, and diurnal O3 patterns and relationships with micrometeorological parameters, suggesting the possibility of manipulating relevant forest characteristics to reduce Surface ozone (O3) levels. An understanding of O3 levels of urban forest environments is needed to assess potential effects on human health and recreational activities. Such studies in China are scarce. This study investigated urban forest O3 levels to improve understanding and support residents engaging in forest recreational activities. We monitored O3 levels in 2015–2016 for three urban forests representing common habitats (foothill, valley, and ridge) in Yuanshan Forest Park and for an adjacent square. The overall mean daily and daily maximum 8 h mean (MDA8) O3 concentrations were highest for the ridge forest and lowest for the valley forest. Each forest’s O3 concentrations were highest in summer. Diurnally, forest O3 concentrations peaked between 13:00 and 17:00 and reached a minimum between 03:00 and 09:00. The correlation between forest O3 concentrations and air temperature (AT) was strongly positive in summer and autumn but negative in spring. In each season, O3 concentration was negatively correlated with relative humidity (RH). No MDA8 or hourly O3 concentrations in the forests exceeded National Ambient Air Quality Standard Grade I thresholds (100 and 160 μg m−3, respectively). O3 accumulation is present in ridge urban forest in all seasons. Foothill and valley urban forests have better air quality than ridge forestation. Urban forest air quality is better in spring and autumn than in summer and is better from night-time to early morning than from noon to afternoon.
To explore the application value of convolutional neural network combined with residual attention mechanism and Xception model for automatic classification of benign and malignant gastric ulcer lesions in common digestive endoscopy images under the condition of insufficient data. For the problems of uneven illumination and low resolution of endoscopic images, the original image is preprocessed by Sobel operator, etc. The algorithm model is implemented by Pytorch, and the preprocessed image is used as input data. The model is based on convolutional neural network for automatic classification and diagnosis of benign and malignant gastric ulcer lesions in small number of digestive endoscopy images. The accuracy, F1 score, sensitivity, specificity and precision of the Xception model improved by the residual attention module for the diagnosis of benign and malignant gastric ulcer lesions were 81.411%, 81.815%, 83.751%, 76.827% and 80.111%, respectively. The superposition of residual attention modules can effectively improve the feature learning ability of the model. The pretreatment of digestive endoscopy can remove the interference information on the digestive endoscopic image data extracted from the database, which is beneficial to the training of the model. The residual attention mechanism can effectively improve the classification effect of Xception convolutional neural network on benign and malignant lesions of gastric ulcer on common digestive endoscopic images.
The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.
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.