The human daily activity category represents individual lifestyle and pattern, such as sports and shopping, which reflect personal habits, lifestyle, and preferences and are of great value for human health and many other application fields. Currently, compared to questionnaires, social media as a sensor provides low-cost and easy-to-access data sources, providing new opportunities for obtaining human daily activity category data. However, there are still some challenges to accurately recognizing posts because existing studies ignore contextual information or word order in posts and remain unsatisfactory for capturing the activity semantics of words. To address this problem, we propose a general model for recognizing the human activity category based on deep learning. This model not only describes how to extract a sequence of higher-level word phrase representations in posts based on the deep learning sequence model but also how to integrate temporal information and external knowledge to capture the activity semantics in posts. Considering that no benchmark dataset is available in such studies, we built a dataset that was used for training and evaluating the model. The experimental results show that the proposed model significantly improves the accuracy of recognizing the human activity category compared with traditional classification methods. Full article

This research provides a general methodology for distinguishing disaster-related anti-rumor spreaders from a non-ignorant population base, with strong connections in their social circle. Several important influencing factors are examined and illustrated. User information from the most recent posted microblog content of 3793 Sina Weibo users was collected. Natural language processing (NLP) was used for the sentiment and short text similarity analyses, and four machine learning techniques, i.e., logistic regression (LR), support vector machines (SVM), random forest (RF), and extreme gradient boosting (XGBoost) were compared on different rumor refuting microblogs; after which a valid and robust distinguishing XGBoost model was trained and validated to predict who would retweet disaster-related rumor refuting microblogs. Compared with traditional prediction variables that only access user information, the similarity and sentiment analyses of the most recent user microblog contents were found to significantly improve prediction precision and robustness. The number of user microblogs also proved to be a valuable reference for all samples during the prediction process. This prediction methodology could be possibly more useful for WeChat or Facebook as these have relatively stable closed-loop communication channels, which means that rumors are more likely to be refuted by acquaintances. Therefore, the methodology is going to be further optimized and validated on WeChat-like channels in the future. The novel rumor refuting approach presented in this research harnessed NLP for the user microblog content analysis and then used the analysis results of NLP as additional prediction variables to identify the anti-rumor spreaders. Therefore, compared to previous studies, this study presents a new and effective decision support for rumor countermeasures. Full article

The present study aimed to investigate the relationship between the occurrence of ventilator-associated events (VAE) in the intensive care unit and the timing of rehabilitation intervention. We included subjects who underwent emergency tracheal intubation and received rehabilitation. We performed rehabilitation according to our hospital’s protocol. We assessed the mechanical ventilation parameters of inspired oxygen fraction and positive-end expiratory pressure, and a VAE was identified if these parameters stabilized or decreased for ≥2 days and then had to be increased for ≥2 days. We defined time in hours from tracheal intubation to the first rehabilitation intervention as Timing 1 and that to first sitting on the edge of the bed as Timing 2. Data were analyzed by the t-test and χ² tests. We finally analyzed 294 subjects. VAE occurred in 9.9% and high mortality at 48.3%. Median values of Timing 1 and Timing 2 in the non-VAE and VAE groups were 30.3 ± 24.0 and 30.0 ± 20.7 h, and 125.7 ± 136.6 and 127.9 ± 111.4 h, respectively, and the differences were not significant (p = 0.95 and p = 0.93, respectively). We found no significant relationship between the occurrence of VAE leading to high mortality and timing of rehabilitation intervention. Full article

The conflict between economic development and environmental protection has become increasingly prominent in the urbanization process of the Yangtze River urban agglomeration, the most economically developed region in Jiangsu Province in China. In order to investigate the sustainable development status, and thus provide decision support for the sustainable development of this region, the ecological footprint model was utilized to evaluate and analyze the ecological footprint per capita, the ecological carrying capacity per capita, and the ecological deficit per capita for the period from 2013 to 2017. Furthermore, the Grey model is employed to predict the development trend of the ecological footprint for 2018 to 2022. The evaluation results show that the ecological footprint per capita has been increasing year by year since 2013, reaching a peak of 2.3897 hm² in 2015 before declining again. In the same period, the available ecological carrying capacity per capita and the ecological footprint per capita basically developed in the same direction, resulting in an ecological deficit per capita and gradually increasing from 2013 to a peak of 2.0303 hm² in 2015 before declining. It is also found that the change of ecological carrying capacity is not substantial, and the change of the ecological deficit is mainly caused by a huge change of the ecological footprint. The forecast results show that the ecological deficit per capita will reach 1.1713 hm² in 2018, which will be another deficit peak after 2015. However, in the later period until 2022, the ecological deficit per capita will begin to decline year by year. These results can provide effective inspirations for reducing the ecological deficit of the Yangtze River urban agglomeration, thus promoting the coordinated development of the economy and environment in this area. Full article

Urban disaster risk assessment is the most basic and important part of urban safety development. Conducting disaster prevention and mitigation on the basis of urban disaster risk assessment requires an understanding of the relationship between the city and the natural environment. This enhances the city’s ability to withstand various types of disasters and achieves the development of a safe city. Based on a review of the existing literature, we propose a fuzzy comprehensive evaluation method for urban multi-disaster risk assessment. The multi-disaster risk assessment method includes the identification and screening of urban disasters, the assessment of individual disaster risk, and integrated urban disaster risks, the division of urban comprehensive disaster risks into several risk levels, and the determination of coping strategies. Taking Guangzhou (China) as an example, we determined the major disaster risks faced by Guangzhou, assessed the risks of individual disasters, and finally obtained the results of the comprehensive disaster risk of Guangzhou. Second, we analyzed the relationship between the disaster risk assessment and urban safety development, and proposed countermeasures and recommendations for the development of different disaster risk levels. Full article