TL;DR: The results indicate that NO2 level has dropped 20-year low because of the COVID-19 lockdown, and it is determined that the mortality rate because of long-time exposure to NO2 is higher than CO VID-19 and the deaths may be a circumlocutory effect owing to the inhalation of NO2.
Abstract: Purpose - Corona Virus Disease 2019 (COVID-19) is a deadly virus named after severe acute respiratory syndrome coronavirus 2;it affects the respiratory system of the human and sometimes leads to death The COVID-19 mainly attacks the person with previous lung diseases;the major cause of lung diseases is the exposure to nitrogen dioxide (NO2) for a longer duration NO2 is a gaseous air pollutant caused as an outcome of the vehicles, industrial smoke and other combustion processes Exposure of NO2 for long-term leads to the risk of respiratory and cardiovascular diseases and sometimes leads to fatality This paper aims to analyze the NO2 level impact in India during pre- and post-COVID-19 lockdown The study also examines the relationship between the fatality rate of humans because of exposure to NO2 and COVID-19 Design/methodology/approach - Spatial analysis has been conducted in India based on the mortality rate caused by the COVID-19 using the data obtained through Internet of Medical things Meanwhile, the mortality rate because of the exposure of NO2 has been conducted in India to analyze the relationship Further, NO2 level assessment is carried out using Copernicus Sentinel-5P satellite data Moreover, aerosol optical depth analysis has been carried out based on NASA's Earth Observing System data Findings - The results indicate that NO2 level has dropped 20-year low because of the COVID-19 lockdown The results also determine that the mortality rate because of long-time exposure to NO2 is higher than COVID-19 and the mortality rate because of COVID-19 may be a circumlocutory effect owing to the inhalation of NO2 Originality/value - Using the proposed approach, the COVID-19 spread can be identified by knowing the air pollution in major cities The research also identifies that COVID-19 may have an effect because of the inhalation of NO2, which can severe the COVID-19 in the human body
01 Jan 2020
TL;DR: Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future.
Abstract: Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.
TL;DR: In this paper, Parallel based SVM (P-SVM) and IoT has been utilized to examine the ideal order of lung infections caused by genomic sequence, and the proposed method develops a new methodology to locate the ideal characterization of lung sicknesses and determine its growth in its early stages, to control the growth and prevent lung sickness.
Abstract: Attributable to the modernization of Artificial Intelligence (AI) procedures in healthcare services, various developments including Support Vector Machine (SVM), and profound learning. For example, Convolutional Neural systems (CNN) have prevalently engaged in a significant job of various classificational investigation in lung malignant growth, and different infections. In this paper, Parallel based SVM (P-SVM) and IoT has been utilized to examine the ideal order of lung infections caused by genomic sequence. The proposed method develops a new methodology to locate the ideal characterization of lung sicknesses and determine its growth in its early stages, to control the growth and prevent lung sickness. Further, in the investigation, the P-SVM calculation has been created for arranging high-dimensional distinctive lung ailment datasets. The data used in the assessment has been fetched from real-time data through cloud and IoT. The acquired outcome demonstrates that the developed P-SVM calculation has 83% higher accuracy and 88% precision in characterization with ideal informational collections when contrasted with other learning methods.
TL;DR: In this paper, the application of the internet of things (IoT) and machine learning (ML) based system to combat pandemic situation in health care application has been discussed, the developed ML and IoT based monitoring system help in tracking the infected persons from the previous data and makes them get isolate from the noninfected person.
Abstract: The pandemic situation has pretentious the habitual life of the human, it also has surpassed the regional, social, business activities and forced human society to live in a limited boundary. In this paper, the application of the internet of things (IoT) and machine learning (ML) based system to combat pandemic situation in health care application has been discussed. The developed ML and IoT based monitoring system help in tracking the infected persons from the previous data and makes them get isolate from the non-infected person. The developed ML combined IoT system uses parallel computing in tracking the pandemic disease and also in the prevention of pandemic disease by predicting and analysing the data using artificial intelligence. The implementation of ML-based IoT in the pandemic situation in healthcare application has proved its performance in tracking and prevents the spreading of pandemic disease. It also further has a positive impact on reducing medical costs and has recorded improved treatment for infected patients. The proposed methodology has an accuracy of 93 % in monitoring and tracking. The result obtained help in preventing the spread of the pandemic and provide support to the healthcare system.
TL;DR: In this article, the impacts of seasonal diversity of buildings' energy consumption pattern on the tropospheric NO2, CO, and SO2 concentrations over the 22 districts of Kabul City were investigated.
Abstract: Air and environmental pollution are influenced by natural and anthropogenic activities. In addition, seasonal variations also affect the level of air pollutant concentration. Air pollution has a negative impact on climate, human-being health, and the environment. Monitoring of air pollution is a critical challenge in the world for better planning regarding its reduction. This study aims to monitor the impacts of seasonal diversity of buildings’ energy consumption pattern on the tropospheric NO2, CO, and SO2 concentrations over the 22 districts of Kabul City. Sentinel—5P TROPOMI data was used for the space measurement of the selected tropospheric pollutant during the winter (December 2019, January, and February 2020) and summer (June, July, and August 2020) seasons. Google Earth Engine platform was used for the processing and analysis of data, and ArcGIS 10.7.1 was utilized for the plotting of thematic maps. This study’s findings demonstrate that the tropospheric NO2, CO, and SO2 concentrations were reduced from the winter to the summer season. The main sources of NO2, CO, and SO2 pollutants are coal, wood, gas, and biomass burning, since these substances are consumed for heating purposes due to the cold weather during the winter season. Consequently, the results were validated using real-time data to test reliability. There was a high correlation between the output of this study and validation data.
TL;DR: In this paper, the authors presented a novel and generic framework for the recognition of emotions using human body expression like head, hand and leg movements using deep convolutional neural network (DCNN).
Abstract: This paper presents a novel and generic framework for the recognition of emotions using human body expression like head, hand and leg movements. Whole body movements are among the main visual stimulus categories that are naturally associated with faces and the neuro scientific investigation of how body expressions are processed has entered the research agenda this last decade. The database was composed of 254 whole body expressions from 46 actors expressing four emotions (anger, fear, happiness, and sadness). In all pictures the face of the actor was blurred and participants were asked to categorize the emotions expressed in the stimuli in a four alternative-forced-choice task. Using Deep Convolutional Neural Network (DCNN), the input images are trained and modeled. Then the model can be tested by test images for recognizing human emotion from non-verbal communication.