ABSTRACT
In assessing the occurrence of an unexpected medical adverse event following pharmaceutical,medical, or surgical treatment, the causal or contributory roles played by bias, systemic racism, and social determinants of health should be investigated. Up to 80% of clinical outcomes are estimated to be driven by social determinants including the environments in which patients live, work, learn, worship, and play. Among women, there are racial health disparities in sterilization procedures, method of hysterectomy, cesarean birth rates, preterm birth rates, and, most recently, the rates of COVID-19 death and hospitalizations. At the same time, there is little specific guidance of how to investigate social determinants of health that affect patient outcomes. Differences in health equity-related factors affect the quality of gynecologic care. There is immeasurable potential for bias in patient characteristics: race;ethnicity;persons with obesity;LGBTQ+ (lesbian, gay, bisexual, transgender, queer+) persons;socioeconomic factors;and young and old age. Within existing models for patient safety, inclusion of equity-related aspects of care may improve the current understanding of the causes of medical adverse events. It is critical to consider social determinants of health, structural racism, and both overt and implicit bias. The aim of this studywas to establish a sustainable and trackable process to determine the role of social determinants of health, bias, and racism in adverse gynecologic events. Each adverse event case is assessed for preventability, harm, and standards of care. Cases are identified for review utilizing existing hospital event-reporting systems (RLDatix) and enhanced by resident and attending physician self-reporting. The following equity-focused process was used: (1) creating a standardized health equity checklist;(2) applying the checklist to each gynecologic adverse event beginning on September 1, 2020;(3) collecting event review data in a secure central digital repository;(4) reviewing each adverse case to understand apparent causes of the event;(5) exploring areas for improvement using standard fields;and (6) identifying specific ideas for improvement. Within 15 months (between September 1, 2020, and November 30, 2021), 46 safety cases were identified using standard criteria. Twenty-four of these were deemed preventable.Of the 24 cases, 12 cases were identified inwhich social determinants of health, bias, or both had a role. Delays in diagnosis and care were attributed to social determinants of health and implicit bias. This process has mapped areas of infrastructure as well as the need for culture improvement and restorative work to address implicit bias and improve approaches to shared decision-making. These findings show that with use of a health equity checklist, it is feasible to create a systematic and trackable process to begin delineating the role of social determinants of health, bias, and racism in adverse gynecologic events. Copyright © 2023 Lippincott Williams and Wilkins. All rights reserved.
ABSTRACT
As the mobile Internet emerges, numerous Instagram-worthy locations gradually constitute new spaces of urban tourism. For instance, the Xiaohongshu application, a community with shared content, has increasingly become a platform for people to share well-known tourist attractions, providing a new perspective for the study of the popularity of tourism spaces. On the basis of data of ticking off Instagram-worthy locations from the Xiaohongshu application, the present study aims to identify tourism hotspots in Beijing, analyze their spatial characteristics, and explore their evolution features from two dimensions of time and space. In addition, the emotional images of tourism hotspots in Beijing are interpreted by semantic analysis with an internal mechanism that influences those locations explored. The results of the study show that (1) the overall spatial structure of tourism hotspots in Beijing is C-shaped, which expands from the core area to the periphery with the feature of a circle layer. (2) under the influence of the COVID-19 pandemic, the spatial distribution center of tourism hotspots in Beijing is gradually shifting to the Southeast with the tendency of expanding to the surrounding suburbs. (3) the reception and serviceability of the tourist attractions have a significant influence on the popularity of tourism hotspots. To date, less research has been focused on the data of ticking off emerging Instagram-worthy locations like the Xiaohongshu application, and there is a dearth of the study related to in-depth excavation of the internal influencing mechanism of their popularity. This paper, therefore, under the interaction of virtual and reality, provides new ideas and methods for studying the popularity of urban tourist attractions.
ABSTRACT
Background: Shengmai decoction, which has been included in the diagnosis and treatment of coronavirus disease 2019 (COVID-19), is effective in the early treatment of patients with severe COVID-19. Yiqi Fumai lyophilized injection (YQFM) is a modern Chinese medicine preparation of the Shengmai decoction. The mechanism of its intervention at the molecular level in the severe stage of COVID-19 remains unclear. Therefore, it is necessary to investigate the mechanism of YQFM in the treatment of patients with severe COVID-19. Methods: The corresponding target genes of the main active ingredients in YQFM and COVID-19 were obtained by using multiple databases and literature retrieval. A protein-protein interaction network was constructed, and enrichment analysis of the target was performed using Cytoscape 3.8.1. Lastly, the docking of all the identified compounds with angiotensin-converting enzyme II was confirmed by applying molecular docking technology. Results: YQFM has anti-inflammatory effects on RAW267.4 macrophages. The main active compounds of YQFM are all effective anti-inflammatory agents, and these active compounds also show beneficial physiological functions, such as anti-oxidation, anti-bacterial, and anticancer activities. Gene Ontology analysis showed enrichment in the following pathways: lipopolysaccharides, interleukins, NF-kappa B, interleukin-2 and others, revealing that YQFM may play a role in the treatment of patients with severe COVID-19 through these pathways. Conclusion: YQFM has multicomponent and multitarget characteristics, and it could reduce lung injury by inhibiting inflammatory reactions, promoting antiviral activities, and regulating immunity, among other functions, to treat patients with severe COVID-19.
ABSTRACT
Viruses are one of the main pathogens that endanger human health. The infectious diseases caused by virus infection and transmission seriously threaten human health. At present, viral diseases with high morbidity and low cure rate such as AIDS and viral hepatitis are still spreading around the whole world, and respiratory viruses such as influenza virus and corona virus are constantly mutating. Since 2019, the global epidemic caused by SARS-CoV-2 has brought severe challenges to the world, and there are still great uncertainties in the future course of the epidemic. Therefore, the development of safe and effective antiviral drugs has become an important means to deal with viral diseases. On the basis of summarizing the overall status of global antiviral drug research and development, this paper intends to analyze the progress of new drug research in key areas such as anti-HIV, hepatitis virus and SARS-CoV-2, and put forward suggestions to provide guidance and reference for the development of more efficient antiviral drugs in the future. © 2022, China Biotechnology Press. All rights reserved.
ABSTRACT
This article reports on a study using machine learning to identify incidences and shifting dynamics of hate speech in social media archives. To better cope with the archival processing need for such large-scale and fast evolving archives, we propose the Data-driven and Circulating Archival Processing (DCAP) method. As a proof-of-concept, our study focuses on an English language Twitter archive relating to COVID-19: Tweets were repeatedly scraped between February and June 2020, ingested and aggregated within the COVID-19 Hate Speech Twitter Archive (CHSTA), and analyzed for hate speech using the Generative Adversarial Network-inspired DCAP method. Outcomes suggest that it is possible to use machine learning and data analytics to surface and substantiate trends from CHSTA and similar social media archives that could provide immediately useful knowledge for crisis response, in controversial situations, or for public policy development, as well as for subsequent historical analysis. The approach shows potential for integrating multiple aspects of the archival workflow and supporting automatic iterative redescription and reappraisal activities in ways that make them more accountable and more rapidly responsive to changing societal interests and unfolding developments.
ABSTRACT
Aim Human TMPRSS2 is a transmembrane serine protease.In this paper, the structure and function of the protein were systematically analyzed by bioinformatics, the codon was optimized and the pro- karvotie expression vector was constructed to explore the molecular mechanism of SARS-CoV-2 infecting host cells.Methods The recombinant expression vector pET-22b-TMPRSS2 was generated by molecular cloning technology.The homology, functional sites, subcellular localization, three-dimensional structure and evolutionary characteristics of TMPRSS2 protein were systematically analyzed by using analytical tools such as Protparam, NetPhos3.1, Blast, Clustal X2 and MEGA7.0.Results The prokarvotic expression plas- mid was constructed correctly;TMPRSS2 belongs to medium molecular weight protein, which is composed of 492 amino acid residues.The theoretical isoelectric point is 8.12, the molecular extinction coefficient is 118 145 L * mol~1 * cm"1 , and the half-life is 30 h;TMPRSS2 has 15 potential glycosylation sites and 49 possible phosphorylation sites.It is a transmembrane hydrophilie protein without signal sequenee.In addition, the protein has 13 potential B-cell epitopes and 7 T-eell epitopes.Seeondarv structure analysis showed that random coil accounted for the highest proportion of TMPRSS2 protein ( 0.453 3) , followed by extended strand (0.252 0).Sequence comparison and evolutionary analysis showed that the highest sequence consistency and closest genetic relationship with human TMPRSS2 was Pan troglodytes, followed by gorilla.Conclusions Human-derived TMPRSS2 protein is ev- olutionarilv conserved and functionally important.Hie results of this study can help to reveal the structure and mechanism of action of TMPRSS2 protein, provide ideas for the diagnosis and treatment of COYID-19, and accelerate the research and development process of new drugs targeting TMPRSS2 protein. Copyright © 2022 Publication Centre of Anhui Medical University. All rights reserved.
ABSTRACT
As a huge disaster for humanity, the COVID-19 has caused many negative effects on the lives of people around the world with a rapid growth. Moreover, the global pandemic of Neocoronavirushas produced many mutated strains. Although the most commonly used test for COVID-19 is reverse transcription-polymerase chain reaction (RT-PCR), CXR becomes an irreplaceable tool for the diagnosis and analysis for a more complete and accurate visualization of the lung lesion process. Therefore, it is of high value for classification and identification studies. In this paper, the high-frequency emphasis filtering based convolutional neural networks (HFEF-CNN) are proposed for solving the automatic detection of COVID-19. Firstly, the HFEF is used to denoise the image data to make some features in the image more obvious. Then some major CNNs are used to train image classification models to achieve better detection performance. Finally, Some experiments are conducted on the 'COVID-19 Chest X-Ray Database' dataset. To verify the effectiveness of the HFEF-CNN, a histogram equalization based CNN (HE-CNN) and a restricted contrast adaptive histogram equalization based CNN (CLAHE-CNN) are compared. The experimental results show that the HFEF-CNN outperformed the above two methods. © 2022 IEEE.
ABSTRACT
Background: Pathological complete response (pCR) is associated with improved prognosis in triple-negative breast cancer (TNBC). Anlotinib, a novel multi-target tyrosine kinase inhibitor that effectively inhibits VEGFR, FGFR, c-KIT, c-MET, and RET, monotherapy has been proven effective in HER-2 negative metastatic breast cancer, but its efficacy in early-stage TNBC is unknown. This phase 2 study aims to evaluate the efficacy and safety of adding anlotinib to neoadjuvant chemotherapy in patients (pts) with primary TNBC. Methods: Pts with clinical stage II/III TNBC were to be treated with 5 cycles of anlotinib (12mg, d1-14, q3w) plus 6 cycles of taxanes (docetaxel 75 mg/m2 or nab-paclitaxel 260 mg/m2, d1, q3w) and lobaplatin (30 mg/m2, d1, q3w), followed by surgery. The primary endpoint was the total pCR (tpCR;ypT0/is ypN0). A Simon's two-stage optimum design was used, and > 5 of 11 pts were required to achieve tpCR in the first stage, with a pre-specified tpCR rate of 54.5% before proceeding to the second stage. A total of 31 participants was required for the study. Results: Six out of 11 pts achieved tpCR in the first stage, reaching the threshold for the second stage. From Jan 2021 to Jan 2022, a total of 22 pts were enrolled and 12 received surgery after the completion of neoadjuvant therapy, but a total of 2 pts withdrew from the study due to the COVID-19 pandemic or serious adverse events. Of the 22 eligible pts, the median age was 49 years (range, 29-64), 64% were postmenopausal, and 73% were nodal involved. At the time of surgery, 58.3% (7/12) achieved tpCR. Of the 9 pts with the node-positive disease at diagnosis, 88.9% (8/9) became ypN0. The results of FUSCC TNBC classification (IHC-based) revealed the tpCR rates were 57.1% (4/7), 100% (3/3), and 0% (0/2) for BLIS subtype, IM subtype and LAR/unknown subtypes, respectively. Biomarker analysis showed the tpCR rates were 100% (3/3) and 100% (4/4) in patients with gBRCA1 mutation and MYC amplification, respectively. The most common grade 3 or 4 treatment-related adverse events were leucopenia (6/22, 27%), neutropenia (6/22, 27%), anemia (5/22, 23%), decreased appetite (5/22, 23%), hypertension (2/22, 9%), ALT increased (1/22, 5%) and oral mucositis (1/22, 5%). No treatment-related deaths occurred. The trial is ongoing. Conclusions: The addition of anlotinib to neoadjuvant chemotherapy showed manageable toxicity and promising antitumor activity for patients with early-stage TNBC.
ABSTRACT
With the COVID-19 epidemic quickly under control in China in the early stage of 2020, global cooperation/ communications may pose great challenges to epidemic control and prevention in the country. Large-scale spread by asymptomatic carriers was a concern. We obtained data on new cluster outbreak regions with COVID-19 caused by asymptomatic carriers from June 2020 to May 2021 in China, and reported the epidemiological characteristics, the possible routes of viral transmission and infection, and different control strategies. These results show the importance of regular screening for high-risk populations and differential management strategies for epidemic control, which provide an objective basis for suppressing the spread of the SARS-CoV-2 virus. These experiences can be used as a reference to minimize the subsequent spread of virus mutants in various places.
ABSTRACT
Mass suspension of anthropogenic activities is extremely rare, the quarantine due to the coronavirus disease 2019 (COVID-19) represents a natural experiment to investigate the impact of anthropogenic activities on air quality. The mitigation of air pollution during the COVID-19 lock-down has been reported from a global perspective;however, the air pollution levels vary in different regions. This study initiated a novel synthesis of multiple-year satellite observations, national ground measurements towards SO2, NO2 and O3 and meteorological conditions to evaluate the impact of the COVID-19 lockdown in Beihai, a specific city in a less developed area in southwest China, to reveal the potential implications of control strategies for air pollution. The levels of the major air pollutants during the COVID-19 lockdown (LP) and during the same period of previous years (SP) were compared and a series of statistical tools were applied to analyze the sources of air pollution in Beihai. The results show that air pollutant levels decreased with substantial diversity during the LP. Satellite-retrieved NO2 and SO2 levels during the LP decreased by 5.26% and 22.06%, while NO2, SO2, PM2.5 and PM10 from ground measurements during the LP were 25.6%, 2.7%, 22.2% and 22.2% lower than during SP, respectively. Ground measured SO2 concentrations during the LP were only 2.7% lower than during the SP, which may be attributed to uninterrupted essential industrial activ-ities, such as power plants. Polar plots analysis shows that NO2 concentrations were strongly associated with local emission sources, such as automobiles and local industry. Additionally, the much lower levels of NO2 concentrations during the LP and the absence of an evening peak may highlight the significant impact of the traffic sector on NO2. The decrease in daily mean O3 concentrations during the LP may be associated with the reduction in NO2 concentrations. Indications in this study could be beneficial for the formulation of atmospheric protection policies. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
ABSTRACT
Edge detection is an effective method for image segmentation and feature extraction. Therefore, extracting weak edges with the inhomogeneous gray of Corona Virus Disease 2019 (COVID-19) CT images is extremely important. Multiscale morphology has been widely used in the edge detection of medical images due to its excellent boundary detection accuracy. In this paper, we propose a weak edge detection method based on Gaussian filtering and single-scale Retinex (GF_SSR), and improved multiscale morphology and adaptive threshold binarization (IMSM_ATB). As all the CT images have noise, we propose to remove image noise by Gaussian filtering. The edge of CT images is enhanced using the SSR algorithm. In addition, based on the extracted edge of CT images using improved Multiscale morphology, a particle swarm optimization (PSO) algorithm is introduced to binarize the image by automatically getting the optimal threshold. To evaluate our method, we use images from three datasets, namely COVID-19, Kaggle-COVID-19, and COVID-Chestxray, respectively. The average values of results are worthy of reference, with the Shannon information entropy of 1.8539, the Precision of 0.9992, the Recall of 0.8224, the F-Score of 1.9158, running time of 11.3000. Finally, three types of lesion images in the COVID-19 dataset are selected to evaluate the visual effects of the proposed algorithm. Compared with the other four algorithms, the proposed algorithm effectively detects the weak edge of the lesion and provides help for image segmentation and feature extraction. © 2022 Tech Science Press. All rights reserved.
ABSTRACT
We demonstrate a health-friendly speaker verification system for voice-based identity verification on mobile devices. The system is built upon a speech processing module, a ResNet-based local acoustic feature extractor and a multi-head attention-based embedding layer, and is optimized under an additive margin softmax loss for discriminative speaker verification. It is shown that the system achieves superior performance no matter whether there is mask wearing or not. This characteristic is important for speaker verification services operating in regions affected by the raging coronavirus pneumonia. With this demonstration, the audience will have an in-depth experience of how the accuracy of bio-metric verification and the personal health are simultaneously ensured. We wish that this demonstration would boost the development of next-generation bio-metric verification technologies. Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved
ABSTRACT
Dear readers, It is delightful to march to 2022 after two years of the pandemic. Humankind has successfully dealt with COVID-19. In the June 2020 issue of IEEE Electrification Magazine, we commended the tremendous collaborative efforts by scientists worldwide to share the data of virus gene sequencing and develop a vaccine. Advancing technology for humanity is the goal of IEEE, and so it is for this magazine.
ABSTRACT
The outbreak of novel coronavirus disease in 2020 has profoundly impacted all aspects of lives and posed a unique challenge in energy load forecasting. With the increase of the COVID-19 cases, governments worldwide impose strict social distancing and limit the mobility of the population, which causes a shift in load consumption magnitude and pattern. In this paper, we first identify the most influential COVID-19 features for load reduction. Then, we propose a new load forecasting model that includes the new features. The case study on the New York City data set demonstrates that our new forecasting model can efficiently provide new load prediction in the pandemic period. © 2021 IEEE.
ABSTRACT
Objective: To investigate the clinical characteristics, treatment and outcome of elderly patients with COVID-19. Methods: We made a retrospective analysis of the clinical data of elderly patients with COVID-19 admitted by the National Anti-epidemic Medical Team of The First Affiliated Hospital of Xi'an Jiaotong University in Department of the seventh ward of Renmin Hospital of Wuhan University between February 9 and March 15, 2020. We fully extracted the patients' demographics, epidemiological characteristics, clinical manifestations, laboratory examination, imaging performance, treatment and outcomes. Results: In this study we included a total of 30 patients(18 males and 12 females), with an average age of(71.1±14.4) years. Their underlying diseases included cardiovascular and cerebrovascular diseases(23 patients), chronic pulmonary disease(3 patients), digestive disease(2 patients), diabetes mellitus(3 patients), and chronic kidney disease(1 patients). Before admission, 22 patients received oral medication. The initial symptoms were fever and cough. The peak body temperature averaged(38.4±0.6)℃ The mean time from symptom onset to hospitalization was 15.0±7.7 days. The clinical classification was mainly severe type in 26 patients(87%). Laboratory examination revealed lower lymphocyte count(0.7±0.2)×109/L, and higher blood D-D dimer lever(6.9±13)μg/L. Serum lactate dehydrogenase(LDH) significantly increased(310±136)U/L. Serum C-reactive protein(61±52)mg/L and erythrocyte sedimentation rate(ESR)(66±38)mmol/L slightly increased. Imaging performance revealed that diffuse lesions were located in bilateral pulmonary parenchyma(22 patients) and in single pulmonary parenchyma(7 patients). Ground-glass opacity was found in all the patients, and the average number of CT examination during hospitalization was 3.5±1.3. Viral load revealed that nucleic acid in nasopharyngeal swabs of 30 patients was all positive, nucleic acid in the feces of 6 patients was positive, and nucleic acid in nasopharyngeal swab of 1 patient was positive, whose nucleic acid in alveolar lavage fluid was negative. Serum IgG antibody level was(157.5±29.2)AU/mL and IgM antibody level was(69.0±148.7)AU/mL. Complications included ARDS in 5 patients, AKI in 5 patients, cardiac injury in 3 patients, shock in 2 patients, nosocomial infection in 3 patients, coagulation disorder in 3 patients, and gastrointestinal bleeding in 3 patients. Finally, 5 patients received non-invasive mechanical ventilation and 2 patients received invasive mechanical ventilation. Another 2 patients underwent CRRT and 1 patient received CRRT plus ECMO. Of the 3 patients with critical type, 2 died and 1 survived. There were 25 patients who turned from severe type into normal type/light type, and 1 patient finally died(turned from severe type into critical type). In the end, 15 patients were cured and discharged. The average time of viral nucleic acid from positive to negative was 12.4±5.6 and the average time of lesion absorption in computer tomography was 16.9±5.8 days. The total hospital stay was 22.9±8.1 days, and the 28-day mortality rate was 6.7%. Conclusion: COVID-19 in elderly patients is mostly severe and its initial symptoms are still fever and cough. Patients should be immediately hospitalized when symptoms develop. The time of viral nucleic acid transformation and imaging improvement is longer than that of others. The mortality in critically ill patients is higher than that of others. Clinicians should pay more attention to the elderly people. © 2021, Editorial Board of Journal of Xi'an Jiaotong University (Medical Sciences). All right reserved.
ABSTRACT
Student centered, outcome based education, and continuous quality improvement are the core concepts of the construction of the new engineering. Faced with the reality that the students cannot return to school on time during COVID-19, school of computer and information of Anhui polytechnic university introduced service concept, constructed the student-centered online graduation design/thesis education system, and practiced online process management and quality control. By setting up the service consciousness of the teachers, both the teachers and the students actively engaged in the construction of the course of graduation design/thesis and gradually build the teaching ecology for the sustainable improvement. The practice shows that the construction of the intelligent education system improves the enthusiasm of teachers and students to carry out graduation design/thesis, which ensures the training quality of students' ability, and promotes the solution of complex engineering problems. © 2021 IEEE.
ABSTRACT
OBJECTIVE: To analyze the changes and characteristics of pediatric outpatient visits in a general hospital before and after the coronavirus disease (COVID-19) epidemic. METHODS: Based on the registration data of pediatric outpatient visits in the information system (HIS)of Beijing Tsinghua Changgung Hospital, from January 1 2018 to December 31 2020, aged 0 to 16 years, we analyzed the changes of outpatient visits before and after the epidemic, focusing on respiratory infection including influenza. The relationship between the outpatient visits and age and quarterly distribution were also studied. RESULTS: (1) Respiratory infection accounted for the majority of outpatient visits in 2018 and 2019 (60.6% and 60.5%, respectively). Non-respiratory infection accounted for the main proportion of outpatient visits in 2020, while respiratory infection accounted for only 47.4%. Annual respiratory infection visits, respiratory infectious diseases visits especially influenza visits all decreased significantly in 2020 compared with that in 2018 and 2019 (P < 0.05). (2)Respiratory infection visits were highest in the infant group, lowest in the school age group (P < 0.05) and highest in the fourth quarter each year. It decreased significantly in the second quarter of 2020 with statistical significance when compared with the other quarters of 2020(P < 0.05). (3)Influenza accounted for the highest proportion of respiratory infectious diseases visits in each year. It was highest in first quarter, which was significantly different from the other quarters of the year (P < 0.05). There were different distributions of influenza visits throughout 2018 and 2019, while it was only distributed in the first quarter and 99% in January in 2020. CONCLUSION: The respiratory infection and influenza visits have decreased significantly in our pediatric outpatient department after the COVID-19 epidemic, which is considered closely related to the lifestyle and personal protection after the epidemic. It is recommended that health education on respiratory infection and influenza prevention should be strengthened, especially in winter and spring, to promote the development of good respiratory and hand hygiene habits.
ABSTRACT
Lockdown due to the novel coronavirus disease 2019 (COVID-19) pandemic offers a unique opportunity to study the factors governing the variation in air pollution. A number of studies have investigated the cause underlying the occurrence of heavy haze pollution around the world during the lockdown period. However, information about spatiotemporal variations in gaseous pollutants and detailed quantifications of potential meteorological (METRO) impacts are limited. Ground measurements show that carbon monoxide (CO) pollution deteriorated in northern China despite strict control of human and industrial activities during the lockdown period in early 2020. In this study, a four-dimensional decomposition model was used to quantitatively extract the METRO impacts on the CO pollution over China. The results show that weakened winds elevated CO concentrations near Beijing and in northeastern China. Increased temperatures slightly elevated CO concentrations in northern and eastern China but reduced CO concentrations in northwestern China. Remarkable amounts of CO increases in northern China (e.g., by 0.21 mg/m3 within Beijing) were explained by anomalously high humidity, which could be associated with an enhanced interaction between aerosol and the boundary layer. After excluding the METRO impacts, the CO concentrations drastically declined across China (e.g., by 0.22 mg/m3 within Beijing), indicating that the lockdown indeed greatly lessened CO concentrations. However, the adverse METRO conditions counteracted the beneficial outcomes of emission reductions, leading to a deterioration of the CO pollution in northern China. These results indicate that the METRO factors can play a critical role in worsening air pollution despite a strict control of anthropogenic emissions. © 2021 American Chemical Society.
ABSTRACT
We demonstrate a health-friendly speaker verification system for voice-based identity verification on mobile devices. The system is built upon a speech processing module, a ResNet-based local acoustic feature extractor and a multi head attention-based embedding layer, and is optimized under an additive margin softmax loss for discriminative speaker verification. It is shown that the system achieves superior performance no matter whether there is mask wearing or not. This characteristic is important for speaker verification services operating in regions affected by the raging coronavirus pneumonia. With this demonstrationl, the audience will have an in-depth experience of how the accuracy of bio-metric verification and the personal health are simultaneously ensured. We wish that this demonstration would boost the development of next-generation bio-metric verification technologies.