Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 13 de 13
Filtrar
1.
IEEE Access ; : 1-1, 2023.
Artigo em Inglês | Scopus | ID: covidwho-20243873

RESUMO

As intelligent driving vehicles came out of concept into people’s life, the combination of safe driving and artificial intelligence becomes the new direction of future transportation development. Autonomous driving technology is developing based on control algorithms and model recognitions. In this paper, a cloud-based interconnected multi-sensor fusion autonomous vehicle system is proposed that uses deep learning (YOLOv4) and improved ORB algorithms to identify pedestrians, vehicles, and various traffic signs. A cloud-based interactive system is built to enable vehicle owners to master the situation of their vehicles at any time. In order to meet multiple application of automatic driving vehicles, the environment perception technology of multi-sensor fusion processing has broadened the uses of automatic driving vehicles by being equipped with automatic speech recognition (ASR), vehicle following mode and road patrol mode. These functions enable automatic driving to be used in applications such as agricultural irrigation, road firefighting and contactless delivery under new coronavirus outbreaks. Finally, using the embedded system equipment, an intelligent car was built for experimental verification, and the overall recognition accuracy of the system was over 96%. Author

2.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE ; 12465, 2023.
Artigo em Inglês | Scopus | ID: covidwho-20237995

RESUMO

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

4.
Adverse Drug Reactions Journal ; 22(6):373-374, 2020.
Artigo em Chinês | EMBASE | ID: covidwho-2305921

RESUMO

A 50-year-old male patient with agitated depression and hyperlipemia received oral amoxicillin and clavulanate potassium 0.5 g once daily and 2 lopinavir and ritonavir tablets twice daily for novel coronavirus infection, based on previous drugs including quetiapine, clonazepam, and atorvastatin calcium. After 3 days, lopinavir and ritonavir was changed to oral arbidol 200 mg, thrice daily due to suspicious drug interaction. After taking arbidol for 3 days, the patient developed red papules on the whole body. Considering that it might be related to amoxicillin and clavulanate potassium, the drug was stopped and loratadine was given. But the rashes were aggravated. Considering that the drug eruption was caused by arbidol, arbidol was discontinued and the rashes subsided in a large area the next day. Then vitamin C injection, calcium gluconate injection, and ribavirin were added. After 5 days, the rashes subsided completely. After 17 days, the patient recovered from pneumonia.Copyright © 2020 by the Chinese Medical Association.

5.
Adverse Drug Reactions Journal ; 22(3):147-150, 2020.
Artigo em Chinês | EMBASE | ID: covidwho-2294454
7.
18th IEEE/CVF International Conference on Computer Vision (ICCV) ; : 7366-7375, 2021.
Artigo em Inglês | Web of Science | ID: covidwho-1927512

RESUMO

Semi-supervised learning (SSL) algorithms have attracted much attentions in medical image segmentation by leveraging unlabeled data, which challenge in acquiring massive pixel-wise annotated samples. However, most of the existing SSLs neglected the geometric shape constraint in object, leading to unsatisfactory boundary and non-smooth of object. In this paper, we propose a novel boundary-aware semi-supervised medical image segmentation network, named Graph-BAS(3)Net, which incorporates the boundary information and learns duality constraints between semantics and geometrics in the graph domain. Specifically, the proposed method consists of two components: a multi-task learning framework BAS(3)Net and a graph-based cross-task module BGCM. The BAS(3)Net improves the existing GAN-based SSL by adding a boundary detection task, which encodes richer features of object shape and surface. Moreover, the BGCM further explores the co-occurrence relations between the semantics segmentation and boundary detection task, so that the network learns stronger semantic and geometric correspondences from both labeled and unlabeled data. Experimental results on the LiTS dataset and COVID-19 dataset confirm that our proposed Graph-BAS(3) Net outperforms the state-of-the-art methods in semi-supervised segmentation task.

8.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; : 1050-1054, 2021.
Artigo em Inglês | Web of Science | ID: covidwho-1532676

RESUMO

Coronavirus Disease 2019 (COVID-19) has rapidly spread in 2020, emerging a mass of studies for lung infection segmentation from CT images. Though many methods have been proposed for this issue, it is a challenging task because of infections of various size appearing in different lobe zones. To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation. We first incorporate graph convolution to exploit long-term contextual information from multiple lobe zones. Different from previous average pooling or maximum object probability, we propose a saliency-aware projection mechanism to pick up infection-related pixels as a set of graph nodes. After graph reasoning, the relation-aware features are reversed back to the original coordinate space for the down-stream tasks. We further construct multiple graphs with different sampling rates to handle the size variation problem. To this end, distinct multi-scale long-range contextual patterns can be captured. Our Graph-PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance. Experiments demonstrated that the proposed method consistently boost the performance of state-of-the-art backbone architectures on both of public and our private COVID-19 datasets.

9.
Engineering Construction and Architectural Management ; ahead-of-print(ahead-of-print):19, 2021.
Artigo em Inglês | Web of Science | ID: covidwho-1511153

RESUMO

Purpose Psychosocial factors have received increasing attention regarding significantly influencing safety in the construction industry. This research attempts to comprehensively summarize psychosocial factors related to safety performance of construction workers. In the context of coronavirus disease 2019, some typical psychosocial factors are selected to further analyze their influence mechanism of safety performance. Design/methodology/approach First, a literature review process was conducted to identify and summarize relevant psychosocial factors. Then, considering the impact of the epidemic, hypotheses on the relationship between six selected psychosocial factors (i.e. work stress, role ambiguity, work-family conflict, autonomy, social support and interpersonal conflict) and safety performance were proposed, and a hypothetical model was developed based on job demands-resources theory. Finally, a meta-analysis was used to examine these hypotheses and the model. Findings The results showed these psychosocial factors indirectly influenced workers' safety performance by impacting on their occupational psychology condition (i.e. burnout and engagement). Work stress, role ambiguity, work-family conflict and interpersonal conflict were negatively related to safety performance by promoting burnout and affecting engagement. Autonomy and social support were positively related to safety performance by improving work engagement and reducing burnout. Originality/value This research is the pioneer systematically describing the overall picture of psychosocial factors related to the safety performance of construction workers. Through deeply discussed the mechanism of psychosocial factors and safety performance, it could provide a reference for the theory and application of psychosocial factors in the field of construction safety management.

10.
Eur Rev Med Pharmacol Sci ; 25(9): 3614-3622, 2021 May.
Artigo em Inglês | MEDLINE | ID: covidwho-1232734

RESUMO

OBJECTIVE: COVID-19 has become a global public health emergency affecting 223 countries and territories, and it drastically changed the life of public and health care delivery systems. Although many guidelines have been proposed to avoid infection from COVID-19 and to promote the use of telerehabilitation, there is still no clear answer for the current scenario and strategies of therapists' practice during the COVID-19 pandemic lockdown. This study aimed to explore the impact of COVID-19 lockdown on Occupational Therapists' (OTs) practice, the use of telerehabilitation strategies by OTs, and their employment and mental health. Also, this study aimed to explore the OTs perspective on the role of telerehabilitation during this pandemic lockdown. MATERIALS AND METHODS: Online cross-sectional survey was conducted between April 2020 and May 2020. RESULTS: 114 OTs completed the survey. The results of this study showed that 52.8% of therapists had stress and anxiety due to COVID-19 lockdown. We found that 60.7% of OTs (n=65) used telerehabilitation, versus 36.1% (n=39) before the lockdown. Telerehabilitation approaches were mostly implemented during this lockdown for children with autistic problems (66.6%), stroke (12.9%), cerebral palsy (6.4%), learning disabilities (9.6%), Parkinson's diseases (1.6%), and other medical conditions (2.8%). 10% of therapists reported that they lost their job, and 76% reported that this lockdown affected their income negatively. Overall, 87.8% of therapists reported that mobile technology was very useful to overcome the stress due to COVID-19 related lockdown, social isolation, and social distancing. CONCLUSIONS: The COVID-19 pandemic lockdown experiences made us rethink the current approach of therapy services into alternative method (mixed mode) delivery of occupational therapy practice, which is including the combined method of video-based (telerehabilitation) consultation and face to face intervention.


Assuntos
COVID-19/epidemiologia , Terapia Ocupacional/tendências , Aceitação pelo Paciente de Cuidados de Saúde , Quarentena/tendências , Telerreabilitação/tendências , Adulto , Idoso , COVID-19/prevenção & controle , Controle de Doenças Transmissíveis/métodos , Controle de Doenças Transmissíveis/tendências , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Terapia Ocupacional/métodos , Pandemias , Quarentena/métodos , Telerreabilitação/métodos , Adulto Jovem
13.
Lecture Notes in Educational Technology ; : 177-188, 2021.
Artigo em Inglês | Scopus | ID: covidwho-1002026

RESUMO

Given the effects of natural and social crises that disrupt face-to-face education, such as the COVID-19 pandemic, many teachers have been forced to use online tools to provide their students with distance learning. Luckily, with expanding access to online learning technologies, this transition is more possible than it ever has been before. There are many considerations that schools and teachers need to consider when they redesign face-to-face instruction to meet the needs of distance or online learning. This chapter outlines some of the elements of the online learning environment that teachers must address in order to be successful, such as technical professional development, online resources for teacher collaboration, recognition of time and skill constraints, or the “new normal” for education during the coronavirus pandemic, and the role that teacher perceptions and beliefs around technology plays in the classroom. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA