scholarly journals Comparison of the Effectiveness of Deep Learning Methods for Face Mask Detection

2021 ◽  
Vol 38 (4) ◽  
pp. 947-953
Author(s):  
Onur Gedik ◽  
Ayşe Demirhan
Keyword(s):  
Deep Learning ◽  
Prevention And Control ◽  
Face Mask ◽  
Performance Comparison ◽  
Convolutional Network ◽  
Accuracy Comparison ◽  
Comparison Results ◽  
Public Areas ◽  
And Control ◽  
Study Performance

The usage of mask is necessary for the prevention and control of COVID-19 which is a respiratory disease that passes from person to person by contact and droplets from the respiratory tract. It is an important task to identify people who do not wear face mask in the community. In this study, performance comparison of the automated deep learning based models including the ones that use transfer learning for face mask detection on images was performed. Before training deep models, faces were detected within images using multi-task cascaded convolutional network (MTCNN). Images obtained from face mask detection dataset, COVID face mask detection dataset, mask detection dataset, and with/without mask dataset were used for training and testing the models. Face areas that are detected with MTCNN were used as input for convolutional neural network (CNN), MobileNetV2, VGG16 and ResNet50. VGG16 showed best performance with 97.82% accuracy. MobileNetV2 showed the worst performance for detecting faces without mask with 72.44% accuracy. Comparison results show that VGG16 can be used effectively to detect faces without mask. This system can be used in crowded public areas to warn people without mask that may help the reduce the risk of pandemic.

scholarly journals Assessment of knowledge, attitudes and practices towards prevention of coronavirus disease (COVID-19) among Bangladeshi population

2020 ◽  
Vol 46 (2) ◽  
pp. 73-82
Author(s):  
Shah Md. Mahfuzur Rahman ◽  
A Akter ◽  
KF Mostari ◽  
S Ferdousi ◽  
IJ Ummon ◽  
...  
Keyword(s):  
Prevention And Control ◽  
Face Mask ◽  
World Health ◽  
Social Distancing ◽  
Face To Face ◽  
Attitudes And Practices ◽  
Study Population ◽  
Bangladeshi Population ◽  
And Control ◽  
Knowledge Attitudes And Practices

Background: Cornonavirus disease (COVID-19) has been declared pandemic by the World Health Organization on the 11th March 2020. The knowledge, attitudes and practices of the population towards the COVID-19, play an integral role in determining community’s readiness to engage themselves in government measures including behavioural change in prevention and control of the disease. Objectives: The study was aimed to determine the knowledge levels, attitudes and practices towards the COVID-19 among the Bangladeshi population. Methods: A cross sectional study was conducted among 1549 adult population across Bangladesh including Dhaka city and rural areas during March-April 2020. Data were collected using a structured and pretested questionnaire through online, self-administered and face to face interview. The study instrument consisted of 7 items on socio-demographic characteristics, 12 items on knowledge, 4 items on attitudes and 5 items on practices related to COVID-19. Independent sample t-tests, chi-square tests, one-way analysis of variance (ANOVA) and binary logistic regression were performed to assess the attitudes and practices in relation to knowledge. Results: Of the total 1549 study population, 1249 were interviewed online, 194 were self-administered and 106 were through face to face interview. The lowest level of knowledge prevailed among the above 50 years’ age group regarding the disease, which was higher among female (p=0.03), and more among the respondents having education level below graduation (p=0.000; OR=1.6, χ2=17.6). Of the total respondents, 73.5% having negative attitude towards use of face mask, though 69.8% having the appropriate knowledge on mode of transmission of the virus (p=0.000). Though, 51.6% of the study population, having adequate knowledge, but only 52.1% using face mask (p>0.05) and 51.8% practicing hand washing (p>0.05). More than 70.0% respondents having knowledge on social distancing, but only 50.0% was practicing it. Male respondents had 1.5 times more knowledge about the social distancing than the female counterpart (p=0.000). Conclusion: Public awareness campaign should be enhanced critically focusing the target audience covering the knowledge gaps, motivation for appropriate practices and further improvement of attitudes towards prevention and control of COVID-19 in Bangladesh thus suggested. Bangladesh Med Res Counc Bull 2020; 46(2): 73-82

scholarly journals Real-Time Face Mask Detection using Deep Learning

2021 ◽  
Vol 12 (1) ◽  
pp. 25-31
Author(s):  
Pranad Munjal ◽  
Vikas Rattan ◽  
Rajat Dua ◽  
Varun Malik
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Face Mask ◽  
World Health ◽  
Infected Person ◽  
Accuracy Rate ◽  
Public Areas ◽  
Health Organization ◽  
Respiratory Droplets ◽  
Real Time Application

The outbreak of COVID-19 has taught everyone the importance of face masks in their lives. SARS-COV-2(Severe Acute Respiratory Syndrome) is a communicable virus that is transmitted from a person while speaking, sneezing in the form of respiratory droplets. It spreads by touching an infected surface or by being in contact with an infected person. Healthcare officials from the World Health Organization and local authorities are propelling people to wear face masks as it is one of the comprehensive strategies to overcome the transmission. Amid the advancement of technology, deep learning and computer vision have proved to be an effective way in recognition through image processing. This system is a real-time application to detect people if they are wearing a mask or are without a mask. It has been trained with the dataset that contains around 4000 images using 224x224 as width and height of the image and have achieved an accuracy rate of 98%. In this research, this model has been trained and compiled with 2 CNN for differentiating accuracy to choose the best for this type of model.It can be put into action in public areas such as airports, railways, schools, offices, etc. to check if COVID-19 guidelines are being adhered to or not.

IBD1: The metrics and evaluation method for DNN processor benchmark while doing Inference task

2021 ◽  
pp. 1-13
Author(s):  
Wei Min Zhang ◽  
Long Zhang ◽  
Zheyu Zhang ◽  
Mingjun Sun
Keyword(s):  
Deep Learning ◽  
Evaluation System ◽  
Evaluation Method ◽  
Hardware Acceleration ◽  
Performance Comparison ◽  
Current Status ◽  
Input Size ◽  
Comparison Results ◽  
The Difference ◽  
The Many

With the many varieties of AI hardware prevailing on the market, it is often hard to decide which one is the most suitable to use but not only with the best performance. As there is an industry-wide trend demand for deep learning deployment, the inference benchmark for the effectiveness of DNN processor becomes important and is of great help to select and optimize AI hardware. To systematically benchmark deep learning deployment platforms, and give more objective and useful metrics comparison. In this paper, an end to end benchmark evaluation system was brought up called IBD, it combined 4 steps include three components with 6 metrics. The performance comparison results are obtained from the chipsets from Qualcomm, HiSilicon, and NVIDIA, which can provide hardware acceleration for AI inference. To comprehensively reflect the current status of the DNN processor deploying performance, we chose six devices from three kinds of deployment scenarios which are cloud, desktop and mobile, ten models from three different kinds of applications with diverse characteristics are selected, and all these models are trained from three major training frameworks. Several important observations were made by using our methodologies. Experimental results showed that workload diversity should focus on the difference came from training frameworks, inference frameworks with specific processors, input size and precision (floating and quantized).

Data Transcription for India's Supreme Court Documents Using Deep Learning Algorithms

2020 ◽  
Vol 16 (4) ◽  
pp. 21-41
Author(s):  
Vaissnave V. ◽  
P. Deepalakshmi
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Performance Comparison ◽  
Legal Cases ◽  
Learning Techniques ◽  
Proposed Model ◽  
Comparison Results ◽  
Complex Forms ◽  
Indian Law ◽  
Day By Day

The Indian legal system is one of the largest judiciary systems in the world and handles a huge number of legal cases which is increasing rapidly day by day. The computerized documentation of Indian law is highly voluminous and complex forms. This article proposes a model using deep learning techniques to split the judgment text into the issue, facts, arguments, reasoning, and decision. To evaluate the proposed model, the authors conducted experiments that revealed that the convolutional neural network and long short-term memory transcription technique could achieve better accuracy and obtain superior transcription performance. Comparison results indicate that the proposed algorithm gives the highest classification accuracy rate of 95.6%. The adaptation of splitting the judgment text into the issue, facts, arguments, reasoning, and decision helps to find specific portions of the judgment within a second, making the job of analyzing the case more effective, efficient, and faster.

scholarly journals Face Mask Wearing in Public Places is Pseudoscience and Antithesis: A New Tool Adopted for COVID-19 Control

2020 ◽  
pp. 1-2
Author(s):  
Yibala Oboma ◽  
Yibala Oboma
Keyword(s):  
Prevention And Control ◽  
Infection Prevention ◽  
Face Mask ◽  
Control Measures ◽  
Infection Prevention And Control ◽  
Infectious Agents ◽  
Public Places ◽  
Scientific Approach ◽  
Quality Health ◽  
And Control

Infection prevention and control is a scientific approach, application and practical solution of the designed to prevent harm caused by the infectious agents. Control Measures occupies unique and safe positions in terms of patient Safety and quality health for those the measures are directed towards [1].

scholarly journals Comparative assessment of infection prevention and control practice among maternity unit health workers in public and private secondary health facilities in Kaduna state, Nigeria

2021 ◽  
Vol 2 ◽  
pp. 9
Author(s):  
Joseph Sunday ◽  
Muawiyya Babale Sufiyan ◽  
Clara Ladi Ejembi ◽  
Butawa Nuhu Natie ◽  
Abdulhakeem Abayomi Olorukooba ◽  
...  
Keyword(s):  
Prevention And Control ◽  
Infection Prevention ◽  
Health Workers ◽  
Statistical Significance ◽  
Face Mask ◽  
Infection Prevention And Control ◽  
Cross Sectional ◽  
Public And Private ◽  
Significant Difference ◽  
And Control

Objectives: Infection prevention and control (IPC) practice in health facility (HF) is abysmally low in developing countries, resulting in significant preventable morbidity and mortality. This study assessed and compared health workers’ (HWs) practice of IPC strategies in public and private secondary HFs in Kaduna State. Material and Methods: A cross-sectional comparative study was employed. Using multistage sampling, 227 participants each were selected comprising of doctors, midwives, and nurses from public and private HF. Data were collected using interviewer-administered questionnaire and observation checklist and analyzed using bivariate and multivariate analysis. Statistical significance determined at P < 0.05. Results: The practice of infection prevention was poor. Overall, 42.3% of the HWs did not change their gowns in-between patients, with the significantly higher rates in 73.1% of private compared to 42.3% of public HF workers (P < 0.001). In addition, 30.5% and 10.1% of HWs do not use face mask and eye goggle, respectively, when conducting procedures likely to generate splash of body fluids, however, there was no significant difference in these poor practices in public compared to private HFs. The mean IPC practice was 51.6 ± 12.5%, this was significantly lower among public (48.8 ± 12.5%) compared to private (54.5 ± 11.9%) HF workers (P < 0.0001). Private HF workers were 3 times more likely to implement IPC interventions compared to public HF workers. Conclusion: IPC practice especially among public HF workers was poor.

scholarly journals Robotic hex-nut sorting system with deep learning

2021 ◽  
Vol 11 (4) ◽  
pp. 3575
Author(s):  
Cristian Almanza ◽  
Javier Martínez Baquero ◽  
Robinson Jiménez-Moreno
Keyword(s):  
Pattern Recognition ◽  
Deep Learning ◽  
Inverse Kinematic ◽  
Robotic Arm ◽  
Automation System ◽  
Network Architectures ◽  
Convolutional Network ◽  
Arm Work ◽  
Sorting System ◽  
And Control

<span>This article exposes the design and implementation of an automation system based on a robotic arm for hex-nut classification, using pattern recognition and image processing.  The robotic arm work based on three servo motors and an electromagnetic end effector. The pattern recognition implemented allows classifying three different types of hex-nut through deep learning algorithms based on convolutional neural network architectures. The proposed methodology exposes four phases: the first is the design, implementation, and control of a robotic arm. The second is the capture, classification, and image treatment; the third allows gripping the nut through the robot’s inverse kinematic. The final phase is the re-localization of the hex-nut in the respective container. The automation system successfully classifies all the types of hex-nuts, where the convolutional network used is an efficient and recent pattern recognition method, with an accuracy of 100% in 150 iterations. This development allows for obtaining a novel algorithm for robotic applications in hex-nut sorting.</span>

Sign in / Sign up

Export Citation Format

Share Document