ABSTRACT
Under the COVID-19 and other terrible environments workers are constrained to sweep campus and public area. Intelligent and driverless sanitation robot can solve the problem. Obstacle avoidance and garbage cleanup are its important functions. Based on the driverless sanitation robot project introduced by Sanda University, this paper carries out recognition of campus vehicles and improves its obstacle avoidance function. Through image processing, the object features of different environment and climate conditions are extracted, analyzed and recognized, so as to achieve more accurate recognition of campus vehicles. And opencv and python language are used to complete the implementation of vehicle detection. © 2022 IEEE.
ABSTRACT
Aiming at the problem of metro operation and passenger transport organization under the impact of the novel coronavirus (COVID-19), a collaborative determination method of train planning and passenger flow control is proposed to reduce the train load rate in each section and decrease the risk of spreading COVID-19. The Fisher optimal division method is used to determine reasonable passenger flow control periods, and based on this, different flow control rates are adopted for each control period to reduce the difficulty of implementing flow control at stations. According to the actual operation and passenger flow changes, a mathematical optimization model is established. Epidemic prevention risk values (EPRVs) are defined based on the standing density criteria for trains to measure travel safety. The optimization objectives of the model are to minimize the EPRV of trains in each interval, the passenger waiting time and the operating cost of the corporation. The decision variables are the number of running trains during the study period and the flow control rate at each station. The original model is transformed into a single-objective model by the linear weighting of the target, and the model is solved by designing a particle swarm optimization and genetic algorithm (PSO-GA). The validity of the method and the model is verified by actual metro line data. The results of the case study show that when a line is in the moderate-risk area of COVID-19, two more trains should be added to the full-length and short-turn routes after optimization. Combined with the flow control measures for large passenger flow stations, the maximum train load rate is reduced by 35.18%, and the load rate of each section of trains is less than 70%, which meets the requirements of COVID-19 prevention and control. The method can provide a theoretical basis for related research on ensuring the safety of metro operation during COVID-19.
ABSTRACT
Due to the wide variety of pathogens causing respiratory tract infection and the close symptoms, coronavirus disease 2019 (COVID-19) needs to be differentiated from other common infections. Early comprehensive detection and accurate identification of respiratory infection pathogens is of great value for early diagnosis, curative effect, as well as monitor of the diseases. Combined detection of multiple pathogens can quickly and accurately detect and distinguish the pathogens, then provide rapid and reliable laboratory diagnostic basis for further treatment. This article elaborates the application and development of multiplex detection assay in the diagnosis of COVID-19 according to the recent research.
Subject(s)
COVID-19 , Respiratory Tract Infections , Humans , COVID-19/diagnosis , Respiratory Tract Infections/diagnosis , Respiratory Tract Infections/therapy , Sensitivity and SpecificityABSTRACT
AI for infectious disease modelling and therapeutics is an emerging area that leverages new computational approaches and data in this area. Genomics, proteomics, biomedical literature, social media, and other resources are proving to be critical tools to help understand and solve complicated issues ranging from understanding the process of infection, diagnosis and discovery of the precise molecular details, to developing possible interventions and safety profiling of possible treatments.
ABSTRACT
The use of deep learning methods for virus identification from digital images is a timely research topic. Given an electron microscopy image, virus recognition utilizing deep learning approaches is critical at present, because virus identification by human experts is relatively slow and time-consuming. In this project, our objective is to develop deep learning methods for automatic virus identification from digital images, there are four viral species taken into consideration, namely, SARS, MERS, HIV, and COVID-19. In this work, we firstly examine virus morphological characteristics and propose a novel loss function which aims at virus identification from the given electron micrographs. We take into account of attention mechanism for virus locating and classification from digital images. In order to generate the most reliable estimate of bounding boxes and classification for a virus as visual object, we train and test five deep learning models: R-CNN, Fast R-CNN, Faster R-CNN, YOLO, and SSD, based on our dataset of virus electron microscopy. Additionally, we explicate the evaluation approaches. The conclusion reveals SSD and Faster R-CNN outperform in the virus identification.
ABSTRACT
Spatio-temporal data analysis is very important in many time-critical applications. We take Coronavirus disease (COVID-19) as an example, and the key questions that everyone will ask every day are: how does Coronavirus spread? where are the high-risk areas? where have confirmed cases around me? Interactive data analytics, which allows general users to easily monitor and explore such events, plays a key role. However, some emerging cases, such as COVID-19, bring many new challenges: (C1) New information may come with different formats: basic structured data such as confirmed/suspected/serious/death/recovered cases, unstructured data from newspapers for travel history of confirmed cases, and so on. (C2) Discovering new insights: data visualization is widely used for storytelling;however, the challenge here is how to automatically find "interesting stories", which might be different from day to day. We propose DEEPTRACK, a system that monitors spatio-temporal data, using the case of COVID-19. For (C1), we describe (a) how we integrate and clean data from different sources by existing modules. For (C2), we discuss (b) how to build new modules for ad-hoc data sources and requirements, (c) what are the basic (or static) charts used;and (d) how to generate recommended (or dynamic) charts that are based on new incoming data. The attendees can use DeepTrack to interactively explore various COVID-19 cases.
ABSTRACT
OBJECTIVE: On December 8, 2019, many cases of pneumonia with unknown etiology were first reported in Wuhan, China, subsequently identified as a novel coronavirus infection aroused worldwide concern. As the outbreak is ongoing, more and more researchers focused interest on the COVID-19. Therefore, we retrospectively analyzed the publications about COVID-19 to summarize the research hotspots and make a review, to provide reference for researchers in the world. MATERIALS AND METHODS: We conducted a search in PubMed using the keywords "COVID-19" from inception to March 1, 2020. Identified and analyzed the data included title, corresponding author, language, publication time, publication type, research focus. RESULTS: 183 publications published from 2020 January 14 to 2020 February 29 were included in the study. The first corresponding authors of the publications were from 20 different countries. Among them, 78 (42.6%) from the hospital, 64 (35%) from the university and 39 (21.3%) from the research institution. All the publications were published in 80 different journals. Journal of Medical Virology published most of them (n=25). 60 (32.8%) were original research, 29 (15.8%) were review, 20 (10.9%) were short communications. 68 (37.2%) epidemiology, 49 (26.8%) virology and 26 (14.2%) clinical features. CONCLUSIONS: According to our review, China has provided a large number of research data for various research fields, during the outbreak of COVID-19. Most of the findings play an important role in preventing and controlling the epidemic around the world. With research on the COVID-19 still booming, new vaccine and effective medicine for COVID-19 will be expected to come out in the near future with the joint efforts of researchers worldwide.