scholarly journals TinyML-Based Concept System Used to Analyze Whether the Face Mask Is Worn Properly in Battery-Operated Conditions

2022 ◽  
Vol 12 (1) ◽  
pp. 484
Author(s):  
Dominik Piątkowski ◽  
Krzysztof Walkowiak
Keyword(s):  
Low Power ◽  
Low Cost ◽  
Face Mask ◽  
High Accuracy ◽  
Battery Life ◽  
Limited Area ◽  
True Negative ◽  
Concept System ◽  
System Solution ◽  
The Face

As the COVID-19 pandemic emerged, everyone’s attention was brought to the topic of the health and safety of the entire human population. It has been proven that wearing a face mask can help limit the spread of the virus. Despite the enormous efforts of people around the world, there still exists a group of people that wear face masks incorrectly. In order to provide the best level of safety for everyone, face masks must be worn correctly, especially indoors, for example, in shops, cinemas and theaters. As security guards can only handle a limited area of the frequently visited objects, intelligent sensors can be used. In order to mount them on the shelves in the shops or near the cinema cash register queues, they need to be capable of battery operation. This restricts the sensor to be as energy-efficient as possible, in order to prolong the battery life of such devices. The cost is also a factor, as cheaper devices will result in higher accessibility. An interesting and quite novel approach that can answer all these challenges is a TinyML system, that can be defined as a combination of two concepts: Machine Learning (ML) and Internet of Things (IoT). The TinyML approach enables the usage of ML algorithms on boards equipped with low-cost, low-power microcontrollers without sacrificing the classifier quality. The main goal of this paper is to propose a battery-operated TinyML system that can be used for verification whether the face mask is worn properly. To this end, we carefully analyze several ML approaches to find the best method for the considered task. After detailed analysis of computation and memory complexity as well as after some preliminary experiments, we propose to apply the K-means algorithm with carefully designed filters and a sliding window technique, since this method provides high accuracy with the required energy-efficiency for the considered classification problem related to verification of using the face mask. The STM32F411 chip is selected as the best microcontroller for the considered task. Next, we perform wide experiments to verify the proposed ML framework implemented in the selected hardware platform. The obtained results show that the developed ML-system offers satisfactory performance in terms of high accuracy and lower power consumption. It should be underlined that the low-power aspect makes it possible to install the proposed system in places without the access to power, as well as reducing the carbon footprint of AI-focused industry which is not negligible. Our proposed TinyML system solution is able to deliver very high-quality metric values with accuracy, True Positive Ratio (TPR), True Negative Ratio (TNR), precision and recall being over 96% for masked face classification while being able to reach up to 145 days of uptime using a typical 18650 battery with capacity of 2500 mAh and nominal voltage of 3.7 V. The results are obtained using a STM32F411 microcontroller with 100 MHz ARM Cortex M4, which proves that execution of complex computer vision tasks is possible on such low-power devices. It should be noted that the STM32F411 microcontroller draws only 33 mW during operation.

scholarly journals IoT and Deep Learning Based Approach for Rapid Screening and Face Mask Detection for Infection Spread Control of COVID-19

2021 ◽  
Vol 11 (8) ◽  
pp. 3495
Author(s):  
Shabir Hussain ◽  
Yang Yu ◽  
Muhammad Ayoub ◽  
Akmal Khan ◽  
Rukhshanda Rehman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Low Cost ◽  
Face Mask ◽  
World Health ◽  
Rapid Screening ◽  
Screening System ◽  
Source Of Infection ◽  
The Face ◽  
Health Organization ◽  
Vaccine Distribution

The spread of COVID-19 has been taken on pandemic magnitudes and has already spread over 200 countries in a few months. In this time of emergency of COVID-19, especially when there is still a need to follow the precautions and developed vaccines are not available to all the developing countries in the first phase of vaccine distribution, the virus is spreading rapidly through direct and indirect contacts. The World Health Organization (WHO) provides the standard recommendations on preventing the spread of COVID-19 and the importance of face masks for protection from the virus. The excessive use of manual disinfection systems has also become a source of infection. That is why this research aims to design and develop a low-cost, rapid, scalable, and effective virus spread control and screening system to minimize the chances and risk of spread of COVID-19. We proposed an IoT-based Smart Screening and Disinfection Walkthrough Gate (SSDWG) for all public places entrance. The SSDWG is designed to do rapid screening, including temperature measuring using a contact-free sensor and storing the record of the suspected individual for further control and monitoring. Our proposed IoT-based screening system also implemented real-time deep learning models for face mask detection and classification. This module classified individuals who wear the face mask properly, improperly, and without a face mask using VGG-16, MobileNetV2, Inception v3, ResNet-50, and CNN using a transfer learning approach. We achieved the highest accuracy of 99.81% while using VGG-16 and the second highest accuracy of 99.6% using MobileNetV2 in the mask detection and classification module. We also implemented classification to classify the types of face masks worn by the individuals, either N-95 or surgical masks. We also compared the results of our proposed system with state-of-the-art methods, and we highly suggested that our system could be used to prevent the spread of local transmission and reduce the chances of human carriers of COVID-19.

scholarly journals Ultra-Low-Power, High-Accuracy 434 MHz Indoor Positioning System for Smart Homes Leveraging Machine Learning Models

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1401
Author(s):  
Haq Nawaz ◽  
Ahsen Tahir ◽  
Nauman Ahmed ◽  
Ubaid U. Fayyaz ◽  
Tayyeb Mahmood ◽  
...  
Keyword(s):  
Low Power ◽  
Indoor Localization ◽  
Low Cost ◽  
Smart Homes ◽  
Indoor Positioning ◽  
High Accuracy ◽  
Positioning System ◽  
Telemetry Data ◽  
Ultra Low Power ◽  
Indoor Positioning System

Global navigation satellite systems have been used for reliable location-based services in outdoor environments. However, satellite-based systems are not suitable for indoor positioning due to low signal power inside buildings and low accuracy of 5 m. Future smart homes demand low-cost, high-accuracy and low-power indoor positioning systems that can provide accuracy of less than 5 m and enable battery operation for mobility and long-term use. We propose and implement an intelligent, highly accurate and low-power indoor positioning system for smart homes leveraging Gaussian Process Regression (GPR) model using information-theoretic gain based on reduction in differential entropy. The system is based on Time Difference of Arrival (TDOA) and uses ultra-low-power radio transceivers working at 434 MHz. The system has been deployed and tested using indoor measurements for two-dimensional (2D) positioning. In addition, the proposed system provides dual functionality with the same wireless links used for receiving telemetry data, with configurable data rates of up to 600 Kbauds. The implemented system integrates the time difference pulses obtained from the differential circuitry to determine the radio frequency (RF) transmitter node positions. The implemented system provides a high positioning accuracy of 0.68 m and 1.08 m for outdoor and indoor localization, respectively, when using GPR machine learning models, and provides telemetry data reception of 250 Kbauds. The system enables low-power battery operation with consumption of <200 mW power with ultra-low-power CC1101 radio transceivers and additional circuits with a differential amplifier. The proposed system provides low-cost, low-power and high-accuracy indoor localization and is an essential element of public well-being in future smart homes.

Using Dual-Channel D/A Converters Design Successive Approximation A/D Converter

2015 ◽  
Vol 719-720 ◽  
pp. 611-614
Author(s):  
Jia Rong Wang ◽  
Xiao Dong Xia ◽  
Zong Da Zhang ◽  
Han Yang
Keyword(s):  
Power Consumption ◽  
Low Power ◽  
Successive Approximation ◽  
Low Cost ◽  
Electronic Devices ◽  
High Accuracy ◽  
Low Power Consumption ◽  
Digital Converter ◽  
Analog To Digital ◽  
Dual Channel

The successive approximation analog-to-digital converter (ADC) has been widely used in electronic devices due to the corresponding characteristics which are low cost, low power consumption, high accuracy and so on. This paper expounds a design of successive approximation A / D converter to show how to use TCL5615 which is a dual-channel serial 10-bit D/A converter (DAC) to make the conversion accuracy to reach 14-bit.

scholarly journals Use of Multiple Low Cost Carbon Dioxide Sensors to Measure Exhaled Breath Distribution with Face Mask Type and Wearing Behaviour

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6204
Author(s):  
Naveed Salman ◽  
Muhammad Waqas Khan ◽  
Michael Lim ◽  
Amir Khan ◽  
Andrew H. Kemp ◽  
...  
Keyword(s):  
Carbon Dioxide ◽  
Low Cost ◽  
Co2 Concentration ◽  
Face Mask ◽  
Base Station ◽  
Exhaled Breath ◽  
Co2 Sensor ◽  
Improper Use ◽  
The Face ◽  
Carbon Dioxide Co2

The use of cloth face coverings and face masks has become widespread in light of the COVID-19 pandemic. This paper presents a method of using low cost wirelessly connected carbon dioxide (CO2) sensors to measure the effects of properly and improperly worn face masks on the concentration distribution of exhaled breath around the face. Four types of face masks are used in two indoor environment scenarios. CO2 as a proxy for exhaled breath is being measured with the Sensirion SCD30 CO2 sensor, and data are being transferred wirelessly to a base station. The exhaled CO2 is measured in four directions at various distances from the head of the subject, and interpolated to create spatial heat maps of CO2 concentration. Statistical analysis using the Friedman’s analysis of variance (ANOVA) test is carried out to determine the validity of the null hypotheses (i.e., distribution of the CO2 is same) between different experiment conditions. Results suggest CO2 concentrations vary little with the type of mask used; however, improper use of the face mask results in statistically different CO2 spatial distribution of concentration. The use of low cost sensors with a visual interpolation tool could provide an effective method of demonstrating the importance of proper mask wearing to the public.

scholarly journals Optical microscopic study of surface morphology and filtering efficiency of face masks

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e7142 ◽  
Author(s):  
Bhanu Bhakta Neupane ◽  
Sangita Mainali ◽  
Amita Sharma ◽  
Basant Giri
Keyword(s):  
Pore Size ◽  
Low Cost ◽  
Public Awareness ◽  
Face Mask ◽  
Multiple Parameters ◽  
Governmental Agencies ◽  
Long Time ◽  
The Face ◽  
Filtering Efficiency

BackgroundLow-cost face masks made from different cloth materials are very common in developing countries. The cloth masks (CM) are usually double layered with stretchable ear loops. It is common practice to use such masks for months after multiple washing and drying cycles. If a CM is used for long time, the ear loops become stretched. The loop needs to be knotted to make the mask loop fit better on the face. It is not clear how washing and drying and stretching practices change the quality of a CM. The particulate matter (PM) filtering efficiency of a mask depends on multiple parameters, such as pore size, shape, clearance, and pore number density. It is important to understand the effect of these parameters on the filtering efficiency.MethodsWe characterized the surface of twenty different types of CMs using optical image analysis method. The filtering efficiency of selected cloth face masks was measured using the particle counting method. We also studied the effects of washing and drying and stretching on the quality of a mask.ResultsThe pore size of masks ranged from 80 to 500 μm, which was much bigger than particular matter having diameter of 2.5 μm or less (PM2.5) and 10 μm or less (PM10) size. The PM10filtering efficiency of four of the selected masks ranged from 63% to 84%. The poor filtering efficiency may have arisen from larger and open pores present in the masks. Interestingly, we found that efficiency dropped by 20% after the 4th washing and drying cycle. We observed a change in pore size and shape and a decrease in microfibers within the pores after washing. Stretching of CM surface also altered the pore size and potentially decreased the filtering efficiency. As compared to CMs, the less frequently used surgical/paper masks had complicated networks of fibers and much smaller pores in multiple layers in comparison to CMs, and therefore had better filtering efficiency. This study showed that the filtering efficiency of cloth face masks were relatively lower, and washing and drying practices deteriorated the efficiency. We believe that the findings of this study will be very helpful for increasing public awareness and help governmental agencies to make proper guidelines and policies for use of face mask.

scholarly journals Influence of low power consumption on IEEE 802.15.4 in wireless networks performance

2020 ◽  
Vol 9 (1) ◽  
pp. 205-211
Author(s):  
A. Z. Yonis
Keyword(s):  
Phase Shift ◽  
Power Consumption ◽  
Low Power ◽  
Ieee 802.15.4 ◽  
Low Cost ◽  
Average Power ◽  
Low Power Consumption ◽  
Media Access Control ◽  
Battery Life ◽  
Average Power Consumption

IEEE 802.15.4 standard defines both media access control (MAC) and physical (PHY) layer protocols for low power consumption, low peak data rate, and low cost applications. Nowadays the most important feature of IEEE 802.15.4 is maximizing battery life. This paper is focusing how to achieve low average power consumption through assuming that the amount of data transmitted is short and that it is transmitted infrequently so as to keep a low duty cycle. The outcomes demonstrate that the phase shift estimation of Offset quadrature phase-shift keying (OQPSK) modulation has no impact on bit error rate (BER) if it is identical in the transmitter as same as in the receiver.

scholarly journals FahamecV1:A Low Cost Automated Metaphase Detection System

2017 ◽  
Vol 7 (6) ◽  
pp. 2160-2166
Author(s):  
H. Yilmaz ◽  
M. Kamil Turan
Keyword(s):  
Detection System ◽  
Electronic Control Unit ◽  
Low Cost ◽  
Control Unit ◽  
Chromosome Analysis ◽  
Active Role ◽  
High Accuracy ◽  
True Negative ◽  
Metaphase Stage ◽  
Microscope Stage

In this study, FahamecV1 is introduced and investigated as a low cost and high accuracy solution for metaphase detection. Chromosome analysis is performed at the metaphase stage and high accuracy and automated detection of the metaphase stage plays an active role in decreasing analysis time. FahamecV1 includes an optic microscope, a motorized microscope stage, an electronic control unit, a camera, a computer and a software application. Printing components of the motorized microscope stage (using a 3D printer) is of the main reasons for cost reduction. Operations such as stepper motor calibration, are detection, focusing, scanning, metaphase detection and saving of coordinates into a database are automatically performed. To detect metaphases, a filter named Metafilter is developed and applied. Average scanning time per preparate is 77 sec/cm2. True positive rate is calculated as 95.1%, true negative rate is calculated as 99.0% and accuracy is calculated as 98.8%.

scholarly journals Low Cost System for Face Mask Detection Based Haar Cascade Classifier Method

2021 ◽  
Vol 21 (1) ◽  
pp. 21-30
Author(s):  
Radimas Putra Muhammad Davi Labib ◽  
Sirojul Hadi ◽  
Parama Diptya Widayaka
Keyword(s):  
Detection System ◽  
Low Cost ◽  
Face Mask ◽  
World Health ◽  
Cascade Classifier ◽  
The World ◽  
Public Areas ◽  
The Face ◽  
Haar Cascade ◽  
Health Organization

In December 2019, there was a pandemic caused by a new type of coronavirus, namely SARS-CoV-2 (Severe Acute Respiratory Syndrome Corona Virus 2) spread almost throughout the world. The World Health Organization (WHO) named it COVID-19 (Coronavirus Disease). To minimize the spread of the COVID-19, the Indonesian government announced a policy for the social distancing of 1-2 meters and wearing a medical mask. In this study, a mask detection system was built using the Haar Cascade Classifier method by detecting the facial areas such as the nose and lips. The study aims to distinguish between using masks and on the contrary. It is expected that the mask detection system can be implemented to provide direct warnings to people who do not wear masks in public areas. The results using the Haar Cascade Classifier method show that the system designed is able to detect faces, noses, and lips at a light intensity of 80-140 lux. The face is detected at a distance of 30-120cm, while the nose is at a distance of 30-60cm, while the lips are at a distance of 30-70cm. The system designed can perform the detection process at a speed of 5 fps. The overall test results obtained a success rate of 88,89%.

scholarly journals FILLING LEVEL MEASUREMENTS OF MIXED WASTE BINS USING LOW POWER IOT SENSORS AND LORA WAN TECHNOLOGY

2020 ◽  
Author(s):  
Nino Inasaridze ◽  
Vaidotas Vaišis
Keyword(s):  
Low Power ◽  
Mixed Type ◽  
Low Cost ◽  
Empty Space ◽  
Battery Life ◽  
Area Network ◽  
Waste Collection ◽  
Wide Area Network ◽  
Software Optimization ◽  
Cost Components

The article deals with sensor-related solutions to improve waste collection and monitoring in public waste bins. Availability of use of an inexpensive monitoring system for measurement process was tested. The system consists of wireless nodes that use ultrasonic sensors to measure the empty space in the waste bins. A sensor gateway based on Long Rage Wide Area Network (LoRaWAN) protocol was used. Purpose of this work was to describe the new sensor node typology based on low-power and low-cost components. The article analyses the architecture of nodes in detail, focusing on energyefficient technologies and policies to extend battery life by reducing energy consumption through hardware and software optimization. Measurements were performed at five points in two size of containers with different two levels of filling and mixed type of waste. The results show that existing technologies are mature enough to create and deploy inexpensive additional sensors for outbound bins and that such a system can provide the necessary insights on how to optimize waste collection processes and avoid overflowing containers.

scholarly journals Low-Cost Camera-Based Smart Surveillance System for Detecting, Recognizing, and Tracking Masked Human Face

2021 ◽  
Vol 15 (23) ◽  
pp. 104-119
Author(s):  
Ervan Adiwijaya Haryadi ◽  
Grafika Jati ◽  
Ario Yudo Husodo ◽  
Wisnu Jatmiko
Keyword(s):  
Surveillance System ◽  
Low Cost ◽  
Face Mask ◽  
Raspberry Pi ◽  
Surveillance Systems ◽  
Single Shot ◽  
Surveillance Camera ◽  
Smart Surveillance ◽  
The Face ◽  
Smart Surveillance System

A surveillance system is still the most exciting and practical security system to prevent crime effectively. The primary purpose of this system is to recognize the identity of the face caught by the camera. With the advancement of the Internet of things, surveillance systems were implemented on edge devices such as the low-cost Raspberry mobile camera. It raises the challenge of unstructured image/video where the video contains low quality, blur, and variations of human poses. The challenge is increasing because people used to wear a mask during the Covid -19 pandemic.  Therefore, we proposed developing an all-in-one surveillance system with face detection, recognition, and face tracking capabilities. This system integrated three modules: MTCNN face detector, VGGFace2 face recognition, and Discriminative Single-Shot Segmentation (D3S) tracker to create a system capable of tracking the faces of people caught on surveillance camera. We also train new face mask data to recognize and track. This system obtains data from the Raspberry Pi camera and processes images on the cloud as a mobile sensor approach. The proposed system successfully implemented and obtained competitive results in detection, recognition, and tracking under an unconstrained surveillance camera.

Sign in / Sign up

Export Citation Format

Share Document