Ensemble Learning for Interpretable Concept Drift and Its Application to Drug Recommendation

During the COVID-19 epidemic, the online prescription pattern of Internet healthcare pro-vides guarantee for the patients with chronic diseases and reduces the risk of cross-infection, but it also raises the burden of decision-making for doctors. Online drug recommendation system can effectively assist doctors by analysing the electronic medical records (EMR) of patients. Unlike commercial recommendations, the accuracy of drug recommendations should be very high due to their relevance to patient health. Besides, concept drift may occur in the drug treatment data streams, handling drift and location drift causes is critical to the accuracy and reliability of the rec-ommended results. This paper proposes a multi-model fusion online drug recommendation system based on the association of drug and pathological features with online-nearline-offline architecture.The system transforms drug recommendation into pattern classification and adopts interpretable concept drift detection and adaptive ensemble classification algorithms. We apply the system to the Percutaneous Coronary Intervention (PCI) treatment process. The experiment results show our system performs nearly as good as doctors, the accuracy is close to 100%.

Evolution of tourism risk perception: A bibliometrics analysis on multi-dimensional model

How can we establish a risk perception model and method to guide safety management has become an important issue that needs to be solved urgently in the field of tourism management. However, the solution to this issue is inseparable from the objective analysis, induction and deduction, and the analysis of the frontier trend towards the multidimensional model of tourism risk perception. In this paper, 211 articles from the Web of Science are selected as the research object, and the bibliometric analysis is applied to find: (1) Research on tourism risk perception based on multidimensional models can be divided into nascent, developmental, and mature stages;(2) The research on the multi-dimensional model of tourism risk perception has formed a group of academic groups with outstanding contributions and representative authors;(3) The research hotspots in multidimensional models of tourism risk perception focus on the comprehensive study of perceived risk, the outbreak of COVID-19, psychological risk, destination image, and behavioral intention. On this basis, this paper proposes some corresponding research suggestions to address the inadequacies of existing studies, and the research findings have significant theoretical implications for the construction of the theoretical system of tourism risk management. © 2022 The Author(s).

A Robot Assisted High-flow Portable Cyclone Sampler for Bacterial and SARS-CoV-2 Aerosols

Airborne transmission of infectious diseases attracts great attention since the COVID-19 pandemic. Yet, there has been an intense dispute about aerosol transmission of the disease, which is largely due to lack of qualified instruments for studying the subject. Air sampling plays a critical role in all air pollution related study, and particularly critical for airborne pathogen detection. Here, we designed and evaluated a portable and high volume (400 L min-1) cyclone sampler named as Yao-CSpler using aerosolized Polystyrene (PS) uniform microspheres, Bacillus subtilis var. niger, Pseudomonas fluorescens, and both indoor and outdoor air particles. The experimental cutoff size of the Yao-CSpler was demonstrated to be 0.58 m (while the calculated theoretical value is 1.84 m), and the sampler has shown stable microbial collection performances for bacteria, fungi, and even viruses. The sampler had a physical collection efficiency of close 100% for particles of larger than 1 m. Jet-to-liquid distance and sampling duration were shown to substantially influence the sampler performance. Given the same sampling duration, the performances of the Yao-CSpler were significantly higher than those of the traditional BioSampler (SKC Inc.) in terms of samples' bacterial diversity. The developed sampler coupled with a robot has been successfully applied to sampling airborne SARS-CoV-2 in both Wuhan and Beijing during the COVID-19 outbreaks. With a high sampling flow, the Yao-CSpler was shown to be able to collect the SARS-CoV-2 with a detectable concentration level down to 9-219 viruses m-3 in clinical settings housing COVID-19 patients. Further more efficient bioaerosol sampler, which is able to rapidly capture low level pathogenic agents, is urgently required to better understand and confront airborne transmission of infectious diseases.