Back

COVID-19 Contact Tracing Analysis with Bluetooth Technology Using Raspberry Pis

Zhang, D. Y.

2022-08-25 bioinformatics
10.1101/2022.08.23.504944 bioRxiv
Show abstract

Contact tracing, a method for detecting and preventing the spread of a disease, can become more efficient by becoming automated, rather than being done manually. Bluetooth based contact tracing is a potential method for creating an automated method for contact tracing. However, Bluetooth signals cannot always predict something with complete accuracy due to many subtle obstructions. Received signal strength indicator (RSSI), a value produced when Bluetooth devices send and receive signals, generated from Raspberry Pis can predict the distance between the two devices. By running many experiments with variations of obstructions, I was able to successfully create models to correlate RSSI values and distance with a potential success rate of 91.973%. For my research, a success is determined to be anything but a false negative. Despite the limitations when conducting my research, the inaccuracies of my results prove Bluetooth based contact tracing to not be a reliable method for determining people who have been in contact with an index case in the real world.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 3%
35.8%
Similar papers in this journal
2
JMIR mHealth and uHealth
◐ 11 papers in training set
Top 0.1%
7.0%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 27%
3.6%
Similar papers in this journal
4
JMIR Formative Research
◐ 33 papers in training set
Top 0.4%
3.3%
Similar papers in this journal
5
PeerJ
◐ 308 papers in training set
Top 3%
2.9%
Similar papers in this journal
50% of probability mass above
6
PLOS Digital Health
● 106 papers in training set
Top 2%
2.5%
7
Sensors
○ 43 papers in training set
Top 0.5%
2.2%
8
IEEE Access
● 35 papers in training set
Top 0.6%
2.1%
9
Royal Society Open Science
● 214 papers in training set
Top 3%
1.8%
10
Computers in Biology and Medicine
○ 128 papers in training set
Top 3%
1.6%
11
Frontiers in Human Neuroscience
○ 77 papers in training set
Top 1%
1.5%
12
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 3%
1.5%
13
DIGITAL HEALTH
○ 17 papers in training set
Top 0.5%
1.4%
14
BioMed Research International
○ 28 papers in training set
Top 1%
1.2%
15
Chaos, Solitons & Fractals
○ 32 papers in training set
Top 0.6%
1.2%
16
Cureus
○ 68 papers in training set
Top 3%
1.2%
17
Expert Systems with Applications
○ 11 papers in training set
Top 0.2%
1.2%
18
Frontiers in Physiology
○ 106 papers in training set
Top 2%
1.1%
19
F1000Research
○ 88 papers in training set
Top 3%
1.1%
20
Medicine
○ 31 papers in training set
Top 1%
1.0%
21
BMC Public Health
○ 158 papers in training set
Top 4%
1.0%
22
Ecological Informatics
○ 33 papers in training set
Top 0.7%
1.0%
23
Biosystems
○ 31 papers in training set
Top 0.5%
1.0%
24
Statistics in Medicine
○ 40 papers in training set
Top 0.5%
1.0%
25
Materials Today Bio
○ 20 papers in training set
Top 0.7%
0.9%
26
BMC Research Notes
○ 33 papers in training set
Top 1%
0.9%
27
Journal of Medical Internet Research
◐ 87 papers in training set
Top 3%
0.6%
28
PLOS Computational Biology
● 1863 papers in training set
Top 21%
0.6%
29
Gigabyte
● 62 papers in training set
Top 1%
0.6%
30
Heliyon
○ 152 papers in training set
Top 9%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.