Real-Time Mask Identification for COVID-19: An Edge-Computing-Based Deep Learning Framework

Kong, Xiangjie; Wang, Kailai; Wang, Shupeng; Wang, Xiaojie; Jiang, Xin; Guo, Yi; Shen, Guojiang; Chen, Xin; Ni, Qichao

doi:10.1109/jiot.2021.3051844

Cited by 98 publications

(37 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiangjie Kong et al [11] forward an edge figuring based cover recognizable proof structure (ECMask) to help general wellbeing safeguards, which can guarantee constant execution on the low-power camera gadgets of transports. Video reclamation, face location, and cover recognizable proof are its three principal stages.…”

Section: Literature Reviewmentioning

confidence: 99%

CNN Based COVID-19 Prevention System

Shenvi

Shet

2021

2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS)

View full text Add to dashboard Cite

In order to effectively prevent the spread of COVID19 virus, almost everyone wears a mask during coronavirus epidemic. This almost makes conventional facial recognition technology ineffective in many cases, such as community access control, face access control, facial attendance, facial security checks at train stations, etc. Therefore, it is very urgent to improve the recognition performance of the existing face recognition technology on the masked faces. Most current advanced face recognition approaches are designed based on deep learning, which depend on a large number of face samples. However, at present, there are no publicly available masked face recognition datasets. Compared to other datasets, Real-world Masked Face Recognition Dataset (RMFRD) is currently the world's largest real-world masked face dataset. Various COVID-19 prevention measures are undertaken such as wearing mask, sanitization, social distancing and temperature monitoring. An artificial intelligent IOT (Internet of Things) system with temperature monitoring, auto sanitization, mask detection is proposed. In this system, the machine is connected to a server by which the admin can monitor everything live from any place. The system also has face recognition feature by which the registered visitors, students can recognize separately and admin can maintain proper student database with temperature, auto sanitization system for door opening and closing system.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

CNN Based COVID-19 Prevention System

Shenvi

Shet

2021

2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS)

View full text Add to dashboard Cite

show abstract

“…Model optimization and Machine Learning inference are currently the main vectors driving the use of resources at the edge [16]. Many works attempted to adopt Edge-based infrastructure designs to optimize analytics systems, where some systems focus on reducing energy consumption [17], guaranteeing deadlines [18] and meeting real-time requirements [19]. In [19], Kong et al ensure a real-time analysis in consideration of accuracy by adopting an Edge-based system.…”

Section: A Edge-enhanced Data Analytic Systemsmentioning

confidence: 99%

Enabling microservices management for Deep Learning applications across the Edge-Cloud Continuum

Houmani

Balouek-Thomert

Caron

et al. 2021

2021 IEEE 33rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

View full text Add to dashboard Cite

Deep Learning has shifted the focus of traditional batch workflows to data-driven feature engineering on streaming data. In particular, the execution of Deep Learning workflows presents expectations of near-real-time results with user-defined acceptable accuracy. Meeting the objectives of such applications across heterogeneous resources located at the edge of the network, the core, and in-between requires managing trade-offs between the accuracy and the urgency of the results. However, current data analysis rarely manages the entire Deep Learning pipeline along the data path, making it complex for developers to implement strategies in realworld deployments. Driven by an object detection use case, this paper presents an architecture for time-critical Deep Learning workflows by providing a data-driven scheduling approach to distribute the pipeline across Edge to Cloud resources. Furthermore, it adopts a data management strategy that reduces the resolution of incoming data when potential trade-off optimizations are available. We illustrate the system's viability through a performance evaluation of the object detection use case on the Grid'5000 testbed. We demonstrate that in a multi-user scenario, with a standard frame rate of 25 frames per second, the system speed-up data analysis up to 54.4% compared to a Cloud-only-based scenario with an analysis accuracy higher than a fixed threshold.

show abstract

“…Parametric methods provide simple estimates of future traffic conditions with low computational complexity. However, they are only applicable to specific traffic data conditions because changes in external conditions and the randomness and nonlinearity of traffic flow can impact prediction accuracy (Kong et al, 2020(Kong et al, , 2021.…”

Section: Traffic Flow Predictionmentioning

confidence: 99%

Coordinated ramp signal optimization framework based on time series flux-correlation analysis

Zhi¹,

Shu²,

Shen³

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Urban expressways provide an effective solution to traffic congestion, and ramp signal optimization can ensure the efficiency of expressway traffic. The existing methods are mainly based on the static spatial distance between mainline and ramp to achieve multi-ramp coordinated signal optimization, which lacks the consideration of the dynamic traffic flow and lead to the long time-lag, thus affecting the efficiency. This article develops a coordinated ramp signal optimization framework based on mainline traffic states. The main contribution was traffic flow-series flux-correlation analysis based on cross-correlation, and development of a novel multifactorial matric that combines flow-correlation to assign the excess demand for mainline traffic. Besides, we used the GRU neural network for traffic flow prediction to ensure real-time optimization. To obtain a more accurate correlation between ramps and congested sections, we used gray correlation analysis to determine the percentage of each factor. We used the Simulation of Urban Mobility simulation platform to evaluate the performance of the proposed method under different traffic demand conditions, and the experimental results show that the proposed method can reduce the density of mainline bottlenecks and improve the efficiency of mainline traffic.

show abstract

Real-Time Mask Identification for COVID-19: An Edge-Computing-Based Deep Learning Framework

Cited by 98 publications

References 37 publications

CNN Based COVID-19 Prevention System

CNN Based COVID-19 Prevention System

Enabling microservices management for Deep Learning applications across the Edge-Cloud Continuum

Coordinated ramp signal optimization framework based on time series flux-correlation analysis

Contact Info

Product

Resources

About