RESUMEN
Deep learning is a convenient method for doctors to classify pulmonary diseases such as COVID-19, viral pneumonia, bacterial pneumonia, and tuberculosis. However, such a task requires a dataset including samples of all these diseases and a more effective network to capture the features of images accurately. In this paper, we propose a five-classification pulmonary disease model, including the pre-processing of input data, feature extraction, and classifier. The main points of this model are as follows. Firstly, we present a new network named RED-CNN which is based on CNN architecture and constructed using the RED block. The RED block is composed of the Res2Net module, ECA module, and Double BlazeBlock module, which are capable of extracting more detailed information, providing cross-channel information, and enhancing the extraction of global information with strong feature extraction capability. Secondly, by merging two selected datasets, the Curated Chest X-Ray Image Dataset for COVID-19 and the tuberculosis (TB) chest X-ray database, we constructed a new dataset including five types of data: normal, COVID-19, viral pneumonia, bacterial pneumonia, and tuberculosis. In order to assess the efficiency of the proposed five-classification model, a series of experiments based on the new dataset were carried out and based on 5-fold cross validation, and the results of the accuracy, precision, recall, F1 value, and Jaccard scores of the proposed method were 91.796%, 92.062%, 91.796%, 91.892%, and 86.176%, respectively. Our proposed algorithm performs better than other classification algorithms.
RESUMEN
COVID-19 has spread worldwide, leading to a significant impact on daily life. Numerous studies have confirmed that people have changed their travel to urban green spaces during the COVID-19 pandemic. However, in China, where COVID-19 has been effectively controlled, how the travel behavior of visitors to urban parks has changed under different risk levels (RLs) of COVID-19 is unclear. Faced with these gaps, we took a highly developed city, Wuhan, as a case study and a questionnaire survey was conducted with 3276 respondents to analyze the changes in park visitors' travel behaviors under different COVID-19 RLs. Using a stated preference (SP) survey method, four RLs were assigned: new cases in other provinces (RL1), Hubei province (RL2), Wuhan (RL3), and in the district of the park (RL4). The results indicated that visitors reduced their willingness to visit urban parks, with 78.39%, 37.97%, and 13.34% of visitors remaining under RL2, RL3, and RL4, respectively. Furthermore, the service radius of urban parks also shrank from 4230 m under no new cases of COVID-19 to approximately 3000 m under RL3. A higher impact was found for visitors using public transport, those with a higher income and higher education, and female visitors. Based on the modified travel behaviors, the Gaussian-based two-step floating catchment area (2SFCA) method was used to evaluate the accessibility and the Gini coefficient was calculated to represent the equality of the urban parks. A higher RL led to lower accessibility and greater inequitable access. The results should help the government guide residents' travel behaviors after COVID-19.